检索结果-内蒙古大学图书馆

1st International Conference on Innovative engineering sciences and Technological Research, ICIESTR 2024

作者： Wilfred Blessing, N.R. Pyingkodi, M. Wasim Haidar, S.K. Palarimath, Suresh Paravathavarthini, S. Balakumar, C. Sheeja Kumari, V. Sutherlin Subitha, G. Seldev Christopher, S. University of Technology and Applied Sciences-Ibri College of Computing and Information Sciences Ibri Oman Kongu Engineering College Department of Computer Applications Erode India University of Technology and Applied Sciences-Salalah College of Computing and Information Sciences Salalah Oman Kongu Engineering College Department of Computer Technology Erode India Karpagam Academy of Higher Education Department of Computer Science Coimbatore India Saveetha Institute of Medical and Technical Sciences Department of Computational Intelligence Chennai India Stella Mary's College of Engineering Department of Computer Science and Engineering Aruthenganvilai India St. Xavier's Catholic College of Engineering Department of Computer Science and Engineering Nagercoil India

ISBN: (纸本)9798350348637

Precision agriculture, driven by advancements in technology, aims to optimize farming practices by utilizing data and technology to enhance efficiency, productivity, and sustainability This research introduces an innovative pilot investigation centered on the convergence of two revolutionary technologies are the Internet of Things (IoT) and Deep Learning. With a specific focus on advancing precision agriculture, the primary objective of this study is to evaluate the combined effects of data collection facilitated by IoT and analytical capabilities of deep learning in enhancing and optimizing various agricultural processes. The integration of IoT in agriculture has revolutionized data acquisition, employing an array of sensors to monitor critical parameters such as soil moisture, temperature, and crop health. Concurrently, Deep Learning, a subset of artificial intelligence, exhibits the potential to glean actionable insights from voluminous datasets, offering advanced analytics and predictive capabilities. This study investigates the practical implementation and efficacy of this integration in a controlled agricultural setting. Sensors strategically positioned in the pilot study capture real-time data, while deep learning algorithms process and analyze this information. The primary objectives include evaluating the effectiveness of this combined technology in optimizing irrigation schedules, predicting crop yields, and identifying anomalies in crop health. Preliminary findings underscore the transformative potential of IoT and Deep Learning, empowering farmers with real-time data for informed decision-making. Key considerations encompassed in the study include IoT Sensors, Deep learning algorithms, and user adoption. The research not only sheds light on the technical intricacies of the integration but also delves into the challenges and opportunities inherent in merging these technologies within the agricultural landscape. As agriculture transitions towards the next

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

Enhancing action discrimination via category-specific frame clustering for weakly-supervised temporal action localization

引用

Frontiers of Information Technology & Electronic engineering 2024年第6期25卷 809-823页

作者： Huifen XIA Yongzhao ZHAN Honglin LIU Xiaopeng REN School of Computer Science and Communication Engineering Jiangsu UniversityZhenjiang 212013China Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agricultural Applications Zhenjiang 212013China Changzhou Vocational Institute of Mechatronic Technology Changzhou 213164China

Temporal action localization (TAL) is a task of detecting the start and end timestamps of action instances and classifying them in an untrimmed video. As the number of action categories per video increases, existing weakly-supervised TAL (W-TAL) methods with only video-level labels cannot provide sufficient supervision. Single-frame supervision has attracted the interest of researchers. Existing paradigms model single-frame annotations from the perspective of video snippet sequences, neglect action discrimination of annotated frames, and do not pay sufficient attention to their correlations in the same category. Considering a category, the annotated frames exhibit distinctive appearance characteristics or clear action ***, a novel method to enhance action discrimination via category-specific frame clustering for W-TAL is proposed. Specifically,the K-means clustering algorithm is employed to aggregate the annotated discriminative frames of the same category, which are regarded as exemplars to exhibit the characteristics of the action category. Then, the class activation scores are obtained by calculating the similarities between a frame and exemplars of various categories. Category-specific representation modeling can provide complimentary guidance to snippet sequence modeling in the mainline. As a result, a convex combination fusion mechanism is presented for annotated frames and snippet sequences to enhance the consistency properties of action discrimination,which can generate a robust class activation sequence for precise action classification and localization. Due to the supplementary guidance of action discriminative enhancement for video snippet sequences, our method outperforms existing single-frame annotation based methods. Experiments conducted on three datasets (THUMOS14, GTEA, and BEOID) show that our method achieves high localization performance compared with state-of-the-art methods.

关键词： Weakly supervised Temporal action localization Single-frame annotation Category-specific Action discrimination

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Techniques for Fault Detection in Industrial Machinery 5

Deep Learning Techniques for Fault Detection in Industrial M...

引用

5th IEEE International Conference on Recent Trends in computer science and Technology, ICRTCST 2024

作者： Panigrahi, Bhawani Sankar Thiyagarajan, T. Tamilselvi, M. Tilak Babu, S.B.G. Pavithra, G. Shaik, Bazani Vardhaman College of Engineering Department of IT Telangana Hyderabad India Nehru Institute of Information Technology and Management Department of Computer Applications Tamilnadu Coimbatore India Roever Engineering College Computer Science And Engineering Tamilnadu Perambalur India Aditya Engineering College Department of ECE India Dayananda Sagar College of Engineering Department of Electronics & Communication Engineering Karnataka Bangalore India Ramachandra College of Engineering Department of Mechanical Engineering Andhra Pradesh Eluru India

ISBN: (纸本)9798350351378

The use of deep learning techniques for the purpose of improving fault detection in industrial machinery. It is of the utmost importance to have defect detection mechanisms that are both reliable and effective, since the complexity of industrial processes continues to increase. In this paper, the implementation of deep learning algorithms is investigated. These algorithms make use of neural networks to understand complex patterns and anomalies that are present in data coming from machinery. There are many different models that are being researched to see whether or not they are effective in detecting defects at early stages, limiting downtime, and eliminating costly interruptions. These models include convolutional neural networks (CNNs) and recurrent neural networks (RNNs). For the purpose of this , the performance of various methodologies is evaluated over a wide range of industrial situations, taking into consideration issues such as the variability of sensor data and noise. The findings demonstrate the promise of deep learning as a significant tool for enhancing defect detection skills, thereby paving the way for industrial equipment systems that are more reliable and resilient. © 2024 IEEE.

关键词： Condition monitoring

来源：评论

学校读者我要写书评

暂无评论

Enhancing Efficiency in Drain Cleaning Operations Using K-Nearest Neighbors Algorithm with IoT-Enabled Robots 1

Enhancing Efficiency in Drain Cleaning Operations Using K-Ne...

引用

1st International Conference on Innovations in Communications, Electrical and computer engineering, ICICEC 2024

作者： Ranganathan, Chitra Sabapathy Vijayalakshmi, Kuppan Kalaichelvi, S. Sivanantham, E. Ganeshbabu, T.R. Murugan, S. Mphasis Corporation Tamil Nadu Chennai India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tami Nadu Chennai India Pg and Research Department of Computer Science and Applications Tamil Nadu Namakkal India Rajalakshmi Institute of Technology Department of Electronics and Communication Engineering Tamil Nadu Chennai India Department of Electronics and Communication Namakkal India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Biomedical Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350376517

Maximizing efficiency in drain cleaning operations is crucial for maintaining municipal infrastructure and the prevention of possible risks like floods and pollution. Conventional approaches often need human examination and approval, which may consume a significant amount of time and require substantial effort. This research proposes a new method to improve the effectiveness of drain cleaning operations by combining Internet of Things (IoT)-enabled robots with the K-Nearest Neighbors (KNN) algorithm. The robots enabled by the IoT are fitted with sensors to gather real-time data, such as detecting blockages, measuring debris levels, and assessing the status of drains. The KNN algorithm analyzes this data to forecast the most effective cleaning procedures by comparing them to comparable prior situations. The system can adjust and enhance cleaning routes and processes using machine learning techniques, resulting in improved efficiency and effectiveness in drain maintenance. This novel methodology not only decreases human involvement and expenses related to labor but also mitigates the possibility of harm to infrastructure and enhances the overall efficiency of the drainage system. The experimental findings provide evidence of the efficacy of the proposed technique in improving the efficiency and dependability of drain cleaning operations. © 2024 IEEE.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

Estimating fish weight growth in aquaponic farming through machine learning techniques 3

Estimating fish weight growth in aquaponic farming through m...

引用

3rd IEEE International Conference on Intelligent Technologies, CONIT 2023

作者： Kumar, Purushottam Tiwari, Pranav Srinivasulu Reddy, U. Machine Learning & Data Analytics Lab CoE in Artificial Intelligence National Institute of Technology Trichy India Indian Institute of Information Technology Tiruchirappalli Computer Science and Engineering Trichy India National Institute of Technology Machine Learning & Data Analytics Lab Department of Computer Applications Trichy India

ISBN: (纸本)9798350338607

Due to the ever-growing population, rapid urbanization, unusual environmental change, and dwindling water supply, the food production from conventional farming techniques won't be able to keep up with increasing food demand for long, leading to severe food scarcity. Aquaponics is emerging as a viable alternative to food cultivation techniques but lacks efficiency, hindering its adoption on a large-scale production basis. The adoption of Artificial Intelligence (AI) techniques in smart aquaponic farming can further contribute to increasing the yield in aquaponics. In the study, both linear and non-linear regression algorithms such as linear regression, lasso regression, ridge regression, KNN regression, SVR, and decision tree regression were trained on aquaponic fish pond dataset, evaluated on the basis of multiple metrics like MAE, MSE, RMSE, and RMSLE, and a competitive analysis was done to determine the best algorithm for predicting the harvest weight of the fish in aquaponic ponds. The results showed that KNN regression and decision tree regression algorithms have lowest error and highest accuracy of 99.15% and 99.1% respectively, for predicting the harvest weight of the fish. The results obtained could be scaled up to commercial levels and used in regulating nutrient concentration and aquatic environmental conditions © 2023 IEEE.

关键词： Fish

来源：评论

学校读者我要写书评

暂无评论

TPU-Accelerated Deep Learning for Accurate Satellite Land Classification

引用

Procedia computer science 2025年 258卷 1179-1188页

作者： Tina Babu Rekha R Nair Kishore S Department of Computer Science and Engineering School of Advanced Computing Alliance University Bengaluru India Department of Computer Applications Nitte (Deemed to be University) Nitte Institute of Professional Education Mangalore Karnataka India

Tensor Processing Units (TPUs) offer significant computational advantages for deep learning tasks, particularly in processing high-dimensional satellite imagery. This study presents a systematic approach to land classification using Convolutional Neural Networks (ConvNets) accelerated by TPUs. The implemented ConvNet architecture achieved 94.5% classification accuracy across ten land cover categories, outperforming traditional machine learning methods by 6-9% and standard CNN implementations by 4%. The model demonstrated high precision (93.8%), recall (94.2%), and F1-score (94.0%) across diverse land cover types, with particularly strong performance in identifying water bodies (95.1% F1-score) and forest regions (94.9% F1-score). Through ex- tensive hyperparameter optimization enabled by TPU acceleration, training time was reduced by 60% compared to GPU-based implementations. The study utilized a dataset of 27,000 labeled satellite images across 10 land cover categories, with robust validation through 5-fold cross-validation. The improved performance and computational efficiency demonstrate the viability of TPU-accelerated deep learning for large-scale geospatial analysis applications.

关键词： Satellite Land Classification Convolutional Neural Networks (ConvNet) Tensor Processing Units (TPU) Remote Sensing Geospatial Data Deep Learning

来源：评论

学校读者我要写书评

暂无评论

Automated Object Detection and Recognition in Satellite Imagery Using CNNs 1

Automated Object Detection and Recognition in Satellite Imag...

引用

1st International Conference on Innovations in Communications, Electrical and computer engineering, ICICEC 2024

作者： Shanthi, H.J. Shobana, G. Kamalanaban, E. Murugan, J. Senthil Nandhinieswari, S. Stalinbabu, R. Deemed to be University Hindustan Institute of Technology and Science Department of Computer Applications Padur India Takshashila University School of Computer Science Ongurdt Villupuram India Vel Tech High Tech Dr.Rangarajan Dr.Sakunthala Engineering College Department of Computer Science and Engineering India Vel Tech High Tech Dr. Rangarajan Dr.Sakunthala Engineering College India Kongunadu Arts and Science College Gounder Mills Coimbatore India M. Kumarasamy College of Engineering Artificial Intelligence and Machine Learning Karur India

ISBN: (纸本)9798350376517

As increasingly high-resolution satellite photography becomes available, it has led to a growing need for efficient and accurate methods to analyse large databases and extract valuable information. This research presents a comprehensive approach for automated item identification and detection in satellite data using Convolutional Neural Networks (CNNs). This research abstract outlines the critical steps involved in a suggested technique. These steps encompass data cleaning and organisation, model architecture development, training and evaluation, post- processing, deployment, and subsequent management. This study investigates the ability of CNNs to learn intricate spatial characteristics. The research focuses on carefully selecting and annotating training and validation datasets incorporating items of interest. This study uses data augmentation methods to enhance the generalisation capabilities of the model. This research abstract discusses the importance of the preprocessing stage in ensuring the consistent performance of a model by normalising the input data. This research abstract discusses the components of the CNN architecture, namely convolutional, pooling, and fully connected layers. The CNN architecture is specifically designed to capture hierarchical characteristics. This study investigates the utilisation of a cutting-edge optimiser in the training process to optimise a meticulously constructed loss function. This study examines the integration of the model into real-world applications, considering the trade-off between processing speed and resource constraints as crucial considerations for successful deployment. The findings suggest that this methodology holds promise as a valuable tool in various fields. © 2024 IEEE.

关键词： Satellite imagery

来源：评论

学校读者我要写书评

暂无评论

A Prediction of Stock Time Series Data Using Single Layer Long Short-Term Memory 2

A Prediction of Stock Time Series Data Using Single Layer Lo...

引用

2nd IEEE International Conference on Data science and Network Security, ICDSNS 2024

作者： Al-Fatlawy, Ramy Riad Lande, Jayapal Sundaram, S. Meenakshi. Saranya, N. Naga Podaralla, Rakesh College of Technical Engineering The Islamic University Department of Computers Techniques Engineering Najaf Iraq School of Computer Science & Artificial Intelligence Sr University Warangal India Nitte Meenakshi Institute of Technology Department of Cse Bengaluru India Saveetha College of Liberal Arts & Science Simats Department of Computer Applications Chennai India School of Computing and Information Technology Reva University Bangalore India

ISBN: (纸本)9798350373110

Financial and cash flow data is a particular kind of past temporal sequence information which gives a huge quantity of data which is employed often in the task including data analysis. For investors and financial professionals, the major question is how to forecast stock time series data. Stock prices forecasting is a challenging task because of time series data volatility, non-linearity and significant noise on the value of stocks. The earlier study only focused on alone parameter stock called close cost, hence, Single Layer Long Short-term Memory (LSTM) model is proposed. This model suggests the contribution as stock information and it predicts two stocks characteristics namely high cost and close cost for the day after. The dataset for Shanghai composite index is utilized for conducting experiments and by the use of existing techniques the comparisons are done. From the results, it clearly shows that proposed single layer LSTM achieved MAE of 26.961, RMSE of 12.112 and R2 of 0.987 which is better when compared with the existing models. © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Towards Mental stress Detection in University Students Based on RBF and Extreme Learning Based Approach 1

Towards Mental stress Detection in University Students Based...

引用

1st IEEE International Conference on Electronics, Computing, Communication and Control Technology, ICECCC 2024

作者： Anand, Taruna Alam, Mohammad Shabbir Akila, D. Yadav, Manjushri Janardan Mavliya, Anil Kumar Saran Kumar, A. Graphic Era Deemed to be University Department of Humanities and Social Sciences Dehradun India College of Computer Science and Information Technology Jazan university Department of Computer science Jizan Saudi Arabia Saveetha College of Liberal Arts and Sciences SIMATS Department of Computer Applications Tamil Nadu Chennai India International Institute of Business Studies Department of Management Bengluru India COER College of Nursing and Paramedical Sciences Uttarkhand Roorkee India Bannari Amman Institute of Technology Computer Science and Engineering Erode India

ISBN: (纸本)9798350371802

A lot of individuals associate stressful situations with bad experiences. It is concerning that mental health issues are so common, particularly among younger people. The once carefree generation is now under a great deal of stress. Modern society's elevated stress levels are associated with an array of serious health issues, such as an increased risk of suicide, heart disease, depression, and stroke. Within the scope of our research, we are attempting to quantify the degree to which students experience internet-related anxiety in the seven days leading up to an exam. Model training, feature selection, and preprocessing are all tremendously dependent on sequencing. Images with consistent size and intensity can be achieved by removing noise and blinks during this preprocessing step. Classifier performance improvement via feature selection aims to normalize and increase accuracy by utilizing favorable attributes. Feature selection is crucial during the training of a StressNet-C-BiLSTM model. When compared to two state-of-the-art algorithms, BiLSTM and CNN, the suggested technique outperforms them. The results demonstrated a significant improvement, with an accuracy rate of 97.58%. © 2024 IEEE.

关键词： Health risks

来源：评论

学校读者我要写书评

暂无评论

Group Teaching Optimization Algorithm with Machine Learning Model for Big Data Analytics

Group Teaching Optimization Algorithm with Machine Learning ...

引用

2023 International Conference on Sustainable Communication Networks and Application, ICSCNA 2023

作者： Prabaharan, G. Sesha Vidhya, S. Venkatesh, K. Mary Sundararajan, Suma Christal Shobana, G. Srimathi, S. Vel Tech Rangarajan Dr. Sagunthala R & D Institute of Science and Technology Department of Computer Science and Engineering Veltech University Avadi Chennai India Rmk College of Engineering and Technology Department of Ece India Kalasalingam Academy of Research and Education Department of Computer Science and Engineering India Panimalar Engineering College Department of Information Technology Poonamalle Chennai India College of Science and Humanities Srm Institute of Science and Technology Department of Computer Applications SRM Nagar Kattankulathur603 203 India Saveetha School of Engineering Simats Department of Bio Technology Tamilnadu Chennai India

ISBN: (纸本)9798350313987

Big Data An analytics (BDA) plays a significant role in the process of decision-making over several domains. Effective evaluation and processing of enormous data amounts need influential techniques and Machine Learning (ML) methods. BDA by implementing ML and Feature Selection (FS) is an influential model in extracting valued patterns and vision from huge and convolutional datasets. The process encompasses implementing modern ML methods and models for interpreting, processing, and analyzing data on a scale that cannot be handled effectively by conventional models. This research study proposes a design of Group Teaching Optimization Algorithm with Machine Learning model for Big Data Analytics (GTOA-MLBDA) technique. The GTOA-MLBDA technique classifies the big data and it can be managed by Map Reduce tool. The GTOA-MLBDA technique uses GTOA to determine the important features, reduce dimensionality and enhance classifier results. In addition, the classification of big data takes place using functional link neural network (FLNN) model. Finally, the parameter tuning of the FLNN model takes place using Adam optimizer. Experimental analysis has been carried out by using big data datasets and the results highlight that the combination of the GTOA with the FLNN classifier of the GTOA-MLBDA technique resulted in improved results over classical approaches. © 2023 IEEE.

关键词： Big Data Classification Data Analytics Feature Selection Machine Learning Map Reduce

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：