Telecommunication, often used in its plural form or abbreviated as telecom, is the transmission of information over a distance using electrical or electronic means, typically through cables, radio waves, or other communication technologies. These means of transmission may be divided into communication channels for multiplexing, allowing for a single medium to transmit several concurrent communication sessions. Long-distance technologies invented during the 19th, 20th and 21st centuries generally use electric power, and include the electrical telegraph, telephone, television, and radio. Early telecommunication networks used metal wires as the medium for transmitting signals. These networks were used for telegraphy and telephony for many decades. In the first decade of the 20th century, a revolution in wireless communication began with breakthroughs including those made in radio communications by Guglielmo Marconi, who won the 1909 Nobel Prize in Physics. Other early pioneers in electrical and electronic telecommunications include co-inventors of the telegraph Charles Wheatstone and Samuel Morse, numerous inventors and developers of the telephone including Antonio Meucci, Philipp Reis, Elisha Gray and Alexander Graham Bell, inventors of radio Edwin Armstrong and Lee de Forest, as well as inventors of television like Vladimir K. Zworykin, John Logie Baird and Philo Farnsworth. Since the 1960s, the proliferation of digital technologies has meant that voice communications have gradually been supplemented by data. The physical limitations of metallic media prompted the development of optical fibre. The Internet, a technology independent of any given medium, has provided global access to services for individual users and further reduced location and time limitations on communications. == Definition == At the 1932 Plenipotentiary Telegraph Conference and the International Radiotelegraph Conference in Madrid, the two organizations merged to form the International Telecommunication Union (ITU). They defined telecommunication as "any telegraphic or telephonic communication of signs, signals, writing, facsimiles and sounds of any kind, by wire, wireless or other systems or processes of electric signaling or visual signaling (semaphores)." The definition was later reconfirmed, according to Article 1.3 of the ITU Radio Regulations, which defined it as "Any transmission, emission or reception of signs, signals, writings, images and sounds or intelligence of any nature by wire, radio, optical, or other electromagnetic systems". As such, slow communications technologies like postal mail and pneumatic tubes are excluded from the telecommunication's definition. The term telecommunication was coined in 1904 by the French engineer and novelist Édouard Estaunié, who defined it as "remote transmission of thought through electricity". Telecommunication is a compound noun formed from the Greek prefix tele- (τῆλε), meaning distant, far off, or afar, and the Latin verb communicare, meaning to share. Communication was first used as an English word in the late 14th century. It comes from Old French comunicacion (14c., Modern French communication), from Latin communicationem (nominative communication), noun of action from past participle stem of communicare, "to share, divide out; communicate, impart, inform; join, unite, participate in," literally, "to make common", from communis. == History == Many transmission media have been used for long-distance communication throughout history, from smoke signals, beacons, semaphore telegraphs, signal flags, and optical heliographs to wires and empty space made to carry electromagnetic signals. === Before the electrical and electronic era === Long-distance communication was used long before the discovery of electricity and electromagnetism enabled the invention of telecommunications. A few of the many ingenious methods for communicating over distances prior to that are described here. Homing pigeons have been used throughout history by different cultures. Pigeon post had Persian roots and was later used by the Romans to aid their military. Frontinus claimed Julius Caesar used pigeons as messengers in his conquest of Gaul. The Greeks also conveyed the names of the victors at the Olympic Games to various cities using homing pigeons. In the early 19th century, the Dutch government used the system in Java and Sumatra. And in 1849, Paul Julius Reuter started a pigeon service to fly stock prices between Aachen and Brussels, a service that operated for a year until the gap in the telegraph link was closed. In the Middle Ages, chains of beacons were commonly used on hilltops as a means of relaying a signal. Beacon chains suffered the drawback that they could only pass a single bit of information, so the meaning of the message, such as "the enemy has been sighted" had to be agreed upon in advance. One notable instance of their use was during the Spanish Armada, when a beacon chain relayed a signal from Plymouth to London. In 1792, Claude Chappe, a French engineer, built the first fixed visual telegraphy system (or semaphore line) between Lille and Paris. However semaphore suffered from the need for skilled operators and expensive towers at intervals of ten to thirty kilometres (six to nineteen miles). As a result of competition from the electrical telegraph, the last commercial line was abandoned in 1880. === Telegraph and telephone === On July 25, 1837, the first commercial electrical telegraph was demonstrated by English inventor Sir William Fothergill Cooke and English scientist Sir Charles Wheatstone. Both inventors viewed their device as "an improvement to the [existing] electromagnetic telegraph" and not as a new device. Samuel Morse independently developed a version of the electrical telegraph that he unsuccessfully demonstrated on September 2, 1837. His code was an important advance over Wheatstone's signaling method. The first transatlantic telegraph cable was successfully completed on July 27, 1866, allowing transatlantic telecommunication for the first time. After early attempts to develop a talking telegraph by Antonio Meucci and a telefon by Johann Philipp Reis, a patent for the conventional telephone was filed by Alexander Bell in February 1876 (just a few hours before Elisha Gray filed a patent caveat for a similar device). The first commercial telephone services were set up by the Bell Telephone Company in 1878 and 1879 on both sides of the Atlantic in the cities of New Haven and London. === Radio and television === In 1894, Italian inventor Guglielmo Marconi began developing wireless communication using the then-newly discovered phenomenon of radio waves, demonstrating, by 1901, that they could be transmitted across the Atlantic Ocean. This was the start of wireless telegraphy by radio. On 17 December 1902, a transmission from the Marconi station in Glace Bay, Nova Scotia, Canada, became the world's first radio message to cross the Atlantic from North America. In 1904, a commercial service was established to transmit nightly news summaries to subscribing ships, which incorporated them into their onboard newspapers. World War I accelerated the development of radio for military communications. After the war, commercial radio AM broadcasting began in the 1920s and became an important mass medium for entertainment and news. World War II again accelerated the development of radio for the wartime purposes of aircraft and land communication, radio navigation, and radar. Development of stereo FM broadcasting of radio began in the 1930s in the United States and the 1940s in the United Kingdom, displacing AM as the dominant commercial standard in the 1970s. On March 25, 1925, John Logie Baird demonstrated the transmission of moving pictures at the London department store Selfridges. Baird's device relied upon the Nipkow disk by Paul Nipkow and thus became known as the mechanical television. It formed the basis of experimental broadcasts done by the British Broadcasting Corporation beginning on 30 September 1929. === Vacuum tubes === Vacuum tubes use thermionic emission of electrons from a heated cathode for a number of fundamental electronic functions such as signal amplification and current rectification. The simplest vacuum tube, the diode invented in 1904 by John Ambrose Fleming, contains only a heated electron-emitting cathode and an anode. Electrons can only flow in one direction through the device—from the cathode to the anode. Adding one or more control grids within the tube enables the current between the cathode and anode to be controlled by the voltage on the grid or grids. These devices became a key component of electronic circuits for the first half of the 20th century and were crucial to the development of radio, television, radar, sound recording and reproduction, long-distance telephone networks, and analogue and early digital computers. While some applications had used earlier technologies such as the sp
Art Recognition
Art Recognition is a Swiss technology company headquartered in Adliswil, within the Zurich metropolitan area, Switzerland. Art Recognition specializes in the application of artificial intelligence (AI) for art authentication and the detection of art forgeries. == Overview == Art Recognition was established in 2019 by Dr. Carina Popovici and Christiane Hoppe-Oehl. Art Recognition employs a combination of machine learning techniques, computer vision algorithms, and deep neural networks to assess the authenticity of artworks. The company's technology undergoes a process of data collection, dataset preparation, and training. === Academic partnerships and grants === Art Recognition has established a relationship with Innosuisse, a Swiss innovation agency, to expand its research and development initiatives. It has also formed a strategic collaboration with Nils Büttner, an art historian and professor at the State Academy of Fine Arts Stuttgart (ABK Stuttgart). === Notable developments === In May 2024, Art Recognition played a key role in identifying counterfeit artworks, including alleged Monets and Renoirs, being sold on eBay. Germann Auction in November 2024 became the first auction house to successfully conduct a sale of artwork authenticated entirely by artificial intelligence. As of January 2025, Art Recognition has appointed art crime expert and Pulitzer Prize finalist Noah Charney as an advisor. === Recognition and debates === The company was featured on the front page of The Wall Street Journal for its involvement in the authentication case of the Flaget Madonna, believed to have been partly painted by Raphael. A broadcast by the Swiss public television SRF covered how the algorithm can be used to detect art forgeries with high accuracy. The technology developed by Art Recognition has been recognized for its role in providing a technology-based art authentication solution, compared to traditional methods. == Controversial cases == Art Recognition's AI algorithm has been applied to several high-profile and controversial artworks, sparking significant interest and debate in the art world. Samson and Delilah at the National Gallery in London: The National Gallery's "Samson and Delilah", traditionally attributed to the artist Rubens, has also been examined using Art Recognition's AI, which has assessed the painting as non-authentic. De Brecy Tondo Madonna. A research team from Bradford University and the University of Nottingham initially attributed the painting to Raphael, employing an AI face recognition software, while the AI developed at Art Recognition returned a negative result. The Bradford group's AI was trained on 49 images, whereas Art Recognition employed a larger dataset of over 100 images. Lucian Freud Painting Controversy: Featured in The New Yorker, a painting attributed to Lucian Freud became a subject of dispute. Art Recognition's AI analysis played a big role in examining the painting's authenticity. Titian at Kunsthaus Zürich: A painting attributed to Titian, housed at Kunsthaus Zürich, has been a topic of debate among art experts. The application of Art Recognition's technology offered a new perspective. Following this debate, Kunsthaus Zürich has announced plans to initiate a comprehensive project aimed at resolving the authenticity questions surrounding the painting. Art Recognition has contributed to the authentication debate surrounding The Polish Rider, a painting traditionally attributed to Rembrandt but subject to scholarly debate.
Robust principal component analysis
Robust Principal Component Analysis (RPCA) is a modification of the widely used statistical procedure of principal component analysis (PCA) which works well with respect to grossly corrupted observations. A number of different approaches exist for Robust PCA, including an idealized version of Robust PCA, which aims to recover a low-rank matrix L0 from highly corrupted measurements M = L0 +S0. This decomposition in low-rank and sparse matrices can be achieved by techniques such as Principal Component Pursuit method (PCP), Stable PCP, Quantized PCP, Block based PCP, and Local PCP. Then, optimization methods are used such as the Augmented Lagrange Multiplier Method (ALM), Alternating Direction Method (ADM), Fast Alternating Minimization (FAM), Iteratively Reweighted Least Squares (IRLS ) or alternating projections (AP). == Algorithms == === Non-convex method === The 2014 guaranteed algorithm for the robust PCA problem (with the input matrix being M = L + S {\displaystyle M=L+S} ) is an alternating minimization type algorithm. The computational complexity is O ( m n r 2 log 1 ϵ ) {\displaystyle O\left(mnr^{2}\log {\frac {1}{\epsilon }}\right)} where the input is the superposition of a low-rank (of rank r {\displaystyle r} ) and a sparse matrix of dimension m × n {\displaystyle m\times n} and ϵ {\displaystyle \epsilon } is the desired accuracy of the recovered solution, i.e., ‖ L ^ − L ‖ F ≤ ϵ {\displaystyle \|{\widehat {L}}-L\|_{F}\leq \epsilon } where L {\displaystyle L} is the true low-rank component and L ^ {\displaystyle {\widehat {L}}} is the estimated or recovered low-rank component. Intuitively, this algorithm performs projections of the residual onto the set of low-rank matrices (via the SVD operation) and sparse matrices (via entry-wise hard thresholding) in an alternating manner - that is, low-rank projection of the difference the input matrix and the sparse matrix obtained at a given iteration followed by sparse projection of the difference of the input matrix and the low-rank matrix obtained in the previous step, and iterating the two steps until convergence. This alternating projections algorithm is later improved by an accelerated version, coined AccAltProj. The acceleration is achieved by applying a tangent space projection before projecting the residue onto the set of low-rank matrices. This trick improves the computational complexity to O ( m n r log 1 ϵ ) {\displaystyle O\left(mnr\log {\frac {1}{\epsilon }}\right)} with a much smaller constant in front while it maintains the theoretically guaranteed linear convergence. Another fast version of accelerated alternating projections algorithm is IRCUR. It uses the structure of CUR decomposition in alternating projections framework to dramatically reduces the computational complexity of RPCA to O ( max { m , n } r 2 log ( m ) log ( n ) log 1 ϵ ) {\displaystyle O\left(\max\{m,n\}r^{2}\log(m)\log(n)\log {\frac {1}{\epsilon }}\right)} === Convex relaxation === This method consists of relaxing the rank constraint r a n k ( L ) {\displaystyle rank(L)} in the optimization problem to the nuclear norm ‖ L ‖ ∗ {\displaystyle \|L\|_{}} and the sparsity constraint ‖ S ‖ 0 {\displaystyle \|S\|_{0}} to ℓ 1 {\displaystyle \ell _{1}} -norm ‖ S ‖ 1 {\displaystyle \|S\|_{1}} . The resulting program can be solved using methods such as the method of Augmented Lagrange Multipliers. === Deep-learning augmented method === Some recent works propose RPCA algorithms with learnable/training parameters. Such a learnable/trainable algorithm can be unfolded as a deep neural network whose parameters can be learned via machine learning techniques from a given dataset or problem distribution. The learned algorithm will have superior performance on the corresponding problem distribution. == Applications == RPCA has many real life important applications particularly when the data under study can naturally be modeled as a low-rank plus a sparse contribution. Following examples are inspired by contemporary challenges in computer science, and depending on the applications, either the low-rank component or the sparse component could be the object of interest: === Video surveillance === Given a sequence of surveillance video frames, it is often required to identify the activities that stand out from the background. If we stack the video frames as columns of a matrix M, then the low-rank component L0 naturally corresponds to the stationary background and the sparse component S0 captures the moving objects in the foreground. === Face recognition === Images of a convex, Lambertian surface under varying illuminations span a low-dimensional subspace. This is one of the reasons for effectiveness of low-dimensional models for imagery data. In particular, it is easy to approximate images of a human's face by a low-dimensional subspace. To be able to correctly retrieve this subspace is crucial in many applications such as face recognition and alignment. It turns out that RPCA can be applied successfully to this problem to exactly recover the face.
Curriculum learning
Curriculum learning is a technique in machine learning in which a model is trained on examples of increasing difficulty, where the definition of "difficulty" may be provided externally or discovered as part of the training process. This is intended to attain good performance more quickly, or to converge to a better local optimum if the global optimum is not found. == Approach == Most generally, curriculum learning is the technique of successively increasing the difficulty of examples in the training set that is presented to a model over multiple training iterations. This can produce better results than exposing the model to the full training set immediately under some circumstances; most typically, when the model is able to learn general principles from easier examples, and then gradually incorporate more complex and nuanced information as harder examples are introduced, such as edge cases. This has been shown to work in many domains, most likely as a form of regularization. There are several major variations in how the technique is applied: A concept of "difficulty" must be defined. This may come from human annotation or an external heuristic; for example in language modeling, shorter sentences might be classified as easier than longer ones. Another approach is to use the performance of another model, with examples accurately predicted by that model being classified as easier (providing a connection to boosting). Difficulty can be increased steadily or in distinct epochs, and in a deterministic schedule or according to a probability distribution. This may also be moderated by a requirement for diversity at each stage, in cases where easier examples are likely to be disproportionately similar to each other. Applications must also decide the schedule for increasing the difficulty. Simple approaches may use a fixed schedule, such as training on easy examples for half of the available iterations and then all examples for the second half. Other approaches use self-paced learning to increase the difficulty in proportion to the performance of the model on the current set. Since curriculum learning only concerns the selection and ordering of training data, it can be combined with many other techniques in machine learning. The success of the method assumes that a model trained for an easier version of the problem can generalize to harder versions, so it can be seen as a form of transfer learning. Some authors also consider curriculum learning to include other forms of progressively increasing complexity, such as increasing the number of model parameters. It is frequently combined with reinforcement learning, such as learning a simplified version of a game first. Some domains have shown success with anti-curriculum learning: training on the most difficult examples first. One example is the ACCAN method for speech recognition, which trains on the examples with the lowest signal-to-noise ratio first. == History == The term "curriculum learning" was introduced by Yoshua Bengio et al in 2009, with reference to the psychological technique of shaping in animals and structured education for humans: beginning with the simplest concepts and then building on them. The authors also note that the application of this technique in machine learning has its roots in the early study of neural networks such as Jeffrey Elman's 1993 paper Learning and development in neural networks: the importance of starting small. Bengio et al showed good results for problems in image classification, such as identifying geometric shapes with progressively more complex forms, and language modeling, such as training with a gradually expanding vocabulary. They conclude that, for curriculum strategies, "their beneficial effect is most pronounced on the test set", suggesting good generalization. The technique has since been applied to many other domains: Natural language processing: Part-of-speech tagging Intent detection Sentiment analysis Machine translation Speech recognition Language model pre-training Image recognition: Facial recognition Object detection Reinforcement learning: Game-playing Graph learning Matrix factorization
Time-aware long short-term memory
Time-aware LSTM (T-LSTM) is a long short-term memory (LSTM) unit capable of handling irregular time intervals in longitudinal patient records. T-LSTM was developed by researchers from Michigan State University, IBM Research, and Cornell University and was first presented in the Knowledge Discovery and Data Mining (KDD) conference. Experiments using real and synthetic data proved that T-LSTM auto-encoder outperformed widely used frameworks including LSTM and MF1-LSTM auto-encoders.
Cloud-based design and manufacturing
Cloud-based design and manufacturing (CBDM) refers to a service-oriented networked product development model in which service consumers are able to configure products or services and reconfigure manufacturing systems through Infrastructure-as-a-Service (IaaS), Platform-as-a-Service (PaaS), Hardware-as-a-Service (HaaS), and Software-as-a-Service (SaaS). Adapted from the original cloud computing paradigm and introduced into the realm of computer-aided product development, Cloud-Based Design and Manufacturing is gaining significant momentum and attention from both academia and industry. Cloud-based design and manufacturing includes two aspects: cloud-based design and cloud-based manufacturing. Another related concept is cloud manufacturing that is more general and popular. Cloud-Based Design (CBD) refers to a networked design model that leverages cloud computing, service-oriented architecture (SOA), Web 2.0 (e.g., social network sites), and semantic web technologies to support cloud-based engineering design services in distributed and collaborative environments. Cloud-Based Manufacturing (CBM) refers to a networked manufacturing model that exploits on-demand access to a shared collection of diversified and distributed manufacturing resources to form temporary, reconfigurable production lines which enhance efficiency, reduce product lifecycle costs, and allow for optimal resource allocation in response to variable-demand customer generated tasking. The enabling technologies for Cloud-Based Design and Manufacturing include cloud computing, Web 2.0, Internet of Things (IoT), and service-oriented architecture (SOA). == History == The term cloud-based design and manufacturing (CBDM) was initially coined by Dazhong Wu, David Rosen, and Dirk Schaefer at Georgia Tech in 2012 for the purpose of articulating a new paradigm for digital manufacturing and design innovation in distributed and collaborative settings. The main objective of CBDM is to further reduce time and cost associated with maintaining information and communication technology (ICT) infrastructures for design and manufacturing, enhancing digital manufacturing and design innovation in distributed and collaborative environments, and adapting to rapidly changing market demands. In 2014, the same research group also published the worldwide first two books on the subjects of Cloud-Based Design and Manufacturing (CBDM) and Social Product Development (SPD) with Springer, edited by Dirk Schaefer. == Characteristics == CBDM exhibits the following key characteristics: Cloud-based distributed file system High performance computing Cloud-based social collaboration Ubiquitous access to distributed big data Rapid manufacturing scalability Agility On-demand self-service Semantic Web Real-time request for quotation Pay-per-use pricing model Multi-tenancy CBDM differs from traditional collaborative and distributed design and manufacturing systems such as web-based systems and agent-based systems from a number of perspectives, including (1) computing architecture, (2) data storage, (3) sourcing process, (4) information and communication technology infrastructure, (5) business model, (6) programming model, and (7) communication. == Service models == Infrastructure as a service (IaaS) Platform as a service (PaaS) Hardware as a service (HaaS) Software as a service (SaaS) Similar to cloud computing, CBDM services can be categorized into four major deployment models: the public cloud, private cloud, hybrid cloud, and community cloud. == Research progress in Academia == The Defense Advanced Research Projects Agency (DARPA) MENTOR program Engineering and Physical Sciences Research Council cloud manufacturing program European Commission's Seventh Framework Program (EC FP7)
Semantic mapping (statistics)
Semantic mapping (SM) is a statistical method for dimensionality reduction (the transformation of data from a high-dimensional space into a low-dimensional space). SM can be used in a set of multidimensional vectors of features to extract a few new features that preserves the main data characteristics. SM performs dimensionality reduction by clustering the original features in semantic clusters and combining features mapped in the same cluster to generate an extracted feature. Given a data set, this method constructs a projection matrix that can be used to map a data element from a high-dimensional space into a reduced dimensional space. SM can be applied in construction of text mining and information retrieval systems, as well as systems managing vectors of high dimensionality. SM is an alternative to random mapping, principal components analysis and latent semantic indexing methods.