"This book provides a comprehensive reference for the many different types and methods of compression. Included are a detailed and helpful taxonomy, analysis of most common methods, and discussions ...on the use and comparative benefits of methods and description of ""how to"" use them. Detailed descriptions and explanations of the most well-known and frequently used compression methods are covered in a self-contained fashion, with an accessible style and technical level for specialists and nonspecialists. This 4th edition of this successful volume contains significant additional material as there has been tremendous progress in this field, especially in audio compression such as FLAC, AAC, WavPack, ALS and Dolby AC3, which are all covered. Additional key features include: RAR, Tunstall code, Differential and Hyperspectral Compression, LZMA, H.264, 3D data sets, PDF. This book provides an invaluable reference and guide for all researchers and practitioners needing a comprehensive compilation for a broad range of compression methods."
A convolutional neural network (CNN) is one of the most significant networks in the deep learning field. Since CNN made impressive achievements in many areas, including but not limited to computer ...vision and natural language processing, it attracted much attention from both industry and academia in the past few years. The existing reviews mainly focus on CNN's applications in different scenarios without considering CNN from a general perspective, and some novel ideas proposed recently are not covered. In this review, we aim to provide some novel ideas and prospects in this fast-growing field. Besides, not only 2-D convolution but also 1-D and multidimensional ones are involved. First, this review introduces the history of CNN. Second, we provide an overview of various convolutions. Third, some classic and advanced CNN models are introduced; especially those key points making them reach state-of-the-art results. Fourth, through experimental analysis, we draw some conclusions and provide several rules of thumb for functions and hyperparameter selection. Fifth, the applications of 1-D, 2-D, and multidimensional convolution are covered. Finally, some open issues and promising directions for CNN are discussed as guidelines for future work.
This paper reviews big data and Internet of Things (IoT)-based applications in smart environments. The aim is to identify key areas of application, current trends, data architectures, and ongoing ...challenges in these fields. To the best of our knowledge, this is a first systematic review of its kind, that reviews academic documents published in peer-reviewed venues from 2011 to 2019, based on a four-step selection process of identification, screening, eligibility, and inclusion for the selection process. In order to examine these documents, a systematic review was conducted and six main research questions were answered. The results indicate that the integration of big data and IoT technologies creates exciting opportunities for real-world smart environment applications for monitoring, protection, and improvement of natural resources. The fields that have been investigated in this survey include smart environment monitoring, smart farming/agriculture, smart metering, and smart disaster alerts. We conclude by summarizing the methods most commonly used in big data and IoT, which we posit to serve as a starting point for future multi-disciplinary research in smart cities and environments.
Real-time object detection is one of the most important research topics in computer vision. As new approaches regarding architecture optimization and training optimization are continually being ...developed, we have found two research topics that have spawned when dealing with these latest state-of-the-art methods. To address the topics, we propose a trainable bag-of-freebies oriented solution. We combine the flexible and efficient training tools with the proposed architecture and the compound scaling method. YOLOv7 surpasses all known object detectors in both speed and accuracy in the range from 5 FPS to 120 FPS and has the highest accuracy 56.8% AP among all known real-time object detectors with 30 FPS or higher on GPU V100. Source code is released in https://github.com/WongKinYiu/yolov7.
Power analysis attacks allow the extraction of secret information from smart cards. Smart cards are used in many applications including banking, mobile communications, pay TV, and electronic ...signatures. In all these applications, the security of the smart cards is of crucial importance. Power Analysis Attacks: Revealing the Secrets of Smart Cardsis the first comprehensive treatment of power analysis attacks and countermeasures. Based on the principle that the only way to defend against power analysis attacks is to understand them, this book explains how power analysis attacks work. Using many examples, it discusses simple and differential power analysis as well as advanced techniques like template attacks. Furthermore, the authors provide an extensive discussion of countermeasures like shuffling, masking, and DPA-resistant logic styles. By analyzing the pros and cons of the different countermeasures, this volume allows practitioners to decide how to protect smart cards.
Over the last several years, the field of natural language processing has been propelled forward by an explosion in the use of deep learning models. This article provides a brief introduction to the ...field and a quick overview of deep learning architectures and methods. It then sifts through the plethora of recent studies and summarizes a large assortment of relevant contributions. Analyzed research areas include several core linguistic processing issues in addition to many applications of computational linguistics. A discussion of the current state of the art is then provided along with recommendations for future research in the field.
Feature Extraction Algorithms (FEAs) aim to address the curse of dimensionality that makes machine learning algorithms incompetent. Our study conceptually and empirically explores the most ...representative FEAs. First, we review the theoretical background of many FEAs from different categories (linear vs. nonlinear, supervised vs. unsupervised, random projection-based vs. manifold-based), present their algorithms, and conduct a conceptual comparison of these methods. Secondly, for three challenging binary and multi-class datasets, we determine the optimal sets of new features and assess the quality of the various transformed feature spaces in terms of statistical significance and power analysis, and the FEA efficacy in terms of classification accuracy and speed.
Chaos-based cryptography has attracted great interest in the past decade. This book gives a thorough description of chaos-based cryptography. Written by leading experts, it covers the basic theories, ...algorithms and applications of chaos-based cryptography.
Federated learning allows multiple parties to jointly train a deep learning model on their combined data, without any of the participants having to reveal their local data to a centralized server. ...This form of privacy-preserving collaborative learning, however, comes at the cost of a significant communication overhead during training. To address this problem, several compression methods have been proposed in the distributed training literature that can reduce the amount of required communication by up to three orders of magnitude. These existing methods, however, are only of limited utility in the federated learning setting, as they either only compress the upstream communication from the clients to the server (leaving the downstream communication uncompressed) or only perform well under idealized conditions, such as i.i.d. distribution of the client data, which typically cannot be found in federated learning. In this article, we propose sparse ternary compression (STC), a new compression framework that is specifically designed to meet the requirements of the federated learning environment. STC extends the existing compression technique of top-k gradient sparsification with a novel mechanism to enable downstream compression as well as ternarization and optimal Golomb encoding of the weight updates. Our experiments on four different learning tasks demonstrate that STC distinctively outperforms federated averaging in common federated learning scenarios. These results advocate for a paradigm shift in federated optimization toward high-frequency low-bitwidth communication, in particular in the bandwidth-constrained learning environments.