检索结果-内蒙古大学图书馆

Improving hierarchical graph pooling with information bottleneck

Journal of King Saud University Computer and Information sciences 2025年第3期37卷 1-15页

作者： Long, Jun Wang, Zidong Chen, Tingxuan Yang, Liu Big Data Institute Central South University Changsha China School of Computer Science and Engineering Central South University Changsha China

Hierarchical graph pooling has received significant attention in recent years due to its capability to capture hierarchical structures and deliver superior performance on graph-level tasks. However, most existing methods design pooling layers empirically and lack a unified theoretical framework. Consequently, the coarsened graphs generated by these methods frequently contain redundant information, leading to significant semantic bias. In this paper, we propose the principle of “minimal sufficient coarsened graph” to precisely define the desired properties of coarsened graphs. Guided by this principle, we introduce a novel Graph Pooling Information Bottleneck (GPIB) for hierarchical graph pooling. GPIB aims to achieve the desired attributes of minimality and sufficiency in coarsened graphs. Specifically, we first incorporate node degree properties to enrich node representations and introduce a dynamic generation mechanism. This mechanism regulates the information flow, ensuring substantial auxiliary knowledge for downstream tasks and enhancing information sufficiency. Then, we introduce a parameter-learning noise distribution, forcing the elimination of redundant information and thus, facilitating minimality and robustness in our model. Remarkably, we theoretically demonstrate that imposing constraints only on the coarsened graph produced by the final pooling layer equates to constraining all coarsened graphs. This insight simplifies the constraint procedure while ensuring its effectiveness. Extensive experiments on six real-world datasets validate the effectiveness of our proposed model, which consistently outperforms the baseline methods and produces high-quality coarsened graphs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Recognition of American sign language using modified deep residual CNN with modified canny edge segmentation

引用

Multimedia Tools and Applications 2025年 1-28页

作者： Hariharan, U. Devarajan, Devikanniga Kumar, P. Santhosh Rajkumar, K. Meena, M. Akilan, T. Department of Computer Science and Engineering Apex Institute of Technology Chandigarh University Punjab Mohali140413 India Department of Computer Science and Engineering GITAM University Karnataka Bengaluru561203 India Department of Information Technology Faculty of Engineering and technology SRM Institute of Science and Technology Ramapuram Tamil Nadu Chennai600089 India Department of Data Science and Business Systems School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamil Nadu Chennai603203 India Department of Computer Science and Engineering Sri Sairam Engineering College Tamil Nadu Tambaram602109 India Research Coordinator Dept. of IQAC Amity University Kolkata West Bengal 700135 India

American Sign Language (ASL) recognition aims to recognize hand gestures, and it is a crucial solution to communicating between the deaf community and hearing people. However, existing sign language recognition algorithms still have some drawbacks, such as difficulty recognizing hand movements and low recognition accuracy for most sign language recognition. A Modified Convolutional Neural Network (MCNN) deep residual 101 classifier-based American Sign Language identification system has been developed to address this problem. There are three main parts presents in the method. The first part is pre-processing the images to remove the noise, enhance the contrast of the picture, adjust the contrast level and smoothen the picture using various filters. The second part is the segmentation, and it’s used to partition the image using a modified canny edge detection method by removing all weak edges present in the image. Finally, classification will be done using the Modified CNN deep residual 101 classifiers. By classifying the image, the American Sign Language is accurately identified. This process is conducted through images. The outcome shows that the suggested approach has a 0.97% accuracy and a 0.05% False Positive Rate. Other CNN architectures such as resNet 50 and resNet 18 reached 0.90% and 0.80% accuracy, respectively, which is lower than our proposed method. In addition, the resNet 101 classifier effectively recognizes the difficult hand gestures through the image data. It obtains high recognition accuracy for 36 signs is 0 to 9 numbers and a to z alphabets from American Sign Language. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Design, Performance, and Applications of AMMIS: A Novel Airborne Multimodular Imaging Spectrometer for High-Resolution Earth Observations

引用

engineering 2025年第4期47卷 38-56页

作者： Jia, Jianxin Wang, Yueming Zheng, Xiaorou Yuan, Liyin Li, Chunlai Cen, Yi Si, Fuqi Lv, Gang Wang, Chongru Wang, Shengwei Zhang, Changxing Zhang, Dong He, Daogang Zhuang, Xiaoqiong Han, Guicheng Zhang, Mingyang Hyyppä, Juha Wang, Jianyu Key Laboratory of Space Active Opto-Electronics Technology Shanghai Institute of Technical Physics Chinese Academy of Sciences Shanghai200083 China Department of Photogrammetry and Remote Sensing Finnish Geospatial Research Institute EspooFI-02150 Finland Guangdong Provincial Key Laboratory of Multimodal Big Data Intelligent Analysis Guangdong School of Computer Science and Engineering South China University of Technology Guangzhou510641 China State Key Laboratory of Remote Sensing Science Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China Key Laboratory of Environmental Optics and Technology Anhui Institute of Optics and Fine Mechanics Hefei Institutes of Physical Science Chinese Academy of Sciences Hefei230031 China Department of Mechanical Engineering Aalto University EspooFI-02150 Finland

Airborne hyperspectral imaging spectrometers have been used for Earth observation over the past four decades. Despite the high sensitivity of push-broom hyperspectral imagers, they experience limited swath and wavelength coverage. In this study, we report the development of a push-broom airborne multimodular imaging spectrometer (AMMIS) that spans ultraviolet (UV), visible near-infrared (VNIR), shortwave infrared (SWIR), and thermal infrared (TIR) wavelengths. As an integral part of China's High-Resolution Earth Observation Program, AMMIS is intended for civilian applications and for validating key technologies for future spaceborne hyperspectral payloads. It has been mounted on aircraft platforms such as Y-5, Y-12, and XZ-60. Since 2016, AMMIS has been used to perform more than 30 flight campaigns and gather more than 200 TB of hyperspectral data. This study describes the system design, calibration techniques, performance tests, flight campaigns, and applications of the AMMIS. The system integrates UV, VNIR, SWIR, and TIR modules, which can be operated in combination or individually based on the application requirements. Each module includes three spectrometers, utilizing field-of-view (FOV) stitching technology to achieve a 40° FOV, thereby enhancing operational efficiency. We designed advanced optical systems for all modules, particularly for the TIR module, and employed cryogenic optical technology to maintain optical system stability at 100 K. Both laboratory and in-flight calibrations were conducted to improve preprocessing accuracy and produce high-quality hyperspectral data. The AMMIS features more than 1400 spectral bands, with spectral sampling intervals of 0.1 nm for UV, 2.4 nm for VNIR, 3 nm for SWIR, and 32 nm for TIR. In addition, the instantaneous fields of view (IFoVs) for the four modules were 0.5, 0.25, 0.5, and 1 mrad, respectively, with the VNIR module achieving an IFoV of 0.125 mrad in the high-spatial-resolution mode. This study reports on land

关键词： Fighter aircraft

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Offloading Algorithm for Opportunistic Networks Integrating Node Influence Prediction 18th

Probabilistic Offloading Algorithm for Opportunistic Networ...

引用

18th International Conference on Wireless Artificial Intelligent Computing Systems and Applications, WASA 2024

作者： Tang, Qi Xu, Xiaodong Li, Shuai Seah, Winston Xu, Gang College of Computer Science Inner Mongolia University Hohhot010021 China The Engineering Research Center of Ecological Big Data Ministry of Education Inner Mongolia University Hohhot010021 China Victoria University of Wellington Wellington New Zealand

ISBN: (纸本)9783031714634

In Opportunistic Network based mobile data diversion algorithms, the need for multi-hop transmission makes the selection of the next hop node critical. The traditional Prophet algorithm calculates the encounter delivery probability of a node based on historical encounter information as a forwarding condition. However, algorithms for data diversion are more concerned with the issue of nodes’ propagation influence in the network. Therefore, in this paper, we propose a metric to measure the dynamic influence of a node (sir) and use the CNN-BiLSTM-Attention model to predict the sir value of a node during the current time period in the route. After that, a data diversion algorithm based on deep learning prediction of node influence is proposed in combination with encounter delivery probability. The experimental results show that the NS-Prophet algorithm performs well in terms of performance metrics in opportunistic networks, and the triage efficiency in cellular networks is also improved. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： data diversion deep learning prediction node influence opportunistic networks

来源：评论

学校读者我要写书评

暂无评论

Using Blue Whale Technology: An ML Edge Self-Adaptable Vehicle Slowdown Earliest Warning Information System 8th

Using Blue Whale Technology: An ML Edge Self-Adaptable Vehic...

引用

8th International Conference on Microelectronics Electromagnetics and Telecommunications, ICMEET 2023

作者： Murali, N. David, D. Beulah Research Scholar Department of Computer Science and Engineering Saveetha School of Engineering SIMATS Tamilnadu Chennai India Department of Data Analytics Institute of Information Technology Saveetha School of Engineering SIMATS Tamilnadu Chennai India

ISBN: (纸本)9789819784219

Human life is challenged by this main work’s ultimate goal of reducing accidents and ensuring life safety due to the enormous growth of vehicles and those based on safety. Here, cases of suspected drunk driving, reckless driving, etc., are present. In this scenario, vehicles are traveling at full speed and irresponsibly using technology on all roads. An early warning system is used to stop auto accidents. In order to accommodate the city's steadily increasing automobile population, intelligent traffic systems must be designed in a resourceful and sustainable manner using all available technology in both light and dark. The advanced ML's work on unexpected traffic flow and all road conditions resulted in significant real-time changes in the flow of traffic for every significant issue that arose. Here, the Blue Whale technology makes use of clever intelligence to quickly identify, detect, and modify warning systems. The primary objective of the study was to train CNN/BWT on the collected data sets in order to operationalize the unsupervised approach for the prediction of critical situations. Additionally, it makes an effort to clarify the situation so that guests can feel more at ease and help them decide on transfers in time-sensitive situations. IOT is a practical way to locate the nearest object using machine learning methods that are accurate and apply received data sets, resulting in significant findings that support object recognition. The paperwork fully focuses on improving driving knowledge and offering new approaches for quick object recognition. The Fast Warning System Initiative, which aims to increase daytime safety and security, is providing a prior warning system. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Backward wave tubes

来源：评论

学校读者我要写书评

暂无评论

SOLLA: Towards a Speech-Oriented LLM That Hears Acoustic Context

arXiv

引用

arXiv 2025年

作者： Ao, Junyi Chen, Dekun Tian, Xiaohai Feng, Wenjie Zhang, Jun Lu, Lu Wang, Yuxuan Li, Haizhou Wu, Zhizheng School of Data Science Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen China Bytedance China

Large Language Models (LLMs) have recently shown remarkable ability to process not only text but also multimodal inputs such as speech and audio. However, most existing models primarily focus on analyzing input signals using text instructions, overlooking scenarios in which speech instructions and audio are mixed and serve as inputs to the model. To address these challenges, we introduce SOLLA, a novel framework designed to understand speech-based questions and hear the acoustic context concurrently. SOLLA incorporates an audio tagging module to effectively identify and represent audio events, as well as an ASR-assisted prediction method to improve comprehension of spoken content. To rigorously evaluate SOLLA and other publicly available models, we propose a new benchmark dataset called SA-Eval, which includes three tasks: audio event classification, audio captioning, and audio question answering. SA-Eval has diverse speech instruction with various speaking styles, encompassing two difficulty levels, easy and hard, to capture the range of real-world acoustic conditions. Experimental results show that SOLLA performs on par with or outperforms baseline models on both the easy and hard test sets, underscoring its effectiveness in jointly understanding speech and audio. Copyright © 2025, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Correction to: Well-Balanced Fifth-Order Finite Volume WENO Schemes with Constant Subtraction Technique for Shallow Water Equations

引用

Journal of Scientific Computing 2025年第1期103卷 1-4页

作者： Zhao, Lidan Tao, Zhanjing Zhang, Min School of Mathematics Jilin University Changchun China National Engineering Laboratory for Big Data Analysis and Applications Peking University Beijing China Chongqing Research Institute of Big Data Peking University Chongqing China

来源：评论

学校读者我要写书评

暂无评论

Efficient Modeling Attack on Multiplexer PUFs via Kronecker Matrix Multiplication

引用

IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 2025年

作者： Wang, Hongfei Wan, Caixue Jin, Hai Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Wuhan430074 China Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Wuhan430074 China

The Physical Unclonable Function (PUF) is valued for its lightweight nature and unique functionality, making it a common choice for securing hardware products requiring authentication and key generation mechanisms. In response to the susceptibility of individual PUFs to modeling attacks, advanced PUF variants have been developed to improve security measures. One notable type in this regard is the multiplexer-based composition of arbiter PUFs, known as MPUF, which aims to meet high reliability and security standards simultaneously. Current research on attacking MPUF encounters challenges such as substantial demands for training CRPs and low success rates. In this work, we propose a novel numerical modeling attack strategy for MPUFs. Using Kronecker products from mathematical perspective, this method precisely describe the MPUF model without using complex network architectures, boosting attack accuracy and overall efficiency. Experiment comparison with state-of-the-art works demonstrates that our method achieves better performance in terms of attack accuracy, robustness, and efficiency. Our method is able to successfully attack a (512, 8)-MPUF in 32.71 minutes with 97.14% accuracy, outperforming all existing attack methods on MPUFs. More, we validate our method through experiments with hardware implementations on FPGAs. The advantages of our method also include the adaptability to be employed to attack other MPUF variations like cMPUF and rMPUF, and the capability to be integrated with an existing attack method for launching efficient attack on MPUFs leveraging reliability information. © 2025 IEEE.

关键词： modeling attack multiplexer-based PUF Physical unclonable function

来源：评论

学校读者我要写书评

暂无评论

Fast Fractional Programming for Multi-Cell Integrated Sensing and Communications

引用

IEEE Transactions on Wireless Communications 2025年

作者： Chen, Yannan Feng, Yi Li, Xiaoyang Zhao, Licheng Shen, Kaiming School of Science and Engineering Shenzhen518172 China Shenzhen Research Institute of Big Data Shenzhen518172 China

This paper concerns the coordinate multi-cell beamforming design for integrated sensing and communications (ISAC). In particular, we assume that each base station (BS) has massive antennas. The optimization objective is to maximize a weighted sum of the data rates (for communications) and the Fisher information (for sensing). We first show that the conventional beamforming method for the multiple-input multiple-output (MIMO) transmission, i.e., the weighted minimum mean square error (WMMSE) algorithm, works for the ISAC problem case from a fractional programming (FP) perspective. However, the WMMSE algorithm frequently requires computing the N×N matrix inverse, where N is the number of transmit or receive antennas, so the algorithm becomes quite costly when antennas are massively deployed. To address this issue, we develop a nonhomogeneous bound and use it in conjunction with the FP technique to solve the ISAC beamforming problem without the need to invert any large matrices. It is further shown that the resulting new FP algorithm has an intimate connection with gradient projection, based on which we can accelerate the convergence via Nesterov’s gradient extrapolation. © 2002-2012 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Addressing data Imbalance in Machine Learning: Challenges and Approaches 6

Addressing Data Imbalance in Machine Learning: Challenges an...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Langote, Meher Zade, Nikita Gundewar, Swapnil Artificial Intelligence and Data Science Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Maharashtra Sawangi India Artificial Intelligence and Machine Learning Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Maharashtra Sawangi India

ISBN: (纸本)9798331522667

A key difficulty of dealing with imbalanced datasets is that machine learning models are trained to favor the majority class and therefore perform poorly when it comes to a minority class classification. In this paper, we consider the following methods of tackling the issue of the over-representation of a class;random oversampling, undersampling, SMOTE, cost-sensitive learning, and ensemble methods. Comparing them, we assess the performance of each of these techniques within different classifiers. Techniques including SMOTE together with combined methods including Random Forests also show higher capacity in minority class predictions. However, problems such as overfitting and the increase in the computational load are not escapable yet. We briefly recap the strengths and weaknesses of each approach and propose potential refinements including a combination of both methods and dynamic resampling methods to serve as the next steps toward improving the model. Thereby, our results draw attention to the necessity of accurate methods for handling the class imbalance, which will further yield more accurate and fair machine learning solutions across a variety of applications. © 2025 IEEE.

关键词： Adversarial machine learning

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：