检索结果-内蒙古大学图书馆

Wind Speed Forecasting using Deep Learning

Wind Speed Forecasting using Deep Learning

2024 International Conference on Smart systems for Electrical, Electronics, Communication and computer engineering, ICSSEEC 2024

作者： Janakiraman, V. Chitra, P. Thiagarajar College of Engineering Department of Computer Science and Business Systems Madurai India

ISBN: (纸本)9798350378177

Wind energy is a resource that is environmentally sustainable, crucial component needed for wind energy production. Accurate estimation of wind speed is essential for many applications. This paper proposes the Hybrid deep learning model for wind speed forecasting. The hybrid wind speed model was developed based on the Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM). CNN model includes a series of Convolutional layers followed by pooling layers, designed to extract relevant features from the input sequences, final dense layers of the network facilitate the prediction of future wind speeds. LSTM model is used for improving the accuracy of short - term prediction. Using the wind dataset from the National Renewable Energy Laboratory (NREL) in Muppandal, Kanyakumari, Tamil Nadu, wind speed was determined. The performance of the proposed model (CNN-LSTM) is quantified using Mean Absolute Error (MAE), Mean Root Square Error (RMSE), and Mean Absolute Percentage Error (MAPE). The experimental results proved that the proposed hybrid model outperformed the benchmarks models being the RNN, CNN, GRU and LSTM. © 2024 IEEE.

关键词： Wind forecasting

来源：评论

学校读者我要写书评

暂无评论

Tag Prediction of Stack Overflow Questions using NLP and ML 15

Tag Prediction of Stack Overflow Questions using NLP and ML

引用

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Prasad, P. Yogendra Priyanka, Mylavarapu Amreen, Shaik Reddy, N. Desai Sreenivas Teja, Muppala Bhanu Tirupati India Department of Computer Science and Systems Engineering Sree Vidyanikethan Engineering College Tirupati India

ISBN: (纸本)9798331300579

Technology is growing in great leaps and bounds and the number of innovations is increasing every day with major contributor being the advancement in the software development environment. Programming environment includes plethora of tools and support platforms that gives a complete assistance to the programming designers. These platforms can be question- answer based or coding based or tutorial based. Stack Overflow is a very popular online question- answer platform in the current generation and is growing to be the greatest question-answer gathering for programmers and software developers. The amount of information in this forum is so huge that one of the main functionalities of this platform would be tagging i.e., identifying the label or class to which the piece of information belongs to. Tagging helps in easy retrieval and organization of data. We propose a multi label classification system that labels all the questions on the forums with their appropriate tags autonomously. This auto-labelling framework makes it very easy for the users to find answers for the inquiries posted, given significant tags for the same and also helps the site in organizing their questions in a better way. © Grenze Scientific Society, 2024.

关键词： Software design

来源：评论

学校读者我要写书评

暂无评论

Weapon Detection using Mask R-CNN and ResNeXt 7

Weapon Detection using Mask R-CNN and ResNeXt

引用

7th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2024

作者： Kanakang, Sebotso Du, Chunling Olaifa, Oluwasogo Tshwane University of Technology Computer Systems Engineering Department Pretoria South Africa

ISBN: (纸本)9798350350890

We are living in an era marked by security challenges. Traditional surveillance systems are struggling to keep up with new ways of doing crime. The development of advanced weapon detection system has become important in fight against crime. In this study, a weapon detector system using the Mask Region Convolutional Neural Network (Mask R-CNN) algorithm with ResNeXt as a backbone architecture is proposed. We replace the default Mask R-CNN backbone with ResNext to improve the quality of the features extracted because of ResNext's good cardinality and grouped convolutions. The model generates a high quality segmentation mask for each object instance in the image. The system uses the COCO dataset to get pictures of weapons. We evaluated our system using various performance metrics, our experimental results shows that combination of R-CNN and ResNeXt is one of the most effective ways to detect weapons. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Utilizing Multi-Step Loss for Single Image Reflection Removal 21

Utilizing Multi-Step Loss for Single Image Reflection Remova...

引用

2024 IEEE/ACS 21st International Conference on computer systems and Applications, AICCSA 2024

作者： Elnenaey, Abdelrahman Torki, Marwan Alexandria University Faculty of Engineering Department of Computer and Systems Engineering Alexandria Egypt Knights Lab Egypt

ISBN: (纸本)9798331518240

Image reflection removal is crucial for restoring image quality. Distorted images can negatively impact tasks like object detection and image segmentation. In this paper, we present a novel approach for image reflection removal using a single image. Instead of focusing on model architecture, we introduce a new training technique that can be generalized to image-to-image problems, with input and output being similar in nature. This technique is embodied in our multi-step loss mechanism, which has proven effective in the reflection removal task. Additionally, we address the scarcity of reflection removal training data by synthesizing a high-quality, non-linear synthetic dataset called RefGAN using Pix2Pix GAN. This dataset significantly enhances the model's ability to learn better patterns for reflection removal. We also utilize a ranged depth map, extracted from the depth estimation of the ambient image, as an auxiliary feature, leveraging its property of lacking depth estimations for reflections. Our approach demonstrates superior performance on the SIR2 benchmark and other real-world datasets, proving its effectiveness by out-performing other state-of-the-art models. © 2024 IEEE.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

Stress Prediction using Machine Learning Algorithms 15

Stress Prediction using Machine Learning Algorithms

引用

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Sivaiah, B.V. Gayatri, Tangi Setti Umadevi, Thati Reddy, Rajula Partha Siva Sravya, Modiboina Tirupati India Department of Computer Science and Systems Engineering Sree Vidyanikethan Engineering College Tirupati India

ISBN: (纸本)9798331300579

Many people nowadays are dealing with psychological trauma. referred to as stress. Stress is defined as "a state of tension and pressure brought on by any thought or incident that makes you feel anxious, agitated, or frustrated". Many people have experienced stress as a result the current situation, particularly youth and working professionals. These days, a rise in stress can cause a number of issues, including heart attacks, depression, and suicide. Many academics have turned their attention to stress identification as mounting data indicates that stress related health illnesses associated with the demanding modern lifestyle are becoming more and more common. Consequently, this study's main objective is to predict stress levels, using user-retrieved data that is then confirmed using a subjective stress scale. In this case, a ML algorithm should be trained on the data to forecast the stress level. With the help of our stress prediction, you can quickly determine your current stress level and steer clear of any unfavorable circumstances. With the help of this approach, people may proactively handle future problems and avoid unfavorable consequences by having correct insights into their stress levels. The project's ultimate goal is to improve mental health by providing a tool for efficiently determining and controlling stress levels and encouraging a better way of living. © Grenze Scientific Society, 2024.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Enhancing Power Distribution Protection: A Comprehensive Analysis of Renewable Energy Integration Challenges and Mitigation Strategies 14

Enhancing Power Distribution Protection: A Comprehensive Ana...

引用

14th Mediterranean Conference on Power Generation Transmission, Distribution and Energy Conversion, MEDPOWER 2024

作者： Alves, Everton Reiz, Cleberton Melim, André Gouveia, Clara Institute for Systems and Computer Engineering Technology and Science - INESC TEC Porto Portugal

ISBN: (纸本)9781837242689

The integration of Distributed Energy Resources (DER) imposes challenges to the operation of distribution networks. This paper conducts a systematic assessment of the impact of DER on distribution network overcurrent protection, considering the behavior of Inverter Based Resources (IBR) during faults in the coordination of medium voltage (MV) feeders' overcurrent protection. Through a detailed analysis of various scenarios, we propose adaptive protection solutions that enhance the reliability and resilience of distribution networks in the face of growing renewable energy integration. Results highlight the advantages of using adaptive protection over traditional methods and topology changes, and delve into current protection strategies, identifying limitations and proposing mitigation strategies. © The Institution of engineering & Technology 2024.

关键词： Power distribution networks

来源：评论

学校读者我要写书评

暂无评论

Efficient Text Extraction and Summarization using Easyocr and GPT-3 15

Efficient Text Extraction and Summarization using Easyocr an...

引用

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Sriharsha, A.V. Bhavana, Mekala Tejaswee, Syamala Ahmed, Mynasaheb Bushra Reddy, Peddi Reddi Jaipal Tirupati India Department of Computer Science and Systems Engineering Sree Vidyanikethan Engineering College Tirupati India

ISBN: (纸本)9798331300579

Optical character recognition (OCR) extracts text from images while large language models (LLMs) understand and generate human-like text. OCR engines like EasyOCR transform document images into machine-readable text. But this raw extracted text contains artifacts. LLMs like GPT-3 require clean embedding vectors instead of text. We propose an integrated pipeline combining EasyOCR and GPT-3 for enhanced text comprehension from images. EasyOCR optically recognizes text from document images. The extracted text is cleaned and converted into embeddings that are fed to GPT-3. GPT-3's deep language model then provides contextual understanding of the extracted text. This enables interpreting complex concepts, resolving ambiguities, summarizing key ideas, and generating natural language descriptions. Our pipeline establishes a paradigm for augmenting text understanding through synergistic combination of OCR and LLMs. It has diverse applications in document analysis, information retrieval, question answering, and other NLP tasks involving documents. The integrated model outperforms previous approaches on benchmarks for comprehension of extracted text. It demonstrates the benefits of complementing optical text extraction with LLMs' innate language abilities. This paves the way for advanced OCR systems that not just read but also understand text in documents. © Grenze Scientific Society, 2024.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Scheduling Dual-Arm Multi-Cluster Tools With Regulation of Post-Processing Time

引用

IEEE/CAA Journal of Automatica Sinica 2023年第8期10卷 1730-1742页

作者： Qinghua Zhu Bin Li Yan Hou Hongpeng Li Naiqi Wu IEEE the School of Computer Science and Technology Guangdong University of TechnologyGuangzhou 510006China the Institute of Systems Engineering and Collaborative Laboratory for Intelligent Science and Systems Macao University of Science and TechnologyMacao 999078China

As wafer circuit width shrinks down to less than ten nanometers in recent years,stringent quality control in the wafer manufacturing process is increasingly *** to the coupling of neighboring cluster tools and coordination of multiple robots in a multi-cluster tool,wafer production scheduling becomes rather *** a wafer is processed,due to high-temperature chemical reactions in a chamber,the robot should be controlled to take it out of the processing chamber at the right *** order to ensure the uniformity of integrated circuits on wafers,it is highly desirable to make the differences in wafer post-processing time among the individual tools in a multicluster tool as small as *** achieve this goal,for the first time,this work aims to find an optimal schedule for a dual-arm multi-cluster tool to regulate the wafer post-processing *** do so,we propose polynomial-time algorithms to find an optimal schedule,which can achieve the highest throughput,and minimize the total post-processing time of the processing *** propose a linear program model and another algorithm to balance the differences in the post-processing time between any pair of adjacent cluster *** industrial examples are given to illustrate the application and effectiveness of the proposed method.

关键词： Cluster tool optimization scheduling

来源：评论

学校读者我要写书评

暂无评论

2D Ultrasound-Guided Visual Servoing for In-Plane Needle Tracking in Robot-Assisted Percutaneous Nephrolithotomy

2D Ultrasound-Guided Visual Servoing for In-Plane Needle Tra...

引用

2023 IEEE International Conference on systems, Man, and Cybernetics, SMC 2023

作者： Mazdarani, Hoorieh Cotton, Alec Rossa, Carlos Carleton University Systems and Computer Engineering Ottawa Canada

ISBN: (纸本)9798350337020

Ultrasound (US)-guided percutaneous nephrolithotomy is a surgical procedure for large kidney stone removal through an incision in the patient's back. To gain kidney access, the surgeon steers a needle towards the kidney while simultaneously controlling the position and orientation of a US probe to keep the needle in the image plane. To successfully reach the kidney while avoiding delicate structures, a significant level of skill and precision is required. To alleviate the surgeon's cognitive workload, robot-assisted needle tracking can be implemented to autonomously track the needle in the US images and adjust the US probe's position and orientation such that the same portion of the needle is visible in the images. This paper presents a US-guided visual servoing (VS) algorithm to track the translation and rotation of a needle in a plane. Image features representing the desired pose of the needle in the image are defined, through which an interaction matrix is devised to relate the rate of the change of the image features in US images to the required position and orientation of the US probe connected to a robotic manipulator. Experimental results in 4 experimental scenarios in a water tank demonstrate the capability of the proposed method in tracking the needle in real-time with an accuracy of 2.6 mm with a control rate of 20 Hz. Although VS has been used to track surgical targets in the past, this paper proposes the first implementation of VS for needle tracking in longitudinal US images subjected to 3-DOF motion in a plane without any prior knowledge of needle trajectory or additional position sensors. © 2023 IEEE.

关键词： biomedical imaging Medical robotics needle tracking percutaneous nephrolithotomy ultrasound guidance ultrasound imaging visual servoing

来源：评论

学校读者我要写书评

暂无评论

GHA: a Gated Hierarchical Attention Mechanism for the Detection of Abusive Language in Social Media

引用

IEEE Transactions on Affective Computing 2024年第2期16卷 946-959页

作者： Jarquin-Vasquez, Horacio Escalante, Hugo Jair Montes-Y-Gomez, Manuel Gonzalez, Fabio A. Department of Computer Science Instituto Nacional de Astrofisica Óptica y Electrónica Puebla Mexico Department of Computer Systems and Industrial Engineering Universidad Nacional de Colombia Bogotá Colombia

The use of attention mechanisms in deep learning solutions has become popular within natural language processing tasks. The use of these mechanisms allows managing the relevance of the elements of a sequence in accordance with their context, however, this relevance has been observed independently between the pairs of elements of a sequence (self-attention) or between the application domain of a sequence (contextual attention), leading to the loss of relevant information and limiting the representation of the sequences. To tackle these particular issues, we propose a dual attention mechanism, which trades off the previous limitations, by considering the internal and contextual relationships between the elements of the sequence. Additionally, we propose the extension of the dual attention mechanism into a multi-layer perspective, through the weighted fusion of the different encoding layers of deep architectures. As the interpretation of abusive language is highly contextdependent, its identification is an ideal task to evaluate the proposed attention mechanism. Accordingly, we considered six standard collections for the abusive language identification task. The obtained results are encouraging;the proposed hierarchical attention mechanism outperformed the current self-attention and contextual attention mechanisms coupled with recurrent neural networks and Transformers, as well as, state-of-the-art approaches in detecting abusive language. © 2010-2012 IEEE.

关键词： Recurrent neural networks

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：