检索结果-内蒙古大学图书馆

9th IEEE International Conference on computer science and Network technology, ICCSNT 2021

作者： Han, Xiao Wang, Huiqiang Tan, Jing College of Computer Science And Technology Harbin Engineering University Harbin150001 China

ISBN: (纸本)9781665443647

Mobile crowdsensing typically uses multiple copies for data forwarding. Meanwhile, the limited cache of nodes, and the overlapping sensing range between nodes, often leads to network congestion situation. Therefore, it is still a key issue to establish a reasonable and effective cache management strategy in mobile crowdsensing. In this work, we propose a priority queue-based cache management method (PQBM). With the objective to optimal cache management, the PQBM first divides nodes cache into source message queues and relay message queues, then performs different message discard policies according to the prioritization mechanism of queues when congestion occurs in the network. The simulation results highlight the strength of the PQBM strategy as it can guarantee message discard fairness and cache dynamic balance, verify that PQBM strategy can significantly reduce the network overhead, latency, packet loss rate and achieve better performance than other existing schemes. © 2021 IEEE.

关键词： Queueing theory

来源：评论

学校读者我要写书评

暂无评论

Information system for flood monitoring based on IoT and AI 2

Information system for flood monitoring based on IoT and AI

引用

2nd International Conference on Smart Technologies and Systems for Next Generation Computing, ICSTSN 2023

作者： Wilson, Allan J Pon Bharathi, A. Anoop, M. Angelin Jeba Malar, J. Amrita College of Engineering and Technology Department of Electronics and Communication Engineering Nagercoil India Alpha Arts and Science College Department of Computer Applications Chennai India A.M.Jain College Department of Computer Science Chennai India

ISBN: (纸本)9798350348002

One of the most significant areas where realistic solutions have been put into place to minimise harm is flood management. In this research project, we are creating an IoTenabled adaptive AI technique for effective fluid management. Floods in Kerala, India, have recently seriously damaged the environment, infrastructure, and population. Various IoT devices gathered information on temperature, precipitation rates, and other variables. This study uses a real-time flood visualisation technology to provide an information system for flood monitoring. A system is constructed by first creating two systems: a client system comprised of hardware for detecting floods and a server system comprised of software for monitoring floods and distributing the collected data. All of the information on the flood in Kerala is compiled and split in halves, with the first set serving as training data and the second as test data. The suggested hybrid model is trained using six different machine learning models, and it achieves a maximum accuracy of 99.64%. We were able to prevent losses because to the system's seamless design. Research reveals that the client of the flood detection system may deliver real-time data on flood levels, weather conditions, and temperatures. Additionally, data from client systems can be collected by flood monitoring information systems and stored in MySQL. © 2023 IEEE.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

A Hybrid computer Vision enabled GAN Model for Pest and Disease Detection

A Hybrid Computer Vision enabled GAN Model for Pest and Dise...

引用

2024 IEEE International Conference on Intelligent Computing and Emerging Communication Technologies, ICEC 2024

作者： Banerjee, Joydeep Das, Amiya Kumar Sabale, Ketan Alkhayyat, Ahmed Kalinga Institute of Industrial Technology School of Computer Engineering Bhubaneswar India Pandit Deendayal Energy University School of Technology Department of Computer Science and Engineering Gujarat Gandhinagar382007 India The Islamic University College of Technical Engineering Najaf Iraq

ISBN: (纸本)9798331508432

Agriculture is among the most prominent occupation in India and among different parts of the globe, and plant diseases account for 35% of crop yield loss each year. Plants are affected by pests, environmental conditions, and nutritional deficits. Identifying and treating issues early is crucial for accomplishing desired yields. In this paper, an effective way for early detection of bugs in plants which combines Generative Adversarial Networks(GANs) with computer vision techniques is suggested. The proposed model utilizes advanced data augmentation, pre-processing, feature extraction, and classification to improve the precision of bug assessment in plants. Extensive set of simulations were performed to highlight the improved performance of the suggested approach. The experimental outcome has demonstrated promising results of the proposed model over the recent modern appraoches with maximum 95.2% accuracy, 92.6 % f-score, 93.8 % precision and 91.2% recall. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Hand Sign Detection and Voice Conversion for the Hearing and Speech Impaired Using Convolutional Neural Networks 4th

Hand Sign Detection and Voice Conversion for the Hearing and...

引用

4th International Conference on Recent Trends in Machine Learning, IoT, Smart Cities, and Applications, ICMISC 2023

作者： Belgaum, Mohammad Riyaz Sowmya, Kurni Sireesha, Kuruva Priyanka, Tatagari Tony Vyshnavi, Uppara Uravakonda Department of Computer Science and Engineering G. Pullaiah College of Engineering and Technology Kurnool India Faculty of Computing and Informatics Multimedia University Cyberjaya Malaysia

ISBN: (纸本)9789819994410

Sign Language Recognition (SLR) tries to convert sign language into written or spoken form to enable communication between a deaf-mute person and a normal person. The task of communicating with disabled and impaired persons is extremely challenging, owing to its complexity and variety of hand motions that have a major societal impact. In order to depict sign language motions, SLR approaches are increasingly being used. These classification models are based on hand-crafted characteristics. Building reliable features that can adapt to the diverse range of hand signs is nonetheless challenging. To address this issue, the authors proposed a special 3D convolutional neural network (CNN) to ease the communication between normal and mute communities. Our proposed model eliminates the requirement to create features by automatically extracting discriminative spatial–temporal features from the actual livestream without any prior information. To improve performance, the 3D CNN is fed with multiple channels of video feeds that include colour, depth, trajectory information, joint body locations, and depth clues. We illustrate the proposed model's superiority to the conventional methods based on hand-crafted characteristics by testing them against a real dataset collected using a depth camera. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Audition

来源：评论

学校读者我要写书评

暂无评论

ToMFIR and Auxiliary Signals based Active Incipient Fault Detection for Autonomous Underwater Vehicle Thrusters 43

ToMFIR and Auxiliary Signals based Active Incipient Fault De...

引用

43rd Chinese Control Conference, CCC 2024

作者： Zhu, Zefan Wu, Yunkai Zhou, Yang Zhu, Zhiyu Soh, YengChai Jiangsu University of Science and Technology College of Automation Zhenjiang212100 China Jiangsu University of Science and Technology School of Computer Science and Engineering Zhenjiang212100 China Nanyang Technological University School of Electrical and Electronic Engineering Singapore Singapore

ISBN: (纸本)9789887581581

This article proposes an active fault detection method combining the Total Measurable Fault Information Residual (ToMFIR) and auxiliary signals to address the incipient faults of autonomous underwater vehicle (AUV) thrusters. Firstly, the Takagi-Sugeno (T-S) fuzzy medelling of AUV dynamics is establised. Secondly, an auxiliary signal and redundant actuator module are introduced. The auxiliary signal is capable of amplifying the active ToMFIR in the event of a fault, while the redundant actuator ensures that the auxiliary signal does not interfere with the active ToMFIR in fault-free scenarios. Performance indicators and fixed thresholds are provided to assist in designing the parameters of the redundant actuator. This is done by maximizing the impact of the auxiliary signal on ToMFIR signals and minimizing any disturbances. Finally, simulation results demonstrate the effectiveness of the proposed method in improving the sensitivity for incipient faults in AUV propulsion systems. © 2024 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Autonomous underwater vehicles

来源：评论

学校读者我要写书评

暂无评论

A Hybrid LLM based Model for Calorie Tracker and Dietary Control

A Hybrid LLM based Model for Calorie Tracker and Dietary Con...

引用

2024 IEEE International Conference on Intelligent Computing and Emerging Communication Technologies, ICEC 2024

作者： Mishra, Sneha Siddiqui, Ibrahim Ahmad Sabale, Ketan Alkhayyat, Ahmed Kalinga Institute of Industrial Technology School of Computer Engineering Bhubaneswar India Pandit Deendayal Energy University School of Technology Department of Computer Science and Engineering Gujarat Gandhinagar382007 India The Islamic University College of Technical Engineering Najaf Iraq

ISBN: (纸本)9798331508432

The importance of attainable and efficient dietary management options is clearly visible through the increasing occurrences of obesity and associated health conditions. While traditional techniques of calorie tracking are useful, they can be labor-intensive and highly prone to errors, highlighting the requirement for novel technology alternatives. This work presents the use of advanced natural language processing to intensify user experience and accuracy in dietary control for a Large Language Model (LLM)-based calorie tracker. To get a more natural approach for measuring calorie intake, creating customized dietary goals, and receiving real-time feedback we use AI and machine learning algorithms in the program (GPT-3 and GPT-4). To control intermittent fasting habits, measure hydration, and monitor weight variations, various tools are provided by the device. Deep learning techniques such as Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRUs) are implemented to give support and personalized recommendations to help users overcome hindrances and achieve their health goals, thus contributing to overall health and well-being. © 2024 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

Independent Feature Enhanced Crossmodal Fusion for Match-Mismatch Classification of Speech Stimulus and EEG Response

Independent Feature Enhanced Crossmodal Fusion for Match-Mis...

引用

International Symposium on Chinese Spoken Language Processing

作者： Shitong Fan Wenbo Wang Feiyang Xiao Shiheng Zhang Qiaoxi Zhu Jian Guan Group of Intelligent Signal Processing (GISP) College of Computer Science and Technology Harbin Engineering University Harbin Faculty of Computing Harbin Institute of Technology Harbin University of Technology Sydney Ultimo

ISBN: (数字)9798331516826

ISBN: (纸本)9798331516833

It is crucial for auditory attention decoding to classify matched and mismatched speech stimuli with corresponding EEG re-sponses by exploring their relationship. However, existing methods often adopt two independent networks to encode speech stimulus and EEG response, which neglect the relationship between these signals from the two modalities. In this paper, we propose an independent feature enhanced cross-modal fusion model (IFE-CF) for match-mismatch classification, which leverages the fusion feature of the speech stimu-lus and the EEG response to achieve auditory EEG decoding. Specifically, our IFE-CF contains a crossmodal encoder to encode the speech stimulus and the EEG response with a two-branch structure connected via crossmodal attention mechanism in the encoding process, a multi-channel fusion module to fuse features of two modalities by aggregating the interaction feature obtained from the crossmodal encoder and the independent feature obtained from the speech stimulus and EEG response, and a predictor to give the matching result. In addition, the causal mask is introduced to consider the time delay of the speech-EEG pair in the crossmodal encoder, which further enhances the feature representation for match-mismatch classification. Ex-periments demonstrate our method's effectiveness with better classification accuracy, as compared with the baseline of the Auditory EEG Decoding Challenge 2023.

关键词： Attention mechanisms Accuracy Fuses Delay effects Speech enhancement Brain modeling Electroencephalography Encoding Decoding

来源：评论

学校读者我要写书评

暂无评论

Idea23D: Collaborative LMM Agents Enable 3D Model Generation from Interleaved Multimodal Inputs 31

Idea23D: Collaborative LMM Agents Enable 3D Model Generation...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Chen, Junhao Li, Xiang Ye, Xiaojun Li, Chao Fan, Zhaoxin Zhao, Hao Tsinghua University China Tsinghua Shenzhen International Graduate School Tsinghua University China School of Software and Microelectronics Peking University China College of Computer Science Zhejiang University China College of Computer Science and Technology Harbin Engineering University China Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing School of Artificial Intelligence Beihang University China

ISBN: (纸本)9798891761964

With the success of 2D diffusion models, 2D AIGC content has already transformed our lives. Recently, this success has been extended to 3D AIGC, with state-of-the-art methods generating textured 3D models from single images or text. However, we argue that current 3D AIGC methods still don't fully unleash human creativity. We often imagine 3D content made from multimodal inputs, such as what it would look like if my pet bunny were eating a doughnut on the table. In this paper, we explore a novel 3D AIGC approach: generating 3D content from IDEAs. An IDEA is a multimodal input composed of text, image, and 3D models. To our knowledge, this challenging and exciting 3D AIGC setting has not been studied before. We propose the new framework Idea23D, which combines three agents based on large multimodal models (LMMs) and existing algorithmic tools. These three LMM-based agents are tasked with prompt generation, model selection, and feedback reflection. They collaborate and critique each other in a fully automated loop, without human intervention. The framework then generates a text prompt to create 3D models that align closely with the input IDEAs. We demonstrate impressive 3D AIGC results that surpass previous methods. To comprehensively assess the 3D AIGC capabilities of Idea23D, we introduce the Eval3DAIGC-198 dataset, containing 198 multimodal inputs for 3D generation tasks. This dataset evaluates the alignment between generated 3D content and input IDEAs. Our user study and quantitative results show that Idea23D significantly improves the success rate and accuracy of 3D generation, with excellent compatibility across various LMM, Text-to-Image, and Image-to-3D models. Code and dataset are available at https://***/. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Effects of Biowaste-Derived Hydrochar on Anaerobic Digestion:Insights into Hydrochar Characteristics

引用

Journal of Renewable Materials 2023年第10期11卷 3647-3657页

作者： Hongqiong Zhang Xu Wang Zhaojing Qian Buchun Si Kai Jin Tengfei Wang Key Laboratory of Agricultural Renewable Resource Utilization Technology College of EngineeringNortheast Agriculture UniversityHarbin150030China College of Engineering Northeast Agricultural UniversityHarbin150030China College of Food Science Northeast Agricultural UniversityHarbin150030China Laboratory of Environment-Enhancing Energy(E2E) Key Laboratory of Agricultural Engineering in Structure and EnvironmentMinistry of AgricultureCollege of Water Resources and Civil EngineeringChina Agricultural UniversityBeijing100083China Faculty of Geosciences and Environmental Engineering Southwest Jiao Tong UniversityChengdu611756China

Hydrochar prepared with four typical biowastes,pine wood,food waste,digested sewage sludge,and Chlorella were applied for the promotion of anaerobic *** gas production and substrate composition were analyzed associated with the hydrochar *** results suggested that Chlorella hydrochar(C-C)showed the highest cumulative yield of methane(approximately 345 mL)with high total organic carbon(TOC)removal efficiency and low volatile fatty acids(VAFs)***,food waste hydrochar(F-C)showed a poor effect on anaerobic digestion and aroused 1.4–1.6 g/L accumulation of VAFs,in which the toxic components may account for the low *** C-C and sludge hydrochar(S-C)may develop direct interspecific electron transport(DIET)to facilitate the generation of methane by both surface groups and conductivity of the body structure,unlike pinewood hydrochar(P-C),which mainly depended on the aromatic matrix structure of hydrochar *** work suggested that C-C can be the best candidate for the facilitation of anaerobic digestion,and N-containing biowaste like algae and lignocellulose like pine wood may establish different DIET pathways based on the physicochemical characteristics of hydrochar.

关键词： Biowaste hydrochar DIET anaerobic digestion methane

来源：评论

学校读者我要写书评

暂无评论

Super-Resolution of Diffusion-Weighted Images via TDI-Conditioned Diffusion Model 15th

Super-Resolution of Diffusion-Weighted Images via TDI-Cond...

引用

15th International Workshop on Computational Diffusion MRI, CDMRI 2024, held in conjunction with 27th International Conference on Medical Image Computing and computer-Assisted Intervention, MICCAI 2024

作者： Ma, Jiquan Teng, Yujun Chen, Geng Jiang, Haotian Zhang, Kai Liu, Feihong Rekik, Islem Shen, Dinggang School of Computer Science and Technology Heilongjiang University Harbin China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xi’an China School of Biomedical Engineering and State Key Laboratory of Advanced Medical Materials and Devices ShanghaiTech University Shanghai China School of Information Science and Technology Northwest University Xi’an China BASIRA Lab Imperial-X and Department of Computing Imperial College London London United Kingdom

ISBN: (纸本)9783031869198

Diffusion-Weighted Imaging (DWI) is a significant technique for studying white matter. However, it suffers from low-resolution obstacles in clinical settings. Post-acquisition Super-Resolution (SR) can enhance the resolution of DWIs and has gained increasing research interest in recent years. An advanced generative model, the Diffusion Model (DM), exhibits particularly promising performance in image SR. However, effective conditions are required to bootstrap the DM for DWI SR. To this end, we proposed the first DM-based DWI SR model with two effective conditions based on low-solution DWIs and Track Density Imaging (TDI) maps, which possess rich high-resolution prior knowledge Additionally, we consider another condition based on features from low-resolution DWIs. These two conditions are integrated into our model, which comprises three components: DWI Resolution Enhancer (DRE), DWI Feature Extractor (DFE), and TDI Feature Extractor (TFE). DRE combines low-resolution DWI features from DFE with TDI features from TFE to progressively generate high-resolution DWIs. We performed extensive experiments on DWIs of normal subjects from human connectome projects and patients with Parkinson’s disease. The results demonstrate that our model outperforms existing DWI SR models, both qualitatively and quantitatively. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Neurodegenerative diseases

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：