检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Shi, Wenqi Murakoso, Mio Guo, Xiaoyan Xiong, Linxi Chen, Matthew Wang, May D. Georgia Institute of Technology Department of Electrical and Computer Engineering Atlanta United States Kyoto University Department of Applied Life Science Kyoto Japan Georgia Institute of Technology College of Computing Atlanta United States Tsinghua University Tanwei College Beijing China Georgia Institute of Technology Wallace H. Coulter Department of Biomedical Engineering Atlanta United States

ISBN: (纸本)9798350337488

Emerging infectious diseases, such as coronavirus disease 2019 (COVID-19), pose a major threat to public health and present a critical challenge for drug discovery. Due to the cost- and time-consuming process of new drug development, virtual pre-screening methods such as protein-ligand docking prediction have become essential tools in enhancing drug refurbishment and repurposing. In this study, we propose a machine learning-based surrogate model for docking score prediction of drug candidates on SARS-CoV-2 protein targets via deep feature concatenation. We investigate 14 different combinations of rule-based and data-driven fingerprinting methods to identify the optimal representation of candidate drug molecules. Extensive experiments on docking scores of 270,000 molecules across 18 different SARS-CoV-2 protein targets demonstrate the effectiveness of the proposed surrogate models. In addition to unseen drugs, we further investigate the generalization of the proposed framework for unseen protein targets. This study may provide an instrumental and generalizable framework for exploring ligand-protein interaction, serving as a useful tool to facilitate rapid drug pre-screening during emerging public health crises. © 2023 IEEE.

关键词： COVID-19 drug target explainable artificial intelligence feature concatenation interaction prediction neural networks

来源：评论

学校读者我要写书评

暂无评论

IoT-Enhanced Path Planning and Obstacle Avoidance for Autonomous Mobile Robots 3

IoT-Enhanced Path Planning and Obstacle Avoidance for Autono...

引用

3rd International Conference for Advancement in technology, ICONAT 2024

作者： Selvanathan, N. Ramya, S.R. Sureshkumar, C. Kiruthiga, R. Akshya, J. Choudhry, Mani Deepak Sundarrajan, M. Sona College of Technology Department of Information Technology Salem India Dr NGP Institute of Technology Department of Computer Science and Engineering Coimbatore India KGiSL Institute of Technology Department of Information Technology Coimbatore India Bannari Amman Institute of Technology Department of AI&DS Erode India SRM Institute of Science and Technology Department of Computational Intelligence Chennai India SRM Institute of Science and Technology Department of Computing Technologies Chennai India SRM Institute of Science and Technology Department of Networking and Communications Chennai India

ISBN: (纸本)9798350354171

Path planning and obstacle avoidance play a key role in how well autonomous mobile robots work and stay safe when they move through tricky areas. Traditional path-planning methods often can't keep up when new obstacles pop up or existing ones change, which makes them less useful in the real world. To fix these problems, the proposed research work brings in a new IoT-powered path planning and obstacle avoidance system that uses the D∗ Lite and Deep Reinforcement Learning (DRL) algorithms. Our approach brings together D∗ Lite's quick replanning skills with DRL's ability to learn and adapt made even better by live data from IoT sensors. We've put our model through its paces in different simulated environments set up to be as tricky as real-world navigation. Quantitative analysis shows it's a big step up from older models. Adding IoT data leads to a 30% boost in how paths are planned and cut the time robots need to get through complex routes by 20%. Plus, using DRL helps robots deal with moving obstacles 25% better, which means fewer potential crashes. This is a big step forward in the field of autonomous robotics. It gives a robust answer that would not just be reactive to the given environmental inputs but also, through proactivity, prompt possible obstacles, further contributing to smoother and safer output. As we move along with the development of our methodology, we foresee broad applications in many sectors enhancing the autonomy and efficiency of robotic systems working in dynamic and unpredictable environments. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

An Improved Cuttlefish Optimization Algorithm Based Faster R-CNN for Brain Tumour Detection 4

An Improved Cuttlefish Optimization Algorithm Based Faster R...

引用

4th International Conference on Smart Electronics and Communication, ICOSEC 2023

作者： Arunarani, A.R. Bhenia, Vedant Abirami, T. Aparna, N. Abul Ala Walid, Md. Sharada, K.A. School of Computing College of Engineering and Technology Srm Institute of Science and Technology Kattankulathur Campus Department of Computational and Intelligence Tamilnadu Chennai India Ips Academy Institute of Engineering and Science Department of Computer Science and Engineering Madhya Pradesh Indore India Kongu Engineering College Information Technology Tamilnadu Erode India Dhaanish Ahmed Institute of Technology Department of Biomedical Engineering Tamilnadu Coimbatore India Department of Computer Science and Engineering Khulna Bangladesh Hkbk College of Engineering Vtu Department of Cse Karnataka Bengaluru India

ISBN: (纸本)9798350300888

Brain tumor is caused due to the anomalous development of tissues in the brain. Precise identification of the tumor in premature stage is essential to provide effective medication and curtail further impact of the disease in affected individuals. This present research includes four main stages for the diagnosis of brain tumor including segmentation and classification based on deep learning approaches. The preprocessing stage makes use of filters to reduce the noise impact in the brain imagery. The segmentation stage is responsible to segment the tumor portions from the images using Enhanced Region Growth algorithm. Feature selection stage utilizes Improved Cuttlefish Optimization (ICO) algorithm to extricate the optimal features from the segmented images. The final stage is classification in which Faster R-CNN (FRCNN) algorithm is employed to categorize the brain images as tumor affected or not. BRA TS-2020 dataset is used for the experimental investigation of the proposed FRCNN-ICO method. Performance of this method is assessed using parameters such as Accurate Prediction Rate (APR), Imprecise Prediction Rate (IPR) and Imprecise Denial Rate (IDR). The proposed FRCNN-ICO produces the highest APR value of 99.2% compared to the existing researches on brain tumor detection and proves to perform superior than the methods considered for comparison purposes. © 2023 IEEE.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Unveiling Hidden Water Resources: Deep Learning and Remote Sensing for Subsurface Hydrology for Environmental Health

引用

Remote Sensing in Earth Systems sciences 2025年第2期8卷 352-364页

作者： Babu, Jampani Satish G, Dinesh Suganya, R. Radhakrishnan, P. Sutar, Anand S, Alex David Rao, L. Malleswara Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Guntur AP Vaddeswaram India Department of Computational Intelligence School of Computing SRM Institute of Science and Technology Kattankulathur (KTR) Chennai India Department of Computer Science and Engineering (Data Science) New Horizon College of Engineering Karnataka Bengaluru India Department of ECE Tagore Engineering College Chennai India Department of Electronics and Telecommunication Bharati Vidyapeeth College of Engineering Navi Mumbai India Department of Computer Science and Engineering Vel Tech Rangarajan Dr Sagunthala R & d Institute of Science and Technology Chennai India Department of Physics Sri Y N College (A) West Godavari District Andhra Pradesh Narsapur India

Water scarcity in arid regions necessitates innovative solutions to uncover and manage subsurface water resources for environmental health. This study explores the potential of GeoHydroNet, a specialized deep learning framework, in identifying hidden water resources within arid regions. Utilizing remote sensing data such as multispectral and hyperspectral imagery, geological maps, and soil moisture datasets, GeoHydroNet combines graph neural Networks (GNNs), AutoEncoders, and generative adversarial networks (GANs) to address challenges in subsurface hydrology. The model achieved an accuracy of 93.5%, surpassing traditional models like CNNs (85.4%), LSTMs (88.1%), and RNNs (82.6%). GeoHydroNet demonstrates significant precision (0.88), recall (0.87), and sensitivity to data imbalance (0.91). Its physics-informed learning approach incorporates hydrological principles, ensuring realistic predictions. By analyzing subsurface water patterns, recharge zones, and geological influences, the model not only enhances prediction accuracy but also aids in sustainable groundwater management. GeoHydroNet’s performance in identifying groundwater levels, with minimal errors ranging from 0.62 to 3.07%, indicates its robustness in tackling water scarcity challenges in data-constrained environments. These findings highlight its transformative role in hydrological modeling and sustainable water resource management in arid regions. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Aquifers Arid regions Deep learning Generative adversarial networks GeoHydroNet Physics-informed learning Remote sensing Subsurface hydrology Sustainable water management

来源：评论

学校读者我要写书评

暂无评论

Predicting Event Participation for an Event-Based Social Network

Predicting Event Participation for an Event-Based Social Net...

引用

2024 IEEE International Conference on technology Management, Operations and Decisions, ICTMOD 2024

作者： Seedath, Akshay Hosein, Nicholas Hosein, Patrick College of Computing and Engineering Georgia Institute of Technology Atlanta United States CEO VENZI Fort Lauderdale United States The University of the West Indies Department of Computer Science St. Augustine Trinidad and Tobago

ISBN: (纸本)9798350367355

Accurately predicting event attendance is essential for organizers to allocate resources, improve user experience, and ensure success. This study examines user engagement within the Venzi event-based social networking app by analyzing chat interactions, event views, and user applications and approvals. Key factors influencing attendance and turnout rate-the percentage of approved users who attend-are identified and used to build predictive models. We compare the performance of linear regression, XGBoost, and a specialized weighted distance model (Kappa). The analysis highlights the significance of user interaction metrics in forecasting event outcomes and provides actionable insights for organizers to enhance engagement strategies and optimize attendance. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

DISCRETE ENERGY ANALYSIS OF THE THIRD-ORDER VARIABLE-STEP BDF TIME-STEPPING FOR DIFFUSION EQUATIONS

引用

Journal of computational Mathematics 2023年第2期41卷 325-344页

作者： Hong-lin Liao Tao Tang Tao Zhou Department of Mathematics Nanjing University of Aeronautics and AstronauticsNanjing 211106China Key Laboratory of Mathematical Modelling and High Performance Computing of Air Vehicles(NUAA) MIITNanjing 211106China Division of Science and Technology BNU-HKBU United International CollegeZhuhai 519087China Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing100190China

This is one of our series works on discrete energy analysis of the variable-step BDF *** this part,we present stability and convergence analysis of the third-order BDF(BDF3)schemes with variable steps for linear diffusion equations,see,e.g.,[SIAM ***.,58:2294-2314]and[***.,90:1207-1226]for our previous works on the BDF2 *** this aim,we first build up a discrete gradient structure of the variable-step BDF3 formula under the condition that the adjacent step ratios are less than 1.4877,by which we can establish a discrete energy dissipation ***-robust stability and convergence analysis in the L^(2) norm are then *** the mesh robustness means that the solution errors are well controlled by the maximum time-step size but independent of the adjacent time-step *** also present numerical tests to support our theoretical results.

关键词： Diffusion equations Variable-step third-order BDF scheme Discrete gradient structure Discrete orthogonal convolution kernels Stability and convergence

来源：评论

学校读者我要写书评

暂无评论

Securing Neural Network in the Cloud: A Systematic Approach of Cloud Security Based on ANN-SVM Model 4

Securing Neural Network in the Cloud: A Systematic Approach ...

引用

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Arunarani, Ar Vijayagopal, V. Kartheesan, L. Dwivedi, Vijay Kumar Rajesh Kumar, A. Nishant, Neerav School of Computing College of Engineering Srm Institute of Science and Technology Department of Computational Intelligence Tamilnadu Chennai India Dr. M.G.R. Educational and Research Institute Faculty of Computer Applications Tamilnadu Chennai India School of Computing Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamilnadu Chennai India Vishwavidyalaya Engineering College Department of Mathematics Chhattisgarh Surguja India N.S.N. College of Engineering and Technology Department of Computer Science and Engineering Tamilnadu Karur India School of Engineering Babu Banarasi Das University Department of Computer Science and Engineering Lucknow India

ISBN: (纸本)9798331540364

Many services have made the transition to the cloud because of the increased reliability and efficiency of cloud computing. Due to their capacity to ease service access while also securing communications in the public network, the three-factor Mutual Authentication and Key Agreement (MAKA) protocols are seeing increased use in multi-server designs. A lack of formal security proof or high communication and computation costs makes the limited three-factor MAKA protocols that are currently available susceptible to a wide range of attacks. The proposed approach consists of three phases, which are preprocessing, feature selection, and model training. Text scheduling and normalization make up preprocessing. In feature selection, the PSO is an optimization method that uses a population-based approach to find optimal solutions. An ANN-SVM was employed throughout the model's training phase. With an average accuracy of 93.30%, the proposed technique surpasses ANN and SVM. © 2024 IEEE.

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

IoT-Enabled Precision Irrigation for Coconut Plantations: Enhancing Growth and Sustainability 8

IoT-Enabled Precision Irrigation for Coconut Plantations: En...

引用

8th International Conference on Electronics, Communication and Aerospace technology, ICECA 2024

作者： Reddy, M.Jaganmohan Ramu, V. Grace Shalini, T. Vincysahaba, R. Devaki, M. Athiraja, A. Telangana Secunderabad India Telangana Hanamkonda India Srm Institute of Science and Technology Kattankulathur School of Computing Department of Computational Intelligence Chengalpattu India St.Joseph College of Engineering Department of Artificial Intelligence and Data Science Tamil Nadu Chennai India Velammal College of Engineering and Technology Department of Eee Tamil Nadu Madurai India

ISBN: (纸本)9798350367904

In agriculture, precision irrigation plays a pivotal role in optimizing crop growth and resource utilization. In this study, must proposean Internet of Things based irrigation remote monitoring system tailored for enhancing coconut plant growth. The system integrates sensor technology, Internet of Things connectivity, and data analytics to provide real-time monitoring and control of irrigation parameters such as soilmoisture, temperature, and humidity. Leveraging a network of sensors deployed in the coconut plantation, the system collects and analyzes environmental data to optimize irrigation schedules and ensure optimal growing conditions for coconut plants. Through a user-friendly interface accessible via web or mobile applications, farmers can remotely monitor the status of their plantation and adjust irrigation settings as ***, the system incorporates predictive analytics capabilities to anticipate irrigation needs based on historical data and weather forecasts, thereby enhancing water efficiency and crop productivity. Field trials demonstrate the effectiveness of this Internet of Things based irrigation system in improving coconut plant growth while reducing water consumption and operational costs. This findings underscore the potential of Internet of Things technologies in revolutionizing agricultural practices, facilitating sustainable crop management, and enhancing food security in coconut-producing regions. © 2024 IEEE.

关键词： Precision agriculture

来源：评论

学校读者我要写书评

暂无评论

Inverse Reinforcement Learning with the Average Reward Criterion

arXiv

引用

arXiv 2023年

作者： Wu, Feiyang Ke, Jingyang Wu, Anqi School of Computational Science and Engineering College of Computing Georgia Institute of Technology AtlantaGA30332 United States School of Computer Science College of Computing Georgia Institute of Technology AtlantaGA30332 United States

We study the problem of Inverse Reinforcement Learning (IRL) with an average-reward criterion. The goal is to recover an unknown policy and a reward function when the agent only has samples of states and actions from an experienced agent. Previous IRL methods assume that the expert is trained in a discounted environment, and the discount factor is known. This work alleviates this assumption by proposing an average-reward framework with efficient learning algorithms. We develop novel stochastic first-order methods to solve the IRL problem under the average-reward setting, which requires solving an Average-reward Markov Decision Process (AMDP) as a subproblem. To solve the subproblem, we develop a Stochastic Policy Mirror Descent (SPMD) method under general state and action spaces that needs O(1/Ε) steps of gradient computation. Equipped with SPMD, we propose the Inverse Policy Mirror Descent (IPMD) method for solving the IRL problem with a O(1/Ε2) complexity. To the best of our knowledge, the aforementioned complexity results are new in IRL. Finally, we corroborate our analysis with numerical experiments using the MuJoCo benchmark and additional control tasks. © 2023, CC BY.

关键词： Mirrors

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Systems for Autonomous IoT Network Management Using Distributed Reinforcement Learning 3

Multi-Agent Systems for Autonomous IoT Network Management Us...

引用

3rd International Conference on Intelligent Systems, Advanced computing, and Communication, ISACC 2025

作者： Neelamegam, G. Venkatesan, Rajaram Ramya, S.R. Ramya, R.S. Akshya, J. Sundarrajan, M. Choudhry, Mani Deepak VSB College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Coimbatore India Builders Engineering College Department of Artificial Intelligence and Data Science Tamil Nadu Tirupur India Dr NGP Institute of Technology Department of Computer Science and Engineering Tamil Nadu Coimbatore India Sri Ramakrishna Engineering College Department of Computer Science and Engineering Tamil Nadu Coimbatore India SRM Institute of Science and Technology Department of Computational Intelligence Tamil Nadu Chennai India SRM Institute of Science and Technology Department of Networking and Communications Tamil Nadu Chennai India SRM Institute of Science and Technology Department of Computing Technologies Tamil Nadu Chennai India

ISBN: (纸本)9798331523893

The ever-growing complexity of IoT networks ignited by their wide scale adoption in applications such as smart cities, the industrial automation, and health care, compelled to develop sophisticated yet resource efficient and scalable network management solution. Centralized systems are traditional in architecture, which leads to higher latency and bottlenecks, while decentralized systems can distribute workloads however the lack of adaptability to real time, along with the difficulty of extracting maximum resource usage, are limitations. In recent years, reinforcement learning (RL) based approaches have taken shape as a promising alternative to facilitate the automated learning and optimisation of task management. However, there are two challenges for existing RL based methods: slow convergence, inefficient priority assignment of tasks, and poor coordination amongst agents in the case of dynamic, large scale IoT environment. To solve these challenges, in this research we propose a distributed reinforcement learning based multi agent framework for managing IoT network. The framework also integrates a task prioritization mechanism to dynamically choose an optimal task allocation solution. Further validation was performed in a simulated IoT environment where real world inspired datasets were used. The proposed framework demonstrated 30% more task throughput than centralized, 25% less latency than decentralized, and 40% more energy efficiency than current RL based systems. The system was further validated using advanced visualizations such as anomaly detection maps and resource allocation efficiency graphs, demonstrating its capacity to manage dynamic load of tasks and resource allocation. The proposed framework addresses the critical limitations of current methods, through scalable, adaptive, and energy efficient framework for managing IoT network, and accordingly helps advancing the intelligent and autonomous IoT systems. © 2025 IEEE.

关键词： Resource allocation

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：