检索结果-内蒙古大学图书馆

Implementation of PRINCE with resource-efficient structures based on FPGAs

学校读者我要写书评

暂无评论

Frontiers of Information technology & Electronic Engineering 2021年第11期22卷 1505-1516页

作者： Lang LI Jingya FENG Botao LIU Ying GUO Qiuping LI Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang Normal UniversityHengyang421002China College of Information Science and Engineering Hunan Normal UniversityChangsha410081China College of Computer Science and Technology Hengyang Normal UniversityHengyang421002China

In this era of pervasive computing, low-resource devices have been deployed in various fields. PRINCE is a lightweight block cipher designed for low latency, and is suitable for pervasive computing applications. In this paper, we propose new circuit structures for PRINCE components by sharing and simplifying logic circuits, to achieve the goal of using a smaller number of logic gates to obtain the same result. Based on the new circuit structures of components and the best sharing among components,we propose three new hardware architectures for PRINCE. The architectures are simulated and synthesized on different programmable gate array devices. The results on Virtex-6 show that compared with existing architectures, the resource consumption of the unrolled, low-cost, and two-cycle architectures is reduced by 73, 119, and 380 slices, respectively. The low-cost architecture costs only 137 slices. The unrolled architecture costs 409 slices and has a throughput of 5.34 Gb/s. To our knowledge, for the hardware implementation of PRINCE, the new low-cost architecture sets new area records, and the new unrolled architecture sets new throughput records. Therefore, the newly proposed architectures are more resource-efficient and suitable for lightweight,latency-critical applications.

关键词： Lightweight block cipher Field-programmable gate array(FPGA) Low-cost PRINCE Embedded security

Towards the Desirable Decision Boundary by Moderate-Margin Adversarial Training

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Liang, Xiaoyu Qian, Yaguan Huang, Jianchang Ling, Xiang Wang, Bin Wu, Chunming Swaileh, Wassim School of Science Zhejiang University of Science and Technology China Institute of Software Chinese Academy of Sciences China The Zhejiang Key Laboratory of Multidimensional Perception Technology Application and Cybersecurity China The College of Computer Science Zhejiang University China IRISA Laboratory UMR 6074 INSA De Rennes CNRS France

Adversarial training, as one of the most effective defense methods against adversarial attacks, tends to learn an inclusive decision boundary to increase the robustness of deep learning models. However, due to the large and unnecessary increase in the margin along adversarial directions, adversarial training causes heavy cross-over between natural examples and adversarial examples, which is not conducive to balancing the trade-off between robustness and natural accuracy. In this paper, we propose a novel adversarial training scheme to achieve a better trade-off between robustness and natural accuracy. It aims to learn a moderate-inclusive decision boundary, which means that the margins of natural examples under the decision boundary are moderate. We call this scheme Moderate-Margin Adversarial Training (MMAT), which generates finer-grained adversarial examples to mitigate the cross-over problem. We also take advantage of logits from a teacher model that has been well-trained to guide the learning of our model. Finally, MMAT achieves high natural accuracy and robustness under both black-box and white-box attacks. On SVHN, for example, state-of-the-art robustness and natural accuracy are achieved. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep learning

Transformer-Based Hierarchical Dynamic Decoders for Salient Object Detection

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Zheng, Qingping Zheng, Ling Deng, Jiankang Li, Ying Shang, Changjing Shen, Qiang School of Computer Science National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Provincial Key Laboratory of Speech & Image Information Processing Northewestern Polytechnical University Shaanxi Xi’an710129 China Fuzhou Institute of Data Technology Fujian350200 China Department of Computing Imperial College London LondonSW7 2AZ United Kingdom

HighlightsTransformer-Based Hierarchical Dynamic Decoders for Salient Object DetectionQingping Zheng, Ling Zheng, Jiankang Deng, Ying Li, Changjing Shang, Qiang Shen• T-HDDNet employs dynamic upsampling and fusion for data-driven salient object detection.• T-HDDNet uses a spatially sensitive loss to learn salient object structures, yielding a high-resolution map.• Our method exceeds benchmarks at 22.19G MACs and 27M Params, reducing costs compared to the top model. © 2023, The Authors. All rights reserved.

关键词： Object detection

Full-Atom Protein Pocket Design via Iterative Refinement

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Zaixi Lu, Zepu Hao, Zhongkai Zitnik, Marinka Liu, Qi Anhui Province Key Lab of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China China State Key Laboratory of Cognitive Intelligence Anhui Hefei China Dept. of Comp. Sci. and Tech. Institute for AI THBI Lab BNRist Center Tsinghua-Bosch Joint ML Center Tsinghua China Harvard University United States

The design of de novo functional proteins that bind specific ligand molecules is paramount in therapeutics and bio-engineering. A critical yet formidable task in this endeavor is the design of the protein pocket, which is the cavity region of the protein where the ligand binds. Current methods are plagued by inefficient generation, inadequate context modeling of the ligand molecule, and the inability to generate side-chain atoms. Here, we present the Full-Atom Iterative Refinement (FAIR) method, designed to address these challenges by facilitating the co-design of protein pocket sequences, specifically residue types, and their corresponding 3D structures. FAIR operates in two steps, proceeding in a coarse-to-fine manner (transitioning from protein backbone to atoms, including side chains) for a full-atom generation. In each iteration, all residue types and structures are simultaneously updated, a process termed full-shot refinement. In the initial stage, the residue types and backbone coordinates are refined using a hierarchical context encoder, complemented by two structure refinement modules that capture both inter-residue and pocket-ligand interactions. The subsequent stage delves deeper, modeling the side-chain atoms of the pockets and updating residue types to ensure sequence-structure congruence. Concurrently, the structure of the binding ligand is refined across iterations to accommodate its inherent flexibility. Comprehensive experiments show that FAIR surpasses existing methods in designing superior pocket sequences and structures, producing average improvement exceeding 10% in AAR and RMSD metrics. FAIR is available at https://***/zaixizhang/FAIR. © 2023, CC BY.

关键词： Atoms

MMTSA: Multi-Modal Temporal Segment Attention Network for Efficient Human Activity Recognition

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Gao, Ziqi Wang, Yuntao Chen, Jianguo Xing, Junliang Patel, Shwetak Liu, Xin Shi, Yuanchun Institute Tsinghua University China Key Laboratory of Pervasive Computing Ministry of Education Department of Computer Science and Technology Tsinghua University China Department of Computer Technology and Application Qinghai University China University of Virginia United States Department of Computer Science and Technology Tsinghua University China Paul G. Allen School for Computer Science and Engineering University of Washington United States Department of Computer Science and Technology Tsinghua University China Qinghai University China

Multimodal sensors provide complementary information to develop accurate machine-learning methods for human activity recognition (HAR), but introduce significantly higher computational load, which reduces efficiency. This paper proposes an efficient multimodal neural architecture for HAR using an RGB camera and inertial measurement units (IMUs) called Multimodal Temporal Segment Attention Network (MMTSA). MMTSA first transforms IMU sensor data into a temporal and structure-preserving gray-scale image using the Gramian Angular Field (GAF), representing the inherent properties of human activities. MMTSA then applies a multimodal sparse sampling method to reduce data redundancy. Lastly, MMTSA adopts an inter-segment attention module for efficient multimodal fusion. Using three well-established public datasets, we evaluated MMTSA’s effectiveness and efficiency in HAR. Results show that our method achieves superior performance improvements (11.13% of cross-subject F1-score on the MMAct dataset) than the previous state-of-the-art (SOTA) methods. The ablation study and analysis suggest that MMTSA’s effectiveness in fusing multimodal data for accurate HAR. The efficiency evaluation on an edge device showed that MMTSA achieved significantly better accuracy, lower computational load, and lower inference latency than SOTA methods. © 2022, CC BY-NC-SA.

关键词： Ubiquitous computing

A Recommendation Method for Highly Sparse Dataset Based on Teaching Recommendation Factorization Machines

学校读者我要写书评

暂无评论

computers, Materials & Continua 2020年第9期64卷 1959-1975页

作者： Dunhong Yao Shijun Li Ang Li Yu Chen School of Computer Science and Engineering Huaihua UniversityHuaihua418000China Key Laboratory of Wuling-Mountain Health Big Data Intelligent Processing and Application in Hunan Province Universities Huaihua418000China Key Laboratory of Intelligent Control Technology for Wuling-Mountain Ecological Agriculture in Hunan Province Huaihua418000China School of Computer Wuhan UniversityWuhan430072China Department of Electrical and Computer Engineering Duke UniversityDurhamNC 27708USA School of Computer Science and Engineering Yulin Normal UniversityYulin537000China

There is no reasonable scientific basis for selecting the excellent teachers of the school’s *** solve the practical problem,we firstly give a series of normalization models for defining the key attributes of teachers’professional foundation,course difficulty coefficient,and comprehensive evaluation of ***,we define a partial weight function to calculate the key attributes,and obtain the partial recommendation ***,we construct a highly sparse Teaching Recommendation Factorization Machines(TRFMs)model,which takes the 5-tuples relation including teacher,course,teachers’professional foundation,course difficulty,teaching evaluation as the feature vector,and take partial recommendation value as the recommendation ***,we design a novel Top-N excellent teacher recommendation algorithm based on TRFMs by course classification on the highly sparse *** results show that the proposed TRFMs and recommendation algorithm can accurately realize the recommendation of excellent teachers on a highly sparse historical teaching *** recommendation accuracy is superior to that of the three-dimensional tensor decomposition model algorithm which also solves sparse *** proposed method can be used as a new recommendation method applied to the teaching arrangements in all kinds of schools,which can effectively improve the teaching quality.

关键词： Highly sparse dataset normalized models teaching recommendation factorization machines excellent teacher recommendation

A Clustering-Based Routing Protocol Using Path Pattern Discovery Method to Minimize Delay in VANET

学校读者我要写书评

暂无评论

Wireless Communications and Mobile Computing 2023年第1期2023卷

作者： Xie, Xiaoyun Navaei, Yahya Dorostkar Einy, Sajad School of Electronic Information Engineering Gannan University of Science and Technology Jiangxi Ganzhou341000 China Ganzhou Key Laboratory of Cloud Computing and Big Data Jiangxi Ganzhou341000 China Computer and Information Technology Engineering Qazvin Branch Islamic Azad University Qazvin Iran Istanbul Aydin University Department of Application and Research Center for Advanced Studies Istanbul Turkey

In vehicular ad hoc networks (VANETs), vehicle-to-vehicle (V2V) communications can link vehicles to each other, and vehicle-to-infrastructure (V2I) messaging and communications can link roadside infrastructure such as routers. The vehicles in these networks act as relays that transmit critical messages in the network. Due to the high-speed movement of vehicles on the road, real-time messaging and minimizing the delay in sending messages is one of the most important objectives of VANET developers. On the other hand, the high mobility of vehicles causes communication interruptions and decreases the data delivery rate in VANET. To overcome this issue, predicting the path of vehicles can play an important role in sending data from the source to the destination. When an accident occurs on the road, the messages that are sensed by the imbedded sensors in the vehicles need to be sent, and if they are sent by the vehicles that change their route, these messages will not be sent to the destination and the performance of the network will be disturbed. Previous methods in the literature for data transmission in intervehicular networks have focused more on reliability and trust, and little attention has been paid to the prediction of vehicle movement paths in these types of networks. Therefore, for fast and reliable data transmission in VANET, accurate prediction of vehicle movement and creation of movement patterns can be effective in message transmission delay and data delivery rate. In this paper, we present an approach using a combination of cluster-based routing protocols and pattern discovery methods to minimize latency in VANETs. The outline of the proposed method has four modules: primary data collection and analysis, primary data preparation and analysis, pattern extraction and vehicle route discovery, and vehicle clustering and data/information transmission routing. The simulation results show that the proposed method with a delivery rate of 88.56% has significantly i

关键词： Vehicular ad hoc networks

Ipmmg: Information Propagation with Multi-Granularity Morphology-Guided for Nuclear Segmentation and Classification

学校读者我要写书评

暂无评论

SSRN

SSRN 2025年

作者： Fan, Dawei Li, Jun Cai, Chengfei Lin, Lihui Chen, Riqing Chen, Yanping Wei, Lifang College of Computer and Information Science Fujian Agriculture and Forestry University Fuzhou350002 China College of Future Technology Fujian Agriculture and Forestry University Fuzhou350002 China Department of Pathology Clinical Oncology School of Fujian Medical University Fujian Cancer Hospital Fuzhou350014 China School of Artificial Intelligence Nanjing University of Information Science and Technology Nanjing210044 China School of Mathematics and Computer Science Fujian Key Laboratory of Big Data Application and Intellectualization for Tea Industry Wuyi University Wuyishan354300 China

Nuclear segmentation and classification play a pivotal role in pathological image analysis. However, it is often hindered by blurred nuclear boundaries and complex structures in digital pathology slides, caused by factors such as staining techniques and imaging methods, presenting a significant challenge for accurate segmentation and classification. To address this issue, we propose a novel and efficient approach for nuclear identification, termed Information Propagation with Multi-Granularity Morphology-Guided Network (IPMMG). IPMMG progressively captures edge morphology information from different network layers while simultaneously incorporating structural morphology features at multiple granularities. By explicitly propagating features related to both the edge and structure, our approach constrains semantic features to focus on the region of interest's contour, thereby alleviating the challenge of blurred morphology. Experiments on public datasets demonstrate that IPMMG achieves state-of-the-art performance in segmentation, as measured by Dice and IoU scores, while also attaining competitive results in classification with DQ, SQ, and PQ metrics. In particular, it excels in handling nuclei with blurred edges and complex structures. © 2025, The Authors. All rights reserved.

关键词： Semantic Segmentation

Hard Region Aware Network for Remote Sensing Change Detection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Zhenglai Tang, Chang Liu, Xinwang Hu, Xingchen Li, Xianju Li, Ning Li, Changdong The faculty of data science City University of Macau 00853 China The school of computer China University of Geosciences Wuhan430074 China The school of computer National University of Defense Technology Changsha410073 China The College of Systems Engineering National University of Defense Technology Changsha410073 China Key Laboratory of Target Cognition and Application Technology TCAT Aerospace Information Research Institute Beijing100190 China The faculty of engineering China University of Geosciences Wuhan430074 China

Change detection (CD) is essential for various real-world applications, such as urban management and disaster assessment. Numerous CD methods have been proposed, and considerable results have been achieved recently. However, detecting changes in hard regions, i.e., the change boundary and irrelevant pseudo changes caused by background clutters, remains difficult for these methods, since they pose equal attention for all regions in bi-temporal images. This paper proposes a novel change detection network, termed as HRANet, which provides accurate change maps via hard region mining. Specifically, an online hard region estimation branch is constructed to model the pixel-wise hard samples, supervised by the error between predicted change maps and corresponding ground truth during the training process. A cross-layer knowledge review module is introduced to distill temporal change information from low-level to high-level features, thereby enhancing the feature representation capabilities. Finally, the hard region aware features extracted from the online hard region estimation branch and multi-level temporal difference features are aggregated into an unified feature representation to improve the accuracy of CD. Experimental results on two benchmark datasets demonstrate the superior performance of HRANet in the CD task. Copyright © 2023, The Authors. All rights reserved.

关键词： Optical remote sensing