检索结果-内蒙古大学图书馆

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Suresh, P. Aswathy, R.H. Soms, Nisha Niranjani, V. Saveetha School of Engineering Simats Department of Computer Science and Engineering Thandalam Chennai India Kpr Institute of Engineering and Technology Department of Computer Science and Engineering Coimbatore India Sri eshwar college of engineering Department of Computer science and engineering Coimbatore India

ISBN: (纸本)9798331540364

Video surveillance systems employing closed-circuit television (CCTV) are crucial for public safety. Accurately detecting humans within video frames is a core component of this technology. This knowledge is crucial for numerous uses, including detecting possible dangers, observing crowd dynamics, and examining patterns of human behavior. This research introduces a new method called YOLOv8, designed to enhance human detection capabilities within CCTV footage. The proposed algorithm, YOLOv8, is built upon the popular object recognition framework, YOLO, but with significant enhancements to improve its accuracy and efficiency in detecting humans. YOLOv8 utilizes deep convolutional neural networks (CNNs) and advanced object recognition techniques to achieve high accuracy in human detection, even in challenging environments such as low light conditions, occlusions, and varying scales of human poses. To assess the effectiveness of YOLOv8, various tests were performed using standard datasets and real-world CCTV surveillance footage. The results demonstrate that YOLOv8 outperforms existing human detection algorithms regarding accuracy, robustness, and real-time processing capability. YOLOv8 achieved an average precision of over 95% in human detection, making it highly suitable for everyday CCTV surveillance. The proposed YOLOv8 algorithm has the potential to significantly improve human detection in security camera footage and enhance public safety. This research contributes to advancing human detection technology and can benefit various domains, including law enforcement, public safety, and video analytics. © 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

Deep Learning-Driven Sentiment Analysis in Textual Data 5

Deep Learning-Driven Sentiment Analysis in Textual Data

引用

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Kathiravan, M. Saravanan, S. Jagadeesh, M. Lakshmi, I. Durga, V. Sathya Raja, N. Bharathi Computer Science and Engineering Chennai India Computer Science and Engineering Saveetha School of Engineering Chennai Thandalam India Computer Science and Engineering Rajalakshmi Engineering College Chennai India Chitkara University Institute of Engineering and Technology Chitkara University Punjab India

ISBN: (纸本)9798350383522

Emotional recognition from text is essential in natural language processing with far-reaching consequences in areas such as Artificial Intelligence, Human-computer Interaction, and others. Emotions are felt, thought-out physical responses to events. Analyzing these feelings independently of vocal and facial cues is critical to interpreting emotions. Despite these challenges, it is crucial to understand human emotions, especially as people become more comfortable expressing themselves through hate speech on sites like Facebook, Twitter, etc. This paper discusses how to classify many tweets based on their tone. Here, we use deep learning algorithms to determine whether an expression means a happy or sad emotion. There are four distinct negative states of mind: rage, indifference, loneliness, disdain, sadness, and despair. The subset of positive emotions includes zeal, joy, happiness, love, calm, pleasure, and wonder. Using three datasets, we validated and assessed the method's use of long short-term memory and recurrent neural networks to obtain high accuracy in emotion categorization. With an 85.07% predictability for positive and negative classification and an 87.23% and 86.3% accuracy for positive and negative subclasses, respectively, a detailed examination reveals that the system improves emotion prediction using the LSTM model. © 2024 IEEE.

关键词： Deep Learning techniques Emotion Classification Long Short-term memory Recurrent Neural Networks

来源：评论

学校读者我要写书评

暂无评论

Optimized BERT: an effective attention layer based deep learning technique utilizing for multiword term extraction

引用

International Journal of Information Technology (Singapore) 2024年 1-13页

作者： Mandava, Mamatha Vinta, Surendra Reddy School of Computer Science and Engineering VIT-AP University Amaravathi India

Multiword term extraction refers to identifying and extracting meaningful phrases or expressions of multiple words from a given text or a corpus. These multiword terms often represent specific concepts, entities, or domain-specific terminology. Multiword terms often include compound words, combining multiple words to form a single term. Recognizing and extracting compound terms accurately can be challenging, especially when dealing with languages that have flexible word composition rules. To overcome the problems in multiword term extraction, propose a novel deep learning and attention-based technique. There are four steps to evaluate the process. First, collect the data from the datasets, clean the data, and then perform lowercasing, tokenization, stop word removal, stemming, and lemmatization. After that, perform n-grams extraction and part-of-speech tags in the feature extraction step. Then, extract the multiword terms using the attention layer of the pre-trained BERT method. Finally, optimize the hyper-parameters in the pre-trained BERT method using the Enhanced Northern Goshawk Optimization (ENGO) algorithm. The term extraction frameworks used in this study can be presented via the attention-based models. Results indicate that compared to the baseline pre-trained BERT word extraction model, the pre-trained BERT with attention layer can reach a high term extraction accuracy of 98.57%. This study also shows that attention-based models can find pertinent terms with strong associations to the categories found in clinical progress notes. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Feature extraction Natural language processing Optimization Pre-processing Pre-trained BERT Term extraction

来源：评论

学校读者我要写书评

暂无评论

FLBlock: A Sustainable Food Supply Chain Approach Through Federated Learning and Blockchain 2

FLBlock: A Sustainable Food Supply Chain Approach Through Fe...

引用

2nd International Conference on Machine Learning and Data engineering, ICMLDE 2023

作者： Ahamed, N. Nasurudeen Karthikeyan, P. School of Computer Science & Engineering Presidency University Bangalore560064 India School of Computer Science & Engineering RV University Bangalore560059 India

Blockchain technology has become a pivotal asset in many industries, particularly Food Supply Chain Management. This technology, renowned for its capacity to preserve data immutably and expedite tracking across the intricate stages of the food supply chain, plays a pivotal role in enhancing transparency across the food industry. We proposed a Blockchain-based Federated Learning model. This model amalgamates the strengths of Blockchain and federated learning within the food supply chain, focusing on sustainable and high-quality food production. Our primary objective is to fortify data security within various facets of the food supply chain, encompassing raw material suppliers, producers, distributors, and consumers. Simultaneously, we strive to enhance the precision of our model, aiming to outperform existing Blockchain-based solutions in terms of accuracy. The proposed model demonstrates superior accuracy compared to existing methods. © 2024 Elsevier B.V.. All rights reserved.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Predictive Insights for Enhancing Customer Retention in Banking: Integrating Power BI and Random Forest 3rd

Predictive Insights for Enhancing Customer Retention in Bank...

引用

3rd International Conference on Machine Vision and Augmented Intelligence, MAI 2023

作者： Sumanasri, A. Vyshnavi, M. Manogna, R. Nikhila Keerthi, Kelam Kesavarshini, A. Pande, Sagar Dhanraj School of Computer Science Engineering VIT-AP University Andhra Pradesh Amaravati India Department of Computer Science and Engineering School of Engineering and Technology Pimpri Chinchwad University Maharashtra Pune India

ISBN: (纸本)9789819743582

The main goal of the study is to solve the problem of losing customers or clients in various financial organizations, especially in the banking sector. It investigates the use of Random Forest algorithm and the Power BI dashboard which helps to forecast churn and improve retention strategies. Historical data—transactions, demographics, and usage patterns—is collected and a thorough analyzation is done with the help of Power BI to provide a dynamic dashboard that provides insights in real-time. Combining data analytics technologies and predictive skills with their retention initiatives can help banks increase their efficacy and efficiency. Economic loss and operational difficulties are brought on by customer attrition. The outcome of this study suggests a method for forecasting customer attrition in banks that combines Power BI’s amazing data visualization techniques with Random Forest’s highly accurate predictive skills. The Random Forest algorithm integrates multiple decision trees to make predictions in a precise and expandable way. Moreover, it has the capability of handling large data sets. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

A comparative assessment of OMP and MATLAB for parallel computation

引用

International Journal of Hybrid Intelligent Systems 2024年第1期20卷 57-66页

作者： Dash, Yajnaseni Abraham, Ajith School of Computer Science Engineering and Technology (SCSET) Bennett University India

The prime goal of parallel computing is the simultaneous parallel execution of several program instructions. Consequently, to accomplish this, the program should be divided into independent sets so that each processor can execute its program part concurrently with the other processors. This study compares OMP and MATLAB, two important parallel computing simulation tools, through the use of a dense matrix multiplication technique. The results showed that OMP outperformed the MATLAB parallel environment by over 8 times in sequential execution and 6 times in parallel execution. From this proposed method, it was also observed that OMP with an even slower processor performs much better than MATLAB with a higher processor. Thus, the present analysis indicates that OMP is a superior environment for parallel computing and should be preferred over parallel MATLAB. © 2024 - IOS Press. All rights reserved.

关键词： MATLAB matrix multiplication OMP Parallel computing

来源：评论

学校读者我要写书评

暂无评论

A Dynamic and Deadline-Oriented Road Pricing Mechanism for Urban Traffic Management

引用

Tsinghua science and Technology 2022年第1期27卷 91-102页

作者： Jiahui Jin Xiaoxuan Zhu Biwei Wu Jinghui Zhang Yuxiang Wang the School of Computer Science and Engineering Southeast UniversityNanjing 211189China the Department of Computer Science and Engineering Hangzhou Dianzi UniversityHangzhou 310018China

Road pricing is an urban traffic management mechanism to reduce traffic ***,most of the road pricing systems based on predefined charging tolls fail to consider the dynamics of urban traffic flows and travelers’demands on the arrival *** this paper,we propose a method to dynamically adjust online road toll based on traffic conditions and travelers’demands to resolve the above-mentioned *** method,based on deep reinforcement learning,automatically allocates the optimal toll for each road during peak hours and guides vehicles to roads with lower toll ***,it further considers travelers’demands to ensure that more vehicles arrive at their destinations before their estimated arrival *** method can increase the traffic volume effectively,as compared to the existing static mechanisms.

关键词： road pricing traffic congestion al eviation deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A method for recognizing facial expression intensity based on facial muscle variations

引用

Multimedia Tools and Applications 2025年第18期84卷 19087-19116页

作者： Zhang, Yukun Fei, Zixiang Li, Xia Zhou, Wenju Fei, Minrui The School of Mechatronic Engineering and Automation Shanghai University Shanghai200444 China The School of Computer Engineering and Science Shanghai University Shanghai200444 China The Shanghai Jiaotong University Shanghai200240 China

Expression intensity recognition is a research problem in the field of computer vision and pattern recognition, which can be understood as the salience, or intensity, of an expression. Existing techniques for expression intensity recognition find it difficult to capture the texture features of expressions, which results in low recognition accuracy. Therefore, this paper proposes a method for recognizing expression intensity based on facial muscle changes to address this issue. This method captures texture motion information of facial muscles using optical flow, determining the motion regions and static regions of facial texture based on optical flow magnitude. The movement areas of facial expressions are set as salient regions, and the intensity of emotions is classified based on the variation rate of muscles within these regions. The proposed algorithm exhibits good recognition accuracy on publicly available datasets such as CK +, MMI, and datasets collected from real scenarios, including those involving elderly individuals. The average recognition accuracy reaches 82.7%. The proposed algorithm demonstrates a strong ability to recognize the intensity of facial expressions. This study provides technical support for the development of a real-time mood monitoring system. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Short-Term Power Load Forecasting Method Based on GRU-Transformer Combined Neural Network Model

引用

Journal of Computing and Information Technology 2024年第1期32卷 1-14页

作者： Mao, Weiwei Yu, Suping Chen, Wenqing College of Computer and Information Engineering Luoyang Institute of Science and Technology Luoyang China School of Electrical Engineering and Automation Luoyang Institute of Technology Luoyang China

Load Forecast (LF) is an important task in the planning, control and application of public power systems. Accurate Short Term Load Forecast (STLF) is the premise of safe and economical operation of a power system. In the research of short-term power load forecasting, machine learning and deep learning are the most popular methods at present, but there still exists a problem that the single and simple structure of power load forecasting model leads to low accuracy of load forecasting. In order to improve the accuracy of STLF, a Gated Cycle Unit (GRU)-Transformer combined neural network model is proposed. Transformer encoder structure is used as feature extractor to mine the complex mapping relationships between the input features and load. The advantage of self-attention mechanism is used to solve the problem of information loss of long sequences in short-term power load forecasting. At the same time, the multivariate time series model of GRU is used for model training. The experimental results on the power load data set of a certain region in southwest China and Panama City show that the proposed combined model prediction method has higher accuracy than those proposed in other literatures, which further proves its feasibility and superiority. © 2024, University of Zagreb Faculty of Electrical engineering and Computing. All rights reserved.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Deep Recurrent Residual U-Net with Semi-Supervised Learning for Deforestation Change Detection

引用

SN computer science 2024年第7期5卷 1-15页

作者： Bidari, Indira Chickerur, Satyadhyan School of Computer Science and Engineering KLE Technological University Hubballi India

“Deforestation” refers to the systematic removal of trees from forests to facilitate significant human activities. Expansion of agriculture, infrastructure and logging are the main causes of deforestation. Deforestation causes greenhouse gas emissions, water pollution and loss of biodiversity. The forest area is gradually decreasing with time. To overcome the above challenges, detection of forest change is crucial. Recently, due to advances in satellite technology, deforestation images have become accessible. In this study, we proposed a deep recurrent residual network to detect how much forest has been cleared over a period of time. Initially, an image of a particular forest area at two different time periods is provided as input to the change detection technique. The input image is iteratively segmented using a novel recurrent residual U-net. It then aggregates these segmented results and provides input to a semi-supervised learning method. From this, the semi supervised MLP method detects how many changes the current image has undergone from the previous image. Our proposed work is implemented on the platform of Python. Our proposed task is evaluated in terms of precision, accuracy, Fscore, recall, specificity, and sensitivity. Our proposed work achieved a high accuracy rate of 94.26%. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Change detection Deep learning Deforestation Python Segmentation Semi supervised MLP

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：