检索结果-内蒙古大学图书馆

2nd IEEE International Conference on Networks, Multimedia and Information Technology, NMITCON 2024

作者： Padmakala, S. Husain, Saif O. Poornima, Ediga Dutta, Papiya Soni, Mukesh Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Computer Science and Engineering Chennai India The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq Gokaraju Rangaraju Institute of Engineering and Technology Department of Ai&ml Bachupally Hyderabad India Bharat Institute of Engineering and Technology Department of Electronics and Communication Engineering Hyderabad India Department of Cse Uttarakhand Dehradun India

ISBN: (纸本)9798350372892

Hand Gesture Recognition (HGR) is a useful application of Human computer Interaction (HCI) but that still faces difficulty in obtaining high recognition speed and accuracy. Deep Learning (DL) has the ability to quickly and precisely pick up the features of a complex object while demonstrating exceptional performance in speech, face recognition etc. In order to address the challenge of HGR in intricate scenes, a novel method named Adaptive Habitat Biogeography-Based Optimizer (AHBBO) for tuning the hyperparameters of a Deep Convolutional Neural Network (DCNN) model. In the present research, Hand Gesture Recognition Image Dataset (HaGRID) is used which comprises gesture labels to solve hand gesture classification. Compared traditional approaches such as Multi-Culture Sign Language Using Graph and General DL Network (MCSL-GGDLN), Faster Regional Convolutional Neural Network (Faster-RCNN), and Adaptive Hough Transform with DCNN (AHT-DCNN), the AHBBO-DCNN achieves accuracy of 99.53 % and demonstrated that it is able to detect the gesture recognition categories accurately. © 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

Hybrid Detection: Enhancing Network & Server Intrusion Detection Using Deep Learning

Hybrid Detection: Enhancing Network & Server Intrusion Detec...

引用

Cybernetics, Cognition and Machine Learning Applications (ICCCmlA), IEEE International Conference on

作者： Vishnu Kurnala Swaraj Abhishek Naik Dhanush Chowdary Surapaneni Ch. Bharathsimha Reddy Computer Science & Engineering (AI&ML) Vardhaman College of Engineering Hyderabad India

In the ever-evolving landscape of cybersecurity threats, Intrusion detection systems are critical in protecting network and server infrastructure in the ever-changing spectrum of cybersecurity threats. This research introduces a hybrid detection approach that uses deep learning techniques to improve intrusion detection accuracy and efficiency. The proposed prototype combines the strength of the XGBoost and MaxPooling1D algorithms within an ensemble model, resulting in a stable and effective solution. Through the fusion of these methodologies, the hybrid detection system achieves superior performance in identifying and mitigating various types of intrusions. This paper provides an overview of the prototype's architecture, discusses the benefits of using deep learning in intrusion detection, and presents experimental results showcasing the system's efficacy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel CAD Framework with Visual and Textual Interpretability: Multimodal Insights for Predicting Respiratory Diseases 8

A Novel CAD Framework with Visual and Textual Interpretabili...

引用

8th International Artificial Intelligence and Data Processing Symposium, IDAP 2024

作者： Mukhlis, Raza Saleem, Saied Kwon, Hyunwook Hussain, Jamil Aydin, Ahmet Arif Al-Antari, Mugahed A. Sejong University College of Ai Convergence Department of Artificial Intelligence and Data Science Seoul05006 Korea Republic of Inonu University Faculty of Engineering Department of Computer Engineering Malatya Turkey

ISBN: (纸本)9798331531492

Generating textual interpretability using recent advancements in large language models (LLMs) is crucial for enhancing the efficiency of comprehensive computer-aided diagnosis (CAD) systems. This improves transparency between medical staff, intelligent CAD systems, and end-users by creating a trustworthy and effective intermediate medical diagnosis environment. In this paper, an innovative explainable throughout CAD system is introduced, designed to predict diseases from Chest X-rays (CXR) in a comprehensive scenario. The primary goal is to undertake multiple tasks that reduce the burden on medical staff and enrich CAD outcomes, including classification, visual explanations (heatmaps), and textual report generation. The proposed CAD system is developed through eight key steps: Data Collection and Annotation, Data Preparation, Text Vectorizations (Indexing), Visual Encoder, RAG-Fusion, Structural Prompt, Xai LLmTextual Reasoning (LLM Model), and Final Output (LLM textual report, image classification, and heatmap localization). The ai-based CAD system is trained and evaluated using the public benchmark MIMIC-CXR dataset with 14 different classes. The classification performance achieved an overall accuracy of 70 %, precision of 70 %, and F1-score of 0.60 %, while for text report generation, the system obtained an average BERTScore precision of 0.83, RougeL 0.16, and a Meteor score of 0.28. These promising results suggest the potential for further improvement of the CAD system and its applicability to real-world medical tasks. © 2024 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Threat Eye: Behavior Analytics for Cloud Security using ml

Threat Eye: Behavior Analytics for Cloud Security using ML

引用

International Conference on ent Computing and Control Systems (ICICCS)

作者： J. R. V. Jeny S. Shivaspandana K. Pavan N. Muthukumaran K. Akash Department of Computer Science and Engineering (AI & ML) Vignan Institute of Technology and Science Department of ECE Centre for Computational Imaging and Machine Vision Sri Eshwar College of Engineering Coimbatore India

ISBN: (数字)9798331512088

ISBN: (纸本)9798331512095

Cloud computing has developed for its storage and accessibility of data, providing flexibility, scalability, and affordability. But its extensive use has also resulted in cyberattacks and unauthorized access. The traditional intrusion detection mechanisms become ineffective for different attack patterns, insider attacks and zero-day exploits. This paper provides an efficient way to address this issue by providing a mechanism to identify the threat based on the behaviour of the user. Unlike traditional approaches this paper provides a system that monitors the user behaviour patterns considering the features such as login history, authentication attempts, session duration, file access activities, password change frequency and IP location modifications. By considering these features the attack can be detected, and the data access is restricted to prevent from unauthorized access. This paper provides handling of attack with a combination of machine learning algorithms including SVM, Decision tree and XBoost, these help in distinguishing between the attacker and the authorized user. This helps in identifying complex attack behaviours and detect insider threats. Additionally, RSA encryption is integrated to secure data transmissions, preventing unauthorized access. By combining behavioural analysis, attacks prediction, and encryption, this provides a robust cybersecurity framework.

关键词： Support vector machines Logistic regression Machine learning algorithms Cloud computing security Scalability Intrusion detection Passwords Threat assessment Encryption Monitoring

来源：评论

学校读者我要写书评

暂无评论

Ultrasonic Sensor for Blind People 2

Ultrasonic Sensor for Blind People

引用

2nd International Conference on Advancements in Smart, Secure and Intelligent Computing, ASSIC 2024

作者： Purushotham, P. Priya, D. Divya Mounika, G. Venkatesh, B. Chinnasamy, P. Kiran, Ajmeera Mlr Institute of Technology Department of Computer Science and Engineering Hyderabad India and Ai&ds Hyderabad India Bvrit Hyderabad College of Engineering for Women Department of Cse Hyderabad India

ISBN: (纸本)9798350370188

The internet of things makes everyday tasks simpler and more convenient. Using ultrasonic glasses, we come up with a clever solution to this problem that we provide here. Additionally, the glasses are equipped with a vibrator rather than a buzzer because a continuous buzzing sound would be more of a distraction than a benefit in this situation. Vibrations sent out by this device provide a person who is blind with a more precise understanding of the barriers and objects that are in front of each eye. © 2024 IEEE.

关键词： Vibrators

来源：评论

学校读者我要写书评

暂无评论

Leveraging Deep Learning with Automated Fundus Imaging for Early Detection and Diagnosis of Eye Diseases

Leveraging Deep Learning with Automated Fundus Imaging for E...

引用

International Conference on computer and Communications Technologies (ICCCT)

作者： E. Priya M. Dhinesh G. Rohitkumar M. Dheena Department of Computer Science and Engineering (AI&ML) Sri Sairam Engineering College Chennai India Department of Electronics and Communication Sri Sairam Engineering College Chennai India

ISBN: (数字)9798331537579

ISBN: (纸本)9798331537586

The most common causes of blindness and visual loss in the world are eye conditions such as diabetic retinopathy, age-related macular degeneration and glaucoma. Patients may benefit from the greatest outcomes if these illnesses are identified early and diagnosed. Fundus imaging helps in the diagnosis of eye disorders by providing detailed pictures of the optic nerve head as well as the retina. For feature extraction in normal, diabetic retinopathy, glaucoma, and macular degeneration fundus images, CNN was applied. A labeled fundus image dataset supports the training process. These datasets reverse the implications of the model not being generalizable to real world problems. Outcome is provided for a number of models including ResNet, VGG16, and designed custom CNN model. Model performance can be evaluated by means of F1-score, recall, accuracy, and precision metrics. The suggested method aims to provide an automated classification solution for eye diseases that is as scalable and effective as possible. Since early identification is vital for preventing permanent vision loss, this technique could prove beneficial in telemedicine and ophthalmology.

关键词： Glaucoma Macular degeneration Deep learning Diabetic retinopathy Accuracy Computational modeling Telemedicine Blindness Feature extraction Ensemble learning

来源：评论

学校读者我要写书评

暂无评论

Dual Interspersion and Flexible Deployment for Few-Shot Medical Image Segmentation

引用

IEEE Transactions on Medical Imaging 2025年第6期44卷 2732-2744页

作者： Cheng, Ziming Wang, Shidong Long, Yang Zhou, Tao Zhang, Haofeng Shao, Ling Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing210094 China Newcastle University School of Engineering Newcastle upon TyneNE1 7RU United Kingdom Durham University Department of Computer Science DurhamDH1 3LE United Kingdom University of Chinese Academy of Sciences UCAS-Terminus Ai Lab Beijing100049 China

Acquiring a large volume of annotated medical data is impractical due to time, financial, and legal constraints. Consequently, few-shot medical image segmentation is increasingly emerging as a prominent research direction. Nowadays, Medical scenarios pose two major challenges: (1) intra-class variation caused by diversity among support and query sets;(2) inter-class extreme imbalance resulting from background heterogeneity. However, existing prototypical networks struggle to tackle these obstacles effectively. To this end, we propose a Dual Interspersion and Flexible Deployment (DIFD) model. Drawing inspiration from military interspersion tactics, we design the dual Interspersion module to generate representative basis prototypes from support features. These basis prototypes are then deeply interacted with query features. Furthermore, we introduce a fusion factor to fuse and refine the basis prototypes. Ultimately, we seamlessly integrate and flexibly deploy the basis prototypes to facilitate correct matching between the query features and basis prototypes, thus conducive to improving the segmentation accuracy of the model. Extensive experiments on three publicly available medical image datasets demonstrate that our model significantly outshines other SoTAs (2.78% higher dice score on average across all datasets), achieving a new level of performance. The code is available at: https://***/zmcheng9/DIFD. © 2025 IEEE.

关键词： Prototypes Medical diagnostic imaging Predictive models Training Mathematical models Visualization Semantic segmentation Lesions Law Electronic mail

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Approach for Diabetes Prediction using Genetic Algorithm based Feature selection 3

Machine Learning Approach for Diabetes Prediction using Gene...

引用

3rd International Conference for Innovation in Technology, INOCON 2024

作者： Ravi Kiran, T.S. Srisaila, A. Shankar, G. Siva Sowjanya, Bodasingi Lakshmanarao, A. P.B. Siddhartha College of Arts & Science Technology Department of Computer Science A.P Vijayawada India V.R Siddhartha Engineering College Department of Information Technology A.P Vijayawada India Aditya Engineering College Department of Ai&ml Surampalem India Centurion University of Technology and Management Department of CSE Andhra Pradesh Vizianagaram India Aditya Engineering College Department of It Surampalem India

ISBN: (纸本)9798350381931

Diabetes, a prevalent and complex medical condition, demands accurate predictive models for early detection and effective management. This paper introduces a novel approach for diabetes prediction by combining genetic algorithm-based feature selection with ml classification. By combining the genetic algorithm's capability to optimize feature selection and the predictive power of ml classifier, this work offers a promising avenue for improving diabetes prediction accuracy. Two datasets from Kaggle were collected. Initially, RF applied on both datasets. Later, datasets ae balanced using oversampling technique "ADASYN". Later, genetic algorithm is employed to optimize feature selection, with the fitness function minimizing the negative accuracy of the model. The selected features are then used to train a final model, and the accuracy is evaluated on the test set. The results showcase the effectiveness of the proposed approach in enhancing diabetes prediction accuracy when compared to base model. Results from both datasets shown accuracy enhancement with GA feature selection. The selected features provide valuable insights into the influential factors contributing to diabetes outcomes. © 2024 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Robust Facial Biometric Authentication System Using Pupillary Light Reflex for Liveness Detection of Facial Images

引用

computer Modeling in engineering & sciences 2024年第4期139卷 725-739页

作者： Puja S.Prasad Adepu Sree Lakshmi Sandeep Kautish Simar Preet Singh Rajesh Kumar Shrivastava Abdulaziz S.Almazyad Hossam M.Zawbaa Ali Wagdy Mohamed CSE Department Geethanjali College of EngineeringHyderabadTelangana501301India Department of Computer Science LBEF CampusKathmandu44600Nepal School of Computer Science Engineering and Technology(SCSET) Bennett UniversityGreater Noida201310India Department of Computer Engineering College of Computer and Information SciencesKing Saud UniversityP.O.Box 51178Riyadh11543Saudi Arabia CeADAR Ireland’s Centre for AI Technological University DublinDublinD07 EWV4Ireland Operations Research Department Faculty of Graduate Studies for Statistical ResearchCairo UniversityGiza12613Egypt Applied Science Research Center Applied Science Private UniversityAmman11937Jordan

Pupil dynamics are the important characteristics of face spoofing *** face recognition system is one of the most used biometrics for authenticating individual *** main threats to the facial recognition system are different types of presentation attacks like print attacks,3D mask attacks,replay attacks,*** proposed model uses pupil characteristics for liveness detection during the authentication *** pupillary light reflex is an involuntary reaction controlling the pupil’s diameter at different light *** proposed framework consists of two-phase *** the first phase,the pupil’s diameter is calculated by applying stimulus(light)in one eye of the subject and calculating the constriction of the pupil size on both eyes in different video *** above measurement is converted into feature space using Kohn and Clynes model-defined *** Support Vector Machine is used to classify legitimate subjects when the diameter change is normal(or when the eye is alive)or illegitimate subjects when there is no change or abnormal oscillations of pupil behavior due to the presence of printed photograph,video,or 3D mask of the subject in front of the *** the second phase,we perform the facial recognition ***-invariant feature transform(SIFT)is used to find the features from the facial images,with each feature having a size of a 128-dimensional *** features are scale,rotation,and orientation invariant and are used for recognizing facial *** brute force matching algorithm is used for matching features of two different *** threshold value we considered is 0.08 for good *** analyze the performance of the framework,we tested our model in two Face antispoofing datasets named Replay attack datasets and CASIA-SURF datasets,which were used because they contain the videos of the subjects in each sample having three modalities(RGB,IR,Depth).The CASIA-SURF datasets showed an 89.9%Equal Err

关键词： SIFT pupil CASIA-SURF pupillary light reflex replay attack dataset brute force

来源：评论

学校读者我要写书评

暂无评论

FEDERATED RECOMMENDATION WITH ADDITIVE PERSONALIZATION 12

FEDERATED RECOMMENDATION WITH ADDITIVE PERSONALIZATION

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Li, Zhiwei Long, Guodong Zhou, Tianyi Australian AI Institute Faculty of Engineering and IT University of Technology Sydney Australia Department of Computer Science University of Maryland College Park United States

Building recommendation systems via federated learning (FL) is a new emerging challenge for next-generation Internet service. Existing FL models share item embedding across clients while keeping the user embedding private and local on the client side. However, identical item embedding cannot capture users' individual differences in perceiving the same item and may lead to poor personalization. Moreover, dense item embedding in FL results in expensive communication costs and latency. To address these challenges, we propose Federated Recommendation with Additive Personalization (FedRAP), which learns a global view of items via FL and a personalized view locally on each user. FedRAP encourages a sparse global view to save FL's communication cost and enforces the two views to be complementary via two regularizers. We propose an effective curriculum to learn the local and global views progressively with increasing regularization weights. To produce recommendations for a user, FedRAP adds the two views together to obtain a personalized item embedding. FedRAP achieves the best performance in FL setting on multiple benchmarks. It outperforms recent federated recommendation methods and several ablation study baselines. Our code is available at https://***/mtics/FedRAP. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Embeddings

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：