检索结果-内蒙古大学图书馆

5th CPSSI International Symposium on Cyber-Physical Systems (Applications and Theory), CPSAT 2024

作者： Rabbiun, Hossein Mohammadi, Jamal Shirazi, Mahmoud Kargahi, Mehdi Department of Computer Science and Information Technology Zanjan Iran University of Tehran School of Electrical and Computer Engineering College of Engineering Tehran Iran

ISBN: (纸本)9798331529284

This paper advances the schedulability analysis of the Adaptive Mixed-Criticality for Weakly Hard Real-Time Systems (AMC-WH) which allows a specified number of consecutive low-criticality (LO) jobs of tasks to be skipped when the system operates in the high-criticality (HI) mode. The current AMC-WH schedulability test, based on the skip-over model, in which low tasks are guaranteed to meet m-s out of m consecutive deadlines, where s is the number of allowed skips and m is the cycle length, only calculates the worst-case response times (WCRT) for low tasks under a fixed execution pattern post-mode switch. To address this limitation, we propose a new sufficient schedulability test for AMC-WH using the (m,k)-firm model, which allows various execution patterns for low tasks after a mode switch, enhancing the flexibility and applicability. Additionally, we develop an exact schedulability test for AMC-WH based on response time analysis (RTA). This test modifies the existing exact tests for the AMC algorithm, incorporating updates to state-space exploration and pruning rules to account for low task execution after a mode switch. Simulation results validate the effectiveness of our tests, demonstrating enhanced schedulability analysis and optimized resource allocation. © 2024 IEEE.

关键词： Space research

来源：评论

学校读者我要写书评

暂无评论

Deep domain adaptation by joint distribution neural matching

引用

Neural Computing and Applications 2025年第19期37卷 14541-14561页

作者： Hong, Zijie Chen, Sentao Wen, Lisheng Yang, Xiaowei School of Software Engineering South China University of Technology Panyu District Guangdong Guangzhou510006 China Department of Computer Science Shantou University Daxue Road Guangdong Shantou515063 China

Domain adaptation aims to learn a prediction model that performs well in a target domain with unlabeled data by harnessing the distributionally different labeled data from a source domain. In this paper, we design a simple yet powerful neural network approach named joint distribution neural matching (JOINT) to address the challenge of joint distribution difference/mismatch in domain adaptation. Our JOINT approach matches the source joint distribution and the target one in the activation space of a neural network by minimizing an estimate of the Jensen–Shannon (JS) divergence between the two joint distributions. The estimated JS divergence is derived in an explicit form, which frees our approach from solving a minimax adversarial problem when matching the distributions. Experiments on four representative large-scale visual recognition datasets show that our JOINT approach outperforms the state-of-the-art under both unsupervised and semi-supervised domain adaptation settings. Our code will be available at https://***/TitanRisen/JOINT-CODE. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A DL-DeNoiseNet Framework for Robust Image Denoising and Artifact Reduction in Medical Image Diagnostics 2

A DL-DeNoiseNet Framework for Robust Image Denoising and Art...

引用

2nd IEEE International Conference on Integrated Intelligence and Communication Systems, ICIICS 2024

作者： Nanthini, S. Maindola, Meenakshi Madhu, R. Ravishankar, M.D. Gandhi, Jay Patil, Harshal Department of Computer Science and Engineering Saveetha School of Engineering SIMATS Chennai India Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun India Department of Mechanical Engineering The National Institute of Engineering Mysore India Faculty of Engineering and Technology Parul institute of Engineering and Technology Vadodara India School of Computer Science and Engineering IILM University Greater Noida India

ISBN: (纸本)9798331504960

For precise illness diagnosis and therapy planning, medical imaging diagnostics are necessary. Nevertheless, diagnostic errors can occur due to noise and aberrations that are inherent to imaging modalities including CT, MRI, and ultrasound, which can hide important features. In order to overcome this obstacle, we present a medical diagnostics-specific framework for deep learning-based picture denoising and artifact reduction. Our method improves feature extraction while maintaining picture integrity by combining a Convolutional Neural Network (CNN) with a Residual Dense Block (RDB). To guarantee optimal performance across varying degrees of noise and image types, the framework is trained on a broad dataset of medical photos, which includes images that are artifact-laden and noisy. A combination of supervised and adversarial learning techniques is used for this purpose. Adaptive filtering for preprocessing, the CNN-RDB network for denoising, and a refinement module that uses perceptual loss to keep things clinically relevant for postprocessing are the three primary steps in the methodology. The model outperforms traditional denoising methods when tested on various medical imaging metrics, including a PSNR of 40.3 dB and an SSIM of 0.97. Furthermore, the suggested architecture successfully mitigates artifacts by an average of 35% as assessed by the Normalized Root Mean Squared Error (NRMSE), guaranteeing that essential diagnostic characteristics are preserved. The results show that the model can improve image clarity, which means that diagnoses can be made more accurately and fewer scans are needed. Better healthcare outcomes are a direct result of the substantial enhancements to picture quality that this framework provides to physicians and radiologists. © 2024 IEEE.

关键词： Adaptive filtering

来源：评论

学校读者我要写书评

暂无评论

Enhanced Speech Emotion and Gender Recognition Using Hybrid CNN-LSTM Models 4

Enhanced Speech Emotion and Gender Recognition Using Hybrid ...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Priyadharshini, S. Sundar, G. Naveen Narmadha, D. Thangavel, Senthil Kumar Ajibesin, Adeyemi Abel Kolandapalayam Shanmugam, Selvanayaki Karunya Institute of Technology and Sciences Department of Computer Science and Engineering Coimbatore India Amrita School of Computing Department of Computer Science and Engineering Coimbatore India Cape Peninsula University of Technology Faculty of Informatics and Design Department of Information Technology South Africa Ashland University Department of Mathematics and Computer Science United States

ISBN: (纸本)9798331523923

The current paper proposes a new approach for peripheral speech emotion analysis and gender estimation incorporating the best machine learning architectures such as CNNs and LSTMs. Its correct depiction of emotions and the variation of the gendered speech to indicate manifold signal-to-noise ratio make the approach accommodate the difficulty inherent in recognizing emotions from the recording of voices as well as predicting the gender of a speaker. It is then able to ally with preprocessing and collection of a vast range of different speech samples, feature extraction of pitch, tone and spectral data. These features serve as input to the CNNs and LSTMs: LSTMs work well at temporal regular features and the CNNs work well in feature extraction by location (spatio feature). The approach is tested on the RAVDESS and IEMOCAP datasets and establishes a near perfect match to prior approaches with reference to recognition accuracy of emotion analysis and gender prediction. Thus, applying the identified dual method approach, which could be described by such characteristics as highly accurate data pre-preprocessing, clear indication of the features of interest, a different CNN-LSTM model joint training, it offers a reasonably good platform to gain certain insights into such characteristics of the speech as our experiment demonstrates. This work offers satisfactory configurations on concerns such as human computer relation, customer relation and mental health surveillance to suggest that other applications could be achieved in future. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

MEASUREMENT AND COMPUTATION METHOD FOR INTERNALLY GENERATED HEAT IN SINGLE LAYER CERAMIC CAPACITOR (SLCC) IN ELECTRONIC CIRCUIT 10

MEASUREMENT AND COMPUTATION METHOD FOR INTERNALLY GENERATED ...

引用

10th International Symposium on Test Automation and Instrumentation, ISTAI 2024

作者： Li, Xiangjie Liu, Dongning Guangdong University of Technology School of Information Engineering Guangzhou City China School of Computer Science and Technology Guangdong University of Technology Guangzhou City China

ISBN: (纸本)9781837242672

The purpose is to deeper understand the heat generation of ceramic capacitors in electronic circuits when the voltages and frequencies there have been changed, so that the application reliability of electronic products can be improved;by the mean of experimentation, when the voltages and frequencies of Category II single layer ceramic capacitors (SLCC) were changed, their surface temperature showed rising and dropping caused by their internally generated heat. The quick testing method is created, which aims to monitor the temperature changes of electronic components when voltage and frequency in the circuit changing. Meanwhile, the equations about the relations between temperature rise and voltage, frequency of SLCC have been discovered, when voltages and frequencies of SLCC are changed asynchronously and simultaneously in circuits. Therefore, it can be a reference provided for the engineers in the field of electronics to precisely apply SLCC when they design electronic circuit, so as to ensure the designed electronic products to be safe and reliable. Besides, it can also be a prompt detecting method when there are heat generation faults for the ceramic capacitors in circuits in practice. © The Institution of engineering & technology 2024.

关键词： Ceramic capacitors

来源：评论

学校读者我要写书评

暂无评论

Non-Contact Vital Prediction Using rPPG Signals 1

Non-Contact Vital Prediction Using rPPG Signals

引用

1st IEEE International Conference on Contemporary Computing and Communications, InC4 2023

作者： Madhu, Meghna Gurudas, V.R. Manjunath, Chinthakunta Naik, Praveen Kulkarni, Praveen School of Engineering and Technology Department of Computer Science and Engineering Bangalore India Dayananda Sagar University Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350335774

In this paper, we present the clinical significance of various cardiac symptoms with the use of heart rate detection, ongoing monitoring and present emotions. The development of algorithms for remote photoplethysmography has drawn a lot of interest during the past decade (rPPG). As a result, using data gathered from the video feed, we can now precisely follow the heart rate of individuals who are still seated. rPPG algorithms have also been developed, in addition to technique based on hand-crafted characteristics. Deep learning techniques often need a lot of data to train on, but biomedical data frequently lacks real-world examples. The experiment described in this work, we looked at how illumination affected the rPPG signals' SNR. The findings show that the SNR in each RGB channel varies depending on the colour of the light source. Paper describes development in video filtering for recognising the comprehending human face emotions. In our method, emotions are deduced by identifying facial landmarks and analysing their placement. © 2023 IEEE.

关键词： Photoplethysmography

来源：评论

学校读者我要写书评

暂无评论

Region-Based Optimization in Continual Learning for Audio Deepfake Detection 39

Region-Based Optimization in Continual Learning for Audio De...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Chen, Yujie Yi, Jiangyan Fan, Cunhang Tao, Jianhua Ren, Yong Zeng, Siding Zhang, Chu Yuan Yan, Xinrui Gu, Hao Xue, Jun Wang, Chenglong Lv, Zhao Zhang, Xiaohui School of Computer Science and Technology Anhui University China Institute of Automation Chinese Academy of Sciences China Department of Automation Tsinghua University China Beijing National Research Center for lnformation Science and Technology Tsinghua University China

ISBN: (纸本)157735897X

Rapid advancements in speech synthesis and voice conversion bring convenience but also new security risks, creating an urgent need for effective audio deepfake detection. Although current models perform well, their effectiveness diminishes when confronted with the diverse and evolving nature of real-world deepfakes. To address this issue, we propose a continual learning method named Region-Based Optimization (RegO) for audio deepfake detection. Specifically, we use the Fisher information matrix to measure important neuron regions for real and fake audio detection, dividing them into four regions. First, we directly fine-tune the less important regions to quickly adapt to new tasks. Next, we apply gradient optimization in parallel for regions important only to real audio detection, and in orthogonal directions for regions important only to fake audio detection. For regions that are important to both, we use sample proportion-based adaptive gradient optimization. This region-adaptive optimization ensures an appropriate trade-off between memory stability and learning plasticity. Additionally, to address the increase of redundant neurons from old tasks, we further introduce the Ebbinghaus forgetting mechanism to release them, thereby promoting the model’s ability to learn more generalized discriminative features. Experimental results show our method achieves a 21.3 percent improvement in EER over the state-of-the-art continual learning approach RWM for audio deepfake detection. Moreover, the effectiveness of RegO extends beyond the audio deepfake detection domain, showing potential significance in other tasks, such as image recognition. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Based Anonymous Authentication Scheme with Traceable Pseudonym Management in ITS 6th

Blockchain-Based Anonymous Authentication Scheme with Trace...

引用

6th International Conference on Machine Learning for Cyber Security, ML4CS 2024

作者： Wang, Mingliang Tan, Haowen Zheng, Wenying School of Information Science and Engineering Zhejiang Sci-Tech University Hangzhou310018 China School of Computer Science and Technology Zhejiang Sci-Tech University Hangzhou310018 China

ISBN: (纸本)9789819645657

With the continuous development of intelligent transportation systems (ITS), the Vehicular Ad-hoc Networks, as a core component of smart transportation, has become a crucial technology for improving traffic safety and transportation efficiency. However, the open communication environment and highly dynamic nature of VANETs make them vulnerable to many security threats. The existing schemes are difficult to get a balance between anonymity and traceability. Therefore, this paper proposes a blockchain-based anonymous authentication scheme with pseudonym management protocol. Using the decentralized nature of blockchain, the scheme incorporates a pseudonym management mechanism based on smart contracts, ensuring that a user’s real identity can only be revealed upon consensus from a certain number of RSU, thereby enhancing identity privacy protection. Additionally, using the immutability of smart contracts, a vehicle authentication protocol is designed to improve system decentralization, data security, and identity traceability. Through security analysis, the proposed scheme demonstrates superior security performance against common threats. The analysis of performance shows that the performance of our proposed scheme is improved. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Authentication Protocol

来源：评论

学校读者我要写书评

暂无评论

Leverage Sampling Methods and Deep Neural Networks for Fuzzer CAN Bus Message Detection

引用

IEEE Access 2025年 13卷 91533-91551页

作者： Le, Thi-Thu-Huong Hwang, Yeonjeong Son, JunYoung Kim, Howon Pusan National University Blockchain Platform Technology Center Busan609-735 Korea Republic of Pusan National University School of Computer Science and Engineering Busan609-735 Korea Republic of

The Controller Area Network (CAN) is crucial for automotive safety, yet remains vulnerable to various fuzzing attacks that can compromise vehicle operations. This paper presents a comprehensive detection framework that identifies both common CAN vulnerabilities (DoS, Spoofing, Replay, and general Fuzzing) and specific fuzzer attack types (identity, replay, random, brute force, and mutation-based) using deep learning-based models. We evaluate four recurrent neural network architectures, including standard RNN, Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), and Gated Recurrent Unit (GRU), across three CAN datasets: the publicly available Hacking Car and OTIDS datasets, along with our proprietary Multi-FuzzerCAN dataset. To address the inherent class imbalance in attack data, we implement targeted random oversampling and random undersampling techniques tailored to each dataset’s distribution characteristics, significantly improving model performance. Our experimental results demonstrate that all four models achieve exceptional accuracy, recall, precision, and F1 scores across all datasets, with LSTM and BiLSTM architectures consistently outperforming other approaches. These findings establish the viability of combining deep learning models with data balancing techniques to enhance the resilience of automotive CAN networks against diverse cyber threats, especially multi-fuzzer attacks. © 2013 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Spatial data intelligence and city metaverse: A review

引用

Fundamental Research 2025年第3期5卷 1169-1193页

作者： Meng, Xiaofeng Li, Yong Liu, Ke Liu, Yu Yang, Bin Song, Xuan Liao, Guoqiong Wang, Senzhang Yu, Ziqiang Chen, Longbiao Pan, Xiao Lin, Yuming School of Information Renmin University of China Beijing 100872 China Department of Electronic Engineering Tsinghua University Beijing 100084 China Department of Information Sciences National Natural Science Foundation of China Beijing 100085 China Institute of Remote Sensing and Geographic Information Systems School of Earth and Space Sciences Peking University Beijing 100871 China School of Data Science and Engineering East China Normal University Shanghai 200062 China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen 518055 China School of Information Management Jiangxi University of Finance and Economics Nanchang 330013 China School of Computer Science and Engineering Central South University Changsha 410017 China School of Computer and Control Engineering Yantai University Yantai 264005 China Department of Computer Science Xiamen University Xiamen 361000 China College of Information Science and Technology Shijiazhuang Tiedao University Shijiazhuang 050043 China

Spatial Data Intelligence (SDI) encompasses acquiring, storing, analyzing, mining, and visualizing spatial data to gain insights into the physical world and uncover valuable knowledge. These understandings and knowledge play a crucial role in connecting physical and virtual realms, such as in developing a City Metaverse (CM) aimed at enhancing and optimizing modern urban environments. The advancement of CM holds immense potential to benefit urban dwellers, making research on SDI an increasingly prominent area of focus. This paper contributes significantly by organizing the relevant research and technologies within a coherent framework. Firstly, we identify SDI technologies capable of collecting real-world information to construct a virtual CM. Subsequently, we delve into the technologies that can be compositely integrated with SDI to facilitate interaction with and management of actual cities from the virtual perspective. Additionally, we emphasize the effectiveness and potential of these methods in practical applications. Lastly, we conclude our survey by discussing emerging challenges associated with technological progress, the industrial chain, legal and regulatory aspects, and ethical and moral considerations. © 2024

关键词： Application prospect City metaverse Smart city Spatial data intelligence Virtual-real interaction

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：