Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
5,968
result(s) for
"Data compression (Computer science)"
Sort by:
Multilinear subspace learning : dimensionality reduction of multidimensional data
\"Due to advances in sensor, storage, and networking technologies, data is being generated on a daily basis at an ever-increasing pace in a wide range of applications, including cloud computing, mobile Internet, and medical imaging. This large multidimensional data requires more efficient dimensionality reduction schemes than the traditional techniques. Addressing this need, multilinear subspace learning (MSL) reduces the dimensionality of big data directly from its natural multidimensional representation, a tensor. Multilinear Subspace Learning: Dimensionality Reduction of Multidimensional Data gives a comprehensive introduction to both theoretical and practical aspects of MSL for the dimensionality reduction of multidimensional data based on tensors. It covers the fundamentals, algorithms, and applications of MSL. Emphasizing essential concepts and system-level perspectives, the authors provide a foundation for solving many of today's most interesting and challenging problems in big multidimensional data processing. They trace the history of MSL, detail recent advances, and explore future developments and emerging applications.The book follows a unifying MSL framework formulation to systematically derive representative MSL algorithms. It describes various applications of the algorithms, along with their pseudocode. Implementation tips help practitioners in further development, evaluation, and application. The book also provides researchers with useful theoretical information on big multidimensional data in machine learning and pattern recognition. MATLAB source code, data, and other materials are available at www.comp.hkbu.edu.hk/haiping/MSL.html\"-- Provided by publisher
Book
Multilinear Subspace Learning
Emphasizing essential concepts and system-level perspectives, this book provides a foundation for solving many of today's most interesting and challenging problems in big multidimensional data processing. It gives a comprehensive introduction to both theoretical and practical aspects of MSL for the dimensionality reduction of multidimensional data based on tensors. The book follows a unifying MSL framework formulation to systematically derive representative MSL algorithms. It describes various applications of the algorithms, along with their pseudocode. Supporting materials are available online.
eBook
Artificial intelligence in the creative industries: a review
This paper reviews the current state of the art in artificial intelligence (AI) technologies and applications in the context of the creative industries. A brief background of AI, and specifically machine learning (ML) algorithms, is provided including convolutional neural networks (CNNs), generative adversarial networks (GANs), recurrent neural networks (RNNs) and deep Reinforcement Learning (DRL). We categorize creative applications into five groups, related to how AI technologies are used: (i) content creation, (ii) information analysis, (iii) content enhancement and post production workflows, (iv) information extraction and enhancement, and (v) data compression. We critically examine the successes and limitations of this rapidly advancing technology in each of these areas. We further differentiate between the use of AI as a creative tool and its potential as a creator in its own right. We foresee that, in the near future, ML-based AI will be adopted widely as a tool or collaborative assistant for creativity. In contrast, we observe that the successes of ML in domains with fewer constraints, where AI is the ‘creator’, remain modest. The potential of AI (or its developers) to win awards for its original creations in competition with human creatives is also limited, based on contemporary technologies. We therefore conclude that, in the context of creative industries, maximum benefit from AI will be derived where its focus is human-centric—where it is designed to augment, rather than replace, human creativity.
Journal Article
Impact of digital fingerprint image quality on the fingerprint recognition accuracy
Despite the large body of work on fingerprint identification systems, most of it focused on using specialized devices. Due to the high price of such devices, some researchers directed their attention to digital cameras as an alternative source for fingerprints images. However, such sources introduce new challenges related to image quality. Specifically, most digital cameras compress captured images before storing them leading to potential losses of information. This study comes to address the need to determine the optimum ratio of the fingerprint image compression to ensure the fingerprint identification system’s high accuracy. This study is conducted using a large in-house dataset of raw images. Therefore, all fingerprint information is stored in order to determine the compression ratio accurately. The results proved that the used software functioned perfectly until a compression ratio of (30–40%) of the raw images; any higher ratio would negatively affect the accuracy of the used system.
Journal Article
Compressive sensing based image compression-encryption using Novel 1D-Chaotic map
Compressive sensing based encryption achieves simultaneous compression-encryption by utilizing a low complex sampling process, which is computationally secure. In this paper, a new novel 1D–chaotic map is proposed that is used to construct an incoherence rotated chaotic measurement matrix. The chaotic property of the proposed map is experimentally analysed. The linear measurements obtained are confused and diffused using the chaotic sequence generated using the proposed map. The chaos based measurement matrix construction results in reduced data storage and bandwidth requirements. As it needs to store only the parameters required to generate the chaotic sequence. Also, the sensitivity of the chaos to the parameters makes the data transmission secure. The secret key used in the encryption process is dependent on both the input data and the parameter used to generate the chaotic map. Hence the proposed scheme can resist chosen plaintext attack. The key space of the proposed scheme is large enough to thwart statistical attacks. Experimental results and the security analysis verifies the security and effectiveness of the proposed compression-encryption scheme.
Journal Article
Model Compression for Deep Neural Networks: A Survey
Currently, with the rapid development of deep learning, deep neural networks (DNNs) have been widely applied in various computer vision tasks. However, in the pursuit of performance, advanced DNN models have become more complex, which has led to a large memory footprint and high computation demands. As a result, the models are difficult to apply in real time. To address these issues, model compression has become a focus of research. Furthermore, model compression techniques play an important role in deploying models on edge devices. This study analyzed various model compression methods to assist researchers in reducing device storage space, speeding up model inference, reducing model complexity and training costs, and improving model deployment. Hence, this paper summarized the state-of-the-art techniques for model compression, including model pruning, parameter quantization, low-rank decomposition, knowledge distillation, and lightweight model design. In addition, this paper discusses research challenges and directions for future work.
Journal Article
Semantics-to-Signal Scalable Image Compression with Learned Revertible Representations
Image/video compression and communication need to serve both human vision and machine vision. To address this need, we propose a scalable image compression solution. We assume that machine vision needs less information that is related to semantics, whereas human vision needs more information that is to reconstruct signal. We then propose semantics-to-signal scalable compression, where partial bitstream is decodeable for machine vision and the entire bitstream is decodeable for human vision. Our method is inspired by the scalable image coding standard, JPEG2000, and similarly adopts subband-wise representations. We first design a trainable and revertible transform based on the lifting structure, which converts an image into a pyramid of multiple subbands; the transform is trained to make the partial representations useful for multiple machine vision tasks. We then design an end-to-end optimized encoding/decoding network for compressing the multiple subbands, to jointly optimize compression ratio, semantic analysis accuracy, and signal reconstruction quality. We experiment with two datasets: CUB200-2011 and FGVC-Aircraft, taking coarse-to-fine image classification tasks as an example. Experimental results demonstrate that our proposed method achieves semantics-to-signal scalable compression, and outperforms JPEG2000 in compression efficiency. The proposed method sheds light on a generic approach for image/video coding for human and machines.
Journal Article
A Survey of Traffic Prediction: from Spatio-Temporal Data to Intelligent Transportation
Intelligent transportation (e.g., intelligent traffic light) makes our travel more convenient and efficient. With the development of mobile Internet and position technologies, it is reasonable to collect spatio-temporal data and then leverage these data to achieve the goal of intelligent transportation, and here, traffic prediction plays an important role. In this paper, we provide a comprehensive survey on traffic prediction, which is from the spatio-temporal data layer to the intelligent transportation application layer. At first, we split the whole research scope into four parts from bottom to up, where the four parts are, respectively, spatio-temporal data, preprocessing, traffic prediction and traffic application. Later, we review existing work on the four parts. First, we summarize traffic data into five types according to their difference on spatial and temporal dimensions. Second, we focus on four significant data preprocessing techniques: map-matching, data cleaning, data storage and data compression. Third, we focus on three kinds of traffic prediction problems (i.e., classification, generation and estimation/forecasting). In particular, we summarize the challenges and discuss how existing methods address these challenges. Fourth, we list five typical traffic applications. Lastly, we provide emerging research challenges and opportunities. We believe that the survey can help the partitioners to understand existing traffic prediction problems and methods, which can further encourage them to solve their intelligent transportation applications.
Journal Article
Deep Learning Approaches for Video Compression: A Bibliometric Analysis
Every data and kind of data need a physical drive to store it. There has been an explosion in the volume of images, video, and other similar data types circulated over the internet. Users using the internet expect intelligible data, even under the pressure of multiple resource constraints such as bandwidth bottleneck and noisy channels. Therefore, data compression is becoming a fundamental problem in wider engineering communities. There has been some related work on data compression using neural networks. Various machine learning approaches are currently applied in data compression techniques and tested to obtain better lossy and lossless compression results. A very efficient and variety of research is already available for image compression. However, this is not the case for video compression. Because of the explosion of big data and the excess use of cameras in various places globally, around 82% of the data generated involve videos. Proposed approaches have used Deep Neural Networks (DNNs), Recurrent Neural Networks (RNNs), and Generative Adversarial Networks (GANs), and various variants of Autoencoders (AEs) are used in their approaches. All newly proposed methods aim to increase performance (reducing bitrate up to 50% at the same data quality and complexity). This paper presents a bibliometric analysis and literature survey of all Deep Learning (DL) methods used in video compression in recent years. Scopus and Web of Science are well-known research databases. The results retrieved from them are used for this analytical study. Two types of analysis are performed on the extracted documents. They include quantitative and qualitative results. In quantitative analysis, records are analyzed based on their citations, keywords, source of publication, and country of publication. The qualitative analysis provides information on DL-based approaches for video compression, as well as the advantages, disadvantages, and challenges of using them.
Journal Article
Security of the Internet of Things: perspectives and challenges
Internet of Things (IoT) is playing a more and more important role after its showing up, it covers from traditional equipment to general household objects such as WSNs and RFID. With the great potential of IoT, there come all kinds of challenges. This paper focuses on the security problems among all other challenges. As IoT is built on the basis of the Internet, security problems of the Internet will also show up in IoT. And as IoT contains three layers: perception layer, transportation layer and application layer, this paper will analyze the security problems of each layer separately and try to find new problems and solutions. This paper also analyzes the cross-layer heterogeneous integration issues and security issues in detail and discusses the security issues of IoT as a whole and tries to find solutions to them. In the end, this paper compares security issues between IoT and traditional network, and discusses opening security issues of IoT.
Journal Article