检索结果-内蒙古大学图书馆

International Conference on Inventive Computation Technologies (ICICT)

作者： Md Jawed Akhtar Manmohan Singh Sajja Suneel Anand Sutar A. Periya Nayaki Nikhat Raza Khan Department of Computer Science & Engg IES College of Technology Bhopal Department of Computer Science and Engineering IES College of Technology Bhopal Mp India Department of CSE(Data Science) Institute of Aeronautical Engineering Dundigal Hyderabad Telangana India Dept of Electronics and Telecommunication Bharati Vidyapeeh College of Engineering Navi Mumbai Department of Information Technology Velammal College of Engineering and Technology Madurai Tamilnadu Department of Computer Science and Engineering IES College of Technology Bhopal

ISBN: (数字)9798350359299

ISBN: (纸本)9798350359305

In the realm of disaster response, the integration of Internet of Things (IoT) technologies has paved the way for innovative solutions to enhance human detection and rescue operations. This research work introduces a revolutionary approach through the development of the Challenging Human Detection and Rescue Robot (CHDRR). This robot incorporates advanced sensors, including the MQ6 Gas Sensor, LM335 Temperature Sensor, Humidity Sensor, and a Passive Infrared (PIR) Human Body Detection sensor, collectively forming a comprehensive sensory suite. The CHDRR leverages the power of IoT to enable real-time data collection, analysis, and communication, transforming disaster response capabilities. The MQ6 Gas Sensor ensures the detection of hazardous gases in the environment, providing crucial information for safe rescue operations. The LM335 Temperature Sensor and Humidity Sensor contribute to environmental monitoring, allowing the robot to adapt its strategies based on prevailing conditions. The PIR Human Body Detection sensor serves as a key element in the CHDRR's human detection capabilities. Through sophisticated algorithms and machine learning, the robot can identify and locate human presence amidst challenging disaster scenarios. The fusion of these sensors with IoT technology empowers the CHDRR to make informed decisions autonomously, optimizing its efficiency in dynamically changing environments.

关键词： Temperature sensors Disasters Humidity Sensor fusion Robot sensing systems Real-time systems Sensors

来源：评论

学校读者我要写书评

暂无评论

COMET: NFT Price Prediction with Wallet Profiling

arXiv

引用

arXiv 2024年

作者： Wang, Tianfu Deng, Liwei Wang, Chao Lian, Jianxun Yan, Yue Yuan, Nicholas Jing Zhang, Qi Xiong, Hui School of Computer Science and Technology University of Science and Technology of China Hefei China Microsoft Inc Suzhou China School of Artificial Intelligence and Data Science University of Science and Technology of China Hefei China Microsoft Research Asia Beijing China Microsoft Inc Beijing China Guangzhou China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong

As the non-fungible token (NFT) market flourishes, price prediction emerges as a pivotal direction for investors gaining valuable insight to maximize returns. However, existing works suffer from a lack of practical definitions and standardized evaluations, limiting their practical application. Moreover, the influence of users' multi-behaviour transactions that are publicly accessible on NFT price is still not explored and exhibits challenges. In this paper, we address these gaps by presenting a practical and hierarchical problem definition. This approach unifies both collection-level and token-level task and evaluation methods, which cater to varied practical requirements of investors. To further understand the impact of user behaviours on the variation of NFT price, we propose a general wallet profiling framework and develop a COmmunity enhanced Multi-bEhavior Transaction graph model, named COMET. COMET profiles wallets with a comprehensive view and considers the impact of diverse relations and interactions within the NFT ecosystem on NFT price variations, thereby improving prediction performance. Extensive experiments conducted in our deployed system demonstrate the superiority of COMET, underscoring its potential in the insight toolkit for NFT investors. Copyright © 2024, The Authors. All rights reserved.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Decomposed Linear Dynamical Systems for Robust Discovery of Latent Neural Dynamics 38

Probabilistic Decomposed Linear Dynamical Systems for Robust...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Chen, Yenho Mudrik, Noga Johnsen, Kyle A. Alagapan, Sankaraleengam Charles, Adam S. Rozell, Christopher J. Machine Learning Center Georgia Institute of Technology United States School of Electrical and Computer Engineering Georgia Institute of Technology United States Coulter Dept. of Biomedical Engineering Emory University Georgia Institute of Technology United States Department of Biomedical Engineering Mathematical Institute for Data Science Center for Imaging Science Kavli Neuroscience Discovery Institute Johns Hopkins University United States

Time-varying linear state-space models are powerful tools for obtaining mathematically interpretable representations of neural signals. For example, switching and decomposed models describe complex systems using latent variables that evolve according to simple locally linear dynamics. However, existing methods for latent variable estimation are not robust to dynamical noise and system nonlinearity due to noise-sensitive inference procedures and limited model formulations. This can lead to inconsistent results on signals with similar dynamics, limiting the model's ability to provide scientific insight. In this work, we address these limitations and propose a probabilistic approach to latent variable estimation in decomposed models that improves robustness against dynamical noise. Additionally, we introduce an extended latent dynamics model to improve robustness against system nonlinearities. We evaluate our approach on several synthetic dynamical systems, including an empirically-derived brain-computer interface experiment, and demonstrate more accurate latent variable inference in nonlinear systems with diverse noise conditions. Furthermore, we apply our method to a real-world clinical neurophysiology dataset, illustrating the ability to identify interpretable and coherent structure where previous models cannot. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-StudentNet: a Semi-supervised Deep-Learning Framework for Endometrial Segmentation in Transvaginal Ultrasound Images

Multi-StudentNet: a Semi-supervised Deep-Learning Framework ...

引用

International Conference on e-health Networking, Applications and Services (HealthCom)

作者： Boyuan Peng Yiyang Liu Xin Zhu Jie Huang Wenwen Wang Li Fang Qin Zhou Graduate Department of Computer Science and Engineering The University of Aizu Aizu-Wakamatsu Fukushima Japan Department of AI Technology Development M&D Data Science Center Institute of Science Tokyo Chiyodaku Tokyo Japan Graduate Department of Computer Science and Engineering Division of Information Systems The University of Aizu Aizu-Wakamatsu Fukushima Japan Department of Obstetrics and Gynecology Tongji Hospital Huazhong University of Science and Technology Wuhan Hubei China

ISBN: (数字)9798350350548

ISBN: (纸本)9798350350555

Semi-supervised learning (SSL) is a promising solution for the problem of insufficient medical labeled data. However, it is still a challenging task to segment transvaginal ultrasound (TVUS) images because of their poor contrast and speckle noise. In this study, we propose Multi-StudentNet, a semi-supervised deep-learning framework for endometrial segmentation in TVUS images. This method employs multiple student models to effectively integrate labeled and unlabeled data, improving the reliability and performance of segmentation while significantly reducing the need for extensive manual labeling. By leveraging the weights of multiple models, our framework facilitates feature sharing, which enhances model robustness. Specifically, Multi-StudentNet achieves a Dice coefficient (DSC) of 0.81 and a specificity of 0.99. Our multi-student models consistently outperform single-student models across various conditions, including normal, polyp, and cancer cases. Extensive experiments demonstrate that Multi-StudentNet achieves state-of-the-art performance in both accuracy and robustness.

关键词： Image segmentation Ultrasonic imaging Accuracy Manuals Speckle Semisupervised learning Robustness data models Optimization Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Reliable Vertical Ground Reaction Force Estimation with Smart Insole During Walking

arXiv

引用

arXiv 2025年

作者： Olugbon, Femi Ghoreishi, Nozhan Huang, Ming-Chun Xu, Wenyao Chen, Diliang Department of Electrical and Computer Engineering University of New Hampshire DurhamNH03824 United States Department of Data and Computational Science Duke Kunshan University Suzhou China Department of Computer Science & Engineering University at Buffalo The State University of New York BuffaloNY14260 United States

The vertical ground reaction force (vGRF) and its characteristic weight acceptance and push-off peaks measured during walking are important for gait and biomechanical analysis. Current wearable vGRF estimation methods suffer from drifting errors or low generalization performances, limiting their practical application. This paper proposes a novel method for reliably estimating vGRF and its characteristic peaks using data collected from the smart insole, including inertial measurement unit data and the newly introduced center of the pressed sensor data. These data were fused with machine learning algorithms including artificial neural networks, random forest regression, and bi-directional long-short-term memory. The proposed method outperformed the state-of-the-art methods with the root mean squared error, normalized root mean squared error, and correlation coefficient of 0.024 body weight (BW), 1.79% BW, and 0.997 in intra-participant testing, and 0.044 BW, 3.22% BW, and 0.991 in inter-participant testing, respectively. The difference between the reference and estimated weight acceptance and push-off peak values are 0.022 BW and 0.017 BW with a delay of 1.4% and 1.8% of the gait cycle for the intra-participant testing and 0.044 BW and 0.025 BW with a delay of 1.5% and 2.3% of the gait cycle for the inter-participant testing. The results indicate that the proposed vGRF estimation method has the potential to achieve accurate vGRF measurement during walking in free-living environments. Copyright © 2025, The Authors. All rights reserved.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Emergency Care Patient Prediction using Electronic Health Records (EHR) data: An End-to-End Machine Learning Pipeline

Emergency Care Patient Prediction using Electronic Health Re...

引用

International Conference on Future Internet of Things and Cloud (FiCloud)

作者： Maruful Abedin Sumon Tor A. Kwemebe Venkata K. Melapu Md Mohiuddin Hasan Computational Data-Enabled Science and Engineering Jackson State University Jackson USA Department of Mathematics and Computer Science Jackson State University Jackson USA Computer Science and Engineering Jackson State University Jackson USA

Using electronic health records (EHR) data for predicting the condition of patients who are in need of emergency care is a promising application of machine learning. With the help of machine learning, complex problems of identification of patterns can be solved with ease and accuracy when proper machine learning model is implemented. This paper uses EHR data to build an end-to-end machine learning pipeline for predicting the outcome of emergency care patients. As a machine learning process, the pipeline includes data preprocessing, feature engineering, model selection, data set training and testing, evaluation, and deployment. By using EHR data in this pipeline, the model has been trained and tested on a large dataset of many patients information with different types of machine learning algorithms to improve and get the best prediction accuracy. This pipeline can aid in managing primary care patients efficiently and effectively with the implementation of best suitable machine learning algorithm at the time of urgency. By implementing the model on the EHR dataset, an accuracy of more than $75 \%$ is obtained which indicates the efficiency of the machine learning process in the process of identifying patients who need the emergency care more than the general patients when taken to the primary care or emergency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Image Analysis of MRI-based Brain Tumor Classification and Segmentation using BSA and RELM Networks 2

Image Analysis of MRI-based Brain Tumor Classification and S...

引用

2nd International Conference on Automation, Computing and Renewable Systems, ICACRS 2023

作者： Saranya, R. Pushpakumar, R. Srinivasan, P. Aparna, N. Karthika, K. Chauhan, Amit Department of Computer science with Data Analytics PSG College of Arts and Science Coimbatore India Department of Information Technology Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Tamil Nadu Chennai India Department of ECE Sona College of Technology Tamilnadu Salem India Department of Biomedical Engineering Dhaanish Ahmed Institute of Technology Tamil Nadu Veerappanur India Civil Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai India Karnataka Bengaluru India

ISBN: (纸本)9798350340235

Brain tumor segmentation plays a crucial role in medical image analysis. Brain tumor patients considerably benefit from early discovery due to the increased likelihood of a successful outcome from therapy. Due to the sheer volume of MRI images generated in everyday clinical practice, manually isolating brain tumors for cancer diagnosis is a challenging task. Automatic segmentation of images of brain tumors is essential. This system aimed to synthesize previous methods for BSA-RELM-based brain tumor segmentation. The proposed methodology rests on four fundamental pillars: preprocessing, segmentation, feature extraction, and model training. Filtering, scaling, boosting contrast, and sharpening are all examples of preprocessing techniques. When doing segmentation, a clustering technique based on Fuzzy Clustering Means (FCM) is used to breakdown the overall dataset into numerous subsets. The proposed approach used the region of filling for feature extraction. After that, a BSA-RELM is used to train the models with the input features. The proposed technique outperforms BSA and RELM, two of the most common alternatives. There was a 98.61 percent success rate with the recommended method. © 2023 IEEE.

关键词： Brain Tumor Segmentation Central Nervous System (CNS) FuzzyClustering Method (FCM)

来源：评论

学校读者我要写书评

暂无评论

Attention-based Network for Image/Video Salient Object Detection

Attention-based Network for Image/Video Salient Object Detec...

引用

European Workshop on Visual Information Processing (EUVIP)

作者： Omar Elharrouss Soukaina ElIdrissi ElKaitouni Younes Akbari Somaya Al-Maadeed Ahmed Bouridane Department of Computer Science Qatar University Doha Qatar Department of Computer Science Sidi Mohamed Ben Abdellah Univerisity Fez Morocco Centre for Data Analytics and Cybersecurity University of Sharjah Sharjah UAE

The goal of video or image salient object detection is to identify the most important object in the scene, which can be helpful in many computer vision-based tasks. As the human vision framework has a successful capacity to effortlessly perceive locales of interest from complex scenes, salient object detection mimics a similar concept. However, the salient object detection (SOD) of complex video scenes is a challenging task. This paper mainly focuses on learning from channel and Spatiotemporal representations for image/video salient object detection. The proposed method consists of three levels, the frontend, the attention models, and the backend. While the frontend consists of VGG backbone which ultimately learns the representation of the common and the discrimination features. After that, both Attention, Channel-wise, and Spatiotemporal models are applied to highlight the significant object using a feature detector and to calculate the spatial attention. Then the output features are fused to obtain the final saliency result. Experimental investigation evaluations confirm that our proposed model has proved its validity and effectiveness compared with the state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Scalable Multi-agent Reinforcement Learning for Factory-wide Dynamic Scheduling

arXiv

引用

arXiv 2024年

作者： Jang, Jaeyeon Klabjan, Diego Liu, Han Patel, Nital S. Li, Xiuqi Ananthanarayanan, Balakrishnan Dauod, Husam Juang, Tzung-Han Department of Data Science The Catholic University of Korea Korea Republic of Department of Industrial Engineering and Management Sciences Northwestern University United States Department of Computer Science Northwestern University United States Intel Corporation United States

Real-time dynamic scheduling is a crucial but notoriously challenging task in modern manufacturing processes due to its high decision complexity. Recently, reinforcement learning (RL) has been gaining attention as an impactful technique to handle this challenge. However, classical RL methods typically rely on human-made dispatching rules, which are not suitable for large-scale factory-wide scheduling. To bridge this gap, this paper applies a leader-follower multi-agent RL (MARL) concept to obtain desired coordination after decomposing the scheduling problem into a set of sub-problems that are handled by each individual agent for scalability. We further strengthen the procedure by proposing a rule-based conversion algorithm to prevent catastrophic loss of production capacity due to an agent's error. Our experimental results demonstrate that the proposed model outperforms the state-of-the-art deep RL-based scheduling models in various aspects. Additionally, the proposed model provides the most robust scheduling performance to demand changes. Overall, the proposed MARL-based scheduling model presents a promising solution to the real-time scheduling problem, with potential applications in various manufacturing industries. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Transformer-based functional time series modeling to unveil dynamic brain state transitions

Transformer-based functional time series modeling to unveil ...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Yurim Jang Jong Young Namgung Yeongjun Park Bo-Yong Park Artificial Intelligence Convergence Research Center Inha University Incheon Republic of Korea Department of Data Science Inha University Incheon Republic of Korea Department of Computer Engineering Inha University Incheon Republic of Korea Department of Data Science & Center for Neuroscience Imaging Research Inha University & Institute for Basic Science Incheon & Suwon Republic of Korea

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

Brain state is dynamic in nature, and identifying the transitions between different brain states is crucial for understanding ongoing cognitive functions. Here, we opted for a transformer-based blood-oxygen-level-dependent transformer model (BolT) to investigate dynamic transitions of brain states across time. Using the given time series data, the model predicted subsequent time series. At the same time, it provided information about the contribution of each time point for the prediction with the importance weights. We extracted the time series corresponding to the top 10% and bottom 10% contribution of the importance weights. For each time series data, we constructed the connectivity matrix and calculated the degree centrality values. We compared the degree values between the top 10% and bottom 10% contribution data and found significant differences in the regions involved in the default mode network. Specifically, decreases in the degree values were observed at the highly contributed time points. Our findings indicate that the reorganization of connectome organization occurs in the default mode network during transitions in brain states.

关键词： Neuroscience Accuracy Time series analysis Organizations Predictive models Fasteners Brain modeling Transformers data models Engineering in medicine and biology

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：