AI Code Meme

AI Code Meme — independent reviews, comparisons, pricing and step-by-step guides on Aizhi.

• 

  Automotive security

  Automotive security refers to the branch of computer security focused on the cyber risks related to the automotive context. The increasingly high number of ECUs in vehicles and, alongside, the implementation of multiple different means of communication from and towards the vehicle in a remote and wireless manner led to the necessity of a branch of cybersecurity dedicated to the threats associated with vehicles. Not to be confused with automotive safety. == Causes == The implementation of multiple ECUs (Electronic Control Units) inside vehicles began in the early '70s thanks to the development of integrated circuits and microprocessors that made it economically feasible to produce the ECUs on a large scale. Since then the number of ECUs has increased to up to 100 per vehicle. These units nowadays control almost everything in the vehicle, from simple tasks such as activating the wipers to more safety-related ones like brake-by-wire or ABS (Anti-lock Braking System). Autonomous driving is also strongly reliant on the implementation of new, complex ECUs such as the ADAS, alongside sensors (lidars and radars) and their control units. Inside the vehicle, the ECUs are connected with each other through cabled or wireless communication networks, such as CAN bus (controller area network), MOST bus (Media Oriented System Transport), FlexRay (Automotive Network Communications Protocol) or RF (radio frequency) as in many implementations of TPMSs (tire-pressure monitoring systems). Many of these ECUs require data received through these networks that arrive from various sensors to operate and use such data to modify the behavior of the vehicle (e.g., the cruise control modifies the vehicle's speed depending on signals arriving from a button usually located on the steering wheel). Since the development of cheap wireless communication technologies such as Bluetooth, LTE, Wi-Fi, RFID and similar, automotive producers and OEMs have designed ECUs that implement such technologies with the goal of improving the experience of the driver and passengers. Safety-related systems such as the OnStar from General Motors, telematic units, communication between smartphones and the vehicle's speakers through Bluetooth, Android Auto and Apple CarPlay. == Threat model == Threat models of the automotive world are based on both real-world and theoretically possible attacks. Most real-world attacks aim at the safety of the people in and around the car, by modifying the cyber-physical capabilities of the vehicle (e.g., steering, braking, accelerating without requiring actions from the driver), while theoretical attacks have been supposed to focus also on privacy-related goals, such as obtaining GPS data on the vehicle, or capturing microphone signals and similar. Regarding the attack surfaces of the vehicle, they are usually divided in long-range, short-range, and local attack surfaces: LTE and DSRC can be considered long-range ones, while Bluetooth and Wi-Fi are usually considered short-range although still wireless. Finally, USB, OBD-II and all the attack surfaces that require physical access to the car are defined as local. An attacker that is able to implement the attack through a long-range surface is considered stronger and more dangerous than the one that requires physical access to the vehicle. In 2015 the possibility of attacks on vehicles already on the market has been proven possible by Miller and Valasek, that managed to disrupt the driving of a Jeep Cherokee while remotely connecting to it through remote wireless communication. === Controller area network attacks === The most common network used in vehicles and the one that is mainly used for safety-related communication is CAN, due to its real-time properties, simplicity, and cheapness. For this reason the majority of real-world attacks have been implemented against ECUs connected through this type of network. The majority of attacks demonstrated either against actual vehicles or in testbeds fall in one or more of the following categories: ==== Sniffing ==== Sniffing in the computer security field generally refers to the possibility of intercepting and logging packets or more generally data from a network. In the case of CAN, since it is a bus network, every node listens to all communication on the network. It is useful for the attacker to read data to learn the behavior of the other nodes of the network before implementing the actual attack. Usually, the final goal of the attacker is not to simply sniff the data on CAN, since the packets passing on this type of network are not usually valuable just to read. ==== Denial of service ==== Denial of service (DoS) in information security is usually described as an attack that has the objective of making a machine or a network unavailable. DoS attacks against ECUs connected to CAN buses can be done both against the network, by abusing the arbitration protocol used by CAN to always win the arbitration, and targeting the single ECU, by abusing the error handling protocol of CAN. In this second case the attacker flags the messages of the victim as faulty to convince the victim of being broken and therefore shut itself off the network. ==== Spoofing ==== Spoofing attacks comprise all cases in which an attacker, by falsifying data, sends messages pretending to be another node of the network. In automotive security usually spoofing attacks are divided into masquerade and replay attacks. Replay attacks are defined as all those where the attacker pretends to be the victim and sends sniffed data that the victim sent in a previous iteration of authentication. Masquerade attacks are, on the contrary, spoofing attacks where the data payload has been created by the attacker. == Real life automotive threat example == Security researchers Charlie Miller and Chris Valasek have successfully demonstrated remote access to a wide variety of vehicle controls using a Jeep Cherokee as the target. They were able to control the radio, environmental controls, windshield wipers, and certain engine and brake functions. The method used to hack the system was implementation of pre-programmed chip into the controller area network (CAN) bus. By inserting this chip into the CAN bus, he was able to send arbitrary message to CAN bus. One other thing that Miller has pointed out is the danger of the CAN bus, as it broadcasts the signal which the message can be caught by the hackers throughout the network. The control of the vehicle was all done remotely, manipulating the system without any physical interaction. Miller states that he could control any of some 1.4 million vehicles in the United States regardless of the location or distance, the only thing needed is for someone to turn on the vehicle to gain access. The work by Miller and Valasek replicated earlier work completed and published by academics in 2010 and 2011 on a different vehicle. The earlier work demonstrated the ability to compromise a vehicle remotely, over multiple wireless channels (including cellular), and the ability to remotely control critical components on the vehicle post-compromise, including the telematics unit and the car's brakes. While the earlier academic work was publicly visible, both in peer-reviewed scholarly publications and in the press, the Miller and Valesek work received even greater public visibility. == Security measures == The increasing complexity of devices and networks in the automotive context requires the application of security measures to limit the capabilities of a potential attacker. Since the early 2000 many different countermeasures have been proposed and, in some cases, applied. Following, a list of the most common security measures: Sub-networks: to limit the attacker capabilities even if he/she manages to access the vehicle from remote through a remotely connected ECU, the networks of the vehicle are divided in multiple sub-networks, and the most critical ECUs are not placed in the same sub-networks of the ECUs that can be accessed from remote. Gateways: the sub-networks are divided by secure gateways or firewalls that block messages from crossing from a sub-network to the other if they were not intended to. Intrusion Detection Systems (IDS): on each critical sub-network, one of the nodes (ECUs) connected to it has the goal of reading all data passing on the sub-network and detect messages that, given some rules, are considered malicious (made by an attacker). The arbitrary messages can be caught by the passenger by using IDS which will notify the owner regarding with unexpected message. Authentication protocols: in order to implement authentication on networks where it is not already implemented (such as CAN), it is possible to design an authentication protocol that works on the higher layers of the ISO OSI model, by using part of the data payload of a message to authenticate the message itself. Hardware Security Modules: since many ECUs are not powerful enough to keep real-time delays whi

  Read more →
• 

  Convolutional layer

  In artificial neural networks, a convolutional layer is a type of network layer that applies a convolution operation to the input. Convolutional layers are some of the primary building blocks of convolutional neural networks (CNNs), a class of neural network most commonly applied to images, video, audio, and other data that have the property of uniform translational symmetry. The convolution operation in a convolutional layer involves sliding a small window (called a kernel or filter) across the input data and computing the dot product between the values in the kernel and the input at each position. This process creates a feature map that represents detected features in the input. == Concepts == === Kernel === Kernels, also known as filters, are small matrices of weights that are learned during the training process. Each kernel is responsible for detecting a specific feature in the input data. The size of the kernel is a hyperparameter that affects the network's behavior. === Convolution === For a 2D input x {\displaystyle x} and a 2D kernel w {\displaystyle w} , the 2D convolution operation can be expressed as: y [ i , j ] = ∑ m = 0 k h − 1 ∑ n = 0 k w − 1 x [ i + m , j + n ] ⋅ w [ m , n ] {\displaystyle y[i,j]=\sum _{m=0}^{k_{h}-1}\sum _{n=0}^{k_{w}-1}x[i+m,j+n]\cdot w[m,n]} where k h {\displaystyle k_{h}} and k w {\displaystyle k_{w}} are the height and width of the kernel, respectively. This generalizes immediately to nD convolutions. Commonly used convolutions are 1D (for audio and text), 2D (for images), and 3D (for spatial objects, and videos). === Stride === Stride determines how the kernel moves across the input data. A stride of 1 means the kernel shifts by one pixel at a time, while a larger stride (e.g., 2 or 3) results in less overlap between convolutions and produces smaller output feature maps. === Padding === Padding involves adding extra pixels around the edges of the input data. It serves two main purposes: Preserving spatial dimensions: Without padding, each convolution reduces the size of the feature map. Handling border pixels: Padding ensures that border pixels are given equal importance in the convolution process. Common padding strategies include: No padding/valid padding. This strategy typically causes the output to shrink. Same padding: Any method that ensures the output size same as input size is a same padding strategy. Full padding: Any method that ensures each input entry is convolved over for the same number of times is a full padding strategy. Common padding algorithms include: Zero padding: Add zero entries to the borders of input. Mirror/reflect/symmetric padding: Reflect the input array on the border. Circular padding: Cycle the input array back to the opposite border, like a torus. The exact numbers used in convolutions is complicated, for which we refer to (Dumoulin and Visin, 2018) for details. == Variants == === Standard === The basic form of convolution as described above, where each kernel is applied to the entire input volume. === Depthwise separable === Depthwise separable convolution separates the standard convolution into two steps: depthwise convolution and pointwise convolution. The depthwise separable convolution decomposes a single standard convolution into two convolutions: a depthwise convolution that filters each input channel independently and a pointwise convolution ( 1 × 1 {\displaystyle 1\times 1} convolution) that combines the outputs of the depthwise convolution. This factorization significantly reduces computational cost. It was first developed by Laurent Sifre during an internship at Google Brain in 2013 as an architectural variation on AlexNet to improve convergence speed and model size. === Dilated === Dilated convolution, or atrous convolution, introduces gaps between kernel elements, allowing the network to capture a larger receptive field without increasing the kernel size. === Transposed === Transposed convolution, also known as deconvolution, fractionally strided convolution, and upsampling convolution, is a convolution where the output tensor is larger than its input tensor. It's often used in encoder-decoder architectures for upsampling. It's used in image generation, semantic segmentation, and super-resolution tasks. == History == The concept of convolution in neural networks was inspired by the visual cortex in biological brains. Early work by Hubel and Wiesel in the 1960s on the cat's visual system laid the groundwork for artificial convolution networks. An early convolution neural network was developed by Kunihiko Fukushima in 1969. It had mostly hand-designed kernels inspired by convolutions in mammalian vision. In 1979 he improved it to the Neocognitron, which learns all convolutional kernels by unsupervised learning (in his terminology, "self-organized by 'learning without a teacher'"). During the 1988 to 1998 period, a series of CNN were introduced by Yann LeCun et al., ending with LeNet-5 in 1998. It was an early influential CNN architecture for handwritten digit recognition, trained on the MNIST dataset, and was used in ATM. (Olshausen & Field, 1996) discovered that simple cells in the mammalian primary visual cortex implement localized, oriented, bandpass receptive fields, which could be recreated by fitting sparse linear codes for natural scenes. This was later found to also occur in the lowest-level kernels of trained CNNs. The field saw a resurgence in the 2010s with the development of deeper architectures and the availability of large datasets and powerful GPUs. AlexNet, developed by Alex Krizhevsky et al. in 2012, was a catalytic event in modern deep learning. In that year’s ImageNet competition, the AlexNet model achieved a 16% top-five error rate, significantly outperforming the next best entry, which had a 26% error rate. The network used eight trainable layers, approximately 650,000 neurons, and around 60 million parameters, highlighting the impact of deeper architectures and GPU acceleration on image recognition performance. From the 2013 ImageNet competition, most entries adopted deep convolutional neural networks, building on the success of AlexNet. Over the following years, performance steadily improved, with the top-five error rate falling from 16% in 2012 and 12% in 2013 to below 3% by 2017, as networks grew increasingly deep.

  Read more →
• 

  Photometric stereo

  Photometric stereo is a technique in computer vision for estimating the surface normals of objects by observing that object under different lighting conditions (photometry). It is based on the fact that the amount of light reflected by a surface is dependent on the orientation of the surface in relation to the light source and the observer. By measuring the amount of light reflected into a camera, the space of possible surface orientations is limited. Given enough light sources from different angles, the surface orientation may be constrained to a single orientation or even overconstrained. The technique was originally introduced by Woodham in 1980. The special case where the data is a single image is known as shape from shading, and was analyzed by B. K. P. Horn in 1989. Photometric stereo has since been generalized to many other situations, including extended light sources and non-Lambertian surface finishes. Current research aims to make the method work in the presence of projected shadows, highlights, and non-uniform lighting. Photometric stereo is widely used in various fields, including archaeology, cultural heritage conservation, and quality control. It is now integrated into widely used open-source software, such as Meshroom. == Basic method == Under Woodham's original assumptions — Lambertian reflectance, known point-like distant light sources, and uniform albedo — the problem can be solved by inverting the linear equation I = L ⋅ n {\displaystyle I=L\cdot n} , where I {\displaystyle I} is a (known) vector of m {\displaystyle m} observed intensities, n {\displaystyle n} is the (unknown) surface normal, and L {\displaystyle L} is a (known) 3 × m {\displaystyle 3\times m} matrix of normalized light directions. This model can easily be extended to surfaces with non-uniform albedo, while keeping the problem linear. Taking an albedo reflectivity of k {\displaystyle k} , the formula for the reflected light intensity becomes I = k ( L ⋅ n ) . {\displaystyle I=k(L\cdot n).} If L {\displaystyle L} is square (there are exactly 3 lights) and non-singular, it can be inverted, giving L − 1 I = k n . {\displaystyle L^{-1}I=kn.} Since the normal vector is known to have length 1, k {\displaystyle k} must be the length of the vector k n {\displaystyle kn} , and n {\displaystyle n} is the normalised direction of that vector. If L {\displaystyle L} is not square (there are more than 3 lights), a generalisation of the inverse can be obtained using the Moore–Penrose pseudoinverse, by simply multiplying both sides with L T {\displaystyle L^{T}} , giving L T I = L T k ( L ⋅ n ) , {\displaystyle L^{T}I=L^{T}k(L\cdot n),} ( L T L ) − 1 L T I = k n , {\displaystyle (L^{T}L)^{-1}L^{T}I=kn,} after which the normal vector and albedo can be solved as described above. == Non-Lambertian surfaces == The classical photometric stereo problem concerns itself only with Lambertian surfaces, with perfectly diffuse reflection. This is unrealistic for many types of materials, especially metals, glass and smooth plastics, and will lead to aberrations in the resulting normal vectors. Many methods have been developed to lift this assumption. In this section, a few of these are listed. === Specular reflections === Historically, in computer graphics, the commonly used model to render surfaces started with Lambertian surfaces and progressed first to include simple specular reflections. Computer vision followed a similar course with photometric stereo. Specular reflections were among the first deviations from the Lambertian model. These are a few adaptations that have been developed. Many techniques ultimately rely on modelling the reflectance function of the surface, that is, how much light is reflected in each direction. This reflectance function has to be invertible. The reflected light intensities towards the camera is measured, and the inverse reflectance function is fit onto the measured intensities, resulting in a unique solution for the normal vector. === General BRDFs and beyond === According to the Bidirectional reflectance distribution function (BRDF) model, a surface may distribute the amount of light it receives in any outward direction. This is the most general known model for opaque surfaces. Some techniques have been developed to model (almost) general BRDFs. In practice, all of these require many light sources to obtain reliable data. These are methods in which surfaces with general BRDFs can be measured. Determine the explicit BRDF prior to scanning. To do this, a different surface is required that has the same or a very similar BRDF, of which the actual geometry (or at least the normal vectors for many points on the surface) is already known. The lights are then individually shone upon the known surface, and the amount of reflection into the camera is measured. Using this information, a look-up table can be created that maps reflected intensities for each light source to a list of possible normal vectors. This puts constraints on the possible normal vectors the surface may have, and reduces the photometric stereo problem to an interpolation between measurements. Typical known surfaces to calibrate the look-up table with are spheres for their wide variety of surface orientations. Restricting the BRDF to be symmetrical. If the BRDF is symmetrical, the direction of the light can be restricted to a cone about the direction to the camera. Which cone this is depends on the BRDF itself, the normal vector of the surface, and the measured intensity. Given enough measured intensities and the resulting light directions, these cones can be approximated and therefore the normal vectors of the surface. Some progress has been made towards modelling an even more general surfaces, such as Spatially Varying Bidirectional Distribution Functions (SVBRDF), Bidirectional surface scattering reflectance distribution functions (BSSRDF), and accounting for interreflections. However, such methods are still fairly restrictive in photometric stereo. Better results have been achieved with structured light. == Uncalibrated photometric stereo == Uncalibrated Photometric Stereo is an approach in photometric stereo that aims to reconstruct the 3D shape of an object from images captured under unknown lighting conditions. Unlike classical methods, which often assume controlled or known lighting setups, this approach removes these constraints, making it adaptable to diverse and real-world environments. The advent of deep learning has revolutionized universal PS by replacing handcrafted assumptions with data-driven models. Recent approaches leverage Transformer-based architectures and multi-scale encoder–decoder networks to directly estimate surface normals from input images. Uncalibrated Photometric Stereo is inherently an ill-posed problem, as it attempts to recover 3D shape and lighting conditions simultaneously from images alone. This leads to fundamental ambiguities in the reconstruction process, which manifest as systematic errors in the recovered geometry, including global distortions in the object's overall shape, and misinterpretation of surface orientation, where concave regions may appear convex and vice versa. To address the challenges of uncalibrated photometric stereo, hybrid methods have emerged that combine multi-view stereo and photometric stereo. These approaches leverage the strengths of both techniques, including geometric reliability and resolution.

  Read more →
• 

  WaveNet

  WaveNet is a deep neural network for generating raw audio. It was created by researchers at London-based AI firm DeepMind. The technique, outlined in a paper in September 2016, is able to generate relatively realistic-sounding human-like voices by directly modelling waveforms using a neural network method trained with recordings of real speech. Tests with US English and Mandarin reportedly showed that the system outperforms Google's best existing text-to-speech (TTS) systems, although as of 2016 its text-to-speech synthesis still was less convincing than actual human speech. WaveNet's ability to generate raw waveforms means that it can model any kind of audio, including music. == History == Generating speech from text is an increasingly common task thanks to the popularity of software such as Apple's Siri, Microsoft's Cortana, Amazon Alexa and the Google Assistant. Most such systems use a variation of a technique that involves concatenated sound fragments together to form recognisable sounds and words. The most common of these is called concatenative TTS. It consists of large library of speech fragments, recorded from a single speaker that are then concatenated to produce complete words and sounds. The result sounds unnatural, with an odd cadence and tone. The reliance on a recorded library also makes it difficult to modify or change the voice. Another technique, known as parametric TTS, uses mathematical models to recreate sounds that are then assembled into words and sentences. The information required to generate the sounds is stored in the parameters of the model. The characteristics of the output speech are controlled via the inputs to the model, while the speech is typically created using a voice synthesiser known as a vocoder. This can also result in unnatural sounding audio. == Design and ongoing research == === Background === WaveNet is a type of feedforward neural network known as a deep convolutional neural network (CNN). In WaveNet, the CNN takes a raw signal as an input and synthesises an output one sample at a time. It does so by sampling from a softmax (i.e. categorical) distribution of a signal value that is encoded using μ-law companding transformation and quantized to 256 possible values. === Initial concept and results === According to the original September 2016 DeepMind research paper WaveNet: A Generative Model for Raw Audio, the network was fed real waveforms of speech in English and Mandarin. As these pass through the network, it learns a set of rules to describe how the audio waveform evolves over time. The trained network can then be used to create new speech-like waveforms at 16,000 samples per second. These waveforms include realistic breaths and lip smacks – but do not conform to any language. WaveNet is able to accurately model different voices, with the accent and tone of the input correlating with the output. For example, if it is trained with German, it produces German speech. The capability also means that if the WaveNet is fed other inputs – such as music – its output will be musical. At the time of its release, DeepMind showed that WaveNet could produce waveforms that sound like classical music. === Content (voice) swapping === According to the June 2018 paper Disentangled Sequential Autoencoder, DeepMind has successfully used WaveNet for audio and voice "content swapping": the network can swap the voice on an audio recording for another, pre-existing voice while maintaining the text and other features from the original recording. "We also experiment on audio sequence data. Our disentangled representation allows us to convert speaker identities into each other while conditioning on the content of the speech." (p. 5) "For audio, this allows us to convert a male speaker into a female speaker and vice versa [...]." (p. 1) According to the paper, a two-digit minimum amount of hours (c. 50 hours) of pre-existing speech recordings of both source and target voice are required to be fed into WaveNet for the program to learn their individual features before it is able to perform the conversion from one voice to another at a satisfying quality. The authors stress that "[a]n advantage of the model is that it separates dynamical from static features [...]." (p. 8), i. e. WaveNet is capable of distinguishing between the spoken text and modes of delivery (modulation, speed, pitch, mood, etc.) to maintain during the conversion from one voice to another on the one hand, and the basic features of both source and target voices that it is required to swap on the other. The January 2019 follow-up paper Unsupervised speech representation learning using WaveNet autoencoders details a method to successfully enhance the proper automatic recognition and discrimination between dynamical and static features for "content swapping", notably including swapping voices on existing audio recordings, in order to make it more reliable. Another follow-up paper, Sample Efficient Adaptive Text-to-Speech, dated September 2018 (latest revision January 2019), states that DeepMind has successfully reduced the minimum amount of real-life recordings required to sample an existing voice via WaveNet to "merely a few minutes of audio data" while maintaining high-quality results. Its ability to clone voices has raised ethical concerns about WaveNet's ability to mimic the voices of living and dead persons. According to a 2016 BBC article, companies working on similar voice-cloning technologies (such as Adobe Voco) intend to insert watermarking inaudible to humans to prevent counterfeiting, while maintaining that voice cloning satisfying, for instance, the needs of entertainment-industry purposes would be of a far lower complexity and use different methods than required to fool forensic evidencing methods and electronic ID devices, so that natural voices and voices cloned for entertainment-industry purposes could still be easily told apart by technological analysis. == Applications == At the time of its release, DeepMind said that WaveNet required too much computational processing power to be used in real world applications. As of October 2017, Google announced a 1,000-fold performance improvement along with better voice quality. WaveNet was then used to generate Google Assistant voices for US English and Japanese across all Google platforms. In November 2017, DeepMind researchers released a research paper detailing a proposed method of "generating high-fidelity speech samples at more than 20 times faster than real-time", called "Probability Density Distillation". At the annual I/O developer conference in May 2018, it was announced that new Google Assistant voices were available and made possible by WaveNet; WaveNet greatly reduced the number of audio recordings that were required to create a voice model by modeling the raw audio of the voice actor samples.

  Read more →
• 

  1DayLater

  1DayLater was a free, web-based software that was focused on professional invoicing. The company was formed in 2009 and closed in October 2013. The main function of 1DayLater was to help users create invoices for clients. It could also be used to track time and other expenses, work to budgets, and to track projects. Multiple users could simultaneously work on the same projects together. PC Magazine (PCMag) voted 1DayLater as one of the 'Best Free Software of 2010'. == History == The software was developed by two brothers, Paul and David King; after they experienced similar frustrations while working freelance, the brothers wanted to create a product that would let them track time, expenses and business miles in a single online location. == Media coverage == 1DayLater had the following press coverage: BBC Webscape (July 2010) - Kate Russell gives her latest selection of the best sites on the World Wide Web PCMag (March 2010) - The best free software of 2010 Lifehacker (February 2010) - "A worthy addition to our 'Top Ten Tips and Tools for Freelancers'" Gigaom (February 2010) - Taking a closer look with 1DayLater The Journal (May 2009) - "Top Ten Brands of the North East" (UK) Techcrunch (January 2009) - "A 'feisty time tracking solution from the North East of England'"

  Read more →
• 

  Live Transcribe

  Live Transcribe is a mobile app for real-time captioning, developed by Google for the Android operating system. Development on the application began in partnership with Gallaudet University. It was publicly released as a free beta for Android 5.0+ on the Google Play Store on February 4, 2019. As of early 2023 it had been downloaded over 500 million times. == Development == Researchers Dimitri Kanevsky, Sagar Savla and Chet Gnegy at Google developed the app in collaboration with researchers at Gallaudet University, an American university for the education of the deaf and hard of hearing. The app uses machine learning to generate captions, similar to YouTube's auto-generated captions. In August 2019, Google made Live Transcribe an open-source project. == Features == The app uses speech recognition to generate live captions in over 80 languages with varying accuracy. The app, which requires connection to the Internet to function, is available to download on the Google Play Store. A later update to the app displayed information on sounds such as clapping, laughter, music, applause, and whistling. In May 2020, the app started supporting transcription in Albanian, Burmese, Estonian, Macedonian, Mongolian, Punjabi, and Uzbek, supporting 70 languages. In March 2022, the app was updated with support to transcribe offline, without Internet connection, so long as the appropriate language pack has been installed. The offline mode is only available for devices with 6GB of RAM and certain Google Pixel devices.

  Read more →
• 

  INDECT

  INDECT is a research project in the area of intelligent security systems performed by several European universities since 2009 and funded by the European Union. The purpose of the project is to involve European scientists and researchers in the development of solutions to and tools for automatic threat detection through e.g. processing of CCTV camera data streams, standardization of video sequence quality for user applications, threat detection in computer networks as well as data and privacy protection. The area of research, applied methods, and techniques are described in the public deliverables which are available to the public on the project's website. Practically, all information related to the research is public. Only documents that comprise information related to financial data or information that could negatively influence the competitiveness and law enforcement capabilities of parties involved in the project are not published. This follows regulations and practices applied in EU research projects. == Application and target users == The main end-user of INDECT solutions are police forces and security services. The principle of operation of the project is detecting threats and identifying sources of threats, without monitoring and searching for particular citizens or groups of citizens. Then, the system operator (i.e. police officer) decides whether an intervention of services responsible for public security are required or not. Further investigation eventually leading to persons related to threats is performed, preserving the presumption of innocence, based on existing procedures already used by police services and prosecutors. As it can be found in the project deliverables, INDECT does not involve storage of personal data (such as names, addresses, identity document numbers, etc.). A similar, behavior-based surveillance program was SAMURAI (Suspicious and Abnormal behavior Monitoring Using a netwoRk of cAmeras & sensors for sItuation awareness enhancement). == Expected results == The main expected results of the INDECT project are: Trial of intelligent analysis of video and audio data for threat detection in urban environments Creation of tools and technology for privacy and data protection during storage and transmission of information using quantum cryptography and new methods of digital watermarking Performing computer-aided detection of threats and targeted crimes in Internet resources with privacy-protecting solutions Construction of a search engine for rapid semantic search based on watermarking of content related to child pornography and human organ trafficking Implementation of a distributed computer system that is capable of effective intelligent processing == Controversy == Some media and other sources accuse INDECT of privacy abuse, collecting personal data, and keeping information from the public. Consequently, these issues have been commented and discussed by some Members of the European Parliament. As seen in the project's documentation, INDECT does not involve mobile phone tracking or call interception. The rumors about testing INDECT during 2012 UEFA European Football Championship also turned out to be false. The mid-term review of the Seventh Framework Programme to the European Parliament strongly urges the European Commission to immediately make all documents available and to define a clear and strict mandate for the research goal, the application, and the end users of INDECT, and stresses a thorough investigation of the possible impact on fundamental rights. Nevertheless, according to Mr. Paweł Kowal, MEP, the project had the ethical review on 15 March 2011 in Brussels with the participation of ethics experts from Austria, France, Netherlands, Germany and Great Britain.

  Read more →
• 

  Auralization

  Auralization is a procedure designed to model and simulate the experience of acoustic phenomena rendered as a soundfield in a virtualized space. This is useful in configuring the soundscape of architectural structures, concert venues, and public spaces, as well as in making coherent sound environments within virtual immersion systems. == History == The English term auralization was used for the first time by Kleiner et al. in an article in the journal of the AES en 1991. The increase of computational power allowed the development of the first acoustic simulation software towards the end of the 1960s. == Principles == Auralizations are experienced through systems rendering virtual acoustic models made by convolving or mixing acoustic events recorded 'dry' (or in an anechoic chamber) projected within a virtual model of an acoustic space, the characteristics of which are determined by means of sampling its impulse response (IR). Once this h ( t ) {\displaystyle h(t)} has been determined, the simulation of the resulting soundfield s ( t ) {\displaystyle s(t)} in the target environment is obtained by convolution: r ( t ) = h ( t ) ∗ s ( t ) {\displaystyle r(t)=h(t)s(t)} The resulting sound r ( t ) {\displaystyle r(t)} is heard as it would if emitted in that acoustic space. == Binaurality == For auralizations to be perceived as realistic, it is critical to emulate the human hearing in terms of position and orientation of the listener's head with respect to the sources of sound. For IR data to be convolved convincingly, the acoustic events are captured using a dummy head where two microphones are positioned on each side of the head to record an emulation of sound arriving at the locations of human ears, or using an ambisonics microphone array and mixed down for binaurality. Head-related transfer functions (HRTF) datasets can be used to simplify the process insofar as a monaural IR can be measured or simulated, then audio content is convolved with its target acoustic space. In rendering the experience, the transfer function corresponding to the orientation of the head is applied to simulate the corresponding spatial emanation of sound.

  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 →
• 

  Netomi

  Netomi, formerly msg.ai, is an American artificial intelligence company and developer of chatbot technologies. == History == msg.ai was founded in May 2015 by Puneet Mehta. msg.ai worked with Sony Pictures to launch a chat bot on Facebook Messenger for a $100M film, Goosebumps and subsequently joined Y Combinator as a member of the Winter 2016 class. Later that year and in 2017, msg.ai completed two rounds of seed funding, led by Y Combinator and Index Ventures. In 2018, the company changed its name to Netomi. In 2019, the company raised $14.7 million in a Series A funding round also led by Index Ventures. In 2021, the company raised $30 million in a Series B funding round led by WndrCo LLC.

  Read more →
• 

  Ontology learning

  Ontology learning (ontology extraction, ontology augmentation generation, ontology generation, or ontology acquisition) is the automatic or semi-automatic creation of ontologies, including extracting the corresponding domain's terms and the relationships between the concepts that these terms represent from a corpus of natural language text, and encoding them with an ontology language for easy retrieval. As building ontologies manually is extremely labor-intensive and time-consuming, there is great motivation to automate the process. Typically, the process starts by extracting terms and concepts or noun phrases from plain text using linguistic processors such as part-of-speech tagging and phrase chunking. Then statistical or symbolic techniques are used to extract relation signatures, often based on pattern-based or definition-based hypernym extraction techniques. == Procedure == Ontology learning (OL) is used to (semi-)automatically extract whole ontologies from natural language text. The process is usually split into the following eight tasks, which are not all necessarily applied in every ontology learning system. === Domain terminology extraction === During the domain terminology extraction step, domain-specific terms are extracted, which are used in the following step (concept discovery) to derive concepts. Relevant terms can be determined, e.g., by calculation of the TF/IDF values or by application of the C-value / NC-value method. The resulting list of terms has to be filtered by a domain expert. In the subsequent step, similarly to coreference resolution in information extraction, the OL system determines synonyms, because they share the same meaning and therefore correspond to the same concept. The most common methods therefore are clustering and the application of statistical similarity measures. === Concept discovery === In the concept discovery step, terms are grouped to meaning bearing units, which correspond to an abstraction of the world and therefore to concepts. The grouped terms are these domain-specific terms and their synonyms, which were identified in the domain terminology extraction step. === Concept hierarchy derivation === In the concept hierarchy derivation step, the OL system tries to arrange the extracted concepts in a taxonomic structure. This is mostly achieved with unsupervised hierarchical clustering methods. Because the result of such methods is often noisy, a supervision step, e.g., user evaluation, is added. A further method for the derivation of a concept hierarchy exists in the usage of several patterns that should indicate a sub- or supersumption relationship. Patterns like “X, that is a Y” or “X is a Y” indicate that X is a subclass of Y. Such pattern can be analyzed efficiently, but they often occur too infrequently to extract enough sub- or supersumption relationships. Instead, bootstrapping methods are developed, which learn these patterns automatically and therefore ensure broader coverage. === Learning of non-taxonomic relations === In the learning of non-taxonomic relations step, relationships are extracted that do not express any sub- or supersumption. Such relationships are, e.g., works-for or located-in. There are two common approaches to solve this subtask. The first is based upon the extraction of anonymous associations, which are named appropriately in a second step. The second approach extracts verbs, which indicate a relationship between entities, represented by the surrounding words. The result of both approaches need to be evaluated by an ontologist to ensure accuracy. === Rule discovery === During rule discovery, axioms (formal description of concepts) are generated for the extracted concepts. This can be achieved, e.g., by analyzing the syntactic structure of a natural language definition and the application of transformation rules on the resulting dependency tree. The result of this process is a list of axioms, which, afterwards, is comprehended to a concept description. This output is then evaluated by an ontologist. === Ontology population === At this step, the ontology is augmented with instances of concepts and properties. For the augmentation with instances of concepts, methods based on the matching of lexico-syntactic patterns are used. Instances of properties are added through the application of bootstrapping methods, which collect relation tuples. === Concept hierarchy extension === In this step, the OL system tries to extend the taxonomic structure of an existing ontology with further concepts. This can be performed in a supervised manner with a trained classifier or in an unsupervised manner via the application of similarity measures. === Frame and Event detection === During frame/event detection, the OL system tries to extract complex relationships from text, e.g., who departed from where to what place and when. Approaches range from applying SVM with kernel methods to semantic role labeling (SRL) to deep semantic parsing techniques. == Tools == Dog4Dag (Dresden Ontology Generator for Directed Acyclic Graphs) is an ontology generation plugin for Protégé 4.1 and OBOEdit 2.1. It allows for term generation, sibling generation, definition generation, and relationship induction. Integrated into Protégé 4.1 and OBO-Edit 2.1, DOG4DAG allows ontology extension for all common ontology formats (e.g., OWL and OBO). Limited largely to EBI and Bio Portal lookup service extensions.

  Read more →
• 

  Ayoba

  Ayoba is an African communication platform developed in South Africa. It is owned by Progressive Tech Holdings in Mauritius and managed by SIMFY Africa. Launched on May 4, 2019, as of April 2024, it has over 35 million active users. == History == Ayoba was first published on Google Play in February 2019. Its first marketing campaign and brand launch took place in Cameroon on May 4, 2019. In June 2019, the platform introduced its first eight channels. In November 2019, the platform reached one million active users, which increased to two million by June 2020. Subsequently, ayoba expanded its services, including the launch of games for Android in February 2020, Momo (Mobile Money) in Cameroon in May 2020, and MicroApps in May 2020. It also launched music and voice and video calling features in 12 territories in August 2020. The first version of ayoba for iOS was released in September 2020. In December of the same year, games and Messaging 2.0 were launched on the platform. In November 2020, it won Best Mobile Application at the African Digital Awards. In 2021, it won OTT Brand of the Year at the Marketing World Awards in Ghana. In December 2022, it received Top Innovative Technology and Telecom Product of the Year at the National Communications Awards in December 2022. In June 2023 ayoba partnered with BoomPlay and as of April 2024, it had 35 million monthly active users. Ayoba has partnered with Jumia Ghana to offer exclusive deals to users. Ayoba users can get a 10% discount on selected Jumia purchases through the app, with no data charges for MTN users. This partnership aims to make online shopping more affordable and accessible by integrating Jumia's offers into the ayoba app. Ayoba supports over 35 million users across Africa and provides services in 22 languages. To access the deals, users can download the ayoba app from the Google Play Store, iOS Store, or the official website. == Platform features == Chat, Call and Share: ayoba enables instant messaging, voice notes, picture sharing, and file sharing with contacts, even if they do not have the app installed. The app supports voice and video calls on both Android and iOS, as well as group chats, help channel and SMS continuity (non ayoba users receive messages as SMS, their responses appear in the ayoba app). Music: ayoba offers a free music player with daily updates on international and African music. Users can find playlists for different genres. Games: ayoba provides a selection of interactive games, including action, adventure, and children's games available on both Android and iOS. Mobile Money Transfers: In certain territories, ayoba supports mobile money transfers using MTN Mobile Money (MoMo) for transactions within the app. MicroApps: ayoba features individual MicroApps within the platform that offer content and services, including streaming channels, podcasts, and specialized apps. The availability of these apps may vary by country. == Operations == ayoba primarily focuses on the following territories: Nigeria, Cameroon, South Africa, Ghana, Côte d'Ivoire, Uganda, Republic of Congo, Benin, Zambia, Tanzania, Kenya, Senegal, Togo, Guinea Bissau, Guinea Conakry, Sudan, South Sudan, and Liberia. The company operates from its offices in Cape Town and Johannesburg, South Africa. David Gillaranz served as the CEO from 2019 to 2021, and Burak Akinci has been the CEO since 2021.

  Read more →
• 

  Scripped

  Scripped was an online screenplay services company offering three services: script writing, script registration, and script coverage. Scripped did not facilitate collaboration among screenwriters. It combined with Zhura in 2010. According to Techcrunch, Scripped had more than 60,000 writers as of March 2010. Scripped was administered by Sunil Rajaraman, Ryan Buckley and Zak Freer. Actor, writer, and director Edward Burns and screenwriter Steven E. de Souza joined Scripped's Board of Advisers in May 2008. In 2008, the company formed a partnership with Write Brothers, makers of Movie Magic Screenwriter software. On March 29, 2010, Scripped announced that it closed $250,000 in private investment and merged with competitor Zhura. Scripped's CEO, Sunil Rajaraman, remains the merged company's Chief Executive Officer. On April 1, 2015, citing a serious technical failure, Scripped shuttered its service. As part of the announcement, it was disclosed that their backup servers had failed as well, losing all of its users' stored scripts. The website URL currently redirects to WriterDuet's website, another online scriptwriting service; Scripped had advertised WriterDuet in Scripped's shutdown open letter. == Features == The Scripped Writer provided a built-in screenplay template which formatted the document to a standard for scripts as recommended by the AMPAS. The screenplay document was composed of seven elements: scene, action, character, dialog, parenthetical, transition and general. Each element had a specific style to which the Scripped Writer conformed as text was entered. Like other client-side screenplay software, Scripped offered Tab-Enter toggling between screenplay elements, making the writing process much faster. Text files could be imported into the Scripped Writer and automatically conformed to the screenplay template. Completed scripts could be exported as PDF files. In May 2011 the administrators of Scripped launched Scripted.com - a sister site focused on freelance writing jobs. Subsequent to the service's launch, the company was renamed to Scripted, Inc.

  Read more →
• 

  Automatic acquisition of lexicon

  Automatic acquisition of lexicon is a computerized process used for the development of a complex morphological lexicon of a language. The lexicon is essential for the NLP (Natural language processing), as well as a prerequisite to any wide-coverage parser. The two main requirements represent raw corpus and the morphological description of the language. The aim is to provide lemmas that will serve to the explanation of all the words that occur within the corpus. For the achievement of a quality lexicon it is necessary to manually validate the generated lemmas and iterate the whole process several times. The process is focused on the open word classes (e.g. nouns, adjectives, verbs). Closed classes (e.g. prepositions, pronouns, numerals) are excluded. This method is applicable to the languages with a rich morphology, such as Slovak, Russian or Croatian. Applied to Slovak, being an inflectional language, the automatic acquisition focuses on the inflectional morphology as well as on the derivational morphology. This fact enables the users to find out the information about derivational relations (e.g. adjectivizations, prefixes) in the lexicon. For example, Slovak word korpusový is an adjectivization of korpus (eng. corpus). == Three-step loop == Conformably to Benoît Sagot, there are three stages involved in the acquisition of lemmas: Generation and inflection Ranking Manual validation The more iteration will be performed, the more accurate lexicon will be obtained. For each iteration are essential the information given by a manual validator. === Generation and inflection === Firstly, all words which represent the closed word classes (pronouns, prepositions, numerals) are manually excluded from the given corpus. Number of their occurrences in the corpus is provided. Then the automatic generation comes, when the hypothetical lemmas according to the morphological description of a language are created. Generated lemmas are consequently being inflected, so that all of their inflected forms are built. Obtained forms are associated with the corresponding lemma and a morphological tag. === Ranking === There was created a probabilistic model, represented by a fix-point algorithm, to rank the hypothetical lemmas generated in the first step. Best ranked lemmas are expected to be ideally all correct, whereas the least ranked tend to be incorrect. === Manual validation === Correctness of the best- ranked lemmas created in the previous step are checked by the manual validator, who should be a native speaker. Lemmas are at this stage divided into three categories: valid lemmas, appended to lexicon erroneous lemmas generated by valid forms (later associated to another lemmas) erroneous lemmas generated by invalid forms (these need to be excluded) == Future development == Automatic acquisition, in comparison to a purely manual development of the lexicons, seems to be promising, considering the future development, because of the short validation time needed and the relatively small amount of human labor involved.

  Read more →
• 

  Convolutional layer

  In artificial neural networks, a convolutional layer is a type of network layer that applies a convolution operation to the input. Convolutional layers are some of the primary building blocks of convolutional neural networks (CNNs), a class of neural network most commonly applied to images, video, audio, and other data that have the property of uniform translational symmetry. The convolution operation in a convolutional layer involves sliding a small window (called a kernel or filter) across the input data and computing the dot product between the values in the kernel and the input at each position. This process creates a feature map that represents detected features in the input. == Concepts == === Kernel === Kernels, also known as filters, are small matrices of weights that are learned during the training process. Each kernel is responsible for detecting a specific feature in the input data. The size of the kernel is a hyperparameter that affects the network's behavior. === Convolution === For a 2D input x {\displaystyle x} and a 2D kernel w {\displaystyle w} , the 2D convolution operation can be expressed as: y [ i , j ] = ∑ m = 0 k h − 1 ∑ n = 0 k w − 1 x [ i + m , j + n ] ⋅ w [ m , n ] {\displaystyle y[i,j]=\sum _{m=0}^{k_{h}-1}\sum _{n=0}^{k_{w}-1}x[i+m,j+n]\cdot w[m,n]} where k h {\displaystyle k_{h}} and k w {\displaystyle k_{w}} are the height and width of the kernel, respectively. This generalizes immediately to nD convolutions. Commonly used convolutions are 1D (for audio and text), 2D (for images), and 3D (for spatial objects, and videos). === Stride === Stride determines how the kernel moves across the input data. A stride of 1 means the kernel shifts by one pixel at a time, while a larger stride (e.g., 2 or 3) results in less overlap between convolutions and produces smaller output feature maps. === Padding === Padding involves adding extra pixels around the edges of the input data. It serves two main purposes: Preserving spatial dimensions: Without padding, each convolution reduces the size of the feature map. Handling border pixels: Padding ensures that border pixels are given equal importance in the convolution process. Common padding strategies include: No padding/valid padding. This strategy typically causes the output to shrink. Same padding: Any method that ensures the output size same as input size is a same padding strategy. Full padding: Any method that ensures each input entry is convolved over for the same number of times is a full padding strategy. Common padding algorithms include: Zero padding: Add zero entries to the borders of input. Mirror/reflect/symmetric padding: Reflect the input array on the border. Circular padding: Cycle the input array back to the opposite border, like a torus. The exact numbers used in convolutions is complicated, for which we refer to (Dumoulin and Visin, 2018) for details. == Variants == === Standard === The basic form of convolution as described above, where each kernel is applied to the entire input volume. === Depthwise separable === Depthwise separable convolution separates the standard convolution into two steps: depthwise convolution and pointwise convolution. The depthwise separable convolution decomposes a single standard convolution into two convolutions: a depthwise convolution that filters each input channel independently and a pointwise convolution ( 1 × 1 {\displaystyle 1\times 1} convolution) that combines the outputs of the depthwise convolution. This factorization significantly reduces computational cost. It was first developed by Laurent Sifre during an internship at Google Brain in 2013 as an architectural variation on AlexNet to improve convergence speed and model size. === Dilated === Dilated convolution, or atrous convolution, introduces gaps between kernel elements, allowing the network to capture a larger receptive field without increasing the kernel size. === Transposed === Transposed convolution, also known as deconvolution, fractionally strided convolution, and upsampling convolution, is a convolution where the output tensor is larger than its input tensor. It's often used in encoder-decoder architectures for upsampling. It's used in image generation, semantic segmentation, and super-resolution tasks. == History == The concept of convolution in neural networks was inspired by the visual cortex in biological brains. Early work by Hubel and Wiesel in the 1960s on the cat's visual system laid the groundwork for artificial convolution networks. An early convolution neural network was developed by Kunihiko Fukushima in 1969. It had mostly hand-designed kernels inspired by convolutions in mammalian vision. In 1979 he improved it to the Neocognitron, which learns all convolutional kernels by unsupervised learning (in his terminology, "self-organized by 'learning without a teacher'"). During the 1988 to 1998 period, a series of CNN were introduced by Yann LeCun et al., ending with LeNet-5 in 1998. It was an early influential CNN architecture for handwritten digit recognition, trained on the MNIST dataset, and was used in ATM. (Olshausen & Field, 1996) discovered that simple cells in the mammalian primary visual cortex implement localized, oriented, bandpass receptive fields, which could be recreated by fitting sparse linear codes for natural scenes. This was later found to also occur in the lowest-level kernels of trained CNNs. The field saw a resurgence in the 2010s with the development of deeper architectures and the availability of large datasets and powerful GPUs. AlexNet, developed by Alex Krizhevsky et al. in 2012, was a catalytic event in modern deep learning. In that year’s ImageNet competition, the AlexNet model achieved a 16% top-five error rate, significantly outperforming the next best entry, which had a 26% error rate. The network used eight trainable layers, approximately 650,000 neurons, and around 60 million parameters, highlighting the impact of deeper architectures and GPU acceleration on image recognition performance. From the 2013 ImageNet competition, most entries adopted deep convolutional neural networks, building on the success of AlexNet. Over the following years, performance steadily improved, with the top-five error rate falling from 16% in 2012 and 12% in 2013 to below 3% by 2017, as networks grew increasingly deep.

  Read more →