检索结果-内蒙古大学图书馆

3rd International Conference on Smart Data Intelligence, ICSMDI 2023

作者： Bhagya Lakshmi, A. Pradeep, R. Seshadri, K.S. Shriraam, B. Easwari Engineering College Dept. of Computer Science & Engineering TN India

ISBN: (纸本)9781665464871

Everything in today's highly connected digital world is increasingly dependent on instantaneous global data transfers. Internet efficiency facilitates our daily lives. Sharing information online presents significant security dangers and difficulties in the modern day. The use of cryptography is the means through which sensitive information can be protected from various threats. Improved cryptosystems technology is a no-brainer for securing communication networks. An improved cryptosystem is the focus of our research, and to that end we have presented a novel method of data encryption and decryption that guarantees increased efficiency over current best practises. This research work has proposed a noise image encryption and decryption scheme, wherein the noise signal is randomly selected to set the initial values for a chaotic system which also enhances the security of the system. for understanding the effectiveness of the proposed system. Experimental results confirm that the proposed chaos-based cryptosystem is efficient and suitable for information (image) transmission in a highly secured way. This study has developed a file encryption system, where encrypted file is saved to decrypt and download later. The main difference between the existing and proposed system is the implementation of file encryption system using noise images that store key values inside it. © 2023 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Predicting the Likelihood of a Recurrent Febrile Seizure Using Thermographic Images and Deep Learning with Rules Generation 1

Predicting the Likelihood of a Recurrent Febrile Seizure Usi...

引用

1st International Conference on AIML-Applications for engineering and Technology, ICAET 2025

作者： Patil, Pratima Deshpande, Deepa S. MGM University Jawaharlal Nehru Engineering College Dept. of Computer Science and Engineering Chhatrapati Sambhajinagar431003 India

ISBN: (纸本)9798350355611

Recurrent febrile seizures are a common concern in children, often triggered by rapid changes in body temperature during fever episodes. For rapid action and care, early and accurate seizure recurrence prediction is crucial. Limited techniques were developed for predicting the likelihood of a Recurrent Febrile Seizure using a Thermographic image. Several drawbacks were considered for recurrent febrile seizure prediction such as lower performance, high time consumption, and error rate. Hence, the proposed technique is introduced to provide an efficient Deep Learning (DL)-based technique. Initially, the data is gathered from datasets, and the Intra-Attentional Convolutional ResNet (InAtt-CRNet) with the Yolov5-Face model detects the face and reduces the processing time by tacking the face with a bounding box. The patient's forehead or nose temperature is monitored using the Region of Interest (ROI) finding approach following face detection and tracking in each frame. Then, the temperature is predicted using the Enhanced Convolutional Capsule Network (EC2Net). The body temperature, age, duration of fever, and family history are used to construct the clinical decision rule. The Twin-directional Gated Long Short-term memory (TdG-LSTM) is used to predict the likelihood of a subsequent febrile seizure. The proposed technique achieves 98.16% accuracy, 98.45% precision, 0.12 RMSE, and 29 seconds as processing time. © 2025 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

An IoT-Based Health Care Solution: A Smart Medical Box 4

An IoT-Based Health Care Solution: A Smart Medical Box

引用

4th Asia Service sciences and Software engineering Conference, ASSE 2023

作者： Khan, Adib Mahamud Kabir, Raihan Sudha, Nigar Sultana Ahmed, Nadeem Watanobe, Yutaka Islam, Md Rashedul Dept. of Computer Science and Engineering University of Asia Pacific Dhaka1216 Bangladesh Dept. of Computer Science and Engineering University of Aizu Aizuwakamatsu Fukushima Japan

ISBN: (纸本)9798400708534

IoT in healthcare is intended to keep people safe and healthy, with the primary goal of lowering healthcare costs and reducing the involvement of caregivers in the coming years. This research proposes a smart IoT-based health- care system, which includes an intelligent medical box connected to a mobile app for continuous health monitoring. Patients can get regular health care with the help of this medical box with a dedicated app and web server. The proposed system helps the patients to check their heart rate, temperature, and oxygen level, all using just one device. It provides an easy way for the user to do this checkup by themselves without any help from caregivers or even doctors. Moreover, the proposed system assists the patients in taking the proper medicinal drugs in due time with an SMS and buzzer alarm. It additionally creates a clean verbal exchange between medical doctors and patients rather than bodily contact. The proposed system can be accessed through an app that stores all the detailed health reports about the patient. Doctors can easily check the patient's report and can change the prescriptions based on the condition of the reports, if necessary. This box also consists of an emergency button that the user can use in case of any emergency to notify their respective caregivers immediately. © 2023 ACM.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Screening and Ranking resume's using Stacked Model 1

Screening and Ranking resume's using Stacked Model

引用

1st IEEE International Conference on Advances in Electronics, Communication, Computing and Intelligent Information Systems, ICAECIS 2023

作者： Kavitha, D. Padmavathi, B. Sushanth, V. Yashwanth, P. Yuvaraj, R. Easwari Engineering College Dept. of Computer Science & Engineering TN India

ISBN: (纸本)9798350348057

Finding the top candidates for a position is the aim of the resume screening process. The application must make use of machine learning methodologies as well as natural language processing to rate candidates in real time. Natural language processing (NLP) and machine learning methods are used to rate resumes. The output would be the resume of a top candidate, with resumes and job descriptions serving as the input. The output's results are obtained instantly. String matching, Cosine Similarity, and TF-IDF will all be done with Mon. Existing systems are straightforward and efficient, but they lack precision, efficiency, and processing capacity. © 2023 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Leveraging Network Vulnerability Detection using Improved Import Vector Machine and Cuckoo Search based Grey Wolf Optimizer 1

Leveraging Network Vulnerability Detection using Improved Im...

引用

1st International Conference on Optimization Techniques for Learning, ICOTL 2023

作者： Preethi, P. Vasudevan, I. Saravanan, S. Krishna Prakash, R. Devendhiran, A. Kongunadu College of Engineering and Technology Dept. of Computer Science and Engineering Trichy India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Dept. of Computer Science and Engineering Chennai India Kl University Dept. of Computer Science and Engineering Vijayawada India Sona College of Technology Dept. of Information Technology Salem India Vivekanandha College of Engineering for Women Dept. of Computer Science and Technology Namakkal India

ISBN: (纸本)9798350328042

In the current interconnected and susceptible digital environment, the demand for reliable network attack prediction systems has reached a critical level. This research paper presents a novel approach for network intrusion detection utilizing the Improved Import Vector Machine (IVM) classification algorithm combined with feature selection using Cuckoo Search based Grey Wolf Optimization (CS-GWO). The aim is to improve the accuracy and effectiveness of intrusion detection systems by selecting the most relevant features and employing a powerful classification algorithm. The proposed methodology begins with data preprocessing, ensuring the dataset is appropriately cleaned and normalized. Subsequently, the CS-GWO algorithm is applied for feature selection, leveraging the strengths of both Cuckoo Search and Grey Wolf Optimization. This hybrid approach efficiently explores the search space to identify the optimal feature subset that contributes to accurate intrusion detection. Once the feature selection process is completed, the IVM classification algorithm is employed to classify network instances into intrusion or normal categories. The IVM algorithm is chosen for its ability to handle high-dimensional data and its robustness in dealing with imbalanced datasets commonly encountered in network intrusion detection. To evaluate the performance of the proposed approach, extensive experiments are conducted using benchmark datasets. Various evaluation metrics such as accuracy, precision, recall, and F1 score are utilized to assess the effectiveness of the system in detecting network intrusions. The results demonstrate that the combination of IVM classification and CS-GWO feature selection significantly improves the accuracy and efficiency of network intrusion detection. The selected features obtained through CS-GWO contribute to enhanced classification performance, enabling the system to accurately identify and respond to potential intrusions in real-time scenarios. © 2023 IE

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

DeepFuzzLoc Positioning: A Unified Fusion of Fuzzy Clustering and Deep Learning for Scalable Indoor Localization Using Wi-Fi RSSI 13

DeepFuzzLoc Positioning: A Unified Fusion of Fuzzy Clusterin...

引用

Joint 13th International Conference on Soft Computing and Intelligent Systems and 25th International Symposium on Advanced Intelligent Systems, SCIS and ISIS 2024

作者： Mahali, Muhammad Izzuddin Leu, Jenq-Shiou Achmad Sulistyo Putro, Nur Widyawan Prakosa, Setya Avian, Cries National Taiwan University of Science and Technology Dept. of Electronic and Computer Engineering Taipei Taiwan Universitas Negeri Yogyakarta Dept. of Electronics and Informatics Engineering Education Yogyakarta Indonesia Universitas Gadjah Mada Dept. of Computer Science and Electronics Yogyakarta Indonesia

ISBN: (纸本)9798350373332

This research introduces a novel method for indoor positioning by integrating Fuzzy C-Means clustering with deep learning autoencoders, leveraging Wi-Fi RSSI fingerprinting for precise location prediction and building and floor level classification within a unified framework. The approach combines the comprehensibility of Fuzzy C-Means (FCM) with the robust feature extraction capabilities of deep autoencoders through a dual-phase strategy: extensive offline training utilizing RSSI fingerprint data followed by real-time online position prediction. The model's performance was rigorously tested using 5-Fold cross-validation, examining its effectiveness both with and without the integration of FCM on various cluster numbers. Evaluation metrics, including Euclidean distance error for regression and accuracy, F1-score, precision, and specificity for classification effectiveness, were used for comparative analysis. The results were visualized through regression plots, confusion matrices, and learning curves, supplemented by t-SNE visualizations that provide profound insights into the feature space. These detailed analyses highlight the considerable promise of this integrated approach in enhancing the accuracy and reliability of indoor positioning systems. © 2024 IEEE.

关键词： Fuzzy clustering

来源：评论

学校读者我要写书评

暂无评论

An optimal group-wise non-rigid image registration technique based clinical decision support for dementia prediction

引用

Multimedia Tools and Applications 2025年 1-26页

作者： Mary, F. Sheeja Asanambigai, V. Fred, A. Lenin Assistant Professor Senior Grade School of Computing Dept. of CSE Vel Tech Rangarajan Dr. Sagunthala R & D Institute of Science and Technology Chennai India Computer Science and Engineering Annamalai University Chidambaram India Dept. of CSE Mar Ephraem College of Engineering and Technology Marthandam India

The fundamental challenge in clinical practice is predicting whether patients with cognitive symptoms or impairment will improve or stay stable. Population ageing is a worldwide phenomena with various impacts. Among dementia, Alzheimer disease (AD) is common in the elderly which is the most common form of dementia and may contribute to 60–70% of cases. An early and precise AD diagnosis enhances patient quality of life. In this study, we propose an optimal group-wise non-rigid image registration technique for dementia (AD) prediction. We introduce an improved cuckoo search optimization (ICSO) algorithm to search optimal group-wise dense correspondence in large image sets in non-rigid image registration which reduce dimensionality of the search space. Then, we illustrate a teacher-student learning based optimization algorithm which cooperates with PLS regression to extract deformation which separates the relationship information suitable for each other from the raw relationship information. After that, we compute the distribution of morphologies of age by fitting smooth percentile curves to these scores using hybrid capsule neural network with least Median Square (hybrid CNN-LMS) curve fitting model. Finally, the simulation results of proposed hybrid CNN-LMS technique are compared to the existing methods to analyze the measures. We observed that the accuracy of our proposed hybrid CNN-LMS technique is 96.23% and 95.82% for RSS and ANDI datasets respectively. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

DeepLeaf-Attentive: Integrating Attention Mechanisms for Crop Leaf Disease Identification 26

DeepLeaf-Attentive: Integrating Attention Mechanisms for Cro...

引用

26th International Conference on computer and Information Technology, ICCIT 2023

作者： Ahmed, Tanvir Mou, Farzana Sharmin Engineering Dhaka University of Engineering & Technology Dept. of Computer Science Dhaka Gazipur Bangladesh University of Birmingham Dept. of Computer Science Birmingham United Kingdom

ISBN: (纸本)9798350359015

Crop leaf diseases have a detrimental impact on agricultural production. Visual inspection by organic farmers for disease detection is time-consuming and ineffective. To address this, we propose DeepLeaf-Attentive, a novel deep learning model for classifying crop leaf diseases. It combines MobileNet architecture with additional layers and attention mechanism. It is trained on a dataset of 30,000 images including data augmentation representing 60 classes with 500 images per class. The model achieves outstanding performance, with 97.21% accuracy, 97.72% precision, 97.43% recall, 97.49% F1-score and 18.0 ms inference time. Comparative evaluations against state-of-the-art approaches demonstrate the superiority of DeepLeaf-Attentive in crop leaf disease classification. By providing a reliable and efficient tool, our model will empower farmers to accurately identify and categorize various crop leaf diseases, facilitating informed decision-making and enabling the implementation of targeted and timely treatment strategies. The adoption of DeepLeaf-Attentive can significantly improve disease management practices in agriculture, leading to enhanced crop yields, reduced economic losses, and sustainable farming practices. By revolutionizing crop leaf disease identification, our research contributes to the advancement of precision agriculture, benefiting farmers and supporting global food security. © 2023 IEEE.

关键词： Attention Mechanisms Crop Leaf Disease Identification Deep Learning DeepLeaf-Attentive MobileNet Transfer Learning

来源：评论

学校读者我要写书评

暂无评论

Stock Market Prediction Using Genetic Algorithm Assisted LSTM-CNN Hybrid Model 14

Stock Market Prediction Using Genetic Algorithm Assisted LST...

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Nikhil, Shreyas Sah, Rahul Kumar Kumar Parki, Santosh Tamang, Til Bikram Somashekhara Reddy, D. Mahesh, T.R. Faculty of Engineering and Technology Dept. of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350335095

Stock price prediction has always been a tough task for all the stakeholders involved. This paper focusses on four different models, namely LSTM, CNN, LSTM-CNN, and Genetic Algorithm-Assisted LSTM-CNN (GA-LSTM-CNN) for stock price prediction. The day-to-day stock prices of a certain company for a period of more than 10 years make up the dataset utilized in this study. Root mean square error (RMSE) has been utilized as performance metric for each model. Outcomes of our experiment show that the GA-LSTM-CNN model performed better than other models with an RMSE value of 0.0064 upon training and an RMSE value of 0.03 upon testing. The GA-LSTM-CNN model combines the strengths of LSTM as well as CNN models with the help of a genetic algorithm, which helps in optimizing the hyperparameters. According to the results, the GA-LSTM-CNN model can be very helpful for the stakeholders in predicting future stock values. © 2023 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Balancing Safety and Security in Autonomous Driving Systems: A Machine Learning Approach with Safety-First Prioritization 40

Balancing Safety and Security in Autonomous Driving Systems:...

引用

40th Annual computer Security Applications Conference Workshops, ACSACW 2024

作者： Hasani, Afshin Nia, Mehran Alidoost Atani, Reza Ebrahimi University of Guilan Dept. of Computer Engineering Rasht Iran Shahid Beheshti University Faculty of Computer Science and Engineering Tehran Iran

ISBN: (纸本)9798331532819

In the era of autonomous vehicles (AVs), ensuring the safety and security of the system is an ongoing challenge, particularly when faced with increasingly cyber-Attacks such as GPS spoofing and man-in-The-middle. This paper presents a novel reinforcement learning (RL)-based framework that prioritizes safety over security concerns in AVs, ensuring that life-critical tasks such as collision avoidance and speed control are always maintained, even in the presence of security threats. Our system leverages the MAPE-K loop to dynamically adapt to changing conditions, using RL in the Analyzing phase to make real-Time decisions that maximize cumulative safety rewards while addressing security risks that directly affect operational integrity. We demonstrate how our RL-based self-Adaptive system mitigates security threats while maintaining safe driving behaviors through various simulations and experiments. The proposed system shows significant improvements in collision avoidance and threat detection, ultimately ensuring that the AV's safety is preserved in even the most challenging scenarios. © 2024 IEEE.

关键词： Adversarial machine learning

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：