检索结果-内蒙古大学图书馆

2023 International Conference on Evolutionary Algorithms and Soft Computing Techniques, EASCT 2023

作者： Khond, Smita Chythanya, Kanegonda Ravi Munawar, Shaik Mandava, Manjusha Kruthika, G.C. Malla Reddy Engineering College for Women It Department Hyderabad India Sr University School of Computer Science & Artificial Intelligence Warangal India Kakatiya Institute of Technology and Science Warangal India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Vaadeswaram India Nitte Meenakshi Institute of Technology Department of Ai and Ml Bengaluru India

ISBN: (纸本)9798350313413

This research presents an all-encompassing method for improving Narrow Band Internet of Things (NB-IoT) network performance by including network design, interference management, power control techniques, and security measures. Planning your network ahead of time is essential, and will involve decisions like network design, base station placement, and channel allocation. The second stage, interference control, seeks to reduce background noise emanating from various sources. The third and last stage is to use transmission power management algorithms for NB-IoT devices. In real-time, these algorithms optimize power levels for the channel and the task at hand. In the last stage, we apply security measures including authentication, encryption, and other types of network access control. According to the data, the suggested approach would have cost a total of $500,000, but more conventional approaches would have cost between $700,000 and $900,000. Also, the suggested method had an average delay of 1.5 seconds. © 2023 IEEE.

关键词： Interference management NB-IoT networks Network design Network Optimization Power control Security

来源：评论

学校读者我要写书评

暂无评论

SSL4Q: Semi-Supervised Learning of Quantum Data with Application to Quantum State Classification 41

SSL4Q: Semi-Supervised Learning of Quantum Data with Applica...

引用

41st International Conference on Machine Learning, ICml 2024

作者： Tang, Yehui Yang, Nianzu Long, Mabiao Yan, Junchi School of Artificial Intelligence Department of Computer Science and Engineering MoE Lab of AI Shanghai Jiao Tong University Shanghai China

The accurate classification of quantum states is crucial for advancing quantum computing, as it allows for the effective analysis and correct functioning of quantum devices by analyzing the statistics of the data from quantum measurements. Traditional supervised methods, which rely on extensive labeled measurement outcomes, are used to categorize unknown quantum states with different properties. However, the labeling process demands computational and memory resources that increase exponentially with the number of qubits. We propose SSL4Q, manage to achieve (for the first time) semi-supervised learning specifically designed for quantum state classification. SSL4Q’s architecture is tailored to ensure permutation invariance for unordered quantum measurements and maintain robustness in the face of measurement uncertainties. Our empirical studies encompass simulations on two types of quantum systems: the Heisenberg Model and the Variational Quantum Circuit (VQC) Model, with system size reaching up to 50 qubits. The numerical results demonstrate SSL4Q’s superiority over traditional supervised models in scenarios with limited labels, highlighting its potential in efficiently classifying quantum states with reduced computational and resource overhead. Copyright 2024 by the author(s)

关键词： Qubits

来源：评论

学校读者我要写书评

暂无评论

AquaRescue: Intelligent Drowning Detection and Swift Rescue System Using Integrated Approach

AquaRescue: Intelligent Drowning Detection and Swift Rescue ...

引用

Technological Advancements in Computational sciences (ICTACS), International Conference on

作者： Rakshitha P. Sowmya Rashmitha Shettigar N. Nishanth Durgaprasad Dhanush Kumar Department of AI&ML NITTE (Deemed to be University) NMAM Institute of Technology (NMAMIT) NITTE India Department of Computer Science and Engineering Nitte (Deemed to be University) NMAM Institute of Technology (NMAMIT) Nitte India Department of B.sc (IT)/CS Thakur Ramnarayan College of Arts and Commerce East Mumbai India Department of AI&ML NITTE (Deemed to be University) NMAM Institute of Technology (NMAMIT) Nitte India

ISBN: (数字)9798350387490

ISBN: (纸本)9798350387506

Drowning accidents, in pools continue to be a concern calling for creative solutions to improve safety standards. The research aims to establish a framework for identifying and saving drowning cases in pools. Cutting-edge technologies such as computer vision, Artificial Intelligence, and IoT are integrated into the system to quickly and precisely recognize incidents and trigger rescue operations. Utilizing cameras and advanced algorithms like YOLO v3 and CNN, the system continuously observes the pool environment. By assessing people's movements and locations in the water, it accurately detects drowning cases. Once an incident is identified, the system automatically starts rescue procedures by dispatching rescue tools and notifying lifeguards with alarms across the pool premises. Moreover, it enables emergency calls through GSM SIM900A module in case the lifeguard is not present nearby. This innovative detection and rescue system not only enhances swimmer safety but also reduces the workload on lifeguards, allowing them to react more effectively in emergencies. The ultimate goal of this system, driven by technological advancements, is to minimize drowning incidents in pools. The system's performance has been evaluated against other models like Faster R-CNN, YOLO v3, and SSD. YOLO v3 demonstrated superior accuracy of 90% with combined datasets (GF-1 & GF -2).

关键词： YOLO GSM System performance Machine learning Emergency services Public security Time factors Mirrors Standards Accidents

来源：评论

学校读者我要写书评

暂无评论

Temporal-Aware Deep Reinforcement Learning for Energy Storage Bidding in Energy and Contingency Reserve Markets

IEEE Transactions on Energy Markets, Policy and Regulation

引用

IEEE Transactions on Energy Markets, Policy and Regulation 2024年第3期2卷 392-406页

作者： Li, Jinhao Wang, Changlong Zhang, Yanru Wang, Hao Monash University Department of Data Science and AI Faculty of IT and Monash Energy Institute MelbourneVIC3800 Australia Monash University Department of Civil Engineering MelbourneVIC3800 Australia University of Electronic Science and Technology of China School of Computer Science and Engineering Chengdu611731 China

The battery energy storage system (BESS) has immense potential for enhancing grid reliability and security through its participation in the electricity market. BESS often seeks various revenue streams by taking part in multiple markets to unlock its full potential, but effective algorithms for joint-market participation under price uncertainties are insufficiently explored in the existing research. To bridge this gap, we develop a novel BESS joint bidding strategy that utilizes deep reinforcement learning (DRL) to bid in the spot and contingency frequency control ancillary services (FCAS) markets. Our approach leverages a transformer-based temporal feature extractor to effectively respond to price fluctuations in seven markets simultaneously and helps DRL learn the best BESS bidding strategy in joint-market participation. Additionally, unlike conventional 'black-box' DRL model, our approach is more interpretable and provides valuable insights into the temporal bidding behavior of BESS in the dynamic electricity market. We validate our method using realistic market prices from the Australian National Electricity Market. The results show that our strategy outperforms benchmarks, including both optimization-based and other DRL-based strategies, by substantial margins. Our findings further suggest that effective temporal-aware bidding can significantly increase profits in the spot and contingency FCAS markets compared to individual market participation. © 2023 IEEE.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

Specifying Goals to Deep Neural Networks with Answer Set Programming 34

Specifying Goals to Deep Neural Networks with Answer Set Pro...

引用

34th International Conference on Automated Planning and Scheduling, ICAPS 2024

作者： Agostinelli, Forest Panta, Rojina Khandelwal, Vedant AI Institute University of South Carolina United States Department of Computer Science and Engineering University of South Carolina United States

ISBN: (纸本)9781577358893

Recently, methods such as DeepCubeA have used deep reinforcement learning to learn domain-specific heuristic functions in a largely domain-independent fashion. However, such methods either assume a predetermined goal or assume that goals will be given as fully-specified states. Therefore, specifying a set of goal states to these learned heuristic functions is often impractical. To address this issue, we introduce a method of training a heuristic function that estimates the distance between a given state and a set of goal states represented as a set of ground atoms in first-order logic. Furthermore, to allow for more expressive goal specification, we introduce techniques for specifying goals as answer set programs and using answer set solvers to discover sets of ground atoms that meet the specified goals. In our experiments with the Rubik's cube, sliding tile puzzles, and Sokoban, we show that we can specify and reach different goals without any need to re-train the heuristic function. Our code is publicly available at https://***/forestagostinelli/SpecGoal. Copyright © 2024, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Failure Analysis of IoT-based Smart Agriculture System: Towards Sustainable Food Security 5

Failure Analysis of IoT-based Smart Agriculture System: Towa...

引用

5th International Conference on Sustainable Technologies for Industry 5.0, STI 2023

作者： Rahman, Md Mokhlesur Abdulhamid, Alhassan Kabir, Sohag Gope, Prosanta Military Institute of Science and Technology Department of Computer Science and Engineering Bangladesh School of Computer Science Ai and Electronics University of Bradford United Kingdom University of Sheffield Department of Computer Science United Kingdom

ISBN: (纸本)9798350394290

Internet of Things (IoT)-based smart agriculture systems are increasingly being used to improve agricultural yield. IoT devices used for agricultural monitoring are often deployed in outdoor environments in remote areas. Due to the exposure to harsh environments and the nature of deployment, sensors and other devices are susceptible to an increased rate of failure, which can take a system to unsafe and dangerous states. Failure of a smart agriculture system can cause significant harm to nature and people and reduce agricultural production. To address the concerns associated with the failure of the system, it is necessary to understand how the failures of the components of a system can contribute to causing the overall system failure. This paper adopts Fault Tree Analysis, a widely used framework for failure behaviour analysis in other safety-critical domains, to demonstrate the qualitative failure analysis of smart irrigation systems based on the components' failure. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Learning Divergence Fields for Shift-Robust Graph Representations 41

Learning Divergence Fields for Shift-Robust Graph Representa...

引用

41st International Conference on Machine Learning, ICml 2024

作者： Wu, Qitian Nie, Fan Yang, Chenxiao Yan, Junchi School of Artificial Intelligence Department of Computer Science and Engineering MoE Lab of AI Shanghai Jiao Tong University Shanghai China

Real-world data generation often involves certain geometries (e.g., graphs) that induce instance-level interdependence. This characteristic makes the generalization of learning models more difficult due to the intricate interdependent patterns that impact data-generative distributions and can vary from training to testing. In this work, we propose a geometric diffusion model with learnable divergence fields for the challenging generalization problem with interdependent data. We generalize the diffusion equation with stochastic diffusivity at each time step, which aims to capture the multi-faceted information flows among interdependent data. Furthermore, we derive a new learning objective through causal inference, which can guide the model to learn generalizable patterns of interdependence that are insensitive across domains. Regarding practical implementation, we introduce three model instantiations that can be considered as the generalized versions of GCN, GAT, and Transformers, respectively, which possess advanced robustness against distribution shifts. We demonstrate their promising efficacy for out-of-distribution generalization on diverse real-world datasets. Source codes are available at https://***/fannie1208/GLIND. Copyright 2024 by the author(s)

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Federated Learning Methods for Privacy-Preserving Collaborative Machine Learning 10

Federated Learning Methods for Privacy-Preserving Collaborat...

引用

10th IEEE Uttar Pradesh Section International Conference on Electrical, Electronics and computer engineering, UPCON 2023

作者： Nagender, Y. Deena, S. Imran, Shaik Mohammed Singh, Navdeep Anuradha, R. Kapila, Dhiraj School of Cs & Ai Sr University Telangana Warangal India Rmd Engineering College Department of Computer Science and Business Systems Kavarapettai India Cse Ai& Ml Mal1a Reddy Engineering College for Women India Lovely Professional University Phagwara India Institute of Aeronautical Engineering Hyderabad Dundigal India Lovely Professional University Department of Computer Science & Engineering Phagwara India

ISBN: (纸本)9798350382471

Federated learning is a cutting-edge data solution that protects privacy as well as a fresh machine learning model developed on collaborative data sets. A major concern privacy protection aspect of machine learning has proven quite successful. The PFmlP framework, which is based on federated learning as well as collaborative machine learning, is presented in this paper for multi-party safeguarding privacy machine learning. All learning partners ought to send only homomorphic encrypted gradients, according to the basic idea. According to experiments, the PFmlP-trained model almost always achieves the same accuracy, with a variance of less than 1.%. The upcoming privacy-preserving data technology and a fresh category of distributed learning models, federated learning, were both invented by Google. In this research, we examine distributed ml applied to dispersed data sets and federated learning as an option for privacy-preserving data access. Additionally, a federated learning architecture that protects privacy is presented. © 2023 IEEE.

关键词： Federated learning Machine learning Privacy Preserving

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Transmission in Wireless Networks Using Resnet with Gravitational Search Algorithm 2

Energy-Efficient Transmission in Wireless Networks Using Res...

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Rajakumari, S. Hc, Kantharaju Ahmad, Shadab Sharma, Rupa Rani Sudha, S. Ramesh, T. R.M.D. Engineering College Department of Mathematics India Vemana Institute of Technology Department of Ai & Ml Karnataka Bengaluru India Samara University Department of Electrical and Computer Engineering Afar region Ethiopia G.L Bajaj Institute of Technology and Management Department of Applied Science Uttar Pradesh Greater Noida India Sri Ranganathar Institute of Engineering and Technology Department of Ece Tamilnadu Coimbatore India R.M.K Engineering College Department of Computer Science and Engineering India

ISBN: (纸本)9798350371055

Although wireless networks are extremely important in modern communication, one of the most significant challenges they face is the quantity of energy that they use. Within this study, a new way of sending data over wireless networks is suggested. The gravitational search algorithm (GSA) and residue networks of the ResNet type are used together in this method. By using wireless networks, the main goal of this method is to find answers to problems that come up with using energy more efficiently. The creation and use of a hybrid ResNet-GSA model for wireless communication is one of the most important parts of our method. Because it follows the rules of gravity, GSA can quickly look through the solution space to find the right parameter values. At the same time, the network works better when the deep learning features of ResNet are used. The results of our research show that there are big improvements in how much energy is used compared to using traditional ways. If you want to cut down on the amount of energy used, the ResNet-GSA strategy that was suggested also works well. The findings demonstrate that optimisation techniques and deep learning methodologies are not only compatible with one another but also perform effectively together to make wireless networks more environmentally friendly. © 2024 IEEE.

关键词： Energy Efficiency Gravitational Search Algorithm Residual Networks Transmission Optimization

来源：评论

学校读者我要写书评

暂无评论

Empirical Method for Rice Grain Variety Classification

Empirical Method for Rice Grain Variety Classification

引用

Communication & Computing (WCONF), World Conference on

作者： R Ravi Kumar Bhagya Sri G K Sridhar Nagurla Mahender M. Babu Reddy Sallauddin Mohmmad School of Computer Science and Artificial Intelligence SR University Warangal Telangana India Department of CSE(AI&ML) CVR College of Engineering Hyderabad Telangana India Vaageswari College of Engineering Karimnager Telangana India Computer Science Krishna University Machilipatnam AP India

ISBN: (数字)9798350395327

ISBN: (纸本)9798350395334

Rice is grown extensively worldwide and displays a wide genetic diversity., resulting in a variety of traits and characteristics across different types. In order to achieve realistic Rice Grain Classification., this research compared the use of Vgg19., MobileNet., MobileNet v2., CNN and DensNet algorithms. The data set used in this study collected from various data repositories such as kaggle.,GitHub.,VNMN and etc. The dataset comprises a total of 10.,000 high-resolution images of rice grains., with each image labeled according to its corresponding rice variety. The dataset included five distinct rice varieties: Akura., 1001., Konaram., MTU-64., and RNR. Each rice variety is represented by 2.,000 images in the dataset. Then CNN., Vgg19., MobileN et., MobileN et v2 and DensN et are trained and assessed using the enhanced dataset. Our research results revealed successful result with DenseN et emerging as the top performer., achieving an impressive accuracy of 96.87%. Following closely behind., MobileNet V2 demonstrated notable proficiency with a classification accuracy of 94.60%., while MobileNet and VGG 19 attained accuracies of 94 % and 90%., respectively.

关键词： Accuracy Computational modeling Food security Crops computer architecture Quality control Genetics Agriculture Classification algorithms

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：