检索结果-内蒙古大学图书馆

IEEE International Symposium on Consumer Electronics (ISCE)

作者： Shiori Sasaki Ryota Nakamura Prasetyo Wibowo Department of Data Science Musashino University Tokyo Japan Faculty of Data Science Musashino University Tokyo Japan Department of Informatics and Computer Engineering Politeknik Elektronika Negeri Surabaya Indonesia

ISBN: (数字)9798350365191

ISBN: (纸本)9798350365207

This paper describes a Plastic Waste Hotspot Detection System which has been developed in an international collaborative research project to realize an “Environmental AI-Human Actions integration” with marine plastic waste reduction actions. In this project, various local conditions are obtained to the system to realize an environmentally resilient society. The nature conservation activities such as marine plastic waste collection and reduction actions are implemented based on these conditions. In the process of integration of Environmental AI and Human Actions, the effects of these activities and activists' contribution to environmental improvement and global-scale knowledge are accumulated, shared, analyzed, and visualized through global-scale analysis. This paper describes the Plastic Waste Hotspot Detection system as one of the systems that integrate AI systems and human actions. This paper examines the feasibility and effectiveness of the system through the fieldwork tests in Phuket, Thailand and Surabaya, Indonesia.

关键词： Visualization Collaboration Artificial intelligence Environmental management Plastic waste

来源：评论

学校读者我要写书评

暂无评论

Blockchain-based Searchable Encryption Scheme for Spatial Text data 13

Blockchain-based Searchable Encryption Scheme for Spatial Te...

引用

13th International Conference on Communication and Network Security, ICCNS 2023

作者： Lin, Zhirun Yang, Yang Zhan, Yonghua Li, Jiayin Dong, Chen College of Computer and Data Science Fuzhou University Fujian Fuzhou China School of Computing and Information Systems Singapore Management University Singapore Singapore College of Computer and Cyber Security Fujian Normal University Fujian Fuzhou China

ISBN: (纸本)9798400707964

In today's society, an increasing number of users and enterprises encrypt substantial amounts of data, including spatial text data, and outsource it to cloud servers. However, efficiently and securely querying encrypted spatial text data remains a pressing issue. In this article, we propose a blockchain-based searchable encryption scheme for spatial text data. Users encrypt documents using methods such as order-preserving encryption and upload them to the blockchain for on-chain storage. The cloud server can only retrieve information stored within the blocks, facilitating keyword and coordinate comparisons. To enhance query speed, we introduce a sliding window that allows the server to quickly skip through non-matching blocks. Finally, through experiments and comparisons, this paper demonstrates that the proposed scheme excels in query efficiency and computational overhead, proving its superiority and feasibility compared to other solutions. © 2023 ACM.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Development of Low-Cost Surgical Simulator for Neuroendoscopy using Unity3D and HTC VIVE 16

Development of Low-Cost Surgical Simulator for Neuroendoscop...

引用

16th International Conference on Open Source Systems and Technologies, ICOSST 2022

作者： Fatima, Aimen Bukhari, Faisal Iqbal, Waheed University of the Punjab Faculty of Computing and Information Technology Department of Computer Science Lahore Pakistan University of the Punjab Faculty of Computing and Information Technology Department of Data Science Lahore Pakistan

ISBN: (纸本)9781665464772

Neuroendoscopy is being utilized more frequently to treat brain tumors and hydrocephalus brought on by tumors. Neuroendoscopy is a minimally invasive operation that requires a lot of skills. Complete training is needed in hospitals to perform this procedure in the operating room. Simulators are necessary to train doctors due to the deficiency of time, resources, cost, and potential risks. With advancements in computer technology, it is becoming more common to simulate and plan surgery using a VR-based simulation. We have created and developed a surgical simulator to provide endoscopic training for the ETV procedure. A method to use multimedia capabilities for learning is to create a virtual 3D simulator using a game engine and render it using VR technology. The user-friendly collaborative environment of the Unity3D game engine offers good features. We have demonstrated how a simplex mesh depiction in a game-based simulator may effectively deform a soft body in actuality. We have successfully developed a method employing Position Based Dynamics to simulate the actual deformation of TM the cancerous brain. According to our study, the HTC Vive is a suitable VR technology for ETV training because it offers excellent precision, quick tactile feedback, a fast frame rate, and a wide field of vision. In the future, this practical tool might replace more costly training simulators. © 2022 IEEE.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

See Detail Say Clear: Towards Brain CT Report Generation via Pathological Clue-driven Representation Learning

arXiv

引用

arXiv 2024年

作者： Zheng, Chengxin Ji, Junzhong Shi, Yanzhao Zhang, Xiaodan Qu, Liangqiong College of Computer Science Beijing University of Technology Beijing China Department of Statistics and Actuarial Science School of Computing and Data Science University of Hong Kong Hong Kong

Brain CT report generation is significant to aid physicians in diagnosing cranial diseases. Recent studies concentrate on handling the consistency between visual and textual pathological features to improve the coherence of report. However, there exist some challenges: 1) Redundant visual representing: Massive irrelevant areas in 3D scans distract models from representing salient visual contexts. 2) Shifted semantic representing: Limited medical corpus causes difficulties for models to transfer the learned textual representations to generative layers. This study introduces a Pathological Clue-driven Representation Learning (PCRL) model to build cross-modal representations based on pathological clues and naturally adapt them for accurate report generation. Specifically, we construct pathological clues from perspectives of segmented regions, pathological entities, and report themes, to fully grasp visual pathological patterns and learn cross-modal feature representations. To adapt the representations for the text generation task, we bridge the gap between representation learning and report generation by using a unified large language model (LLM) with task-tailored instructions. These crafted instructions enable the LLM to be flexibly fine-tuned across tasks and smoothly transfer the semantic representation for report generation. Experiments demonstrate that our method outperforms previous methods and achieves SoTA performance. Our code is available at https://***/ChaunceyJheng/PCRL-MRG. © 2024, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

t-READi: Transformer-Powered Robust and Efficient Multimodal Inference for Autonomous Driving

arXiv

引用

arXiv 2024年

作者： Hu, Pengfei Qian, Yuhang Zheng, Tianyue Li, Ang Chen, Zhe Gao, Yue Cheng, Xiuzhen Luo, Jun School of Computer Science and Technology Shandong University China Department of Computer Science and Engineering Southern University of Science and Technology China Department of Electrical and Computer Engineering University of Maryland College Park United States Institue of Space Internet School of Computer Science Fudan University China College of Computing and Data Science Nanyang Technological University Singapore

Given the wide adoption of multimodal sensors (e.g., camera, lidar, radar) by autonomous vehicles (AVs), deep analytics to fuse their outputs for a robust perception become imperative. However, existing fusion methods often make two assumptions rarely holding in practice: i) similar data distributions for all inputs and ii) constant availability for all sensors. Because, for example, lidars have various resolutions and failures of radars may occur, such variability often results in significant performance degradation in fusion. To this end, we present t-READi, an adaptive inference system that accommodates the variability of multimodal sensory data and thus enables robust and efficient perception. t-READi identifies variation-sensitive yet structure-specific model parameters;it then adapts only these parameters while keeping the rest intact. t-READi also leverages a cross-modality contrastive learning method to compensate for the loss from missing modalities. Both functions are implemented to maintain compatibility with existing multimodal deep fusion methods. The extensive experiments evidently demonstrate that compared with the status quo approaches, t-READi not only improves the average inference accuracy by more than 6% but also reduces the inference latency by almost 15× with the cost of only 5% extra memory overhead in the worst case under realistic data and modal variations. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Optimization technique based on cluster head selection algorithm for 5G-enabled IoMT smart healthcare framework for industry

引用

Paladyn 2022年第1期13卷 99-109页

作者： Jaaz, Zahraa A. Ansari, Mohd Dilshad Josephng, P.S. Gheni, Hassan Muwafaq Computer Department College of Science AlNahrain University Baghdad Iraq Selangor Malaysia CMR College of Engineering Technology Hyderabad India Faculty of Data Science Information Technology INTI International University Persiaran Perdana BBN Negeri Sembilan71800 Malaysia Computer Techniques Engineering Department Al-Mustaqbal University College Hillah51001 Iraq

Internet of medical things (IoMT) communication has become an increasingly important component of 5G wireless communication networks in healthcare as a result of the rapid proliferation of IoMT devices. Under current network architecture, widespread access to IoMT devices causes system overload and low energy efficiency. 5G-based IoMT systems aim to protect healthcare infrastructure and medical device functionality for longer. Therefore, using energy-efficient communication protocols is essential for enhancing QoS in IoMT systems. Several methods have been developed recently to improve IoMT QoS;however, clustering is more popular because it provides energy efficiency for medical applications. The primary drawback of the existing clustering technique is that their communication model does not take into account the chance of packet loss, which results in unreliable communication and drains the energy of medical nodes. In this study, we concentrated on designing a clustering model named Whale optimized weighted fuzzy-based cluster head selection algorithm to facilitate successful communication for IoMT-based systems. The experimental study shows that the proposed strategy performs better in terms of QoS than compared approaches. Inferring from this, the proposed method not only reduces energy consumption levels of 5G-based IoMT systems but also uniformly distributes cluster-head over a network to improve QoS. © 2022 Zahraa A. Jaaz et al., published by De Gruyter.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Integrated Leaf Disease Recognition Across Diverse Crops through Transfer Learning

引用

Procedia computer science 2024年 233卷 22-34页

作者： Utkarsh Yashwant Tambe Dr. A. Shanthini Pao-Ann Hsiung Department of Data Science and Business Systems SRM Institute of Science and Technology Kattankulathur (Chennai) 603203 India Department of Computer Science and Information Engineering National Chung Cheng University Chiayi 621301 Taiwan (R.O.C.)

Global food security is seriously threatened by plant diseases and can cause severe economic losses to farmers. Automated detection of plant diseases using computer vision and machine learning techniques has become a popular research area due to its potential to provide faster and more accurate results than traditional methods. In this research, we propose a plant disease detection model based on transfer learning using the MobileNetV2. We evaluate the suggested method on a dataset consisting of 38 various kinds of diseases across 14 different plants. Our experimental findings indicate that the proposed method has a typical accuracy of 91.98% and outperforms additional cutting-edge CNN models for plant disease detection. The experimental findings support the suggested approach's validity and show that it effectively detects plant diseases. We also have put forth the evaluation metrics to investigate the model. The suggested method has potential applications in real-world scenarios and can help farmers detect diseases in their crops at an early stage, allowing them to take timely action to minimize crop losses.

关键词： Plant Disease Detection Crop Protection Image Processing Crop Health Monitoring computers in Agriculture

来源：评论

学校读者我要写书评

暂无评论

CrossTrace: Privacy-aware Cross-System Trajectory Recovery via Hybrid Split and Federated Learning

引用

IEEE Transactions on Mobile Computing 2025年

作者： Cao, Zijian Zhao, Dong Wang, Qiyue Yuan, Haitao Ma, Huadong Yu, Shui Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology School of Computer Science Beijing100876 China Nanyang Technological University College of Computing and Data Science 639798 Singapore University of Technology Sydney School of Computer Science UltimoNSW2007 Australia

Massive urban-scale vehicle trajectories benefit various downstream applications. However, trajectories collected from existing sensing systems are often incomplete, necessitating the recovery of coarse-grained trajectories. Considering that mobility knowledge learned from a single system is less representative of all vehicles or covers only partial road segments, it becomes essential to combine diverse data from multiple systems to support trajectory recovery. Therefore, we learn the impacts of mobility intentions and dynamic traffic conditions on the movement of vehicles from trajectories aggregated across different systems to recover their travel routes on unobservable road intersections. Nonetheless, aggregating raw data across multiple systems raises privacy concerns. This data isolation compounds challenges in acquiring comprehensive mobility intentions and traffic conditions, thereby impairing recovery performance. In this paper, we propose CrossTrace, a two-stage framework for privacy-aware cross-system trajectory recovery: in the Traffic Condition Inference stage, a Split Learning pipeline with a multi-view graph neural network is utilized to infer complete traffic conditions for all road segments;in the Trajectory Recovery stage, a Federated Learning pipeline with dedicated modules is utilized to recover missing points by fusing inferred traffic conditions and mobility intentions. Extensive experiments on two large-scale trajectory datasets demonstrate that CrossTrace outperforms all alternative schemes. © 2002-2012 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Comparative Evaluation of Attribute-Enabled Supervised Classification in Predicting the Air Quality

引用

Spatial Information Research 2023年第4期31卷 399-407页

作者： Subbulakshmi, P. Vimal, S. Robinson, Y. Harold Verma, Amit Nayak, Janmenjoy School of computer science and Engineering VIT Chennai campus Tamilnadu India Data Analytics Lab Department of Artificial Intelligence and Data Science Ramco Institute of Technology Rajapalayam India Department of Computer Science and Engineering Francis Xavier Engineering College Tirunelveli India Department of Computer Science & Engineering University Centre for Research & Development Chandigarh University Gharuan Mohali India Department of Computer Science Maharaja Sriram Chandra Bhanja Deo University Odisha India

Air pollution demonstrates the appearance of toxins into the air which is blocking human prosperity and the earth. It will portray as potentially the riskiest threats that humanity anytime faced. It makes hurt animals, harvests to thwart these issues in transportation territories need to expect air quality from pollutions utilizing AI systems and IoT. Along these lines, air quality evaluation and assumption has become a huge target for human health factors and also affect internal organs related to respiratory. The accuracy of Air Pollution prediction has been involved with the machine learning techniques and the best accuracy model is identified. The air quality prediction dataset is used for identifying the meteorology air pollution data while the predicted model is involved the decision tree computation for predicting the toxin contents in the region, the Air quality indicator is used to assess the pollution level and monitoring the air quality. The performance analysis shows that the decision tree technique has produced the better results in the performance metrics of Accuracy, precision, recall, and F1-score with the minimized error values while the comparative evaluation of Attribute-enabled classification has identified the best technique for predicting the air quality.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generalized Self-Adaption Network for Domain Adaptation 2

Generalized Self-Adaption Network for Domain Adaptation

引用

2nd International Conference on Artificial Intelligence and Intelligent Information Processing, AIIIP 2023

作者： Bian, Yongheng Ke, Xiao College of Computer and Data Science Fuzhou University Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing Fuzhou350116 China Key Laboratory of Spatial Data Mining & Information Sharing Ministry of Education Fuzhou350003 China

ISBN: (纸本)9798350371451

The purpose of domain adaptation is to transfer knowledge learned in the labeled source domain to unlabeled but related target domains without requiring a large number of target domain labels. The latest method of domain adaptation mainly adjusts the distribution of the source and target domains to adapt to the target domain. Despite significant success, when there are significant distribution differences between the source and target domains, the adaptability in the target domain still decreases, which may be due to insufficient exploration of domain specific features leading to domain offset issues. To address this issue, we propose the GSA-NET framework in this article. We designed an adversarial dropout method to improve the generalization performance of the model in the target domain by pushing the decision boundary away from the feature dense region. At the same time, in order to effectively match the distribution of advanced features across domains, we deploy feature adaptation modules before the classification layer, which can significantly reduce domain differences. Our experiments on two cross domain benchmarks, Office Home and Office-31, have shown that the proposed method is significantly superior to existing methods. © 2023 IEEE.

关键词： computer vision

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：