检索结果-内蒙古大学图书馆

Swarm-LSTM: Condition Monitoring of Gearbox Fault Diagnosis Based on Hybrid LSTM Deep Neural Network Optimized by Swarm Intelligence Algorithms

引用

computers, Materials & Continua 2021年第2期66卷 2041-2059页

作者： Gopi Krishna Durbhaka Barani Selvaraj Mamta Mittal Tanzila Saba Amjad Rehman Lalit Mohan Goyal School of Electrical and Electronics Sathyabama Institute of Science and TechnologyChennai600119India Department of Computer Science and Engineering G.B.Pant Government Engineering CollegeNew Delhi110020India Artificial Intelligence and Data Analytics(AIDA)Laboratory CCISPrince Sultan UniversityRiyadh11586Saudi Arabia Department of Computer Engineering J.C.Bose University of Science and TechnologyFaridabad121006India

Nowadays,renewable energy has been emerging as the major source of energy and is driven by its aggressive expansion and falling *** of the renewable energy sources involve turbines and their operation and maintenance are vital and a difficult *** monitoring and fault diagnosis have seen remarkable and revolutionary up-gradation in approaches,practices and technology during the last *** mostly do use a rotating type of machinery and analysis of those signals has been challenging to localize the *** paper proposes a new hybrid model wherein multiple swarm intelligence models have been evaluated to optimize the conventional Long Short-Term Memory(LSTM)model in classifying the faults from the vibration signals data acquired from the *** helps to analyze the performance and behavioral patterns of the system more effectively and efficiently which helps to suggest for replacement of the unit with higher *** results have demonstrated that the proposed hybrid modeling approach is effective in classifying the faults of the gearbox from the time series data and achieve higher diagnostic accuracy in comparison to the conventional LSTM methods.

关键词： Gearbox long short term memory fault classification swarm intelligence optimization condition monitoring

来源：评论

学校读者我要写书评

暂无评论

PipeMoE: Accelerating Mixture-of-Experts through Adaptive Pipelining

PipeMoE: Accelerating Mixture-of-Experts through Adaptive Pi...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Shaohuai Shi Xinglin Pan Xiaowen Chu Bo Li School of Computer Science and Technology Harbin Institute of Technology Shenzhen Department of Computer Science Hong Kong Baptist University Data Science and Analytics Thrust The Hong Kong University of Science and Technology (Guangzhou) Department of Computer Science and Engineering The Hong Kong University of Science and Technology

Large models have attracted much attention in the AI area. The sparsely activated mixture-of-experts (MoE) technique pushes the model size to a trillion-level with a sub-linear increase of computations as an MoE layer can be equipped with many separate experts, but only one or two experts need to be trained for each input data. However, the feature of dynamically activating experts of MoE introduces extensive communications in distributed training. In this work, we propose PipeMoE to adaptively pipeline the communications and computations in MoE to maximally hide the communication time. Specifically, we first identify the root reason why a higher pipeline degree does not always achieve better performance in training MoE models. Then we formulate an optimization problem that aims to minimize the training iteration time. To solve this problem, we build performance models for computation and communication tasks in MoE and develop an optimal solution to determine the pipeline degree such that the iteration time is minimal. We conduct extensive experiments with 174 typical MoE layers and two real-world NLP models on a 64-GPU cluster. Experimental results show that our PipeMoE almost always chooses the best pipeline degree and outperforms state-of-the-art MoE training systems by 5%-77% in training time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Approaches for Proactive Phishing Attack Detection 7

Machine Learning Approaches for Proactive Phishing Attack De...

引用

7th International Conference on Circuit Power and Computing Technologies, ICCPCT 2024

作者： Geetha, B. Malathi, P. Thirumalaikumari, T. Janakiraman, V. Basha, H. Anwer Rukmani Devi, S. Saveetha Institute of Medical and Technical Sciences Science Saveetha College of Liberal Arts and Sciences Department of Computer Tamil Nadu Chennai India Saveetha Institute of Medical and Technical Sciences Saveetha College of Liberal Arts and Sciences Department of Data Analytics Tamil Nadu Chennai India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of ECE Tamil Nadu Chennai India

ISBN: (纸本)9798350372816

Phishing attacks remain a serious problem in cybersecurity, necessitating advances in detection methods. The study describes a novel method for detecting phishing attacks that use advanced machine learning (ML) techniques, notably convolutional neural networks (CNNs) and recurrent neural networks (RNNs). CNNs and RNNs were chosen because of their ability to detect spatial and sequential patterns in phishing data. The system achieves improved performance by iterative model refinement and ensemble learning, beating existing rule-based systems in terms of precision (96%), recall (94%), and F1-score (95%). Furthermore, the proposed strategy has significantly lower false positive (3.8%) and false negative (5.7%) rates than existing systems, indicating greater dependability in distinguishing between legitimate and malicious emails. Cross-validation validates that the proposed system is stable and ready for real-world use. As a result, the proposed ML-driven strategy represents a substantial leap in phishing detection, providing increased accuracy (F1-score: 95%) and resilience to emerging cybersecurity threats. © 2024 IEEE.

关键词： Phishing

来源：评论

学校读者我要写书评

暂无评论

AI based Stock Market Analysis and Decision Making System using Design Thinking Approach 8

AI based Stock Market Analysis and Decision Making System us...

引用

8th International Conference on Inventive Systems and Control, ICISC 202

作者： Kumar, M.Venkatesh Umamaheswari, M. Bharathi, C. Hema Maruthaveni, R. Devi, M.Nirmala Prasanna, R. Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Tamilnadu Chennai India Dr. Sns Rajalakshmi College of Arts and Science Department of Business Administration Tamilnadu Coimbatore India Tamil Nadu Agricultural University Department of Physical Science and Information Technology Tamilnadu Coimbatore India Dr. Sns Rajalakshmi College of Arts and Science Department of Computer Science with Data Analytics Tamilnadu Coimbatore India Dr. Sns Rajalakshmi College of Arts and Science Department of Management Studies Tamilnadu Coimbatore India

ISBN: (纸本)9798350386578

Stock market is a dynamic and ever-changing environment that can be both exciting and challenging for investors. Equities, primarily referred to as stocks, are traded on stock exchanges around the world and reflect ownership in a business. The stock market is an essential tool for companies to raise capital, and investors use it to grow their wealth. Investing in stocks requires a thorough understanding of the market and the individual companies in which you are interested. The financial health of a company must be taken into account and can be analyzed using financial statements and other data. Another critical factor is the overall economic climate, as market conditions can significantly impact stock prices. It's crucial to have a long-term outlook and avoid being influenced by momentary market changes when making equity investments. A random walk is a mathematical model used to describe a sequence of steps or movements where each step is determined by chance. It is often used in various fields, including physics, finance, and statistics. Random walk theory has important implications in various fields, including the efficient market hypothesis in finance and the modeling of diffusion processes in physics. To effectively predict the future stock price using conventional and modern machine learning models. Compare the performance of different models and identify a higher accuracy prediction model using the selected important factors from disparate data sources. © 2024 IEEE.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

Hybrid Convolutional Neural Networks for Enhanced Detection of Mango Leaf Diseases

Hybrid Convolutional Neural Networks for Enhanced Detection ...

引用

Cybernetics, Cognition and Machine Learning Applications (ICCCMLA), IEEE International Conference on

作者： Shweta Bhattacharjee Porna Md Firoz Kabir Md Imran Chowdhury Rana Md Saiful Islam Sajol Tonmoy Roy Mohammad Aman Ullah Khan Md Al Adnan Girigula Durga Bhavani Department of Computer Science and Engineering Ahsanullah University of Science and Technology Dhaka Bangladesh Master’s in Information Technology University of the Cumberlands USA Bachelor of Business Administration International American university Los Angeles California USA Department of Computer Science and Engineering Louisiana State University Louisiana USA Data Analytics & Information Systems Utah State University Logan USA Department of Computer Science and Engineering School of Data and Sciences BRAC University Dhaka Bangladesh Bsc in software engineering Noakhali Science And Technology University School of Computer Science & Engineering (SCOPE) VIT-AP University Amaravati Andhra Pradesh India

ISBN: (数字)9798331505790

ISBN: (纸本)9798331505806

The classification of mango leaf diseases is critical for effective disease management and ensuring high-quality yields in mango cultivation. This paper presents a comprehensive study on using deep learning techniques to classify various mango leaf diseases, leveraging convolutional neural networks (CNNs) and hybrid models. A total of 7,524 images were used in our study. These included 4,000 training samples and 3,524 testing samples. The images were split into eight groups, which were powdery mildew, cutting weevil, anthracnose, bacterial canker, sooty mold, gall midge, healthy, and die back. The suggested method starts with feature extraction using VGG19 and MobileNetB1, then classification using both standalone models (ResNet50V2 + EfficientNetB1 and VGG16 + MobileNetB1). We employed data augmentation techniques like random brightness adjustment, rotation, and flipping to enhance the robustness of the model. We conducted hyperparameter tuning using hyperband and Bayesian optimization to optimize the model’s performance. Experimental results demonstrate that the hybrid models achieved superior performance, with ResNet50V2 and EfficientNetB1 attaining a perfect accuracy of $100 \%$ on the test set. These findings highlight the potential of deep learning techniques to improve the accuracy and reliability of mango leaf disease diagnosis, contributing significantly to the advancement of precision agriculture.

关键词： Deep learning Training Precision agriculture Accuracy Robustness Convolutional neural networks Tuning Optimization Diseases Testing

来源：评论

学校读者我要写书评

暂无评论

Galaxy: A Resource-Efficient Collaborative Edge AI System for In-situ Transformer Inference

Galaxy: A Resource-Efficient Collaborative Edge AI System fo...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Shengyuan Ye Jiangsu Du Liekang Zeng Wenzhong Ou Xiaowen Chu Yutong Lu Xu Chen School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China IoT Thrust and Research Center for Digital World With Intelligent Things HKUST (Guangzhou) Guangzhou China Data Science and Analytics Thrust HKUST (Guangzhou) Guangzhou China Department of Computer Science and Engineering HKUST Hong Kong SAR China

ISBN: (数字)9798350383508

ISBN: (纸本)9798350383515

Transformer-based models have unlocked a plethora of powerful intelligent applications at the edge, such as voice assistant in smart home. Traditional deployment approaches offload the inference workloads to the remote cloud server, which would induce substantial pressure on the backbone network as well as raise users’ privacy concerns. To address that, in-situ inference has been recently recognized for edge intelligence, but it still confronts significant challenges stemming from the conflict between intensive workloads and limited on-device computing resources. In this paper, we leverage our observation that many edge environments usually comprise a rich set of accompanying trusted edge devices with idle resources and propose Galaxy, a collaborative edge AI system that breaks the resource walls across heterogeneous edge devices for efficient Transformer inference acceleration. Galaxy introduces a novel hybrid model parallelism to orchestrate collaborative inference, along with a heterogeneity-aware parallelism planning for fully exploiting the resource potential. Furthermore, Galaxy devises a tile-based fine-grained overlapping of communication and computation to mitigate the impact of tensor synchronizations on inference latency under bandwidth-constrained edge environments. Extensive evaluation based on prototype implementation demonstrates that Galaxy remarkably outperforms state-of-the-art approaches under various edge environment setups, achieving up to 2.5× end-to-end latency reduction.

关键词： Tensors Computational modeling Collaboration Prototypes Edge AI Smart homes Parallel processing

来源：评论

学校读者我要写书评

暂无评论

Development of Business Intelligence Framework for Open Government data Portal Usage Analysis: A Case Study of Thailand 13

Development of Business Intelligence Framework for Open Gove...

引用

13th International Conference Knowledge and Systems engineering, KSE 2021

作者： Sripramong, Sahaporn Anutariya, Chutiporn Buranarach, Marut Tumsangthong, Patipat Wutthitasarn, Theerawat School of Engineering and Technology Asian Institute of Technology Ict Department Thailand National Electronics and Computer Technology Center Data Science and Analytics Research Group Thailand

ISBN: (纸本)9781665499750

The usage of Open Government data (OGD) can enable the government transparency for better governance, increase citizen collaboration, and promote innovation through public service improvement. OGD initiatives involve different stakeholders and complex publishing guidelines. In general, governments initiate OGD in their countries and provide the government-run portals to support the provision and consumption process of OGD. Insufficient usage of OGD and limited provision by the government is a great challenge to OGD development. Monitoring the operation and constantly analyzing the usage can be beneficial for OGD policymakers to gain insight into usage, to plan, and to enact the law to support the OGD initiative. This study proposes a Business Intelligence (BI) framework to analyze OGD portal datasets and its usage. The data from Thailand's OGD (ThOGD) portal was derived to validate our framework. The work focuses on designing and implementing the BI framework. We demonstrated the features of the prototyped BI system in supporting the analysis through various data visualization. © 2021 IEEE.

关键词： Open data

来源：评论

学校读者我要写书评

暂无评论

IoMT Enabled Melanoma Detection Using Improved Region Growing Lesion Boundary Extraction

引用

computers, Materials & Continua 2022年第6期71卷 6219-6237页

作者： Tanzila Saba Rabia Javed Mohd Shafry Mohd Rahim Amjad Rehman Saeed Ali Bahaj Artificial Intelligence&Data Analytics Lab CCIS Prince Sultan UniversityRiyadh11586Saudi Arabia School of Computing Faculty of EngineeringUniversiti Teknologi MalaysiaSkudai81310Johor BahruMalaysia Department of Computer Science Lahore College for Women UniversityLahore54000Pakistan MIS Department College of Business Administration Prince Sattam bin Abdulaziz UniversityAlkharj11942Saudi Arabia

The Internet ofMedical Things(IoMT)and cloud-based healthcare applications,services are beneficial for better decision-making in recent *** is a deadly cancer with a highermortality rate than other skin cancer types such as basal cell,squamous cell,andMerkel ***,detection and treatment at an early stage can result in a higher chance of *** classical methods of detection are expensive and ***,they rely on a trained practitioner’s level,and the availability of the needed equipment is essential for the early detection of *** current improvement in computer-aided systems is providing very encouraging results in terms of precision and *** this article,we propose an improved region growing technique for efficient extraction of the lesion *** analysis and detection ofMelanoma are helpful for the expert *** CNN features are extracted using the pre-trained VGG-19 deep learning *** the end,the selected features are classified by *** proposed technique is gauged on openly accessible two datasets ISIC 2017 and *** the evaluation of our proposed framework,qualitative and quantitative experiments are *** suggested segmentation method has provided encouraging statistical results of Jaccard index 0.94,accuracy 95.7%on ISIC 2017,and Jaccard index 0.91,accuracy 93.3%on the PH2 *** results are notably better than the results of prevalent methods available on the same *** machine learning SVMclassifier executes significantly well on the suggested feature vector,and the comparative analysis is carried out with existing methods in terms of *** proposed method detects and classifies melanoma far better than other ***,our framework gained promising results in both segmentation and classification phases.

关键词： Deep features extraction lesion segmentation melanoma detection SVM VGG-19 healthcare IoMT public health

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence and data science for Social Good: The Case for the SDGs

Artificial Intelligence and Data Science for Social Good: Th...

引用

2022 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT)

作者： Maria Fasli Business and Local Government Data Research Centre School of Computer Science and Electronic Engineering Institute for Analytics and Data Science University of Essex Colchester United Kingdom

Technologies have always been reshaping our economic, social and cultural environments but more recently we have seen the speed of change and impact of ICT technologies in particular rapidly increasing. These phenomenal changes are fuelled by the proliferation of data and the advances in computational methods. Though Artificial Intelligence as a (sub)discipline has been around for over 60 years, it is only in the last decade or so that we have seen very significant improvements in techniques such as machine learning. The potential of Artificial Intelligence to transform multiple aspects of our lives is huge, but there is an equally huge challenge in ensuring that the benefits of these technologies reach all.

关键词： Economics Transforms Machine learning data science Intelligent agents Cultural differences

来源：评论

学校读者我要写书评

暂无评论

An Industrial IoT Driven Approach for Sewage Gas Identification and Reporting System using Intelligent Sensors with Logical Controller 1

An Industrial IoT Driven Approach for Sewage Gas Identificat...

引用

1st International Conference on Innovative Sustainable Technologies for Energy, Mechatronics and Smart Systems, ISTEMS 2024

作者： Rajasubha, J. Ramya, R. Juliet, A. Hency Janakiraman, V. Devi, S. Rukmani Karuppaiah, S. Dhanalakshmi College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Chennai India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Nano Electronics Materials and Sensors Tamil Nadu Chennai India Saveetha College of Liberal Arts and Sciences Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Data Analytics Tamil Nadu Chennai India Prince Shri Venkateshwara Padmavathy Engineering College Department of Mechanical Engineering Chennai India Saveetha College of Liberal Arts and Sciences Simats Deemed to Be University Department of Computer Science Tamil Nadu Chennai India R.M.D Engineering College Department of Electronics and Communication Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350384246

Based on a real-time sewage gas level detection and monitoring system, this system seeks to offer intelligent solutions for the monitoring of toxic sewage gases. An alarm is issued to the observer who is looking at the circumstances from a distance whenever a specific threshold is crossed. Following this, the data is transmitted together with different gas ppm levels, indicating if the worker can clean or operate securely in that region. The suggested solution incorporates both the IoT platform and the remotely located IoT monitoring devices. This necessitates finding the appropriate threshold values for septic plants and facilities, as well as calibrating gas sensors for use in industry. The gear is meant to provide the sewage worker advance notification whenever the concentration of toxic gaseous substances grows over time, ensuring their safety. The presence of gas, temperature, and other factors in sewage may be detected using a variety of sensors. By notifying sewage workers as well as cleaners via SMS whenever the threshold value drops below the observed levels, this technology helps save people from harmful infections, which is a social good. A number of harmful gas concentrations are graphed out for real-time monitoring, and this is how it accomplishes its job. In order to assess the efficacy of the suggested model, this paper cross-validates it with the Conventional Sewage Gas Detection (CSGD) based on GPRS functioning. The goal of the cross-validation is to create an IoT based Sewage Gas Detection (IoTSGD) system that can monitor and analyze toxic gas levels in real-time and notify workers. Firebase receives the measured gas levels. If the levels rise over a certain point, it will notify the authorized individuals working remotely through their linked mobile devices. An SMS message can alert the authorities if the sewage system is likely to overflow. For the purpose of monitoring, an android app was created and connected with the planned system. © 2024 IEE

关键词： Internet of things

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：