检索结果-内蒙古大学图书馆

International Conference on science Technology engineering and Management (ICONSTEM)

作者： M. Beula Kutti T. Karthick Department of computer science and Engineering SRMIST Kattankulathur Chennai India Department of Datascience and Business system SRMIST Kattankulathur School of Computing Chennai India

ISBN: (数字)9798350365092

ISBN: (纸本)9798350365108

Effective identification and severity analysis of two serious respiratory diseases-pneumonia and corona-are desperately needed, and this study attempts to fill that gap. Early diagnosis and treatment of many conditions depend critically on prompt intervention. Diagnoses are made slowly and subjectively by existing procedures, which frequently rely on human interpretation of medical imaging data. The existing methods for severity analysis do not have a cohesive structure. Our study presents an all-encompassing strategy to get around these restrictions. First, to improve the quality of the images, grayscale-based pre-processing is applied. Next, marker-based watershed segmentation is used to precisely locate anomalies. Feature extraction and categorization are done using a convolutional neural network, or CNN. Specifically, for severity analysis, we optimize the CNN parameters by including the Wolf Optimization Algorithm (WOA). Grayscale pre-processing guarantees the best possible picture quality; marker-based watershed segmentation improves the accuracy of lesion identification; CNN streamlines feature extraction; and WOA supports the study of disease severity. Python is used in the study's implementation, which takes advantage of its many machine learning frameworks and tools. The outcomes show how well the suggested methodology works for precisely identifying and evaluating the levels of corona and pneumonia. By integrating WOA with CNN, the shortcomings of current techniques are addressed and diagnostic accuracy and severity evaluation are improved. When compared to alternative approaches like CNN-SVM, Bayesian CNN, DCNN with BPNN, the suggested CNN with WOA (99.3%) shows an average accuracy gain of about 11.68%, demonstrating higher performance in disease diagnosis and severity analysis. This innovative method offers a methodical and effective framework for better patient treatment, which has the potential to advance the field of respiratory disease diagnostics.

关键词： Training Learning systems Accuracy Pneumonia Watersheds Corona Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An In-Depth Study of Cybersecurity Threats and Intelligent Broadcasting Network Topology 1

An In-Depth Study of Cybersecurity Threats and Intelligent B...

引用

1st IEEE International Interdisciplinary Humanitarian Conference for Sustainability, IIHC 2022

作者： Chauhan, Usha Gupta, Manali Galgotias University Department of Electrical Electronics and Communication Engineering Uttar Pradesh Greater Noida India Noida Institute of Engineering and Technology Department of Computer Science and Business System Uttar Pradesh Greater Noida India

ISBN: (纸本)9781665456876

The smart grid has stacked ICT power equipment. Smart grids use modern electrical sensors. Future adoption of smart devices and their interaction with networks may offer cyberthreats. Several smart grid subsystems may be exposed if a component doesn't respond in real time, reducing efficiency and reliability. Superannuated networks create cyber security risks. This article explores a secure cyber infrastructure, related breakthroughs, and cyber security concerns in a complex system. Cybersecurity goals, objectives, and risk assessments are complete. These papers are summarized. Prioritize security. Then, examine smart grid hacks to uncover weaknesses and their repercussions. This research designed a cyber-security plan for breaches, counterattacks, and actions. Future research is discussed. © 2022 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Leveraging Predictive Maintenance for Photovoltaic systems 9th

Leveraging Predictive Maintenance for Photovoltaic Systems

引用

9th International Conference on Smart City Applications, SCA 2024

作者： Ledmaoui, Younes Raif, Mourad El Aroussi, Mohamed Saadane, Rachid Jakimi, Abdeslam Chehri, Abdellah Laboratory Engineering System Hassania School of Public Works Casablanca Morocco Software Engineering and Information Systems Engineering Team FST of Errachidia Moulay Ismail University Meknes Morocco Department of Mathematics and Computer Science Royal Military College of Canada KingstonONK7K 7B4 Canada

ISBN: (纸本)9783031886522

This paper introduces a novel edge device architecture designed to optimize solar energy management systems. It integrates cutting-edge functionalities such as generation prediction, maintenance alerts, and anomaly detection into a unified framework. Through the utilization of edge computing, the system enables real-time analysis and decision-making at the network’s edge. Leveraging machine learning algorithms and predictive models, these edge devices provide highly accurate energy generation forecasts, facilitating efficient energy utilization and strategic planning. Additionally, the architecture incorporates anomaly detection techniques to proactively identify deviations from normal operation, minimizing downtime and enabling timely maintenance interventions. The seamless integration of these features within the edge devices significantly enhances the overall efficiency, reliability, and performance of energy monitoring systems. By adopting this advanced edge device architecture, energy stakeholders can reap benefits such as improved energy management, reduced operational costs, and enhanced system reliability. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Battery management systems

来源：评论

学校读者我要写书评

暂无评论

Prediction of Solar Energy Production Using Low-Cost Data Logger and ANN Algorithm 9th

Prediction of Solar Energy Production Using Low-Cost Data L...

引用

9th International Conference on Smart City Applications, SCA 2024

作者： Raif, Mourad Ledmaoui, Younes El Aroussi, Mohamed Saadane, Rachid Jakimi, Abdeslam Chehri, Abdellah Laboratory Engineering System Hassania School of Public Works Casablanca Casablanca Morocco Software Engineering and Information Systems Engineering Team FST of Errachidia Moulay Ismail University Meknes Morocco Department of Mathematics and Computer Science Royal Military College of Canada KingstonONK7K 7B4 Canada

ISBN: (纸本)9783031886522

This article introduces a novel method for predicting solar energy production using an affordable data logger and the Artificial Neural Network (ANN) algorithm. The main goal of this research is to create a precise predictive model for solar energy output, addressing the critical need for accurate forecasting in the renewable energy industry. The study capitalizes on the accessibility and cost-efficiency of a low-cost data logger to collect detailed environmental and solar irradiance data. The ANN algorithm is utilized to analyze the collected dataset, providing a robust and effective approach for forecasting solar energy production. Extensive experiments demonstrate that the developed model achieves an impressive R2 score of 0.95, indicating a high degree of accuracy and reliability in predicting solar energy output. This significant R2 score highlights the proposed methodology’s effectiveness, demonstrating its potential for practical applications in solar energy planning and management. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： data logger Machine learning Photovoltaic prediction Renewable energy

来源：评论

学校读者我要写书评

暂无评论

Intelligent Medical Diagnostic system for Hepatitis B

引用

computers, Materials & Continua 2022年第12期73卷 6047-6068页

作者： Dalwinder Singh Deepak Prashar Jimmy Singla Arfat Ahmad Khan Mohammed Al-Sarem Neesrin Ali Kurdi Lovely Professional University Punjab144402India College of Computing Khon Kaen UniversityKhon Kaen40000Thailand College of Computer Science and Engineering Taibah UniversityMedina41477Saudi Arabia Information System Department Sheba Region UniversityMarib14400Yemen

The hepatitis B virus is the most deadly virus,which significantly affects the human *** termination of the hepatitis B virus is mandatory and can be done by taking precautions as well as a suitable cure in its introductory stage;otherwise,it will become a severe problem and make a human liver suffer from the most dangerous diseases,such as liver *** this paper,two medical diagnostic systems are developed for the diagnosis of this life-threatening *** methodologies used to develop thesemodels are fuzzy logic and the neuro-fuzzy *** diverse parameters that assist in the evaluation of performance are also determined by using the observed values from the proposed system for both *** classification accuracy of a multilayered fuzzy inference system is 94%.The accuracy with which the developed medical diagnostic system by using Adaptive Network based Fuzzy Interference system(ANFIS)classifies the result corresponding to the given input is 95.55%.The comparison of both developed models on the basis of their performance parameters has been *** is observed that the neuro-fuzzy technique-based diagnostic system has better accuracy in classifying the infected and non-infected patients as compared to the fuzzy diagnostic ***,the performance evaluation concluded that the outcome given by the developed medical diagnostic system by using ANFIS is accurate and correct as compared to the developed fuzzy inference system and also can be used in hospitals for the diagnosis of Hepatitis B *** other words,the adaptive neuro-fuzzy inference system has more capability to classify the provided inputs adequately than the fuzzy inference system.

关键词： Artificial intelligence fuzzy logic hepatitis B hybrid system medical diagnostic system neural network neuro-fuzzy technique

来源：评论

学校读者我要写书评

暂无评论

Recommending Public Transit Route: Ant-Colony Optimization or Dijkstra?

Recommending Public Transit Route: Ant-Colony Optimization o...

引用

Modeling & E-Information Research, Artificial Learning and Digital Applications (ICMERALDA), International Conference on

作者： Abdul Jabbar Aryo Pinandito Informatics Engineering Department Faculty of Computer Science Universitas Brawijaya Malang Indonesia Information System Department Faculty of Computer Science Universitas Brawijaya Malang Indonesia

Advances in algorithmic studies have been made recently, especially in the area of finding the shortest path. Despite taking a greedy approach, the Dijkstra algorithm is well recognized for its efficacy and has established itself as the industry standard for identifying the shortest path in a graph. Conversely, scientists have embraced the Ant-Colony Optimization (ACO) approach, which draws inspiration from the behavior of ants. This study examines the two methods and determines if, given equivalent resources, ACO can generate Dijkstra-like recommendations. Research data is subjected to both algorithms, and the outcomes are presented visually. In data measurement, Dijkstra is processed first to determine the best path, and then the ACO method is applied to produce findings that are similar to Dijkstra. In data measurement, Dijkstra is processed first to determine the best path, and then the ACO method is applied to produce findings that are similar to Dijkstra. Memory consumption, computation time, initial memory allocation, and final memory allocation are evaluation parameters. ACO is more efficient than Dijkstra in terms of execution time and number of pathways traversed, according to the study's repeated evaluation methodology. This iterative assessment procedure is carried out to address the possibility of single measurements resulting from the JavaScript Garbage Collector. The study's findings imply that a larger memory may be necessary for ACO to deliver the desired outcomes. These results could also be impacted by each algorithm's distinct qualities.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Kaijun Deng Dezhi Zheng Jindong Xie Jinbao Wang Weicheng Xie Linlin Shen Siyang Song Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Provincial Key Laboratory of Intelligent Information Processing Department of Computer Science University of Exeter

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Accurately synthesizing talking face videos and capturing fine facial features for individuals with long hair presents a significant challenge. To tackle these challenges in existing methods, we propose a decomposed per-embedding Gaussian fields (DEGSTalk), a 3D Gaussian Splatting (3DGS)-based talking face synthesis method for generating realistic talking faces with long hairs. Our DEGSTalk employs Deformable Pre-Embedding Gaussian Fields, which dynamically adjust pre-embedding Gaussian primitives using implicit expression coefficients. This enables precise capture of dynamic facial regions and subtle expressions. Additionally, we propose a Dynamic Hair-Preserving Portrait Rendering technique to enhance the realism of long hair motions in the synthesized videos. Results show that DEGSTalk achieves improved realism and synthesis quality compared to existing approaches, particularly in handling complex facial dynamics and hair preservation. Our code is available at https://***/CVI-SZU/DEGSTalk.

关键词： Hair Training Three-dimensional displays Dynamics Signal processing Rendering (computer graphics) Noise measurement Speech processing Faces Videos

来源：评论

学校读者我要写书评

暂无评论

GHVC-Net: Hypervolume Contribution Approximation Based on Graph Neural Network

GHVC-Net: Hypervolume Contribution Approximation Based on Gr...

引用

IEEE International Conference on systems, Man and Cybernetics

作者： Guotong Wu Yang Nan Ke Shang Hisao Ishibuchi Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

This paper proposes a framework called GHVC-Net that uses the graph neural network (GNN) model to approximate each solution's hypervolume contribution (HVC). GHVC-Net is permutation invariant and can handle solution sets of arbitrary size, similar to the properties of GNN. Compared to HVC-Net (i.e., a machine learning model for HVC approximation), GHVC-Net achieves better accuracy with less training time. GHVC-Net is also compared with traditional approximation methods, such as line-based and point-based methods, to demonstrate its ability to identify the solution with the smallest (largest) HVC.

关键词： Training Accuracy Machine learning Approximation algorithms Graph neural networks Approximation methods Cybernetics Testing

来源：评论

学校读者我要写书评

暂无评论

Filter-Based Adaptive Model Pruning for Efficient Incremental Learning on Edge Devices

Filter-Based Adaptive Model Pruning for Efficient Incrementa...

引用

Design, Automation and Test in Europe Conference and Exhibition

作者： Jing-Jia Hung Yi-Jung Chen Hsiang-Yun Cheng Hsu Kao Chia-Lin Yang Department of Computer Science and Information Engineering National Taiwan University Taipei Taiwan Department of Computer Science and Information Engineering National Chi Nan University Nantou Taiwan Research Center for Information Technology Innovation Academia Sinica Taipei Taiwan Department of Engineering and System Science National Tsing Hua University Hsinchu Taiwan

ISBN: (数字)9783982674100

ISBN: (纸本)9798331534646

Incremental Learning (IL) enhances Machine Learning (ML) models over time with new data, ideal for edge devices at the forefront of data collection. However, executing IL on edges faces challenges due to limited resources. Common methods involve IL followed by model pruning or specialized IL methods for edges. However, the former increases training time due to fine-tuning and compromises accuracy for past classes due to limited retained samples or features. Meanwhile, existing edge-specific IL methods utilize weight pruning, which requires specialized hardware or compilers to speed up and cannot reduce computations on general embedded platforms. In this paper, we propose Filter-based Adaptive Model Pruning (FAMP), the first pruning method designed specifically for IL. FAMP prunes the model before the IL process, allowing fine-tuning to occur concurrently with IL, thereby avoiding extended training time. To maintain high accuracy for both new and past data classes, FAMP adapts the compressed model based on observed data classes and retains filter settings from the previous IL iteration to mitigate forgetting. Across all tests, FAMP achieves the best average accuracy, with only a 2.78% accuracy drop over full ML models with IL. Moreover, unlike the common methods that prolong training time, FAMP takes 35% shorter training time on average than using the full ML models for IL.

关键词： Training Adaptation models Accuracy Incremental learning Computational modeling Adaptive filters Hardware Data models Software Usability

来源：评论

学校读者我要写书评

暂无评论

Two-timescale derivative free optimization for performative prediction with Markovian data 24

Two-timescale derivative free optimization for performative ...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Haitong Liu Qiang Li Hoi-To Wai Department of Computer Science ETH Zurich and The Chinese University of Hong Kong Department of System Engineering and Engineering Management The Chinese University of Hong Kong Hong Kong China

This paper studies the performative prediction problem where a learner aims to minimize the expected loss with a decision-dependent data distribution. Such setting is motivated when outcomes can be affected by the prediction model, e.g., strategic classification. We consider a state-dependent setting where the data distribution evolves according to a controlled Markov chain. We focus on stochastic derivative free optimization (DFO) where the learner is given access to a loss function evaluation oracle with the above Markovian data. We propose a two-timescale DFO(λ) algorithm that features (i) a sample accumulation mechanism that utilizes every observed sample to estimate the gradient of performative risk, (ii) a two-timescale diminishing step size that balances the rates of DFO updates and bias reduction. Under a non-convex optimization setting, we show that DFO(λ) requires O(1/ε3) samples (up to a log factor) to attain a near-stationary solution with expected squared gradient norm less than ε. Numerical experiments verify our analysis.

关键词：

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：