检索结果-内蒙古大学图书馆

Supervised Machine Learning Strategy for detection of covid19 patients

学校读者我要写书评

暂无评论

Supervised Machine Learning Strategy for detection of covid1...

2023 International Conference on Artificial Intelligence and knowledge Discovery in Concurrent engineering, ICECONF 2023

作者： Punithavathi, I.S. Hephzi Deepa, K. Rao, Cheruku Poorna Venkata Srinivasa Gopal, S. Raja Rajasekar, P. Kumar, Ashok Department of Artificial Intelligence Vidya Jyothi Institute of Technology Telagana Hyderabad500075 India Department of Computer Science and Artificial Intelligence Sr University Kavaraipettai Telangana Hasanparthy India Department of Information Technology Laki Reddy Balireddy College of Engineering Andhra Pradesh Mylavaram521230 India Department of Electronics and Communication Engineering KoneruLakshmaiah Education Foundation Andhra Pradesh Vaddeswaram522302 India Department of Data Science and Business Systems SRM Institute of Science and Technology Tamil Nadu Kattankulathur603203 India Department of Computer Science Banasthali Vidyapith Rajasthan304022 India

ISBN: (纸本)9798350334357

The current severe acute respiratory syndrome corona virus 2 (SARS-CoV-2) public health catastrophe, both human lives have been lost and the economy has disrupted severely the current scenario. In this paper, we develop a detection module using a series of steps that involves pre-processing, feature extraction and detection of covid-19 patients based on the images collected from the computerized tomography (CT) images. The images are initially pre-processed and then the features are extracted using Gray Level Co-occurrence Matrix (GLCM) and then finally classified using back propagation neural network (BPNN). The simulation is conducted to test the efficacy of the model against various CT image datasets of numerous patients. The results of simulation shows that the proposed method achieves higher detection rate, and reduced mean average percentage error (MAPE) than other existing methodologies. © 2023 IEEE.

关键词： SARS

ReSync: Riemannian Subgradient-based Robust Rotation Synchronization

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liu, Huikang Li, Xiao So, Anthony Man-Cho School of Information Management and Engineering Shanghai University of Finance and Economics China School of Data Science The Chinese University of Hong Kong Shenzhen China Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Hong Kong

This work presents ReSync, a Riemannian subgradient-based algorithm for solving the robust rotation synchronization problem, which arises in various engineering applications. ReSync solves a least-unsquared minimization formulation over the rotation group, which is nonsmooth and nonconvex, and aims at recovering the underlying rotations directly. We provide strong theoretical guarantees for ReSync under the random corruption setting. Specifically, we first show that the initialization procedure of ReSync yields a proper initial point that lies in a local region around the ground-truth rotations. We next establish the weak sharpness property of the aforementioned formulation and then utilize this property to derive the local linear convergence of ReSync to the ground-truth rotations. By combining these guarantees, we conclude that ReSync converges linearly to the ground-truth rotations under appropriate conditions. Experiment results demonstrate the effectiveness of ReSync. Copyright © 2023, The Authors. All rights reserved.

关键词： Rotation

Machine Learning Heart Disease Prediction Using KNN and RTC Algorithm 3

学校读者我要写书评

暂无评论

Machine Learning Heart Disease Prediction Using KNN and RTC ...

3rd International Conference on Power, Energy, Control and Transmission systems, ICPECTS 2022

作者： Senthil, G.A. Prabha, R. Razmah, M. Veeramakali, T. Sridevi, S. Yashini, R. Agni College of Technology Dept of Information Technology Chennai India Sri Sai Ram Institute of Technology Dept of Electronics and Communication Engineering Chennai India School of Computing SRM Institute of Science and Technology Dept of Data Science and Business Systems Chennai India Sri Ramachandra Engineering and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9781665462754

Heart Disease or cardiovascular disease refers to the range of heart conditions like cardiac arrest, coronary artery disease. Heart disease can be very well hindered through certain lifestyle changes. There is a significant increase in the mortality rate recently due to the distinctive heart diseases. Machine learning uses mathematical models to work efficiently with the enormous amount of data. It plays a crucial role in medical science in the prediction of distinctive diseases. Cardiologists inspects the heart functionality using electrocardiography, computed tomography. These tests are quite expensive for a common man. Recent times, the life span of a human is guaranteed only with the support of medications. As prevention is better than the cure, machine learning helps to predict the vulnerability of a heart disease with few elemental symptoms and health factors. It is been fed by the basic data of the patients like age, sex. Machine learning helps to predict the vulnerability in advance which provides the cardiologists with great acumen for the adaption of the treatment. Machine learning algorithms have proven to produce reliable and accurate output with the help of the inputs. The algorithms used in the article include KNN and decision tree classifier which is compared to yield the desired and efficient output. © 2022 IEEE.

关键词： Heart

Crowd tracking and monitoring middleware via Map-Reduce

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Gazis, Alexandros Katsiri, Eleftheria Department of Electrical and Computer Engineering School of Engineering Democritus University of Thrace Xanthi Greece Institute for the Management of Information Systems Athena Research Innovation Center in Information Communication & Knowledge Technologies Marousi Greece

This paper presents the design, implementation, and operation of a novel distributed fault-tolerant middleware. It uses interconnected WSNs that implement the MapReduce paradigm, consisting of several low-cost and low-power mini-computers (Raspberry Pi). Specifically, we explain the steps for the development of a novice, fault-tolerant Map-Reduce algorithm which achieves high system availability, focusing on network connectivity. Finally, we showcase the use of the proposed system based on simulated data for crowd monitoring in a real case scenario, i.e., a historical building in Greece (M. Hatzidakis' residence). The technical novelty of this article lies in presenting a viable low-cost and low-power solution for crowd sensing without using complex and resource-intensive AI structures or image/video recognition techniques. © 2022, CC BY.

关键词： Middleware

RIS-Assisted Passive Localization (RAPL): An Efficient Zero-Overhead Framework Using Conditional Sample Mean

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Yao, Jiawei Mao, Yijie Chen, Mingzhe Hu, Ye School of Information Science and Technology ShanghaiTech University Shanghai201210 China Department of Electrical and Computer Engineering Frost Institute for Data Science and Computing University of Miami Coral GablesFL33146 United States Department of Industrial and Systems Engineering University of Miami Coral GablesFL33146 United States

Reconfigurable Intelligent Surface (RIS) has been recognized as a promising solution for enhancing localization accuracy. Traditional RIS-based localization methods typically rely on prior channel knowledge, beam scanning, and pilot-based assistance. These approaches often result in substantial energy and computational overhead, and require real-time coordination between the base station (BS) and the RIS. To address these challenges, in this work, we move beyond conventional methods and introduce a novel data-driven, multiple RISs-assisted passive localization approach (RAPL). The proposed method includes two stages, the angle-of-directions (AoDs) between the RISs and the user is estimated by using the conditional sample mean in the first stage, and then the user’s position is determined based on the estimated multiple AoD pairs in the second stage. This approach only utilizes the existing communication signals between the user and the BS, relying solely on the measurement of received signal power at each BS antenna for a set of randomly generated phase shifts across all RISs. Moreover, by obviating the need for real-time RIS phase shift optimization or user-to-BS pilot transmissions, the method introduces no additional communication overhead, making it highly suitable for deployment in real-world networks. The proposed scheme is then extended to multi-RIS scenarios considering both parallel and cascaded RIS topologies. Numerical results show that the proposed RAPL improves localization accuracy while significantly reducing energy and signaling overhead compared to conventional methods. Copyright © 2025, The Authors. All rights reserved.

关键词： Image coding

Joint Multi-grained Popularity-aware Graph Convolution Collaborative Filtering for Recommendation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Liu, Kang Xue, Feng He, Xiangnan Guo, Dan Hong, Richang The School of Computer Science and Information Engineering Key Laboratory of Knowledge Engineering with Big Data Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Anhui Hefei China The School of Software Key Laboratory of Knowledge Engineering with Big Data Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Anhui Hefei China The University of Science and Technology of China Anhui Hefei China

Graph Convolution Networks (GCNs), with their efficient ability to capture high-order connectivity in graphs, have been widely applied in recommender systems. Stacking multiple neighbor aggregation is the major operation in GCNs. It implicitly captures popularity features because the number of neighbor nodes reflects the popularity of a node. However, existing GCN-based methods ignore a universal problem: users’ sensitivity to item popularity is differentiated, but the neighbor aggregations in GCNs actually fix this sensitivity through Graph Laplacian Normalization, leading to suboptimal personalization. In this work, we propose to model multi-grained popularity features and jointly learn them together with high-order connectivity, to match the differentiation of user preferences exhibited in popularity features. Specifically, we develop a Joint Multi-grained Popularity-aware Graph Convolution Collaborative Filtering model, short for JMP-GCF, which uses a popularity-aware embedding generation to construct multi-grained popularity features, and uses the idea of joint learning to capture the signals within and between different granularities of popularity features that are relevant for modeling user preferences. Additionally, we propose a multistage stacked training strategy to speed up model convergence. We conduct extensive experiments on three public datasets to show the state-of-the-art performance of JMP-GCF. Copyright © 2022, The Authors. All rights reserved.

关键词： Convolution

Location-Based Scene Reconstruction for Long-Tail Recognition 8

学校读者我要写书评

暂无评论

Location-Based Scene Reconstruction for Long-Tail Recognitio...

8th IEEE International Conference on Computer and Communications, ICCC 2022

作者： Yang, Jiaxin Li, Xiaofei Zhang, Weiqi Hu, Tao Zhang, Jun Li, Shuohao Laboratory for Big Data and Decision National University of Defense Technology Changsha City China National University of Defense Technology Scientific Research Department Changsha City China The Science and Technology on Information Systems Engineering Laboratory National University of Defense Technology Changsha City China

ISBN: (纸本)9781665450515

Real-world data often exhibit a long-tailed distribution with severe class imbalance. In such cases, the majority class dominates the deep learning training, which changes the decision boundary of the minority class and reduces the classification accuracy. In this paper, we propose a novel location-based scene reconstruction(LSR) data augmentation method for long-tail recognition. This approach uses a gradient localization method to increase the scenes of tail class samples and enhance the discrimination of the model between head and tail classes, thus the accuracy of long-tail recognition is improved. Experiments on two benchmark datasets show that the LSR method achieves state-of-the-art performance on the long-tail recognition task. More importantly, our method can be easily combined with other classification methods and improves the performance of these traditional classification methods © 2022 IEEE.

关键词： Benchmarking

Adaptive Student Inference Network for Efficient Single Image Super-Resolution

学校读者我要写书评

暂无评论

Adaptive Student Inference Network for Efficient Single Imag...

IEEE International Conference on data Mining (ICDM)

作者： Kang Miao Zhao Zhang Jiahuan Ren Mingbo Zhao Haijun Zhang Richang Hong School of Computer Science and Information Engineering Hefei University of Technology Hefei China Key Laboratory of Knowledge Engineering with Big Data (Ministry of Education) & Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei China Yunnan Key Laboratory of Software Engineering Kunming China School of Information Science and Technology Donghua University Shanghai China Department of Computer Science Harbin Institute of Technology (Shenzhen) Shenzhen China

Recent advances in single image super-resolution (SISR) have achieved remarkable performance through deep learning. However, the high computational cost hinders the deployment of SISR models on edge devices. Instead of proposing new SISR models, a new trend is emerging to improve network efficiency by reducing parameters, FLOPs, and inference time through slight modifications to the original models. However, recent methods usually focus on reducing only one of three metrics, i.e., FLOPs, parameters and inference time, which inevitably increases the other two metrics. In this paper, we propose a novel Adaptive Student Inference Network (ASIN) on popular SISR models, which aims at reducing FLOPs and inference time while maintaining the number of parameters and restoring clearer high-resolution images. Specifically, our ASIN divides a SISR model into three components (head, body and tail) and adopts various strategies for each part. For head and tail parts, to ensure the restored images contain more detailed information, a novel auxiliary Enhanced Teacher Network (ETNet) is designed, which is trained with the ground-truth images to obtain more prior knowledge to guide student network to extract more accurate textures using a new knowledge distillation method. For the body part, owing to the varying difficulties of the reconstructions in different regions, we propose an Adaptive Depth Predicted Module (ADPM) to dynamically shorten average depth of network to reduce the computational cost of overall network. Extensive experiments on two datasets demonstrate the effectiveness and state-of-the-art performance of our ASIN compared to its counterparts.

关键词：

Leveraging Instruction-based Learning for Effective UAV Traffic Management in Dynamic Environment

学校读者我要写书评

暂无评论

Leveraging Instruction-based Learning for Effective UAV Traf...

Multi-Agent systems for Collaborative Intelligence (ICMSCI), International Conference on

作者： R.S. Ramya Keren Lois Daniel S. Rajkumar Sruthi S Madhavan Akshya. J Mani Deepak Choudhry Department of Computer Science and Engineering Sri Ramakrishna Engineering College Coimbatore Department of Computer Science and Business Systems KGiSL Institute of Technology Coimbatore Department of Information Technology Sona College of Technology Salem Department of Artificial Intelligence and Data Science Nehru Institute of Engineering and Technology Coimbatore Department of Computational Intelligence SRM Institute of Science and Technology Chennai Department of Computing Technologies SRM Institute of Science and Technology Chennai

ISBN: (数字)9798331509828

ISBN: (纸本)9798331509835

With the popularization of UAVs (Unmanned Aerial Vehicles) in surveillance, delivery services, environmental monitoring, and increasingly other operational aspects, besides the need to take off and land, efficient traffic management becomes integral for assuring and securing further development and exploitation. Most of the existing traffic management systems for UAVs depend on traditional rule-based algorithms or simpler machine learning techniques, such as DQN or PPO. However, these systems also have enormous challenges: dynamic environments, high-density traffic, and robust decision-making over unpredictable weather and network conditions. In addition, the above traditional models usually experience difficulties in balancing exploration and exploitation, leading to suboptimal routing and enlarged collision risks in complicated urban airspaces. These challenges have driven us to develop a new proposal: a UA V traffic management framework based on Double Deep Q-Network (DDQN) combined with Instruction-Based Learning. In this approach, advanced learning for DDQN optimizes processes at decision-making points for UAVs. The model proposed herein, along with comprehensive simulations and quantitative analyses, demonstrated higher performance in terms of leadership and cumulative rewards while keeping lower training loss compared to the classical algorithms such as DQN, A3C, and PPO. At the same time, the DDQN model presented a better success rate (95%), as also reflected in the balanced precision-recall curve showing an area under the curve of 0.90, over others in the on-point prediction of UAVstate and safety margin of collision. Our experimental results demonstrate that the proposed DDQN-based framework significantly enhances UA V traffic management by optimizing energy consumption in complex airspaces and reducing the risk of collision.

关键词： Training Analytical models Adaptation models Statistical analysis Atmospheric modeling Computational modeling Decision making Predictive models Autonomous aerial vehicles Safety