检索结果-内蒙古大学图书馆

Adaptive design and implementation of automatic modulation recognition accelerator

Journal of Ambient Intelligence and Humanized Computing 2024年第1期15卷 779-795页

作者： Wang, Bin Wei, Xianglin Wang, Chao Li, Junnan Jiao, Xiang Fan, Jianhua Li, Peng School of Electronics and Information Engineering Nanjing University of Information Science and Technology Nanjing210044 China School of Computer and Software Nanjing University of Information Science and Technology Nanjing210044 China 63rd Research Institute National University of Defense Technology Nanjing210007 China

Automatic modulation recognition-oriented Deep Neural Networks (ADNNs) have achieved higher recognition accuracy than traditional methods with less labor overhead. However, their high computation complexity usually far exceeds the computation capacity of communication devices built on Field Programmable Gate Array (FPGA) platform. When solving the problem of insufficient resources, the complete operation of FPGA-based accelerator can be achieved by dividing the calculation into several parts and calculating them separately, but this will cause unaccepTable latency. In this backdrop, we develop a new ADNN model, named VT-CNN2+, to promote the recognition accuracy. Then, after stating the resources and latency problems for implementing VT-CNN2+ on the FPGA platform, an adaptive hardware accelerator is put forward. To implement the accelerator, Area folding is introduced to optimize resources consumption. Moreover, Literacy Optimization, Parallelism Optimization, Inter-layer Cascading, Temporary Cache and Data Loading Optimization are adopted to reduce latency. Afterwords, the two components in our accelerator are detailed, i.e., Once-designed module and Re-designed module. Finally, to evaluate the performance and adaptivity of our accelerator, a series of experiments are conducted on two different FPGA platforms, i.e., AX7350 and ZedBoard. Results show that our accelerator can successfully adapt to different FPGA platforms and it can remarkably reduce the processing latency. Moreover, our accelerator’s processing speed of 0.066249s per single data sample with much lower energy consumption is one order of magnitude faster than desktop-level Central Processing Units (CPUs), two orders of magnitude faster than embedded CPUs. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Al-Mg@PVDF and Al-Si@PVDF composites with enhanced combustion and energy release characteristics

引用

Defence technology 2025年 48卷 1-25页

作者： Yang, Zhanjun Liu, Hao Li, Mi Wang, Xiaoqian Das, Oisik Han, Zhong xuan Jiang, Lin School of Mechanical Engineering Nanjing University of Science and Technology Nanjing210094 China School of Safety Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Hu Bei Sanjiang Aerospace Jianghe Chemical Technology Co. Ltd. Yichang444200 China Department of Civil Environmental and Natural Resources Engineering Luleå University of Technology Luleå97187 Sweden

To investigate the differences in combustion and energy release characteristics of metastable intermolecular composite materials composed of aluminum alloys and polyvinylidene fluoride (PVDF) with different compositions, two types of alloys were selected: Al-Mg and Al-Si. Pure aluminum powder of the same size was also chosen for comparison. The PVDF-coated metal particle composites and the mixtures of PVDF with metal particles were prepared using electrospray (ES) and physical blending methods (PM), respectively. A systematic study was conducted on the morphology, compositional structure, combustion performance, energy release characteristics, and thermal reactivity of the fabricated composites and their combustion products through scanning electron microscopy (SEM), energy-dispersive X-ray spectroscopy (EDS), X-ray diffraction (XRD), combustion performance experiments, closed vessel pressure tests, and simultaneous thermogravimetric-differential scanning calorimetry (TG-DSC). The experimental results indicated that the PVDF-coated metal particles prepared by the electrospray method exhibited a distinct core-shell structure, with the metal particles in close contact with the PVDF matrix. Compared to the PM blended materials, the ES composites demonstrated superior combustion performance and energy release characteristics during combustion. Analysis of different metal fuel systems under identical preparation conditions revealed that Al-Mg and Al-Si fuels modulate the combustion and energy release properties of aluminum alloy-PVDF MICs through two distinct pathways. © 2025 China Ordnance Society

关键词： Thermogravimetric analysis

来源：评论

学校读者我要写书评

暂无评论

Core-Competitiveness in Partially Observable Networked Market 24

Core-Competitiveness in Partially Observable Networked Marke...

引用

33rd ACM Web Conference, WWW 2024

作者： Li, Bin Hao, Dong School of Computer Science and Engineering Nanjing University of Science and Technology Jiangsu Nanjing China School of Computer Science and Engineering University of Electronic Science and Technology of China Sichuan Chengdu China

ISBN: (纸本)9798400701719

In auction theory, a core is a stable outcome where no subgroup of participants can achieve better results for themselves. Core-competitive auctions aim to generate revenue that is achievable in a core. They are particularly important because they not only generate optimized revenue for the seller, but also provide an efficient and stable environment for participants. We generalize the design of core-competitive auctions to encompass partially observable networked markets (PONM). Unlike traditional auctions, which often deal with scenarios of limited trading activity, our approach to core-competitive auctions for PONM captures the nature of real-world transaction markets, which is a large linking world for the economic entities and commodities circulate among the entities in the market. Our generalizing the auction market to PONM can much improve the liquidity of the auction, and is especially meaningful for the web economics. Specifically, we quantify the upper and lower bounds of the minimum core revenue in PONM, and further prove that there does not exist any truthful auction for PONM which is efficient and core-competitive. Governed by this impossible result, we identify the criteria that the allocation rule for PONM should meet. Based on these criteria, we propose a new class of auction mechanisms for PONM that is individually rational, incentive-compatible, and core-competitive. © 2024 ACM.

关键词： Competition

来源：评论

学校读者我要写书评

暂无评论

TRE-DSP:A traceable and revocable CP-ABE based data sharing scheme for IoV with partially hidden policy

引用

Digital Communications and Networks 2025年第2期11卷 455-464页

作者： Yousheng Zhou Rundong Peng Yuanni Liu Pandi Vijayakumar Brij Gupta College of Computer Science and Technology Chongqing University of Posts and TelecommunicationsChongqing 400065China College of Cyber Security and Information Law Chongqing University of Posts and TelecommunicationsChongqing 400065China Department of Computer Science and Engineering University College of EngineeringTindivanamMelpakkamTamil nadu 604001India Department of Computer Engineering National Institute of Technology KurukshetraIndia

With the popularity of the Internet of Vehicles(IoV),a large amount of data is being generated every *** to securely share data between the IoV operator and various value-added service providers becomes one of the critical *** to its flexible and efficient fine-grained access control feature,Ciphertext-Policy Attribute-Based Encryption(CP-ABE)is suitable for data sharing in ***,there are many flaws in most existing CP-ABE schemes,such as attribute privacy leakage and key *** paper proposes a Traceable and Revocable CP-ABE-based Data Sharing with Partially hidden policy for IoV(TRE-DSP).A partially hidden access structure is adopted to hide sensitive user attribute values,and attribute categories are sent along with the ciphertext to effectively avoid privacy *** addition,key tracking and malicious user revocation are introduced with broadcast encryption to prevent key *** the main computation task is outsourced to the cloud,the burden of the user side is relatively *** of security and performance demonstrates that TRE-DSP is more secure and practical for data sharing in IoV.

关键词： Privacy-preserving Attribute-based encryption Partially hidden policy Traceability User revocation Internet of vehicles

来源：评论

学校读者我要写书评

暂无评论

Spark workflow task scheduling with deadline and privacy constraints in hybrid cloud networks

引用

Soft Computing 2025年第2期29卷 783-801页

作者： Rajput, Kamran Yaseen Xiaoping, Li Lakhan, Abdullah School of Computer Science and Engineering Southeast University Nanjing China School of Economics Innovations and Technology Kristiania University College Oslo Norway Department of Cybersecurity Dawood University of Engineering and Technology Karachi Pakistan

The increasing adoption of hybrid clouds in organizations stems from their ability to bolster private cloud resources with additional public cloud capacity when required. However, scheduling distributed applications, such as workflow tasks, on hybrid cloud resources presents new and intricate challenges. A significant concern revolves around the potential exposure of private data and tasks within third-party, public cloud infrastructures, especially within sensitive domains like healthcare applications. The complexity escalates when considering the selection of resources from multiple cloud providers due to the fluctuating resource computation prices and data transmission costs. This paper presents the Spark Workflow Task Scheduling to Hybrid Cloud (SWSHC) framework, designed to schedule Spark workflows precisely while adhering to deadline and task privacy constraints within a hybrid cloud setting. Our innovative approach encompasses developing and implementing three pivotal components: deadline division, stage order optimization, and task scheduling mechanisms. We segregate the workflow deadline for each stage to bridge the gaps between stages effectively. Additionally, job prioritization is achieved using the maximum rank rule. The proposed solution considers diverse factors, including interval pricing variations, utilization of heterogeneous VM instances, intra- and inter-bandwidth considerations, and the efficient utilization of private cloud resources. Through meticulous calibration of our algorithm and comprehensive experimentation with various realistic workflows, our findings unequivocally demonstrate that SWSHC surpasses existing solutions in the current literature the cost by up to 40–70% in terms of cost efficiency and resource utilization. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Deepfake Audio Detection for Urdu Language Using Deep Neural Networks

引用

IEEE Access 2025年 13卷 97765-97778页

作者： Ahmad, Omair Khan, Muhammad Sohail Jan, Salman Khan, Inayat University of Engineering and Technology Department of Computer Software Engineering Mardan Pakistan Arab Open University Faculty of Computer Studies A’Ali732 Bahrain University of Engineering and Technology Department of Computer Science Mardan Pakistan

Audio Deepfakes, which are highly realistic fake audio recordings driven by AI tools that clone human voices, With Advancements in Text-Based Speech Generation (TTS) and Vocal Conversion (VC) technologies have enabled it easier to create realistic synthetic and imitative speech, making audio Deepfakes a common and potentially dangerous form of deception. Well-known people, like politicians and celebrities, are often targeted. They get tricked into saying controversial things in fake recordings, causing trouble on social media. Even kids’ voices are cloned to scam parents into ransom payments, etc. Therefore, developing effective algorithms to distinguish Deepfake audio from real audio is critical to preventing such frauds. Various Machine learning (ML) and Deep learning (DL) techniques have been created to identify audio Deepfakes. However, most of these solutions are trained on datasets in English, Portuguese, French, and Spanish, expressing concerns regarding their correctness for other languages. The main goal of the research presented in this paper is to evaluate the effectiveness of deep learning neural networks in detecting audio Deepfakes in the Urdu language. Since there’s no suitable dataset of Urdu audio available for this purpose, we created our own dataset (URFV) utilizing both genuine and fake audio recordings. The Urdu Original/real audio recordings were gathered from random youtube podcasts and generated as Deepfake audios using the RVC model. Our dataset has three versions with clips of 5, 10, and 15 seconds. We have built various deep learning neural networks like (RNN+LSTM, CNN+attention, TCN, CNN+RNN) to detect Deepfake audio made through imitation or synthetic techniques. The proposed approach extracts Mel-Frequency-Cepstral-Coefficients (MFCC) features from the audios in the dataset. When tested and evaluated, Our models’ accuracy across datasets was noteworthy. 97.78% (5s), 98.89% (10s), and 98.33% (15s) were remarkable results for the RNN+LSTM

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Contactless and Real-time Hand Gesture Recognition using Inductive Proximity Technique for Wrist-worn Wearables

引用

IEEE Sensors Journal 2025年第11期25卷 20474-20485页

作者： Lin, Pei-Jung Shih, Chi-Huang Weng, Tzu-Hsuan Feng Chia University Department of Information Engineering and Computer Science Taichung407 Taiwan National Chin-Yi University of Technology Department of Computer Science and Information Engineering Taichung411 Taiwan

This study proposes a contactless and real-time hand gesture recognition system suitable for smartwatches. The proposed system adopts inductive proximity sensing to collect Mechanomyography (MMG) signals induced by finger-based gestures above the wrist. After the signal processing and feature extraction stages, machine-learning models can be built for gesture classification. Compared with the Electromyography (EMG)-based method generally deployed in the forearm, inductive MMG applies an electromagnetic field to the body surface and is suitable for use on the wrist. Compared to the existing contact methods, such as EMG and accelerometer-based MMG, the inductive MMG method does not require contact with the body surface to collect muscle action signals and can avoid interference from environmental factors such as sweat and dust. The main contributions of this study are (1) a watch-type prototype with inductive MMG sensing technique, including hardware and firmware;(2) a lightweight and efficient signal processing mechanism that can capture the inductive signal characteristics of gestures for the above-mentioned embedded system (i.e., watch-type prototype);and (3) the tempo-spatial feature extraction method to improve the accuracy of gesture recognition. The experiment results show that for six common machine learning models, the gesture recognition accuracy of the proposed system is above 95%, with a maximum of 97.47%. In the briefing control application for verification purposes, the average accuracy of the inductive gesture recognition system can achieve 98.26%, and the average processing time is 14.37 ms. According to the experimental results, the inductive MMG system can provide a feasible gesture recognition solution for wrist-worn wearable devices. © 2001-2012 IEEE.

关键词： Firmware

来源：评论

学校读者我要写书评

暂无评论

Breathers and multi wave solutions of three different space-time fractional nonlinear coupled waves dynamical models and their applications

引用

Applied Mathematics(A Journal of Chinese Universities) 2025年第1期40卷 33-52页

作者： Ambreen Sarwar GANG Tao Muhammad Arshad Iftikhar Ahmed LU Dian-chen School of Energy and Power Engineering Nanjing University of Science and TechnologyNanjing 210094China Department of Mathematics&Statistics University of AgricultureFaisalabadPakistan Faculty of Science Jiangsu UniversityZhenjiang 212013China

In this article,several kinds of novel exact waves solutions of three well-known different space-time fractional nonlinear coupled waves dynamical models are constructed with the aid of simpler and effective improved auxiliary equation *** we will investigate space-time fractional coupled Boussinesq-Burger dynamical model,which is used to model the propagation of water waves in shallow sea and harbor,and has many applications in ocean ***,we will investigate the space-time fractional coupled Drinfeld-SokolovWilson equation which is used to characterize the nonlinear surface gravity waves propagation over horizontal ***,we will investigate the space-time-space fractional coupled Whitham-Broer-Kaup equation which is used to model the shallow water waves in a porous medium near a *** obtained different solutions in terms of trigonometric,hyperbolic,exponential and Jacobi elliptic ***,graphics are plotted to explain the different novel structures of obtained solutions such as multi solitons interaction,periodic soliton,bright and dark solitons,Kink and anti-Kink solitons,breather-type waves and so on,which have applications in ocean engineering,fluid mechanics and other related *** hope that our results obtained in this article will be useful to understand many novel physical phenomena in applied sciences and other related fields.

关键词： conformable fractional derivative solitons breather waves jacobi elliptic function solutions

来源：评论

学校读者我要写书评

暂无评论

A Domain-Adaptive Large Language Model With Refinement Framework For IoT Cybersecurity 17

A Domain-Adaptive Large Language Model With Refinement Frame...

引用

IEEE Congress on Cybermatics: 17th IEEE International Conference on Internet of Things, iThings 2024, 20th IEEE International Conference on Green Computing and Communications, GreenCom 2024, 17th IEEE International Conference on Cyber, Physical and Social Computing, CPSCom 2024, 10th IEEE International Conference on Smart Data, SmartData 2024

作者： Che, Xun Zheng, Yu Zhu, Minhao Li, Qianmu Dong, Xu Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing China Nari Group Corporation Nanjing China Nanjing University of Science and Technology School of Cyber Science and Engineering Nanjing China

ISBN: (纸本)9798350351637

To address the increasingly complex security challenges in Internet-of-Things (IoT) environments, Large Language Models (LLMs) have demonstrated effectiveness in enhancing device and data security, as well as improving the security and reliability overall IoT system. However, general LLMs struggle to effectively handle IoT security data. Therefore, developing IoT security domain-specific LLMs based on IoT-specific corpus and terminologies has become a key focus for enhancing cybersecurity defense capabilities. These areas of focus can be broadly categorized into three main directions: training from scratch, retrieval-augmented prompting, and instruction fine-tuning. Training from scratch is discouraged in cybersecurity due to its high computational and data requirements, making effective model training and convergence difficult given the scarcity of cybersecurity data. Retrieval-augmented prompting may suffer from incomplete or conflicting information, impacting the accuracy and reliability of the model. Conversely, instruction fine-tuning allows for the usage of domain-specific task instructions to adjust the model, achieving effective domain adaptation on limited datasets. However, inadequate or inaccurate instructions may degrade the generalization ability and performance. For these shortcomings, we propose a novel and robust fine-tuning framework to refine the original corpus and output a refined corpus for high-quality domain adaptation. Furthermore, we introduce two auxiliary strategies in the training phase to enhance efficiency and accuracy. Finally, our framework is evaluated across multiple task scenarios and demonstrates the best performance on most of them, which proves the effectiveness and efficiency of the model presented in this work. © 2024 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

VoteDroid: a new ensemble voting classifier for malware detection based on fine-tuned deep learning models

引用

Multimedia Tools and Applications 2025年第12期84卷 10923-10944页

作者： Bakır, Halit Faculty of Engineering and Natural Sciences Department of Computer Engineering Sivas University of Science and Technology Sivas Turkey

In this work, VoteDroid a novel fine-tuned deep learning models-based ensemble voting classifier has been proposed for detecting malicious behavior in Android applications. To this end, we proposed adopting the random search optimization algorithm for deciding the structure of the models used as voter classifiers in the ensemble classifier. We specified the potential components that can be used in each model and left the random search algorithm taking a decision about the structure of the model including the number of each component that should be used and its location in the structure. This optimization method has been used to build three different deep learning models namely CNN-ANN, pure CNN, and pure ANN. After selecting the best structure for each DL model, the selected three models have been trained and tested using the constructed image dataset. Afterward, we suggested hybridizing the fine-tuned three deep-learning models to form one ensemble voting classifier with two different working modes namely MMR (Malware Minority Rule) and LMR (Label Majority Rule). To our knowledge, this is the first time that an ensemble classifier has been fine-tuned and hybridized in this way for malware detection. The results showed that the proposed models were promising, where the classification accuracy exceeded 97% in all experiments. © The Author(s) 2024.

关键词： Android malware

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：