检索结果-内蒙古大学图书馆

7th IFIP TC 12 International Conference on Computational Intelligence in Data science, ICCIDS 2024

作者： Sham Sundhar, R. Shivavardhini, T. Daphine Desona Clemency, C.A. Roobini, M.S. Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India

ISBN: (纸本)9783031699818

Mental Illnesses such as Anxiety and Depression are fairly prevalent in modern society. Yet most people do not get diagnosed, cannot afford treatment, or there simply aren’t any readily available practitioners. In the worst-case scenario, avoiding treatment can increase the likelihood of self-harm in affected individuals, both emotionally and physically. A low-cost and easily available solution is required to provide the benefits of therapy to the masses. In this paper, we introduce "Lecter", a chatbot solution specifically targeted to providing free mental health care to individuals who cannot access an actual therapist. With the help of the superior conversational abilities of an LLM (large language model), Lecter listens to the concerns and problems that patients face and helps them introspect, and better understand their feelings using a popular therapy technique called Cognitive Behavioral Therapy (CBT). Lecter provides its services using technologies such as an LLM called Mythomax, React Js for the front end of the application, Flask for the back end, and MongoDB for authentication and storage. © IFIP International Federation for Information Processing 2024.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Secure Remote Access to Local Network with Distributed Tunnel Management

Secure Remote Access to Local Network with Distributed Tunne...

引用

2024 International Conference on Advances in Data engineering and Intelligent Computing Systems, ADICS 2024

作者： Priyan Kishore, M.S. Chandana Sathwika, U. Malarvel, Muthukumaran Hindustan Institute Of Technology And Science Department Of Computer Science And Engineering Chennai India

ISBN: (纸本)9798350364828

The proliferation of distributed networks and the increasing demand for remote collaboration and maintenance have highlighted the need for secure and controlled remote access solutions. This paper presents a novel approach to establishing remote network access through a distributed tunneling management system. The proposed methodology addresses the challenges of providing authenticated and controlled access to private networks while facilitating seamless remote collaboration and maintenance tasks. The system architecture comprises a public tunneling server responsible for hosting the tunneling service and a separate management server dedicated to handling client connections, tunnel creation, and termination. Client networks run background processes that communicate with the communication server through websocket connections, enabling tunnel establishment and termination based on authorized requests. The methodology incorporates authentication mechanisms and secure protocols to ensure the confidentiality and integrity of communication channels. The distributed nature of the architecture enhances scalability, allowing multiple client networks to leverage the tunneling service concurrently. Experimental results demonstrate the viability of the implemented protocols, showcasing efficient computation, storage, communication and practical solutions for remote access to local networks, with potential applications across various industries, including IT support, remote collaboration, and maintenance operations while ensuring the confidentiality and integrity of sensitive data. © 2024 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Morphological Classification of Galaxies using Enhanced Deep Learning Model 5

Morphological Classification of Galaxies using Enhanced Deep...

引用

5th IEEE International Conference on Communication, Computing and Industry 6.0, C2I6 2024

作者： Nemade, Rohan Jha, Suraj Anand, Harsh Chandrasekaran, Saravanan Srm Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350379884

Galaxies in astrophysics are one of its fundamental, their morphological classification remains an essential key to unlock countless doors about the structure, formation and history of our Universe. For nearly a century, astronomers have assigned galaxies to perceptual categories such as ellipticals, spirals and irregulars. However, the extraordinary expansion of the galaxy database catalysed and instigated by sky surveys of ever-increasing scales rendered this classification more manual than practical. Because of the learning capability and its scaling nature, to learn hierarchical abstract features from the visual data Convolutional Neural Networks (CNN) are powerful tools to recognize complex patterns and structures in images, such as spiral arms or central bulges that contribute significantly to accurate morphological classification. That is why CNN are particularly well suited to the problem of galaxy classification. While traditional classification work used to solve the problem, it is not feasible for today's huge amounts of generated data. This attempt to build and train a CNN model using galaxy images as our domain. The Enhanced CNN model can achieve the high accuracy to morphological type of galaxies. The Enhanced CNN increase both efficiency and classification accuracy, particularly when processing large dataset. The Galaxy Zoo dataset indicated that our study can provide a tool for other astronomical research in future. The Enhanced CNN gain the overall accuracy rate are 95.29% with the performance indicator were calculated including average precision, recall, F1-score and Area under curve (AUC) is 0.9513, 0.9531, 0.9525 and 0.9853 respectively. The Enhanced CNN outperforms the various existing state-of-the models. © 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

Localize the Copy-Move Forged Region of an Image Using Improved SIFT

引用

SN computer science 2024年第1期5卷 71页

作者： Dhanaraj, Rachel Selva Sridevi, M. Department of Computer Science and Engineering National Institute of Technology Tamil Nadu Tiruchirappalli India

With the advancement in technology, digital images have become a very popular source of information. But this source of information is also being used to mislead people and society by altering the original image. One of the ways through which digital images are tampered with is the copy-move forgery method, wherein a part of an image is copied and pasted into another area inside the same image. To avoid and prevent any kind of anomalies, this paper focuses on ways to detect this copy and move forgery in an image using the keypoint-based approach in an efficient manner. The methodology involves detecting key points using Improved Scale Invariant Feature Transform (SIFT) based on which features are identified. Within the isolated descriptors, the deployed K-Nearest Neighbor (K-NN) classifier determines the closest match. Now in order to remove the outliers present in the features, Hierarchical Clustering is used to cluster similar descriptors. Experimental result has proved this methodology to be effective in detecting the forgery in an image for different kinds of related transformations. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Copy-move forgery Hierarchical clustering K-NN classifier Scale invariant feature transform

来源：评论

学校读者我要写书评

暂无评论

Predicting Macro-Economic Factors of WTI Crude Oil Using Monte Carlo Simulation

Predicting Macro-Economic Factors of WTI Crude Oil Using Mon...

引用

2024 International Conference on Advances in Data engineering and Intelligent Computing Systems, ADICS 2024

作者： Divyaa, Sharon Saravanane, Roshan Kumar, Mohan Hindustan Institute Of Technology And Science Department Of Computer Science & Engineering Chennai India

ISBN: (纸本)9798350364828

In this paper, we use regression equations and Monte Carlo simulations to study the dynamics of WTI crude oil prices. Our research takes the price of WTI crude oil as the dependent variable and looks at how it relates to nine key macroeconomic variables, most of which have to do with supply. We recognize the importance of these factors affecting the price of crude oil by using the knowledge from earlier studies. In order to make our study easier, we compile historical WTI crude oil price data from the last 60 months and combine it with the chosen macroeconomic indicators. The choice of the variables stem from their critical role in shaping crude oil markets. Through a multiple regression model, we aim to establish a comprehensive understanding of the dependencies between WTI crude oil prices and the macroeconomic factors. To ensure the robustness of our model, we assess multicollinearity among the independent variables, emphasizing that while they are related to WTI crude prices, they should not exhibit high intercorrelations. Our research provides a valuable framework for scenario generation, allowing us to explore potential future price movements based on the identical relationships. By unveiling the intricate interplay between these factors and WTI crude oil prices our study contributes to informed decision-making for investors and policymakers. © 2024 IEEE.

关键词： Crude oil

来源：评论

学校读者我要写书评

暂无评论

Intelligent Automation and Monitoring of Environmental Characteristics for Hydroculture Systems using IoT 4

Intelligent Automation and Monitoring of Environmental Chara...

引用

4th International Conference on Expert Clouds and Applications, ICOECA 2024

作者： Seth, Saksham Mishra, Sachin Kumar Malarselvi, G. SRM Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350385793

The need for adopting Hydroculture systems (viz. hydroponics, aeroponics, aquaponics) is increasing subsequently with the increase in demand for Sustainable farming solutions for populous countries like India. Industrial Hydroculture systems do exist at this current time, but these systems are still far from the reach of smaller scale implementations in terms of cost. The Ambient temperature, temperature of water, pH of water and Electrical Conductivity are considered as the key factors for the growth of plants in such systems. Some of these factors can be controlled and governed as per the requirements of plants. This work aims to develop a proof of concept and automate the process of monitoring, logging and controlling these factors with IoT. The implementation eliminates rudimentary manual monitoring of environmental characteristics, while logging data on an Azure cloud server, with insights delivered via PowerBI. © 2024 IEEE.

关键词： Environmental monitoring

来源：评论

学校读者我要写书评

暂无评论

Decision Tree Ensemble Approach for Recidivism Risk Classification Among Heinous Crime Convicts

引用

SN computer science 2024年第1期5卷 195页

作者： Singh, Aman Mohapatra, Subrajeet Department of Computer Science Engineering Birla Institute of Technology Mesra Jharkhand Ranchi India

Early prediction of violent recidivism is one of the most essential tasks of the judiciary system. Being able to accurately forecast violent recidivism in offenders with heinous crime conviction can facilitate judiciary in taking decisions about sentencing, release, parole, and probation. Additionally, because violent offenders have a higher recidivism rate than nonviolent offenders, the development of intelligent risk assessment tools for early prediction of violent recidivism becomes highly essential. However, few such approaches exist, and their efficacy in the Indian context is often limited. As a result, in the present work, the aim is to develop an computational learning-based risk assessment tool for early prediction of violent recidivism among criminals with heinous crime convictions. In particular, we classify individual offenders as high, low, or moderate risk based on a variety of factors such as anger level (a psychological emotion), demography, and psycho-social factors. Effectiveness of different machine learning models ***, PNN, SVM, KNN, LDA have been simulated for recidivism risk assessment of offenders. The current findings demonstrate that violent recidivism at the individual level can be anticipated using a bagged tree ensemble classifier achieving maximum accuracy of 89 % . © 2024, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Ensemble learning Machine learning Quantitative risk assessment Violent recidivism

来源：评论

学校读者我要写书评

暂无评论

Enhanced Visual Question Answering System Using DenseNet

Enhanced Visual Question Answering System Using DenseNet

引用

2024 International Conference on Advances in Data engineering and Intelligent Computing Systems, ADICS 2024

作者： Nithish, S. Kawinbalaji, E.M. Sudalaimuthu, T. Hindustan Institute Of Technology And Science Department Of Computer Science And Engineering Chennai India

ISBN: (纸本)9798350364828

Visual Question Answering (VQA) system represents an essential usage of computer vision and natural language processing, enabling machines to understand and react to inquiries about images. This study outlines the architecture and methodologies employed in VQA system. Initially, the image undergoes feature selection and extraction using Dense Convolutional Neural Network (DenseNet) to capture its visual aspects. Simultaneously, LSTM (Long Short-Term Memory), a recurrent neural network interprets the textual question, deciphering its semantic context. The multimodal fusion of visual and textual information with the help of attention mechanism, facilitates the creation of a cohesive representation. ViLBERT (Vision-and-Language BERT), a natural language processing technique leverages this joint representation to infer and generate accurate responses to the posed questions. The complexities of VQA systems lie in managing diverse visual content, resolving ambiguities, and reasoning about relationships within images. This system demonstrates promising applications in aiding the visually impaired, enhancing human-computer interaction, and refining image-based retrieval systems, aim to enhance their accuracy, robustness, and interpretability. © 2024 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Diagnosis Of Cardio Vascular Diseases Using Retinal Fundus Scans Via Deep Learning

Diagnosis Of Cardio Vascular Diseases Using Retinal Fundus S...

引用

2024 International Conference on Advances in Modern Age Technologies for Health and engineering science, AMATHE 2024

作者： Pryadarshne, D. Madireddy, Sai Ruthvik Vaishnnave, M.P. Paul, Mercy Sathyabama Institute Of Science And Technology Department Of Computer Science And Engineering Chennai India

ISBN: (纸本)9798350371567

Cardiovascular disease (CVD) remains a leading global health concern, necessitating early and accurate detection methods for effective intervention. This study presents a groundbreaking approach to CVD detection leveraging deep learning techniques applied to retinal fundus scans. Retinal fundus scans offer a non-invasive, cost-effective, and easily accessible source of information for potential CVD risk assessment. The utilization of deep learning algorithms, such as Convolution Neural Networks (CNNs), has demonstrated remarkable promise in identifying subtle pathological changes within the retinal vasculature and optic nerve. This study reviews the current state of research on CVD risk prediction and highlights the potential of retinal fundus scans as a valuable diagnostic tool. The integration of deep learning methods facilitates the automatic extraction of intricate features from retinal images, enabling the development of accurate and efficient CVD detection models. By examining retinal vasculature, microaneurysms, hemorrhages, and other relevant features, these models can aid in early risk stratification and timely intervention. Furthermore, this study delves into the challenges and future prospects of this novel approach, emphasizing the importance of large, diverse datasets, model interpretability, and the integration of clinical data to enhance predictive accuracy. As the field of deep learning continues to advance, this innovative strategy has the potential to revolutionize cardiovascular disease detection, enabling proactive healthcare measures and ultimately improving patient outcomes. © 2024 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

A Cybercrime Detection and Mitigation Framework for Online Credit Card Frauds

A Cybercrime Detection and Mitigation Framework for Online C...

引用

2024 International Conference on computer, Electronics, Electrical engineering and their Applications, IC2E3 2024

作者： Karnatak, Vijay Mishra, Amit Kumar Tripathi, Neha Gupta, Ashish Dumka, Ankur Sharma, Hemendra Shanker THDC Institute of Hydropower Engineering and Technology Department of Computer Science & Engineering Uttarakhand Tehri India Graphic Era Hill University Department of Computer Science and Engineering Dehradun India Department of Computer Science & Engineering Dehradun India Tula's Institute Department of Computer Science & Engineering Dehradun India Women Intitute of Technology Dehradun India Department of Computer Science and Engineering Uttarakhand India COER University Department of Computer Science and Engineering CSA Roorkee India

ISBN: (纸本)9798350388534

The word 'cybercrime' refers to any illegal behavior that is carried out with the use of computing devices, smartphones, desktops, and laptops via the Internet. This includes any type of activity that comes under 'computer crime.' The scope of these crimes and the damage they cause can vary widely, and they frequently take advantage of flaws in computer systems. Cybercrime is a massive and rapidly growing problem that can have significant ramifications not only for individuals but also for businesses, including monetary, legal, and personal problems. Money, happiness, and ideology are some of their sinister objectives. It could devastate individuals, companies, and society. These effects range from human injury and national security threats to monetary damages and damage to reputation. Law enforcement, cybersecurity specialists, and policymakers must comprehend cybercrime's causes to develop effective prevention and prosecution strategies. Cybercrime prevention must involve individuals, companies, governments, and regulatory authorities. The fight against cybercrime is an ongoing process that calls for constant vigilance and the ability to react to new dangers quickly. In this paper, we propose a cybercrime mitigation framework. We also discuss the motivation behind online criminal activity. Further, the devastating effects of cybercrimes are discussed. Further, the conjoin of cybercrimes and social security is provided. Finally, some of the future research directions related to cybercrime mitigation framework are given. © 2024 IEEE.

关键词： Critical infrastructures

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：