检索结果-内蒙古大学图书馆

E-SWAN:Efficient Sliding Window Analysis Network for Real-Time Speech Steganography Detection

computers, Materials & Continua 2025年第3期82卷 4797-4820页

作者： Kening Wang Feipeng Gao Jie Yang Hao Zhang School of Engineering and Technology Jiyang College of Zhejiang A & F UniversityZhuji311800China College of Mathematics and Computer Science Zhejiang A & F UniversityHangzhou311300China

With the rapid advancement of Voice over Internet Protocol(VoIP)technology,speech steganography techniques such as Quantization Index Modulation(QIM)and Pitch Modulation Steganography(PMS)have emerged as significant challenges to information *** techniques embed hidden information into speech streams,making detection increasingly difficult,particularly under conditions of low embedding rates and short speech *** steganalysis methods often struggle to balance detection accuracy and computational efficiency due to their limited ability to effectively capture both temporal and spatial features of speech *** address these challenges,this paper proposes an Efficient Sliding Window Analysis Network(E-SWAN),a novel deep learning model specifically designed for real-time speech steganalysis.E-SWAN integrates two core modules:the LSTM Temporal Feature Miner(LTFM)and the Convolutional Key Feature Miner(CKFM).LTFM captures long-range temporal dependencies using Long Short-Term Memory networks,while CKFM identifies local spatial variations caused by steganographic embedding through convolutional *** modules operate within a sliding window framework,enabling efficient extraction of temporal and spatial *** results on the Chinese CNV and PMS datasets demonstrate the superior performance of *** conditions of a ten-second sample duration and an embedding rate of 10%,E-SWAN achieves a detection accuracy of 62.09%on the PMS dataset,surpassing existing methods by 4.57%,and an accuracy of 82.28%on the CNV dataset,outperforming state-of-the-art methods by 7.29%.These findings validate the robustness and efficiency of E-SWAN under low embedding rates and short durations,offering a promising solution for real-time VoIP *** work provides significant contributions to enhancing information security in digital communications.

关键词： Steganalysis speech convolutional sliding window deep learning

来源：评论

学校读者我要写书评

暂无评论

Global Color-Aware Arbitrary Style Transfer with Discrete Wavelet Transform 20th

Global Color-Aware Arbitrary Style Transfer with Discrete W...

引用

20th IFIP WG 10.3 International Conference on Network and Parallel Computing, NPC 2024

作者： Chen, Bochao Tan, Junhao Li, Xiaoqiang Pei, Songwen School of Computer Engineering and Science Shanghai University Shanghai200444 China School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai200093 China

ISBN: (纸本)9789819628292

The purpose of image arbitrary style transfer is to apply a given artistic or photorealistic style to a target content image. While existing methods can effectively transfer style information, the variability in color brightness features between the style and content images can significantly impact the quality of the style transfer. Specifically, traditional arbitrary style transfer relies on an encoder-decoder architecture of spatial-aware neural networks operating in the RGB domain, which typically preserves only local color brightness information and lacks a global color perception compared to the wavelet frequency domain. In this paper, we address the issue of insufficient global color perception in images from the perspective of image enhancement. We propose Global Color-aware Arbitrary Style Transfer with Discrete Wavelet Transform (GCAST), which achieves a balance between the global color characteristics of style images and the local details of content images. Our approach involves an encoder that integrates preliminary feature encoding through cross-layer attention fusion, while the decoder modifies frequency features using a wavelet-based adjustment block. To maintain a balance between content and style in the stylized images, we design a comprehensive loss function that incorporates multiple restoration loss, double style loss, and noise regularization loss. Extensive experiments comparing our method with state-of-the-art techniques demonstrate that our proposed model generates stylized images with superior results in terms of global color perception and human perceptual studies. © IFIP International Federation for Information Processing 2025.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Automatic Positioning of Intelligent Mobile Robot Based on Improved Front-End Scanning Matching

Journal of Network Intelligence

引用

Journal of Network Intelligence 2025年第1期10卷 559-572页

作者： Wang, Hong Wang, Yi-Gui Zhang, Jie Department of Computer and Software Engineering Shandong College of Electronic Technology Jinan250200 China School of Computer Science and Technology Shandong Jianzhu University Jinan250101 China College of Agricultural Science and Technology Yana Royal Polytechnic University Chiang Mai50000 Thailand

Traditional autonomous navigation methods for mobile robots mainly rely on geometric feature-based LiDAR scan-matching algorithms, but in complex environments, this method is often affected due to the presence of moving objects, occlusions, and other interfering factors, resulting in a decrease in positioning accuracy. With the growing demand for robotics applications in logistics, security, exploration and other fields, the need for robust autonomous navigation and high-precision mapping in highly dynamic and complex environments is becoming more and more urgent. To solve this problem, an improved front-end scan matching algorithm based on Frequency Modulated Continuous Wave (FMCW) LiDAR is proposed in this paper. Firstly, by using the target Doppler velocity information provided by the FMCW LiDAR, we design a novel point cloud segmentation algorithm based on velocity clustering, which is able to effectively distinguish between stationary and moving objects, and avoid the dynamic interference affecting the position estimation. Secondly, we introduce the Gaussian Mixture Model Sampling Consistency (GMMSC) algorithm, which is more robust to reject the mis-matched pairs in the scanning matching process and improve the alignment accuracy. Finally, based on the residual high-quality matched pairs, we combine the classical ICP algorithm with the robust kernel function to further enhance the stability of the position estimation in the case of occlusion and local mismatch. The experimental results show that the proposed improved algorithm significantly improves the mapping capability of mobile robots in complex environments compared with the existing techniques. The average relative error of the improved front-end scanning matching algorithm is reduced by 40.6 % compared with the pre-improved one. © 2025, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

An Improved Hybrid Deep Learning Approach for Security Requirements Classification

引用

computers, Materials & Continua 2025年第3期82卷 4041-4067页

作者： Shoaib Hassan QianmuLi Muhammad Zubair Rakan AAlsowail Muhammad Umair School of Computer Science and Engineering Nanjing University of Science and TechnologyNanjing210094China Faculty of Information Technology and Computer Science University of Central PunjabLahore5400Pakistan Computer Skills Self-Development Skills DevelopmentDeanship of Common First YearKing Saud UniversityRiyadh11362Saudia Arabia

As the trend to use the latestmachine learning models to automate requirements engineering processes continues,security requirements classification is tuning into the most researched field in the software engineering *** literature studies have proposed numerousmodels for the classification of security ***,adopting those models is constrained due to the lack of essential datasets permitting the repetition and generalization of studies employing more advanced machine learning ***,most of the researchers focus only on the classification of requirements with security *** did not consider other nonfunctional requirements(NFR)directly or indirectly related to *** has been identified as a significant research gap in security requirements *** major objective of this study is to propose a security requirements classification model that categorizes security and other relevant security *** use PROMISE_exp and DOSSPRE,the two most commonly used datasets in the software engineering *** proposed methodology consists of two *** the first step,we analyze all the nonfunctional requirements and their relation with security *** found 10 NFRs that have a strong relationship with security *** the second step,we categorize those NFRs in the security requirements *** proposedmethodology is a hybridmodel based on the ConvolutionalNeural Network(CNN)and Extreme Gradient Boosting(XGBoost)***,we evaluate the model by updating the requirement type column with a binary classification column in the dataset to classify the requirements into security and non-security *** performance is evaluated using four metrics:recall,precision,accuracy,and F1 Score with 20 and 28 epochs number and batch size of 32 for PROMISE_exp and DOSSPRE datasets and achieved 87.3%and 85.3%accuracy,*** proposed study shows an enhancement in metrics

关键词： Requirements engineering security requirements deep learning CNN XGBoost classification

来源：评论

学校读者我要写书评

暂无评论

Behavioral insights into compression: a study of Move-to-Front-or-Middle deterministic online algorithm through sequence classification and characterization

引用

International Journal of Information technology (Singapore) 2025年第1期17卷 189-203页

作者： Baisakh Mohapatra, Hitesh Guru, Abhishek Department of Computer Science and Engineering Sambalpur University Institute of Information Technology Sambalpur India Computer Science and Engineering GMR Institute of Technology Andhra Pradesh Rajam India School of Computer Engineering KIIT Deemed to Be University Bhubanseswar India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram India

Since the list update problem was applied to data compression as an effective encoding technique, numerous deterministic algorithms have been studied and analyzed. A powerful strategy, Move-to-Front (MTF), involves moving an accessed item to the front of the list immediately. Theoretical analysis has demonstrated MTF’s potential, showing it to be 2-competitive through competitive analysis. This success has inspired researchers to develop various intriguing MTF variants and assess their performance both theoretically and experimentally. One such variant, Move-to-Front-or-Middle (MFM), has been experimentally shown that MFM performed better than the classic MTF on Calgary and Cantebury Datasets. However, the experimental performance alone does not provide sufficient insight into the internal behavior of the algorithm or explain why its performance surpasses MTF on certain datasets. Therefore, in this paper, we conduct a detailed behavioral study of MFM through sequence classification and characterization to gain deeper understanding of the algorithm and aims to reconcile the disparity between theoretical and experimental outcomes. This paper also by classifying and characterizing MFM’s performance across various request sequences, considering both the presence and absence of locality of reference. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Competitive analysis Deterministic list update algorithm List update problem Sequence classification

来源：评论

学校读者我要写书评

暂无评论

Pruning techniques for artificial intelligence networks: a deeper look at their engineering design and bias: the first review of its kind

引用

Multimedia Tools and Applications 2025年第11期84卷 9591-9665页

作者： Mohanty, Lopamudra Kumar, Ashish Mehta, Vivek Agarwal, Mohit Suri, Jasjit S. School of Computer Science Engineering and Technology Bennett University Gr. Noida India Department of Computer Science ABES Engineering College UP Ghaziabad India Stroke Diagnostic and Monitoring Division AtheroPoint™ RosevilleCA United States

Trained Artificial Intelligence (AI) models are challenging to install on edge devices as they are low in memory and computational power. Pruned AI (PAI) models are therefore needed with minimal degradation in performance. This is the first study of its kind where we have characterized three types of PAI paradigms, namely, weight pruning (WP), channel pruning (CP), and hybrid pruning (HP). Further, the study also analyses the risk of bias (RoB) in PAI models, and explainable PAI (XPAI) networks. PRISMA model was adapted for the selection of the best 145 studies. The review had two hypotheses: (i) PAI had bias and (ii) the order of performance for the three PAI is: HP > CP > WP in terms of performance. Thirty-two AI attributes using each of two experts were categorized into four clusters, namely, architecture, optimization, dataset design, and scientific validation. The RoB was analyzed in these PAI studies using AP(ai)Bias 2.0 (AtheroPoint™, CA, USA), which was based on a scoring-and-ranking strategy. This was then compared against the Butterfly model, composed of radial and regional biases, and analyzed using a Venn diagram in three independent bins based on low-moderate and moderate-high cut-offs. Recommendations were laid out for low-bias studies. PAI studies that lack adequate AI attributes were more inclined to the RoB. It has been observed that 19.64%, 21.42%, and 58.92% studies were in low-bias, moderate-bias, and high-bias bins, respectively. Pruning made inference faster and reduced sparsity. We have observed low participation of the PAI studies in the XPAI framework. The study presented the challenges and five-step recommendations for mitigating bias in PAI models. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

An Encoding-Based Privacy-Preserving Security Control Strategy Under Stealthy Attacks

IEEE Transactions on Industrial Cyber-Physical Systems

引用

IEEE Transactions on Industrial Cyber-Physical Systems 2025年 3卷 208-217页

作者： Liu, Jian Wang, Shuailong Zha, Lijuan Liu, Jinliang Tian, Engang Nanjing University of Finance and Economics School of Computer and Artificial Intelligence Nanjing210023 China Nanjing Forestry University School of Science Nanjing210037 China Nanjing University of Information Science and Technology School of Computer Science Nanjing210044 China University of Shanghai for Science and Technology School of Optical-Electrical and Computer Engineering Shanghai200093 China

This paper focuses on the privacy-preserving security control issue for cyber-physical systems (CPSs) via an encoding-decoding communication scheme (EDCS). To considerably contemplate the delayed data acquisition and analysis, the integral measurement model is established, which is governed by the function related to system states within a certain period. The EDCS designed has a certain resistant to the non-ideal communication network with limited bandwidth capacity and fading channels. Then the controller is constructed by utilizing the decoding data. Furthermore, in the controller-to-actuator channel, assuming the stealthy false data injection attacks occur randomly and the injected pseudo data is associated with transmission data that has been eavesdropped. By virtue of deriving sufficient conditions, the CPS with EDCS can achieve input-to-state stability as well as the corresponding controller and observer gain parameters are acquired. Eventually, the effectiveness of the designed EDCS and control algorithm is illustrated by a case study involving an autonomous underwater vehicle system. © 2023 IEEE.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

Sufficient learning: mining denser high-quality pixel-level labels for edge detection

引用

Neural Computing and Applications 2025年第14期37卷 8245-8260页

作者： Chen, Xiaodiao Yang, Wenya Wu, Wen Tao, Xiuting Mao, Xiaoyang School of Computer Science and Technology Hangzhou Dianzi University Hangzhou310018 China School of Media and Design Hangzhou Dianzi University Hangzhou310018 China Department of Computer Science and Engineering University of Yamanashi Kofu400-8511 Japan

The success of deep neural networks can largely be attributed to large-scale datasets with accurate annotations. In many practical applications, labels are annotated by multiple annotators, resulting in ambiguous labels. To mitigate the impact of such labels, existing deep edge detectors tend only to exploit sparsely reliable samples with high-confident labels by simple voting mechanism. However, lacking sufficient pixel-level learnable samples would severely degrade detection performance. To combat this issue, this work designs a sufficient learning framework for edge detection (SLED) to sufficiently explore reliable samples for model learning, which consists of three stages: sample selection, label refinement, and retraining. Firstly, we propose a sample selection scheme founded on history prediction, which aims to identify more reliable samples and locate unreliable regions containing potentially reliable samples. Secondly, we design an efficient label refinement strategy based on a graph convolutional network (GCN) to propagate reliable label information to unreliable nodes. This strategy can generate "new training targets" with denser, reliable labels for all images. Finally, we retrain the network with these new targets, obtaining a more robust model. Experimental results on three widely used benchmarks show that the proposed detector outperforms all compared SOTA methods. Our code will be released at https://***/wenya1994/SLED. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Secured IIoT against trust deficit - A flexi cryptic approach

引用

Multimedia Tools and Applications 2025年第9期84卷 5625-5652页

作者： Padmapriya, V.M. Thenmozhi, K. Hemalatha, M. Thanikaiselvan, V. Lakshmi, C. Chidambaram, Nithya Rengarajan, Amirtharajan Department of Computer Sciences Marquette University MilwaukeeWI53233 United States School of Electrical & Electronics Engineering SASTRA Deemed University Thanjavur613401 India Department of Electrical and Computer Engineering Faculty of Engineering King Abdulaziz University Jeddah22254 Saudi Arabia School of Electronics Engineering Vellore Institute of Technology Vellore632014 India

This research allows the secure surveillance approach for the Internet of Things (IoT) methodology to be developed by integrating wireless signalling and image encryption strategy. Since the Cloud Service Telco (CST) is a semi-trusted body in cloud services, user data is encrypted before uploading to a cloud server for data protection from disclosure. The flexibility of encrypted data sharing is essential for cloud storage users. This study investigates the Discrete Wavelet Transform (DWT) technique with modified Huffman compression and Elliptic Curve Cryptography (ECC). It encrypts and decrypts the data and enhances industrial security surveillance in transmission. It uses the wireless network’s next generation (5G or 6G) as uplink Single Carrier Frequency Division Multiple Access (SC-FDMA) strategies via the IoT. This study presented a novel approach to proposing hardware architecture for a secure web camera integrated with the Atmel in the mega AVR family (ATMEGA) microcontroller, suitable for IoT applications. The experimental results confirm the proposed model’s efficacy compared with existing robustness and security analysis algorithms. These systems are also used by implementing industry-standard protocols using IoTs to monitor industrial applications. The proposed framework can also minimise bandwidth, transmission cost, storage space, tracking data, and decisions about abnormal events such as potential fraud and extinguisher detection in surveilling applications. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

ResDecode: Accelerating Large Language Models Inference via Residual Decoding Heads

引用

Big Data Mining and Analytics 2025年第4期8卷 779-793页

作者： Zeng, Ziqian Yu, Jiahong Pang, Qianshi Wang, Zihao Zhuang, Huiping Yu, Fan Shao, Hongen Zou, Xiaofeng Shien Ming Wu School of Intelligent Engineering South China University of Technology Guangzhou511442 China School of Computer Science and Engineering South China University of Technology Guangzhou510006 China School of Engineering The Hong Kong University of Science and Technology Department of Computer Science and Engineering 999077 Hong Kong Huawei Technologies Co. Ltd. Hangzhou310000 China School of Future Technology South China University of Technology Guangzhou511442 China

Large language Models (LLMs) have immense potential to enhance the capabilities of Cyber-Physical-Social Intelligence (CPSI) systems, enabling them to better engage with complex cyber, physical, and social environments. However, the high inference latency of LLMs, which is inherited from the autoregressive decoding process, hinders their wide application in CPSI systems. To address this challenge, current approaches have incorporated speculative decoding to enable parallel prediction of multiple subsequent tokens, thereby achieving inference acceleration. Nevertheless, the accuracy of these decoding heads falls short of the autoregressive decoding approach. In light of these limitations, we propose ResDecode, a novel speculative decoding method characterized by its efficient and accurate decoding heads. Within the lightweight draft model, we propose a residual decoding head to compensate for the full context encoder's limited capability on long-range dependencies, thus improving accuracy. ResDecode demonstrates impressive results, achieving a maximum speedup ratio of 3.2× on the MT-bench compared to vanilla autoregressive decoding. © 2018 Tsinghua University Press.

关键词： Decoding

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：