AI Analytics Healthcare

AI Analytics Healthcare — independent reviews, comparisons, pricing and step-by-step guides on Aizhi.

Super-resolution imaging

Super-resolution imaging (SR) is a class of techniques that improve the resolution of an imaging system. In optical SR the diffraction limit of systems is transcended, while in geometrical SR the resolution of digital imaging sensors is enhanced. In some radar and sonar imaging applications (e.g. magnetic resonance imaging (MRI), high-resolution computed tomography), subspace decomposition-based methods (e.g. MUSIC) and compressed sensing-based algorithms (e.g., SAMV) are employed to achieve SR over standard periodogram algorithm. Super-resolution imaging techniques are used in general image processing and in super-resolution microscopy. == Super-resolution principles == Several concepts are fundamental to super-resolution imaging: Diffraction limit: the capacity of an optical instrument to reproduce the details of an object in an image has limits that are imposed by laws of physics: the diffraction equations in the wave theory of light, or the uncertainty principle for photons in quantum mechanics. Information transfer can never be increased beyond this boundary, but packets outside the limits can be cleverly swapped for (or multiplexed with) some inside it. Super-resolution microscopy does not so much “break” as “circumvent” the diffraction limit. New procedures probing electro-magnetic disturbances at the molecular level (in the so-called near field) remain fully consistent with Maxwell's equations. Spatial frequency domain: A succinct expression of the diffraction limit is given in the spatial frequency domain. In Fourier optics light distributions are expressed as superpositions of a series of grating light patterns in a range of fringe widths - these widths represent the spatial frequencies. It is generally taught that diffraction theory stipulates an upper limit, the cut-off spatial-frequency, beyond which pattern elements fail to be transferred into the optical image, i.e., are not resolved. But in fact what is set by diffraction theory is the width of the passband, not a fixed upper limit. No laws of physics are broken when a spatial frequency band beyond the cut-off spatial frequency is swapped for one inside it: this has long been implemented in dark-field microscopy. Nor are information-theoretical rules broken when superimposing several bands, disentangling them in the received image needs assumptions of object invariance during multiple exposures, i.e., the substitution of one kind of uncertainty for another. Information: When the term super-resolution is used in techniques based on the inference of object details using a statistical treatment of the image within standard resolution limits (for example, averaging multiple exposures), it involves an exchange of one kind of information (extracting signal from noise) for another (the assumption that the target has remained invariant). Recent breakthroughs incorporate quantum-transformer hybrids into super-resolution, such as QUIET‑SR, a 2025 model that employs shifted quantum window attention within a transformer to enhance image detail while respecting diffraction and information-theory limits Similarly, frequency-integrated transformers (e.g., FIT) enrich super-resolution by explicitly combining spatial and frequency-domain information via FFT-based attention, improving reconstruction across scales Resolution and localization: True resolution involves the distinction of whether a target, e.g. a star or a spectral line, is single or double, ordinarily requiring separable peaks in the image. When a target is known to be single, its location can be determined with higher precision than the image width by finding the centroid (center of gravity) of its image light distribution. The word ultra-resolution had been proposed for this process but it did not catch on, and the high-precision localization procedure is typically referred to as super-resolution. == Techniques == === Optical or diffractive super-resolution === Substituting spatial-frequency bands: Though the bandwidth allowable by diffraction is fixed, it can be positioned anywhere in the spatial-frequency spectrum. Dark-field illumination in microscopy is an example. See also aperture synthesis. ==== Multiplexing spatial-frequency bands ==== An image is formed using the normal passband of the optical device. Then, some known light structure (for example, a set of light fringes) is superimposed on the target. The image now contains components resulting from the combination of the target and the superimposed light structure, e.g. moiré fringes, and carries information about target detail which simple unstructured illumination does not. The “superresolved” components, however, need disentangling to be revealed. For an example, see structured illumination (figure to left). ==== Multiple parameter use within traditional diffraction limit ==== If a target has no special polarization or wavelength properties, two polarization states or non-overlapping wavelength regions can be used to encode target details, one in a spatial-frequency band inside the cut-off limit the other beyond it. Both would use normal passband transmission but are then separately decoded to reconstitute target structure with extended resolution. ==== Probing near-field electromagnetic disturbance ==== Super-resolution microscopy is generally discussed within the realm of conventional optical imagery. However, modern technology allows the probing of electromagnetic disturbance within molecular distances of the source, which has superior resolution properties. See also evanescent waves and the development of the new super lens. === Geometrical or image-processing super-resolution === ==== Multi-exposure image noise reduction ==== When an image is degraded by noise, the resolution may be improved by averaging multiple exposures. See example on the right. ==== Single-frame deblurring ==== Known defects in a given imaging situation, such as defocus or aberrations, can sometimes be mitigated in whole or in part by suitable spatial-frequency filtering of even a single image. Such procedures all stay within the diffraction-mandated passband, and do not extend it. ==== Sub-pixel image localization ==== The location of a single source can be determined by computing the "center of gravity" (centroid) of the light distribution extending over several adjacent pixels (see figure on the left). Provided that there is enough light, this can be achieved with arbitrary precision, very much better than pixel width of the detecting apparatus and the resolution limit for the decision of whether the source is single or double. This technique, which requires the presupposition that all the light comes from a single source, is at the basis of what has become known as super-resolution microscopy, e.g. stochastic optical reconstruction microscopy (STORM), where fluorescent probes attached to molecules give nanoscale distance information. It is also the mechanism underlying visual hyperacuity. ==== Bayesian induction beyond traditional diffraction limit ==== Some object features, though beyond the diffraction limit, may be known to be associated with other object features that are within the limits and hence contained in the image. Then conclusions can be drawn, using statistical methods, from the available image data about the presence of the full object. The classical example is Toraldo di Francia's proposition of judging whether an image is that of a single or double star by determining whether its width exceeds the spread from a single star. This can be achieved at separations well below the classical resolution bounds, and requires the prior limitation to the choice "single or double?" The approach can take the form of extrapolating the image in the frequency domain, by assuming that the object is an analytic function, and that we can exactly know the function values in some interval. This method is severely limited by the ever-present noise in digital imaging systems, but it can work for radar, astronomy, microscopy or magnetic resonance imaging. More recently, a fast single image super-resolution algorithm based on a closed-form solution to ℓ 2 − ℓ 2 {\displaystyle \ell _{2}-\ell _{2}} problems has been proposed and demonstrated to accelerate most of the existing Bayesian super-resolution methods significantly. == Aliasing == Geometrical SR reconstruction algorithms are possible if and only if the input low resolution images have been under-sampled and therefore contain aliasing. Because of this aliasing, the high-frequency content of the desired reconstruction image is embedded in the low-frequency content of each of the observed images. Given a sufficient number of observation images, and if the set of observations vary in their phase (i.e. if the images of the scene are shifted by a sub-pixel amount), then the phase information can be used to separate the aliased high-frequency content from the true low-frequency content, and the full-resolution image can be accurate
Read more →
Fragment (computer graphics)

In computer graphics, a fragment is the data necessary to generate a single pixel's worth of a drawing primitive in the frame buffer. These data may include, but are not limited to: raster position depth interpolated attributes (color, texture coordinates, etc.) stencil alpha window ID As a scene is drawn, drawing primitives (the basic elements of graphics output, such as points, lines, circles, text etc.) are rasterized into fragments which are textured and combined with the existing frame buffer. How a fragment is combined with the data already in the frame buffer depends on various settings. In a typical case, a fragment may be discarded if it is further away than the pixel which is already at that location (according to the depth buffer). If it is nearer than the existing pixel, it may replace what is already there, or, if alpha blending is in use, the pixel's color may be replaced with a mixture of the fragment's color and the pixel's existing color, as in the case of drawing a translucent object. In general, a fragment can be thought of as the data needed to shade the pixel, plus the data needed to test whether the fragment survives to become a pixel (depth, alpha, stencil, scissor, window ID, etc.). Shading a fragment is done through a fragment shader (or pixel shaders in Direct3D). In computer graphics, a fragment is not necessarily opaque, and could contain an alpha value specifying its degree of transparency. The alpha is typically normalized to the range of [0, 1], with 0 denotes totally transparent and 1 denotes totally opaque. If the fragment is not totally opaque, then part of its background object could show through, which is known as alpha blending.
Read more →
Waveform graphics

Waveform graphics is a simple vector graphics system introduced by Digital Equipment Corporation (DEC) on the VT55 and VT105 terminals in the mid-1970s. It was used to produce graphics output from mainframes and minicomputers. DEC used the term "waveform graphics" to refer specifically to the hardware, but it was used more generally to describe the whole system. The system was designed to use as little computer memory as possible. At any given X location it could draw two dots at given Y locations, making it suitable for producing two superimposed waveforms, line charts or histograms. Text and graphics could be mixed, and there were additional tools for drawing axes and markers. The waveform graphics system was used only for a short period of time before it was replaced by the more sophisticated ReGIS system, first introduced on the VT125 in 1981. ReGIS allowed the construction of arbitrary vectors and other shapes. Whereas DEC normally provided a backward compatible solution in newer terminal models, they did not choose to do this when ReGIS was introduced, and waveform graphics disappeared from later terminals. == Description == Waveform graphics was introduced on the VT55 terminal in October 1975, an era when memory was extremely expensive. Although it was technically possible to produce a bitmap display using a framebuffer using technology of the era, the memory needed to do so at a reasonable resolution was typically beyond the price point that made it practical. All sorts of systems were used to replace computer memory with other concepts, like the storage tubes used in the Tektronix 4010 terminals, or the zero memory racing-the-beam system used in the Atari 2600. DEC chose to attack this problem through a clever use of a small buffer representing only the vertical positions on the screen. Such a system could not draw arbitrary shapes, but would allow the display of graph data. The system was based on a 512 by 236 pixel display, producing 512 vertical columns along the X-axis, and 236 horizontal rows on the Y-axis. Y locations were counted up from the bottom, so the coordinate 0,0 was in the lower left, and 511, 235 in the upper right. Had this been implemented using a framebuffer with each location represented by a single bit, 512 × 236 × 1 = 120,832 bits, or 15,104 bytes, would have been required. At the time, memory cost about $50 per kilobyte, so the buffer alone would cost over $700 (equivalent to $4,570 in 2025). Instead, the waveform graphic system used one byte of memory for each X axis location, with the byte's value representing the Y location. This required only 512 bytes for each graph, a total of 1024 bytes for the two graphs. Drawing a line required the programmer to construct a series of Y locations and send them as individual points, the terminal could not connect the dots itself. To make this easier, the terminal automatically incremented the X location every time an Y coordinate was received, so a graph line could be sent as a long string of numbers for subsequent Y locations instead of having to repeatedly send the X location every time. Drawing normally started by sending a single instruction to set the initial X location, often 0 on the left, and then sending in data for the entire curve. The system also included storage for up to 512 markers on both lines. These were always drawn centered on the Y value of the line they were associated with, meaning that a simple on/off indication for X locations was all that was needed, requiring only 1024 bits, or 128 bytes, in total. The markers extended 16 pixels vertically, and could only be aligned on 16-pixel boundaries, so they were not necessarily centered across the underlying graph. Markers were used to indicate important points on the graph, where a symbol of some sort would normally be used. The system also allowed a vertical line to be drawn for every horizontal location and a horizontal one at every vertical location. These were also stored as simple on/off bits, requiring another 128 bytes of memory. These lines were used to draw axes and scale lines, or could be used for a screen-spanning crosshair cursor. A separate set of two 7-bit registers held additional information about the drawing style and other settings. Although complex from the user's perspective, this system was easy to implement in hardware. A cathode ray tube produces a display by scanning the screen in a series of horizontal motions, moving down one vertical line after each horizontal scan. At any given instant during this process, the display hardware examines a few memory locations to see if anything needs to be displayed. For instance, it can determine whether to draw a marker on graph 0 by examining register 1 to see if markers are turned on, looking in the marker buffer to see if there is a 1 at the current X location, and then examining the Y location of graph 0 to see if it is within 16 pixels of the current scan line. If all of these are true, a spot is drawn to present that portion of the marker. As this will be true for 16 vertical locations during the scanning process, a 16-pixel high marker will be drawn. Sold alone, the VT55 was priced at $2,496 (equivalent to $16,295 in 2025),. Like other models of the VT50 series, the terminal could be equipped with an optional wet-paper printer in a panel on the right of the screen. This added $800 (equivalent to $5,223 in 2025) to the price. DEC also offered VT55 in a package with a small model of the PDP-11 to create one model of the DEClab 11/03 system. The DEClab normally sold for $14,000 (equivalent to $91,397 in 2025) with a DECwriter II (LA36) hard-copy terminal for $15,000 (equivalent to $97,925 in 2025), with the VT55. The system had I/O channels for up to 15 lab devices, and included libraries for FORTRAN and BASIC for reading the data and creating graphs. The fairly extensive VT55 Programmers Manual covered the latter in depth. == Commands and data == Data was sent to the terminal using an extended set of codes similar to those introduced on the VT52. VT52 codes generally started with the ESC character (octal 33, decimal 27) and was then followed by a single letter instruction. For instance, the string of four characters ESC H ESC J would reposition the cursor in the upper left (home) and then clear the screen from that point down. These codes were basically modeless; triggered by the ESC the resulting escape mode automatically exited again when the command was complete. Escape codes could be interspersed with display text anywhere in the stream of data. In contrast, the graphics system was entirely modal, with escape sequences being sent to cause the terminal to enter or exit graph drawing mode. Data sent between these two codes were interpreted by the graphics hardware, so text and graphics could not be mixed in a single stream of instructions. Graphics mode was entered by sending the string ESC 1, and exited again with the string ESC 2. Even the commands within the graphics mode were modal; characters were interpreted as being additional data for the previous load character (command) until another load character is seen. Ten load characters were available: @ - no operation, used to tell the terminal the last command is no longer active A - load data into register 0, selecting the drawing mode for the two graphs I - load data into register 1, selecting other drawing options H - load the starting X position (Horizontal) for the following commands B - load data for Y locations for graph 0 starting at the H position selected earlier J - load data for Y locations for graph 1 starting at the H position selected earlier C - store a marker on graph 0 at the following X location K - store a marker on graph 1 at the following X location D - draw a horizontal line at the given Y location L - draw a vertical line at the given X location X and Y locations were sent as 10-bit decimal numbers, encoded as ASCII characters, with 5 bits per character. This means that any number within the 1024 number space (210) can be stored as a string of two characters. To ensure the characters can be transmitted over 7-bit links, the pattern 01 is placed in front of both 5-bit numbers, producing 7-bit ASCII values that are always within the printable range. This results in a somewhat complex encoding algorithm. For instance, if one wanted to encode the decimal value 102, first you convert that to the 10-bit decimal pattern 0010010010. That is then split that into upper and lower 5-bit parts, 00100 and 10010. Then append 01 binary to produce 7-bit numbers 0100100 and 0110010. Individually convert back to decimal 40 and 50, and then look up those characters in an ASCII chart, finding ( and 2. These have to be sent to the terminal least significant character first. If these were being used to set the X coordinate, the complete string would be H2(. When used as X and Y locations for the graphs, extra digits were ignored. For instance, the 512 pixel X axis r
Read more →
Lossless join decomposition

In database design, a lossless join decomposition is a decomposition of a relation r {\displaystyle r} into relations r 1 , r 2 {\displaystyle r_{1},r_{2}} such that a natural join of the two smaller relations yields back the original relation. This is central in removing redundancy safely from databases while preserving the original data. Lossless join can also be called non-additive. == Definition == A relation r {\displaystyle r} on schema R {\displaystyle R} decomposes losslessly onto schemas R 1 {\displaystyle R_{1}} and R 2 {\displaystyle R_{2}} if π R 1 ( r ) ⋈ π R 2 ( r ) = r {\displaystyle \pi _{R_{1}}(r)\bowtie \pi _{R_{2}}(r)=r} , that is r {\displaystyle r} is the natural join of its projections onto the smaller schemas. A pair ( R 1 , R 2 ) {\displaystyle (R_{1},R_{2})} is a lossless-join decomposition of R {\displaystyle R} or said to have a lossless join with respect to a set of functional dependencies F {\displaystyle F} if any relation r ( R ) {\displaystyle r(R)} that satisfies F {\displaystyle F} decomposes losslessly onto R 1 {\displaystyle R_{1}} and R 2 {\displaystyle R_{2}} . Decompositions into more than two schemas can be defined in the same way. == Criteria == A decomposition R = R 1 ∪ R 2 {\displaystyle R=R_{1}\cup R_{2}} has a lossless join with respect to F {\displaystyle F} if and only if the closure of R 1 ∩ R 2 {\displaystyle R_{1}\cap R_{2}} includes R 1 ∖ R 2 {\displaystyle R_{1}\setminus R_{2}} or R 2 ∖ R 1 {\displaystyle R_{2}\setminus R_{1}} . In other words, one of the following must hold: ( R 1 ∩ R 2 ) → ( R 1 ∖ R 2 ) ∈ F + {\displaystyle (R_{1}\cap R_{2})\to (R_{1}\setminus R_{2})\in F^{+}} ( R 1 ∩ R 2 ) → ( R 2 ∖ R 1 ) ∈ F + {\displaystyle (R_{1}\cap R_{2})\to (R_{2}\setminus R_{1})\in F^{+}} === Criteria for multiple sub-schemas === Multiple sub-schemas R 1 , R 2 , . . . , R n {\displaystyle R_{1},R_{2},...,R_{n}} have a lossless join if there is some way in which we can repeatedly perform lossless joins until all the schemas have been joined into a single schema. Once we have a new sub-schema made from a lossless join, we are not allowed to use any of its isolated sub-schema to join with any of the other schemas. For example, if we can do a lossless join on a pair of schemas R i , R j {\displaystyle R_{i},R_{j}} to form a new schema R i , j {\displaystyle R_{i,j}} , we use this new schema (rather than R i {\displaystyle R_{i}} or R j {\displaystyle R_{j}} ) to form a lossless join with another schema R k {\displaystyle R_{k}} (which may already be joined (e.g., R k , l {\displaystyle R_{k,l}} )). == Example == Let R = { A , B , C , D } {\displaystyle R=\{A,B,C,D\}} be the relation schema, with attributes A, B, C and D. Let F = { A → B C } {\displaystyle F=\{A\rightarrow BC\}} be the set of functional dependencies. Decomposition into R 1 = { A , B , C } {\displaystyle R_{1}=\{A,B,C\}} and R 2 = { A , D } {\displaystyle R_{2}=\{A,D\}} is lossless under F because R 1 ∩ R 2 = A {\displaystyle R_{1}\cap R_{2}=A} and we have a functional dependency A → B C {\displaystyle A\rightarrow BC} . In other words, we have proven that ( R 1 ∩ R 2 → R 1 ∖ R 2 ) ∈ F + {\displaystyle (R_{1}\cap R_{2}\rightarrow R_{1}\setminus R_{2})\in F^{+}} .
Read more →
Instance selection

Instance selection (or dataset reduction, or dataset condensation) is an important data pre-processing step that can be applied in many machine learning (or data mining) tasks. Approaches for instance selection can be applied for reducing the original dataset to a manageable volume, leading to a reduction of the computational resources that are necessary for performing the learning process. Algorithms of instance selection can also be applied for removing noisy instances, before applying learning algorithms. This step can improve the accuracy in classification problems. Algorithm for instance selection should identify a subset of the total available data to achieve the original purpose of the data mining (or machine learning) application as if the whole data had been used. Considering this, the optimal outcome of IS would be the minimum data subset that can accomplish the same task with no performance loss, in comparison with the performance achieved when the task is performed using the whole available data. Therefore, every instance selection strategy should deal with a trade-off between the reduction rate of the dataset and the classification quality. == Instance selection algorithms == The literature provides several different algorithms for instance selection. They can be distinguished from each other according to several different criteria. Considering this, instance selection algorithms can be grouped in two main classes, according to what instances they select: algorithms that preserve the instances at the boundaries of classes and algorithms that preserve the internal instances of the classes. Within the category of algorithms that select instances at the boundaries it is possible to cite DROP3, ICF and LSBo. On the other hand, within the category of algorithms that select internal instances, it is possible to mention ENN and LSSm. In general, algorithm such as ENN and LSSm are used for removing harmful (noisy) instances from the dataset. They do not reduce the data as the algorithms that select border instances, but they remove instances at the boundaries that have a negative impact on the data mining task. They can be used by other instance selection algorithms, as a filtering step. For example, the ENN algorithm is used by DROP3 as the first step, and the LSSm algorithm is used by LSBo. There is also another group of algorithms that adopt different selection criteria. For example, the algorithms LDIS, CDIS and XLDIS select the densest instances in a given arbitrary neighborhood. The selected instances can include both, border and internal instances. The LDIS and CDIS algorithms are very simple and select subsets that are very representative of the original dataset. Besides that, since they search by the representative instances in each class separately, they are faster (in terms of time complexity and effective running time) than other algorithms, such as DROP3 and ICF. Besides that, there is a third category of algorithms that, instead of selecting actual instances of the dataset, select prototypes (that can be synthetic instances). In this category it is possible to include PSSA, PSDSP and PSSP. The three algorithms adopt the notion of spatial partition (a hyperrectangle) for identifying similar instances and extract prototypes for each set of similar instances. In general, these approaches can also be modified for selecting actual instances of the datasets. The algorithm ISDSP adopts a similar approach for selecting actual instances (instead of prototypes).
Read more →
Truth discovery

Truth discovery (also known as truth finding) is the process of choosing the actual true value for a data item when different data sources provide conflicting information on it. Several algorithms have been proposed to tackle this problem, ranging from simple methods like majority voting to more complex ones able to estimate the trustworthiness of data sources. Truth discovery problems can be divided into two sub-classes: single-truth and multi-truth. In the first case only one true value is allowed for a data item (e.g birthday of a person, capital city of a country). While in the second case multiple true values are allowed (e.g. cast of a movie, authors of a book). Typically, truth discovery is the last step of a data integration pipeline, when the schemas of different data sources have been unified and the records referring to the same data item have been detected. == General principles == The abundance of data available on the web makes more and more probable to find that different sources provide (partially or completely) different values for the same data item. This, together with the fact that we are increasing our reliance on data to derive important decisions, motivates the need of developing good truth discovery algorithms. Many currently available methods rely on a voting strategy to define the true value of a data item. Nevertheless, recent studies, have shown that, if we rely only on majority voting, we could get wrong results even in 30% of the data items. The solution to this problem is to assess the trustworthiness of the sources and give more importance to votes coming from trusted sources. Ideally, supervised learning techniques could be exploited to assign a reliability score to sources after hand-crafted labeling of the provided values; unfortunately, this is not feasible since the number of needed labeled examples should be proportional to the number of sources, and in many applications the number of sources can be prohibitive. == Single-truth vs multi-truth discovery == Single-truth and multi-truth discovery are two very different problems. Single-truth discovery is characterized by the following properties: only one true value is allowed for each data item; different values provided for a given data item oppose to each other; values and sources can either be correct or erroneous. While in the multi-truth case the following properties hold: the truth is composed by a set of values; different values could provide a partial truth; claiming one value for a given data item does not imply opposing to all the other values; the number of true values for each data item is not known a priori. Multi-truth discovery has unique features that make the problem more complex and should be taken into consideration when developing truth-discovery solutions. The examples below point out the main differences of the two methods. Knowing that in both examples the truth is provided by source 1, in the single truth case (first table) we can say that sources 2 and 3 oppose to the truth and as a result provide wrong values. On the other hand, in the second case (second table), sources 2 and 3 are neither correct nor erroneous, they instead provide a subset of the true values and at the same time they do not oppose the truth. == Source trustworthiness == The vast majority of truth discovery methods are based on a voting approach: each source votes for a value of a certain data item and, at the end, the value with the highest vote is select as the true one. In the more sophisticated methods, votes do not have the same weight for all the data sources, more importance is indeed given to votes coming from trusted sources. Source trustworthiness usually is not known a priori but estimated with an iterative approach. At each step of the truth discovery algorithm the trustworthiness score of each data source is refined, improving the assessment of the true values that in turn leads to a better estimation of the trustworthiness of the sources. This process usually ends when all the values reach a convergence state. Source trustworthiness can be based on different metrics, such as accuracy of provided values, copying values from other sources and domain coverage. Detecting copying behaviors is very important, in fact, copy allows to spread false values easily making truth discovery very hard, since many sources would vote for the wrong values. Usually systems decrease the weight of votes associated to copied values or even don’t count them at all. == Single-truth methods == Most of the currently available truth discovery methods have been designed to work well only in the single-truth case. Below are reported some of the characteristics of the most relevant typologies of single-truth methods and how different systems model source trustworthiness. === Majority voting === Majority voting is the simplest method, the most popular value is selected as the true one. Majority voting is commonly used as a baseline when assessing the performances of more complex methods. === Web-link based === These methods estimate source trustworthiness exploiting a similar technique to the one used to measure authority of web pages based on web links. The vote assigned to a value is computed as the sum of the trustworthiness of the sources that provide that particular value, while the trustworthiness of a source is computed as the sum of the votes assigned to the values that the source provides. === Information-retrieval based === These methods estimate source trustworthiness using similarity measures typically used in information retrieval. Source trustworthiness is computed as the cosine similarity (or other similarity measures) between the set of values provided by the source and the set of values considered true (either selected in a probabilistic way or obtained from a ground truth). === Bayesian based === These methods use Bayesian inference to define the probability of a value being true conditioned on the values provided by all the sources. P ( v ∣ ψ ( o ) ) = P ( ψ ( o ) ∣ v ) ⋅ P ( v ) P ( ψ ( o ) ) {\displaystyle P(v\mid \psi (o))={\frac {P(\psi (o)\mid v)\cdot P(v)}{P(\psi (o))}}} where v {\displaystyle \textstyle v} is a value provided for a data item o {\displaystyle \textstyle o} and ψ ( o ) {\displaystyle \textstyle \psi (o)} is the set of the observed values provided by all the sources for that specific data item. The trustworthiness of a source is then computed based on the accuracy of the values that provides. Other more complex methods exploit Bayesian inference to detect copying behaviors and use these insights to better assess source trustworthiness. == Multi-truth methods == Due to its complexity, less attention has been devoted to the study of the multi-truth discovery Below are reported two typologies of multi-truth methods and their characteristics. === Bayesian based === These methods use Bayesian inference to define the probability of a group of values being true conditioned on the values provided by all the data sources. In this case, since there could be multiple true values for each data item, and sources can provide multiple values for a single data item, it is not possible to consider values individually. An alternative is to consider mappings and relations between set of provided values and sources providing them. The trustworthiness of a source is then computed based on the accuracy of the values that provides. More sophisticated methods also consider domain coverage and copying behaviors to better estimate source trustworthiness. === Probabilistic Graphical Models based === These methods use probabilistic graphical models to automatically define the set of true values of given data item and also to assess source quality without need of any supervision. == Applications == Many real-world applications can benefit from the use of truth discovery algorithms. Typical domains of application include: healthcare, crowd/social sensing, crowdsourcing aggregation, information extraction and knowledge base construction. Truth discovery algorithms could be also used to revolutionize the way in which web pages are ranked in search engines, going from current methods based on link analysis like PageRank, to procedures that rank web pages based on the accuracy of the information they provide.
Read more →
ImageNet

The ImageNet project is a large visual database designed for use in visual object recognition software research. More than 14 million images have been hand-annotated by the project to indicate what objects are pictured and in at least one million of the images, bounding boxes are also provided. ImageNet contains more than 20,000 categories, with a typical category, such as "balloon" or "strawberry", consisting of several hundred images. The database of annotations of third-party image URLs is freely available directly from ImageNet, though the actual images are not owned by ImageNet. Since 2010, the ImageNet project runs an annual software contest, the ImageNet Large Scale Visual Recognition Challenge (ILSVRC), where software programs compete to correctly classify and detect objects and scenes. The challenge uses a "trimmed" list of one thousand non-overlapping classes. == History == AI researcher Fei-Fei Li began working on the idea for ImageNet in 2006. At a time when most AI research focused on models and algorithms, Li wanted to expand and improve the data available to train AI algorithms. In 2007, Li met with Princeton professor Christiane Fellbaum, one of the creators of WordNet, to discuss the project. As a result of this meeting, Li went on to build ImageNet starting from the roughly 22,000 nouns of WordNet and using many of its features. She was also inspired by a 1987 estimate that the average person recognizes roughly 30,000 different kinds of objects. As an assistant professor at Princeton, Li assembled a team of researchers to work on the ImageNet project. They used Amazon Mechanical Turk to help with the classification of images. Labeling started in July 2008 and ended in April 2010. It took 49K workers from 167 countries filtering and labeling over 160M candidate images. They had enough budget to have each of the 14 million images labelled three times. The original plan called for 10,000 images per category, for 40,000 categories at 400 million images, each verified 3 times. They found that humans can classify at most 2 images/sec. At this rate, it was estimated to take 19 human-years of labor (without rest). They presented their database for the first time as a poster at the 2009 Conference on Computer Vision and Pattern Recognition (CVPR) in Florida, titled "ImageNet: A Preview of a Large-scale Hierarchical Dataset". The poster was reused at Vision Sciences Society 2009. In 2009, Alex Berg suggested adding object localization as a task. Li approached PASCAL Visual Object Classes contest in 2009 for a collaboration. It resulted in the subsequent ImageNet Large Scale Visual Recognition Challenge starting in 2010, which has 1000 classes and object localization, as compared to PASCAL VOC which had just 20 classes and 19,737 images (in 2010). === Significance for deep learning === On 30 September 2012, a convolutional neural network (CNN) called AlexNet achieved a top-5 error of 15.3% in the ImageNet 2012 Challenge, more than 10.8 percentage points lower than that of the runner-up. Using convolutional neural networks was feasible due to the use of graphics processing units (GPUs) during training, an essential ingredient of the deep learning revolution. According to The Economist, "Suddenly people started to pay attention, not just within the AI community but across the technology industry as a whole." In 2015, AlexNet was outperformed by Microsoft's very deep CNN with over 100 layers, which won the ImageNet 2015 contest, having 3.57% error on the test set. Andrej Karpathy estimated in 2014 that with concentrated effort, he could reach 5.1% error rate, and ~10 people from his lab reached ~12-13% with less effort. It was estimated that with maximal effort, a human could reach 2.4%. == Dataset == ImageNet crowdsources its annotation process. Image-level annotations indicate the presence or absence of an object class in an image, such as "there are tigers in this image" or "there are no tigers in this image". Object-level annotations provide a bounding box around the (visible part of the) indicated object. ImageNet uses a variant of the broad WordNet schema to categorize objects, augmented with 120 categories of dog breeds to showcase fine-grained classification. In 2012, ImageNet was the world's largest academic user of Mechanical Turk. The average worker identified 50 images per minute. The original plan of the full ImageNet would have roughly 50M clean, diverse and full resolution images spread over approximately 50K synsets. This was not achieved. The summary statistics given on April 30, 2010: Total number of non-empty synsets: 21841 Total number of images: 14,197,122 Number of images with bounding box annotations: 1,034,908 Number of synsets with SIFT features: 1000 Number of images with SIFT features: 1.2 million === Categories === The categories of ImageNet were filtered from the WordNet concepts. Each concept, since it can contain multiple synonyms (for example, "kitty" and "young cat"), so each concept is called a "synonym set" or "synset". There were more than 100,000 synsets in WordNet 3.0, majority of them are nouns (80,000+). The ImageNet dataset filtered these to 21,841 synsets that are countable nouns that can be visually illustrated. Each synset in WordNet 3.0 has a "WordNet ID" (wnid), which is a concatenation of part of speech and an "offset" (a unique identifying number). Every wnid starts with "n" because ImageNet only includes nouns. For example, the wnid of synset "dog, domestic dog, Canis familiaris" is "n02084071". The categories in ImageNet fall into 9 levels, from level 1 (such as "mammal") to level 9 (such as "German shepherd"). === Image format === The images were scraped from online image search (Google, Picsearch, MSN, Yahoo, Flickr, etc) using synonyms in multiple languages. For example: German shepherd, German police dog, German shepherd dog, Alsatian, ovejero alemán, pastore tedesco, 德国牧羊犬. ImageNet consists of images in RGB format with varying resolutions. For example, in ImageNet 2012, "fish" category, the resolution ranges from 4288 x 2848 to 75 x 56. In machine learning, these are typically preprocessed into a standard constant resolution, and whitened, before further processing by neural networks. For example, in PyTorch, ImageNet images are by default normalized by dividing the pixel values so that they fall between 0 and 1, then subtracting by [0.485, 0.456, 0.406], then dividing by [0.229, 0.224, 0.225]. These are the mean and standard deviations for ImageNet, so this whitens the input data. === Labels and annotations === Each image is labelled with exactly one wnid. Dense SIFT features (raw SIFT descriptors, quantized codewords, and coordinates of each descriptor/codeword) for ImageNet-1K were available for download, designed for bag of visual words. The bounding boxes of objects were available for about 3000 popular synsets with on average 150 images in each synset. Furthermore, some images have attributes. They released 25 attributes for ~400 popular synsets: Color: black, blue, brown, gray, green, orange, pink, red, violet, white, yellow Pattern: spotted, striped Shape: long, round, rectangular, square Texture: furry, smooth, rough, shiny, metallic, vegetation, wooden, wet === ImageNet-21K === The full original dataset is referred to as ImageNet-21K. ImageNet-21k contains 14,197,122 images divided into 21,841 classes. Some papers round this up and name it ImageNet-22k. The full ImageNet-21k was released in Fall of 2011, as fall11_whole.tar. There is no official train-validation-test split for ImageNet-21k. Some classes contain only 1-10 samples, while others contain thousands. === ImageNet-1K === There are various subsets of the ImageNet dataset used in various context, sometimes referred to as "versions". One of the most highly used subsets of ImageNet is the "ImageNet Large Scale Visual Recognition Challenge (ILSVRC) 2012–2017 image classification and localization dataset". This is also referred to in the research literature as ImageNet-1K or ILSVRC2017, reflecting the original ILSVRC challenge that involved 1,000 classes. ImageNet-1K contains 1,281,167 training images, 50,000 validation images and 100,000 test images. Each category in ImageNet-1K is a leaf category, meaning that there are no child nodes below it, unlike ImageNet-21K. For example, in ImageNet-21K, there are some images categorized as simply "mammal", whereas in ImageNet-1K, there are only images categorized as things like "German shepherd", since there are no child-words below "German shepherd". === Later developments === In the WordNet they built ImageNet on, there were 2832 synsets in the "person" subtree. During 2018--2020 period, they removed the download of the ImageNet-21k as they went through extensive filtering in these person synsets. Out of these 2832 synsets, 1593 were deemed "potentially offensive". Out of the remaining 1239, 1081 were deemed not really "visual". The result was that only 158 syn
Read more →
Texture compression

Texture compression is a specialized form of image compression designed for storing texture maps in 3D computer graphics rendering systems. Unlike conventional image compression algorithms, texture compression algorithms are optimized for random access. Texture compression can be applied to reduce memory usage at runtime. Texture data is often the largest source of memory usage in a mobile application. == Tradeoffs == In their seminal paper on texture compression, Beers, Agrawala and Chaddha list four features that tend to differentiate texture compression from other image compression techniques. These features are: Decoding Speed It is highly desirable to be able to render directly from the compressed texture data and so, in order not to impact rendering performance, decompression must be fast. Random Access Since predicting the order that a renderer accesses texels would be difficult, any texture compression scheme must allow fast random access to decompressed texture data. This tends to rule out many better-known image compression schemes such as JPEG or run-length encoding. Compression Rate and Visual Quality In a rendering system, lossy compression can be more tolerable than for other use cases. Some texture compression libraries, such as crunch, allow the developer to flexibly trade off compression rate vs. visual quality, using methods such as rate–distortion optimization (RDO). Encoding Speed Texture compression is more tolerant of asymmetric encoding/decoding rates as the encoding process is often done only once during the application authoring process. Given the above, most texture compression algorithms involve some form of fixed-rate lossy vector quantization of small fixed-size blocks of pixels into small fixed-size blocks of coding bits, sometimes with additional extra pre-processing and post-processing steps. Block Truncation Coding is a very simple example of this family of algorithms. Because their data access patterns are well-defined, texture decompression may be executed on-the-fly during rendering as part of the overall graphics pipeline, reducing overall bandwidth and storage needs throughout the graphics system. As well as texture maps, texture compression may also be used to encode other kinds of rendering map, including bump maps and surface normal maps. Texture compression may also be used together with other forms of map processing such as mipmaps and anisotropic filtering. == Availability == Some examples of practical texture compression systems are S3 Texture Compression (S3TC), PVRTC, Ericsson Texture Compression (ETC) and Adaptive Scalable Texture Compression (ASTC); these may be supported by special function units in modern graphics processing units (GPUs). OpenGL and OpenGL ES, as implemented on many video accelerator cards and mobile GPUs, can support multiple common kinds of texture compression - generally through the use of vendor extensions. == Supercompression == A compressed-texture can be further compressed in what is called "supercompression". Fixed-rate texture compression formats are optimized for random access and are much less efficient compared to image formats such as PNG. By adding further compression, a programmer can reduce the efficiency gap. The extra layer can be decompressed by the CPU so that the GPU receives a normal compressed texture, or in newer methods, decompressed by the GPU itself. Supercompression saves the same amount of VRAM as regular texture compression, but saves more disk space and download size. == Neural Texture Compression == Random-Access Neural Compression of Material Textures (Neural Texture Compression) is a Nvidia's technology which enables two additional levels of detail (16× more texels, so four times higher resolution) while maintaining similar storage requirements as traditional texture compression methods. The key idea is compressing multiple material textures and their mipmap chains together, and using a small neural network, that is optimized for each material, to decompress them.
Read more →
Sentence extraction

Sentence extraction is a technique used for automatic summarization of a text. In this shallow approach, statistical heuristics are used to identify the most salient sentences of a text. Sentence extraction is a low-cost approach compared to more knowledge-intensive deeper approaches which require additional knowledge bases such as ontologies or linguistic knowledge. In short, sentence extraction works as a filter that allows only meaningful sentences to pass. The major downside of applying sentence-extraction techniques to the task of summarization is the loss of coherence in the resulting summary. Nevertheless, sentence extraction summaries can give valuable clues to the main points of a document and are frequently sufficiently intelligible to human readers. == Procedure == Usually, a combination of heuristics is used to determine the most important sentences within the document. Each heuristic assigns a (positive or negative) score to the sentence. After all heuristics have been applied, the highest-scoring sentences are included in the summary. The individual heuristics are weighted according to their importance. === Early approaches and some sample heuristics === Seminal papers which laid the foundations for many techniques used today have been published by Hans Peter Luhn in 1958 and H. P Edmundson in 1969. Luhn proposed to assign more weight to sentences at the beginning of the document or a paragraph. Edmundson stressed the importance of title-words for summarization and was the first to employ stop-lists in order to filter uninformative words of low semantic content (e.g. most grammatical words such as of, the, a). He also distinguished between bonus words and stigma words, i.e. words that probably occur together with important (e.g. the word form significant) or unimportant information. His idea of using key-words, i.e. words which occur significantly frequently in the document, is still one of the core heuristics of today's summarizers. With large linguistic corpora available today, the tf–idf value which originated in information retrieval, can be successfully applied to identify the key words of a text: If for example the word cat occurs significantly more often in the text to be summarized (TF = "term frequency") than in the corpus (IDF means "inverse document frequency"; here the corpus is meant by document), then cat is likely to be an important word of the text; the text may in fact be a text about cats.
Read more →
Texture compression

Texture compression is a specialized form of image compression designed for storing texture maps in 3D computer graphics rendering systems. Unlike conventional image compression algorithms, texture compression algorithms are optimized for random access. Texture compression can be applied to reduce memory usage at runtime. Texture data is often the largest source of memory usage in a mobile application. == Tradeoffs == In their seminal paper on texture compression, Beers, Agrawala and Chaddha list four features that tend to differentiate texture compression from other image compression techniques. These features are: Decoding Speed It is highly desirable to be able to render directly from the compressed texture data and so, in order not to impact rendering performance, decompression must be fast. Random Access Since predicting the order that a renderer accesses texels would be difficult, any texture compression scheme must allow fast random access to decompressed texture data. This tends to rule out many better-known image compression schemes such as JPEG or run-length encoding. Compression Rate and Visual Quality In a rendering system, lossy compression can be more tolerable than for other use cases. Some texture compression libraries, such as crunch, allow the developer to flexibly trade off compression rate vs. visual quality, using methods such as rate–distortion optimization (RDO). Encoding Speed Texture compression is more tolerant of asymmetric encoding/decoding rates as the encoding process is often done only once during the application authoring process. Given the above, most texture compression algorithms involve some form of fixed-rate lossy vector quantization of small fixed-size blocks of pixels into small fixed-size blocks of coding bits, sometimes with additional extra pre-processing and post-processing steps. Block Truncation Coding is a very simple example of this family of algorithms. Because their data access patterns are well-defined, texture decompression may be executed on-the-fly during rendering as part of the overall graphics pipeline, reducing overall bandwidth and storage needs throughout the graphics system. As well as texture maps, texture compression may also be used to encode other kinds of rendering map, including bump maps and surface normal maps. Texture compression may also be used together with other forms of map processing such as mipmaps and anisotropic filtering. == Availability == Some examples of practical texture compression systems are S3 Texture Compression (S3TC), PVRTC, Ericsson Texture Compression (ETC) and Adaptive Scalable Texture Compression (ASTC); these may be supported by special function units in modern graphics processing units (GPUs). OpenGL and OpenGL ES, as implemented on many video accelerator cards and mobile GPUs, can support multiple common kinds of texture compression - generally through the use of vendor extensions. == Supercompression == A compressed-texture can be further compressed in what is called "supercompression". Fixed-rate texture compression formats are optimized for random access and are much less efficient compared to image formats such as PNG. By adding further compression, a programmer can reduce the efficiency gap. The extra layer can be decompressed by the CPU so that the GPU receives a normal compressed texture, or in newer methods, decompressed by the GPU itself. Supercompression saves the same amount of VRAM as regular texture compression, but saves more disk space and download size. == Neural Texture Compression == Random-Access Neural Compression of Material Textures (Neural Texture Compression) is a Nvidia's technology which enables two additional levels of detail (16× more texels, so four times higher resolution) while maintaining similar storage requirements as traditional texture compression methods. The key idea is compressing multiple material textures and their mipmap chains together, and using a small neural network, that is optimized for each material, to decompress them.
Read more →
T-pose

In computer animation, a T-pose is a default posing for a humanoid 3D model's skeleton before it is animated. It is called so because of its shape: the straight legs and arms of a humanoid model combine to form a capital letter T. When the arms are angled downwards, the pose is sometimes referred to as an A-pose instead. Likewise, if the arms are angled upward, it is called a Y-pose. Generic terms encompassing all these (especially for non-humanoid models) include bind pose, blind pose, and reference pose. == Usage == The T-pose is primarily used as the default armature pose for skeletal animation in 3D software, which is then manipulated to create animation. The purpose of the T-pose relates to the important elements of the body being axis-aligned, thereby making it easier to rig the model for animation, physics, and other controls. Depending on the exact geometry of the model, other poses such as the A-pose may be more suitable for vertex deformation around areas such as the shoulders. Outside of being default poses in animation software, T-poses are typically used as placeholders for animation not yet completed, particularly in 3D animated video games. In some motion capture software, a T-pose must be assumed by the actor in the motion capture suit before motion capturing can begin. There are other poses used, but the T-pose is the most common one. == As an Internet meme == Starting in 2016 and resurfacing in 2017, the T-pose has become a widespread Internet meme due to its bizarre and somewhat comedic appearance, especially in video game glitches where a character's animation is unexpectedly supplanted by a T-pose. In a prerelease video of the game NBA Elite 11, the demo was filled with glitches, notably one unintentionally showing a T-pose in place of the proper animation for the model of player Andrew Bynum. The glitch later gained fame as the "Jesus Bynum glitch". Publisher EA eventually cancelled the game as they found it unsatisfactory. A similar occurrence happened with Cyberpunk 2077. In the 2023 Formula One season, driver George Russell performed a T-pose in the opening credits of the series' TV broadcasts. This quickly became a meme within the motorsports community. Russell repeated the pose after claiming pole position at the 2024 Canadian Grand Prix and winning the 2024 Austrian Grand Prix.
Read more →
MY F.C.

MY F.C. is a freemium app designed to organise and administer football teams. It is developed by MY F.C. Limited, a private company headquartered in Auckland, New Zealand. The app allows users to build a team by adding players and from there they can create trainings and matches, keep up with relevant news in the curated newsfeed, record statistics both individually and team based, follow the games live in the match-centre. The app also features integrated lineup builder with custom team kits. == History == Founders Sam Jenkins, Mike Simpson and Sam Jasper started MY F.C. in 2015 to help them "run their football lives". The app was launched on Android and iOS on 14 February 2017. == Accolades == MY F.C. won the first place prize at Bank of New Zealand Start-up Alley 2017 competition that aims to discover New Zealand start-ups who are doing innovative work and ready to establish themselves as long-term, sustainable businesses. The prize package included $15,000 and a trip to San Francisco.
Read more →
BeeSafe

BeeSafe is a personal safety mobile app launched in 2015 as a Slovak startup. It is a location-based security service that notifies family members and friends in case the user of the app gets in danger. The app has received numerous awards. The app has more than 700 downloads and 250 active logins from more than 60 countries worldwide. == History == BeeSafe was founded on March 20, 2015 by Peter Stražovec and Michal Kačerík. The project was a winner of Žilina’s Startup Weekend 2013 and a StartupAwards.SK 2015 finalist. Later on, the app was released in the Android and iOS marketplace. The whole BeeSafe project was in The Spot booster and incubator in Bratislava for three months. BeeSafe entered into an agreement with the city of Piešťany in November 2015 to increase the security of its citizen by connecting the mobile app with the police platform. It is the first city that started using the BeeSafe platform. Further on, the application tries to help people in other Slovak cities. The cities can see the users only if they are in danger. == Awards == BeeSafe app received the Via Bona award, it is a winner of a Slovak startup and has other nominations too.
Read more →
Load file

A load file in the litigation community is commonly referred to as the file used to import data (coded, captured or extracted data from ESI processing) into a database; or the file used to link images. These load files carry commands, commanding the software to carry out certain functions with the data found in them. Load files are usually ASCII text files that have delimited fields of information. Such load files may have data about documents to be imported into a document management software such as Concordance or Summation. Or they may have the path or directory where images may reside so that the software can link such images to their corresponding records. Some database programs take one load file for importing images and another for importing data while others take only one load file for both pieces of information. OCR or Search-able Text which is considered "data" is also imported into most database programs via the same load files. Though some people prefer to load the OCR into their databases by running a separate command to search and find the desired text. Commonly used databases and their corresponding file extensions are: Summation (DII , CSV), Concordance (OPT, DAT), Sanction (SDT), IPRO (LFP), Ringtail (MDB) and DB/TextWorks (TXT).
Read more →
Mobile Passport Control

Mobile Passport Control (MPC) is a mobile app that enables eligible travelers entering the United States to submit their passport information and customs declaration form to Customs and Border Protection via smartphone or tablet and go through the inspections process using an expedited lane. It is available to "U.S. citizens, U.S. lawful permanent residents, Canadian B1/B2 citizen visitors and returning Visa Waiver Program travelers with approved ESTA". The app is available on iOS and Android devices and is operational at 34 US airports, 14 international airports offering preclearance facilities, and 4 seaports. The use of Mobile Passport Control operations have increased threefold from 2016 to 2017. == History == Mobile Passport Control operations were launched in Atlanta at the Hartsfield-Jackson International Airport in 2016 and is now available at 34 U.S. airports, 14 international airports that offer preclearance and 4 U.S. cruise ports. The Mobile Passport app is authorized by CBP and sponsored by the Airports Council International-North America, Boeing, and the Port of Everglades. Airside Mobile, Inc. secured a Series A funding of $6 million in the fall of 2017. == How it works == During the customs process at the Federal Inspection Service (FIS) area of a U.S. airport, travelers arriving from international locations typically wait in long lines before presenting passports and paperwork and verbally answering questions made by CBP officials. Eligible travelers who have downloaded the Mobile Passport app can expedite this process by submitting information regarding their passport and trip details, and a newly-taken selfie, via their mobile device to CBP officials, then access an expedited line. Mobile Passport Control users will be required to show their physical passport(s) and briefly talk to a CBP officer. == Locations == === US airports === Atlanta (ATL) Baltimore (BWI) Boston (BOS) Charlotte (CLT) Chicago (ORD) Dallas/Ft Worth (DFW) Denver (DEN) Detroit (DTW) as of 7/2024 Ft. Lauderdale (FLL) Honolulu (HNL) Houston (HOU and IAH) Kansas City (MCI) Las Vegas (LAS) Los Angeles (LAX) Miami (MIA) Minneapolis (MSP) New York (JFK) Newark (EWR) Oakland (OAK) Orlando (MCO) Palm Beach (PBI) Philadelphia (PHL) Phoenix (PHX) Pittsburgh (PIT) Portland (PDX) Sacramento (SMF) San Diego (SAN) San Francisco (SFO) San Jose (SJC) San Juan (SJU) Seattle (SEA) Tampa (TPA) Washington Dulles (IAD) === International Preclearance locations === Abu Dhabi (AUH) Aruba (AUA) Bermuda (BDA) Calgary (YYC) Dublin (DUB) Edmonton (YEG) Halifax (YHZ) Montreal (YUL) Nassau (NAS) Ottawa (YOW) Shannon (SNN) Toronto (YYZ) Vancouver (YVR) Winnipeg (YWG) Sepinggan (BPN) === Seaports === Fort Lauderdale (PEV) Miami (MSE) San Juan (PUE) West Palm Beach (WPB)
Read more →