检索结果-内蒙古大学图书馆

5th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2024

作者： Sathiyapriyan, C. Manikandan, B. Gokul, S. Satheesh, Rewin Nivetha, S. Leelavathy, S. Aarupadai Veedu Institute of Technology Cyber Security Department of Computer Science and Engineering Chennai603104 India Aarupadai Veedu Institute of Technology Department of Computer Science and Engineering Chennai603104 India Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai600119 India

ISBN: (纸本)9798350395235

Ensuring the security of web applications is paramount in safeguarding sensitive data and maintaining user trust. This study presents a comprehensive overview of strategies for building and maintaining secure web applications, acknowledging their inherent limitations and outlining potential areas for future work. The strategies discussed encompass fundamental aspects of web application security, including input validation and sanitization, robust authentication and authorization mechanisms, secure communication through HTTPS, timely security patching, implementation of security headers, monitoring and logging, client-side security measures, and vigilance in handling third-party components.. This research employed algorithms include Routing Algorithms, Middleware Execution Order Algorithms, Eloquent ORM Algorithms, Encryption and Hashing Algorithms, Session Handling Algorithms, Queue Management Algorithms, and Dependency Injection Algorithms. © 2024 IEEE.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

Implementing Machine Learning Techniques for Hair Health Prediction in Follicle Futures 2

Implementing Machine Learning Techniques for Hair Health Pre...

引用

2nd International Conference on Data science and Information System, ICDSIS 2024

作者： Duraisamy, Premkumar Vidhya, V. Preetha, T. Niranjani, V. 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)9798350381665

This study explores the effectiveness of various machine learning algorithms in forecasting hair health using a comprehensive dataset incorporating individual traits and lifestyle elements. Logistic regression, random forest, and AdaBoost were assessed, with random forest notably achieving a remarkable 94.6% accuracy. These results emphasize machine learning's potential for precise, non-invasive personalized hair health predictions. Key factors such as genetics, diet, and stress were pinpointed, informing targeted care approaches. The research underscores machine learning's promise in accurately anticipating hair loss and suggests future avenues for expanding datasets, integrating diverse data sources, and developing user-friendly tools for improved hair care management. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Renal Cyst Detection using Deep Learning 2

Renal Cyst Detection using Deep Learning

引用

2nd IEEE International Conference on IoT, Communication and Automation technology, ICICAT 2024

作者： Velusamy, Dhanalakshmi Harish, U. Lingesh, P. Kaviyarasan, P. Cyril Poornaraj, J. Prem, D. Sharan, K. Jeppiaar Institute of Technology Department of Computer Science and Engineering Chennai India Jeppiaar Institute of Technology Bachelor of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350368109

Around the world, kidney diseases are a major open prosperity concern. Environmental components, tall salt levels, and additional minutes are all risk factors. Kidney dissatisfaction can be a critical prosperity issue, and it has gotten to be more transcendent in afterward a long time, with horribleness and mortality extending by 100% over the ultimate decade. Several kidney sicknesses, tallying those caused by renal stones and rankles, can be easily recognized through CT imaging. In separate, manual examination of a CT picture is time-consuming and requires a portion of effort. Deep learning methods, checking 3D CNNs, can be utilized to recognize plans of hurt and make assurance easier. By planning these calculations on clarified datasets, they can distinguish kidney stones and rankles with tall accuracy. Despite its potential to assist inside the early recognizing verification and treatment of ailments, modified revelation has to be utilized with caution and not as an elective to restorative information. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Predictive Vigilance: AI And ML Methods For DDOS Attack Detection And Forecasting 2

Predictive Vigilance: AI And ML Methods For DDOS Attack Dete...

引用

2nd IEEE Global Conference on Communications and Information Technologies, GCCIT 2024

作者： Ravikumar, S. Rajendran, P. Revathi, S. Kumar, K. Antony Saranraj, S. Vel Tech Rangarajan Dr Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Chennai India Cmr Institute of Technology Department of Computer Science & Engineering Telangana Hyderabad India Kongunadu College of Engineering and Technology Department of Computer Science & Engineering Trichy India

ISBN: (纸本)9798350388916

Distributed network attacks are referred to, usually, as Distributed Denial of Service (DDoS) attacks. These attacks take advantage of specific limitations that apply to any arrangement asset, such as the framework of the authorized organization's site. In the existing research study, the author worked on an old KDD dataset. It is necessary to work with the latest dataset to identify the current state of DDoS attacks. They used a machine learning approach for DDoS attack types classification and prediction. For this purpose, used Random Forest and XGBoost classification algorithms. To access the research proposed a complete framework for DDoS attacks prediction. For the proposed work, the UNWS-np-15 dataset was extracted from the GitHub repository and Python was used as a simulator. After applying the machine learning models, the generated a confusion matrix for identification of the model performance. In the first classification, the results showed that both Precision (PR) and Recall (RE) are 89% for the Random Forest algorithm. The average Accuracy (AC) of the proposed model is 89% which is superb and enough good. In the second classification, the results showed that both Precision (PR) and Recall (RE) are approximately 90% for the XGBoost algorithm. The average Accuracy (AC) of the suggested model is 90%. By comparing present work to the existing research works, the accuracy of the defect determination was significantly improved which is approximately 85% and 79%, respectively. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Mask Attention-Based Vision Transformer (MA-ViT) for PCB Defect Detection 6

Mask Attention-Based Vision Transformer (MA-ViT) for PCB Def...

引用

6th IEEE International Conference on Emerging Smart Computing and Informatics, ESCI 2024

作者： Hasan, Jahid Tamanna, Ummey Habiba Rimi, Habiba Akter Akhter, Shamim Shanto-Mariam University of Creative Technology Department of Computer Science and Engineering Dhaka Bangladesh Department of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798350306613

PCBs (Printed Circuit Boards) are valuable components in a wide variety of electronic devices, which are used for industry purposes. PCB defects can have detrimental effects on system performance, resulting in malfunctions, failures, compromised connectivity, and signal distortion. It is essential to detect and classify these defects promptly and effectively. In light of the advancements made in artificial intelligence, this topic has garnered significant attention in the research community, resulting in numerous dedicated research and publications. A recently published automated model utilizing CNN-based autoencoders has shown promise in detecting and classifying various problems. However, some challenges such as overfitting, transitive invariance, and model performance need to be addressed explicitly. To address these challenges, we propose a Mask Attention-based Vision Transformer (MA-ViT) model, which offers a promising solution. The MA-ViT model has demonstrated exceptional performance, showcasing its effectiveness in overcoming the aforementioned issues. © 2024 IEEE.

关键词： Deep Learning MA-ViT Mask attention PCB defect detection and classification vision transformer

来源：评论

学校读者我要写书评

暂无评论

Simulating Application Driven Mobile D2D underlay Networks using Gym API 17

Simulating Application Driven Mobile D2D underlay Networks u...

引用

17th International Conference on COMmunication Systems and NETworkS, COMSNETS 2025

作者： Batabyal, Suvadip National Institute of Technology Department of Computer Science & Engineering Durgapur India

ISBN: (纸本)9798331531195

Device-to-device (D2D) communication underlay cellular network improves spectral efficiency by reusing cellular resources over short and low-power links between the devices. For this, the D2D paradigm is considered to be an integral part of all kinds of future networks and is an active area of research at different levels. This requires a simple, configurable, scalable, and realistic evaluation of the protocols proposed for the D2D networking paradigm. Although there exists a few platform to evaluate a D2D underlay network, they have one or more of the following drawbacks: (i) long development time and complex environment, (ii) limited support for mobility, (iii) no support for application specific development and evaluation. In this work, we developed a framework for simulating an application-driven mobile D2D underlay network using the Gym API, where D2D connections are made spontaneously based on the application requirements. The proposed framework includes modules for generating application-specific traffic, buffer for transmission and caching of application data, and mobility management. This complements several earlier works on application (or utility) driven resource allocation in D2D underlay network. The framework is used to evaluate a D2D network using different mobility models and performance of cache based video streaming in a D2D underlay network. Finally, the framework is compared with ns-3 and OMNET++ simulators and is observed to have lower CPU utilization and run-time under the same network settings. © 2025 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Detection and Navigation of Unmanned Vehicles in Wooded Environments Using Light Detection and Ranging Sensors

引用

Sensors and Materials 2023年第11期35卷 3637-3654页

作者： Zhang, Zhiwei Jhang, Jyun-Yu Lin, Cheng-Jian School of Electronic Information Engineering Hebei University of Technology Tianjin300401 China Department of Computer Science and Information Engineering National Taichung University of Science and Technology Taichung404 Taiwan Department of Computer Science & Information Engineering National Chin-Yi University of Technology Taichung411 Taiwan

With the advancement of automatic navigation, navigation control has become an indispensable core technology in the movement of unmanned vehicles. In particular, research on navigation control in outdoor wooded environments, which are more complex, less controlled, and more unpredictable than indoor environments, has received widespread attention. To realize the movement control and obstacle avoidance of unmanned vehicles in unknown environments, in this study, we use light detection and ranging (LiDAR) sensors to sense the surrounding environment. By plane meshing the point cloud reflected from LiDAR, we can instantly establish feasible regions. At the same time, using the artificial potential field algorithm, a stable obstacle avoidance and navigation path is planned for use in an unknown environment. In an actual woods navigation experiment to evaluate our proposed LiDAR detection method, we used an independently developed unmanned vehicle with Ackermann steering geometry. Experimental results indicate that the proposed method can effectively detect obstacles. The accuracy requirement is within 30 cm from the navigation target, and the experimental results show that the average navigation success rate of the proposed method is as high as 85%. The experimental results demonstrate that the system can stably and safely navigate in scenarios with different unknown environments. © MYU K.K.

关键词： Navigation

来源：评论

学校读者我要写书评

暂无评论

OSINT at GenAI Detection Task 1: Multilingual MGT Detection: Leveraging Cross-Lingual Adaptation for Robust LLMs Text Identification 1

OSINT at GenAI Detection Task 1: Multilingual MGT Detection:...

引用

1st Workshop on GenAI Content Detection, GenAIDetect 2025

作者： Agrahari, Shifali Singh, Sanasam Ranbir Department of Computer Science and Engineering Indian Institute of Technology Guwahati India

ISBN: (纸本)9798891762053

Detecting AI-generated text has become increasingly prominent. This paper presents our solution for the DAIGenC Task 1 Subtask 2, where we address the challenge of distinguishing human-authored text from machine-generated content, especially in multilingual contexts. We introduce Multi-Task Detection (MLDet), a model that leverages Cross-Lingual Adaptation and Model Generalization strategies for Multilingual Machine-Generated Text (MGT) detection. By combining language-specific embeddings with fusion techniques, MLDet creates a unified, language-agnostic feature representation, enhancing its ability to generalize across diverse languages and models. Our approach demonstrates strong performance, achieving macro and micro F1 scores of 0.7067 and 0.7187, respectively, and ranking 15th in the competition1. We also evaluate our model across datasets generated by different distinct models in many languages, showcasing its robustness in multilingual and cross-model scenarios. © 2025 International Conference on Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Air Pollution Monitoring and Forecasting

Machine Learning-Based Air Pollution Monitoring and Forecast...

引用

International Conference on Machine Learning and Big Data Analytics, ICMLBDA 2023

作者： M, Naga Ravindra Babu Durga Satish, M. Prasanthi, B.V. Jagadeesh, S.V.V.D. Janardhana Naidu, J.N.S.S. Pradeep, Immidi Kali Department of Computer Science & Engineering Vishnu Institute of Technology Bhimavaram India

ISBN: (纸本)9783031513374

Today, the governments of developing countries are focusing more on air pollution. Air pollution occurs because of factors like fuel use in vehicles such as private transport, industries, and, more importantly, the burning of waste like plastic and grass. These are a few of the elements that contribute to air pollution. All of these factors have an impact on air quality. It can be calculated or determined by using PM2.5 and other variables. If this level is high, then it may be a serious problem for people’s health. To control air pollution, continuous pollution monitoring is required. Here, different machine learning models like linear regression, decision tree classifiers, random forest classifiers, and KNN classifiers are used to detect whether the sample of air is polluted or not. On the basis of previous readings of PM2.5, NH3, CO, NO, NOx, and NO2, SO2 is used to predict the future values of the AQI. By collecting datasets of the daily atmospheric conditions of a specific city or town, this system is able to predict the PM2.5 level and also detect the air pollution status. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Air quality

来源：评论

学校读者我要写书评

暂无评论

Generative Adversarial Networks (GANs) for Education: State-Of-Art and Applications

Generative Adversarial Networks (GANs) for Education: State-...

引用

International Conference on Power engineering and Intelligent Systems, PEIS 2024

作者： Kavyashree, K.N. Shidaganti, Ganeshayya Department of Computer Science and Engineering Ramaiah Institute of Technology Bangalore India

ISBN: (纸本)9789819767090

In the ever-changing educational landscape, technology integration has become essential to improving students’ understanding of basic topics. The COVID-19 pandemic hastened the transition to online education while posing new difficulties for teachers and students alike. The disruption of traditional classroom dynamics was exacerbated by the lack of digital innovation and interactive instructional tools, which made student participation less effective. Traditional teaching paradigms must make way for ones that encourage self-directed learning and fortify technical infrastructure in order to handle these difficulties. Generative Adversarial Networks (GANs), a cutting-edge use of deep learning, are starting to revolutionize educational technology. With the use of GANs, a range of features that are tailored to the individual learning preferences of each student may be created, thereby bridging knowledge gaps and providing a more dynamic and interesting learning environment for students. This research investigates several state-of-the-art features that leverage technology linked to GANs to enhance students’ virtual learning environments. The novel applications of generative adversarial networks are explored, with a focus on applications for student observation, academic performance, questioning and answering, and personalized learning. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Generative adversarial 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：