检索结果-内蒙古大学图书馆

Improvement on masked S-box hardware implementation

学校读者我要写书评

暂无评论

Improvement on masked S-box hardware implementation

International Conference on Innovations in Information Technology

作者： Juanli Zeng Yi Wang Cheng Xu Renfa Li College of Information Science and Engineering Hunan University Changsha Hunan P. R. China Department of Electrical & Computer Engineering National University of Singapore Singapore Hunan Province Key Laboratory of Network and Information Security

Masking in gate level could efficiently protect AES S-box out of power analysis attack. But there still exists a kind of attack, called glitch attack, to achieve the sensitive information from gate cell leakage. Some works had been done to resist against glitch attack, which carefully masked AND gate or used Wave Dynamic Differential Logic (WDDL) cell. In this paper, we propose an improved masked AND gate, in which the relationship between input masked values and masks is nonlinear. Usually, when converting S-box operations from GF(2 8 ) to GF(((2 2 ) 2 ) 2 ), all the necessary computations become XOR and AND operations. Therefore, to fully mask AES S-box is to substitute the unmasked XOR and AND operations with the proposed masked AND gate and protected XOR gate. Although the proposed masked AND gate take up one extra XOR gate than Trichina's design and Baek's design, it can resist against glitch attack without using specific gate cell, such as WDDL.

关键词： Logic gates Hardware CMOS integrated circuits Encryption Field programmable gate arrays Computer architecture

Energy-Efficient Functional Safety Design Methodology Using ASIL Decomposition for Automotive Cyber-Physical Systems

学校读者我要写书评

暂无评论

IEEE Transactions on Reliability 2024年 1-23页

作者： Xie, Guoqi Peng, Hao Huang, Jing Li, Renfa Li, Keqin Department of Computer Engineering College of Computer Science and Electronic Engineering Hunan University Changsha 410082 China and also with the Key Laboratory for Embedded and Cyber-Physical Systems of Hunan Province Changsha 410082 China College of Computer Science and Electronic Engineering Hunan University Changsha 410082 China and also with the Department of Computer Science State University of New York New Paltz NY 12561 USA

Automotive cyber-physical systems (ACPS) are typical cyber-physical systems because of the joint interaction between the cyber part and physical part. Functional safety requirement (including response time and reliability requirements) for an ACPS function must be assured for safe driving. Auto industry is cost-sensitive, power-sensitive, and environment-friendly. Energy consumption affects the development efficiency of the ACPS and the living environment of people. This paper solves the problem of optimizing the energy consumption for an ACPS function while assuring its functional safety requirement (i.e., energy-efficient functional safety for ACPS). However, implementing minimum response time, maximum reliability, and minimum energy consumption is a conflicting problem. Consequently, solving the problem is a challenge. In this paper, we propose a three-stage design process toward energy-efficient functional safety for ACPS. The topic problem is divided into three sub-problems, namely, response time requirement verification (first stage), functional safety requirement verification (second stage), and functional safety-critical energy consumption optimization (third stage). The proposed energy-efficient functional safety design methodology is implemented by using automotive safety integrity level decomposition, which is defined in the ACPS functional safety standard ISO 26262. Experiments with real-life and synthetic ACPS functions reveal the advantages of the proposed design methodology toward energy-efficient functional safety for ACPS compared with state-of-the-art algorithms. IEEE

关键词： Energy utilization

Monocular Camera-Based Visual Truck Type Recognition

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Luo, Haibo Ye, Huaisheng Feng, Chao Shi, Xin Xie, Guoqi School of Computer and Data Science Minjiang University Fuzhou350018 China College of Computer and Data Science Fuzhou University Fuzhou350018 China College of Network and Information Security Fujian Agriculture and Forestry University Fuzhou350018 China Key Laboratory for Embedded and Network Computing of Hunan Province College of Computer Science and Electronic Engineering Hunan University Changsha410082 China College of Computer Science and Electronic Engineering Hunan University Changsha410082 China

Truck overload and over-limit are the primary causes of infrastructure damage and traffic safety accidents. In the past 2 years, researchers have started to deploy intelligent Internet of Things system at the source of truck delivery to enforce permit control. Truck type recognition is the core of such a system. However, existing methods suffer from limitations such as low recognition accuracy, high costs, difficult maintenance, and the need for road surface modifications. This study proposes a monocular camera-based visual truck type recognition method. First, the optimized lightweight deep neural network based on machine vision is utilized to detect truckaxles and recognize wheel hub categories. Next, a tracking algorithm and the video streamcontext information are employed to complete the robust statistics of the axle by neighborhoodcounting. Finally, the proposed method further achieves truck type recognition by leveragingavailable prior knowledge. Experimental results demonstrate that this method exhibits superiortime efficiency compared with existing algorithms, and it reduces average processing time by92.37% to 96.24% while ensuring high accuracy. Moreover, the method has been deployed onembedded devices with low computing power to enable real-time operation onsite. © 2024, The Authors. All rights reserved.

关键词： Object detection

Nonlinear Prediction with Deep Recurrent Neural networks for Non-Blind Audio Bandwidth Extension

学校读者我要写书评

暂无评论

China Communications 2018年第4期15卷 72-85页

作者： Lin Jiang Ruimin Hu Xiaochen Wang Weiping Tu Maosheng Zhang National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan 430072 China Institute of Big Data and internet Innovation Hunan University of Commerce Changsha 410205 China Software College East China University of Technology Nanchang 330013 China Collaborative Innovation Center for Economics crime investigation and prevention technology Jiangxi Province Nanchang 330103China Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan 430072 China Collaborative Innovation Center of Geospatial Technology Wuhan 430079 China

Non-blind audio bandwidth extension is a standard technique within contemporary audio codecs to efficiently code audio signals at low bitrates. In existing methods, in most cases high frequencies signal is usually generated by a duplication of the corresponding low frequencies and some parameters of high frequencies. However, the perception quality of coding will significantly degrade if the correlation between high frequencies and low frequencies becomes weak. In this paper, we quantitatively analyse the correlation via computing mutual information value. The analysis results show the correlation also exists in low frequency signal of the context dependent frames besides the current frame. In order to improve the perception quality of coding, we propose a novel method of high frequency coarse spectrum generation to improve the conventional replication method. In the proposed method, the coarse high frequency spectrums are generated by a nonlinear mapping model using deep recurrent neural network. The experiments confirm that the proposed method shows better performance than the reference methods.

关键词： audio coding non-blind audiobandwidth extension context correlation deeprecurrent neural network

DFTerNet: Towards 2-bit dynamic fusion networks for accurate human activity recognition

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Yang, Zhan Raymond, Osolo Ian Zhang, Cheng Yuan Wan, Ying Long, Jun School of Information Science and Engineering Central South University Changsha410083 China Network Resources Management and Trust Evaluation Key Laboratory of Hunan Province

Deep Convolutional Neural networks (DCNNs) are currently popular in human activity recognition (HAR) applications. However, in the face of modern artificial intelligence sensor-based games, many research achievements cannot be practically applied on portable devices (i.e., smart phone, VR/AR). DCNNs are typically resource-intensive and too large to be deployed on portable devices, thus this limits the practical application of complex activity detection. In addition, since portable devices do not possess high-performance Graphic Processing Units (GPUs), there is hardly any improvement in Action Game (ACT) experience. Besides, in order to deal with multi-sensor collaboration, all previous human activity recognition models typically treated the representations from different sensor signal sources equally. However, distinct types of activities should adopt different fusion strategies. In this paper, a novel scheme is proposed. This scheme is used to train 2-bit Convolutional Neural networks with weights and activations constrained to {-0.5, 0, 0.5}. It takes into account the correlation between different sensor signal sources and the activity types. This model, which we refer to as DFTerNet, aims at producing a more reliable inference and better trade-offs for practical applications. It's known that quantization of weights and activations can substantially reduce memory size and use more efficient bitwise operations to replace floating or matrix operations to achieve much faster calculation and lower power consumption. Our basic idea is to exploit quantization of weights and activations directly in pre-trained filter banks and adopt dynamic fusion strategies for different activity types. Experiments demonstrate that by using a dynamic fusion strategy, it is possible to exceed the baseline model performance by up to ∼5% on activity recognition datasets like the OPPORTUNITY and PAMAP2 datasets. Using the quantization method proposed, we were able to achieve performances c

关键词： Deep neural networks

Asymmetric residual neural network for accurate human activity recognition

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Long, Jun Sun, WuQing Raymond, Osolo Ian Yang, Zhan School of Information Science and Engineering Central South University Changsha410083 China Network Resources Management and Trust Evaluation Key Laboratory of Hunan Province

Human Activity Recognition (HAR) using deep neural network has become a hot topic in human-computer interaction. Machine can effectively identify human naturalistic activities by learning from a large collection of sensor data. Activity recognition is not only an interesting research problem, but also has many real-world practical applications. Based on the success of residual networks in achieving a high level of aesthetic representation of the automatic learning, we propose a novel Asymmetric Residual network, named ARN. ARN is implemented using two identical path frameworks consisting of (1) a short time window, which is used to capture spatial features, and (2) a long time window, which is used to capture fine temporal features. The long time window path can be made very lightweight by reducing its channel capacity, yet still being able to learn useful temporal representations for activity recognition. In this paper, we mainly focus on proposing a new model to improve the accuracy of HAR. In order to demonstrate the effectiveness of ARN model, we carried out extensive experiments on benchmark datasets (i.e., OPPORTUNITY, UniMiB-SHAR) and compared with some conventional and state-of-the-art learning-based methods. Then, we discuss the influence of networks parameters on performance to provide insights about its optimization. Results from our experiments show that ARN is effective in recognizing human activities via wearable datasets. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep neural networks

Asymmetric deep semantic quantization for image retrieval

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Yang, Zhan Raymond, Osolo Ian Sun, WuQing Long, Jun School of Computer Science and Engineering Central South University Changsha410083 China Network Resources Management and Trust Evaluation Key Laboratory of Hunan Province

Due to its fast retrieval and storage efficiency capabilities, hashing has been widely used in nearest neighbor retrieval tasks. By using deep learning based techniques, hashing can outperform non-learning based hashing technique in many applications. However, we argue that the current deep learning based hashing methods ignore some critical problems (e.g., the learned hash codes are not discriminative due to the hashing methods being unable to discover rich semantic information and the training strategy having difficulty optimizing the discrete binary codes). In this paper, we propose a novel image hashing method, termed as Asymmetric Deep Semantic Quantization (ADSQ). ADSQ is implemented using three stream frameworks, which consist of one LabelNet and two ImgNets. The LabelNet leverages the power of three fully-connected layers, which are used to capture rich semantic information between image pairs. For the two ImgNets, they each adopt the same convolutional neural network structure, but with different weights (i.e., asymmetric convolutional neural networks). The two ImgNets are used to generate discriminative compact hash codes. Specifically, the function of the LabelNet is to capture rich semantic information that is used to guide the two ImgNets in minimizing the gap between the real-continuous features and the discrete binary codes. Furthermore, ADSQ can utilize the most critical semantic information to guide the feature learning process and consider the consistency of the common semantic space and Hamming space. Experimental results on three benchmarks (i.e., CIFAR-10, NUS-WIDE, and ImageNet) demonstrate that the proposed ADSQ can outperforms current state-of-the-art methods. Copyright © 2019, The Authors. All rights reserved.

关键词： Hash functions

Deep attention-guided Hashing

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Yang, Zhan Raymond, Osolo Ian Sun, WuQing Long, Jun School of Information Science and Engineering Central South University Changsha410083 China Network Resources Management and Trust Evaluation Key Laboratory of Hunan Province

With the rapid growth of multimedia data (e.g., image, audio and video etc.) on the web, learning-based hashing techniques such as Deep Supervised Hashing (DSH) have proven to be very efficient for large-scale multimedia search. The recent successes seen in Learning-based hashing methods are largely due to the success of deep learning-based hashing methods. However, there are some limitations to previous learning-based hashing methods (e.g., the learned hash codes containing repetitive and highly correlated information). In this paper, we propose a novel learning-based hashing method, named Deep Attention-guided Hashing (DAgH). DAgH is implemented using two stream frameworks. The core idea is to use guided hash codes which are generated by the hashing network of the first stream framework (called first hashing network) to guide the training of the hashing network of the second stream framework (called second hashing network). Specifically, in the first network, it leverages an attention network and hashing network to generate the attention-guided hash codes from the original images. The loss function we propose contains two components: the semantic loss and the attention loss. The attention loss is used to punish the attention network to obtain the salient region from pairs of images;in the second network, these attention-guided hash codes are used to guide the training of the second hashing network (i.e., these codes are treated as supervised labels to train the second network). By doing this, DAgH can make full use of the most critical information contained in images to guide the second hashing network in order to learn efficient hash codes in a true end-to-end fashion. Results from our experiments demonstrate that DAgH can generate high quality hash codes and it outperforms current state-of-the-art methods on three benchmark datasets, CIFAR-10, NUS-WIDE, and ImageNet. Copyright © 2018, The Authors. All rights reserved.

关键词： Hash functions

Accurate Recovery of Internet Traffic Data: A Sequential Tensor Completion Approach

学校读者我要写书评

暂无评论

Accurate Recovery of Internet Traffic Data: A Sequential Ten...

作者： Xie, Kun Wang, Lele Wang, Xin Xie, Gaogang Wen, Jigang Zhang, Guangxing Cao, Jiannong Zhang, Dafang College of Computer Science and Electronics Engineering Hunan University Changsha410006 China CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing100864 China Department of Electrical and Computer Engineering State University of New York at Stony Brook Stony BrookNY11794 United States Network Research Center Institute of Computing Technology Chinese Academy of Sciences Beijing100864 China Department of Computing Hong Kong Polytechnic University Hong Kong Hong Kong

The inference of traffic volume of the whole network from partial traffic measurements becomes increasingly critical for various network engineering tasks, such as capacity planning and anomaly detection. Previous studies indicate that the matrix completion is a possible solution for this problem. However, as a 2-D matrix cannot sufficiently capture the spatial-temporal features of traffic data, these approaches fail to work when the data missing ratio is high. To fully exploit hidden spatial-temporal structures of the traffic data, this paper models the traffic data as a 3-way traffic tensor and formulates the traffic data recovery problem as a low-rank tensor completion problem. However, the high computation complexity incurred by the conventional tensor completion algorithms prevents its practical application for the traffic data recovery. To reduce the computation cost, we propose a novel sequential tensor completion algorithm, which can efficiently exploit the tensor decomposition result based on the previous traffic data to derive the tensor decomposition upon arriving of new data. Furthermore, to better capture the changes of data correlation over time, we propose a dynamic sequential tensor completion algorithm. To the best of our knowledge, we are the first to propose sequential tensor completion algorithms to significantly speed up the traffic data recovery process. This facilitates the modeling of Internet traffic with the tensor to well exploit the hidden structures of traffic data for more accurate missing data inference. We have done extensive simulations with the real traffic trace as the input. The simulation results demonstrate that our algorithms can achieve significantly better performance compared with the literature tensor and matrix completion algorithms even when the data missing ratio is high. © 1993-2012 IEEE.

关键词： Tensors