检索结果-内蒙古大学图书馆

Classification of X-Ray Images for the Automated Severity Grading of Knee Osteoarthritis by Ensemble Learning Through EfficientNet Architectures with Grad-CAM Visualization 2

Classification of X-Ray Images for the Automated Severity Gr...

引用

2nd International Conference on Power, Electrical, Electronics and Industrial Applications, PEEIACON 2024

作者： Dipto, Sajid Fardin Goni, Md. Omaer Faruq Rajshahi University of Engineering & Technology Department of Electrical & Computer Engineering Rajshahi6204 Bangladesh

ISBN: (纸本)9798331517984

Knee osteoarthritis (KOA) is a degenerative form of arthritis in the knee joints commonly occurring in old-aged individuals which can cause extreme pain, deterioration of bone joints, joint membranes or ligaments, and irregularity in the knee joints. Being affected by KOA, individuals experience limited social interaction and diminished quality of life. The KOA can be assessed using the Kellgren-Lawrence (KL) grading method. In this study, an ensemble model was developed to predict a KL grading reliably and precisely. Several EfficientNet architectures were implemented for the ensembling of this study. Among them, an ensemble of EfficientNetB0 and EfficientNetB4 pre-trained models gave satisfactory results compared to other deep learning or ensembling models. Here, the proposed model underwent evaluation utilizing the Osteoarthritis Initiative (OAI) dataset which contains X-ray radiographs. The dataset was split into training, testing, and validation sets with percentages of 75%, 17%, and 8% respectively. The overall multiclass classification accuracy was 96.03% with an F1-score of 93%, specificity of 98.56%, and recall of 93%. The proposed model achieved an optimistic result compared to the transfer learning models and state-of-the-art models. Gradient-Weighted Class Activation Mapping was also applied for the radiographs to implement Explainable AI for generating visual explanations for the predictions made by the deep learning networks which revealed the model's potential for grading the severity of KOA. © 2024 IEEE.

关键词： X ray radiography

来源：评论

学校读者我要写书评

暂无评论

Skin cancer classification using machine learning

Skin cancer classification using machine learning

引用

International Conference on Artificial Intelligence, Blockchain, Computing and Security, ICABCS 2023

作者： Sujatha, E. Lavanya, T. Niveditha, C.M. Saranya, S. Department of Computer Science and Engineering Saveetha Engineering College Tamil Nadu Chennai India

ISBN: (纸本)9781032669663

The skin diseases are manifest in variousforms, scarcity and low prevalence of efficient dermatologists, and the need for rapid and automated diagnosis. This aims to extend other works on dermatology by utilizing various methods of machine learning to distinguish various skin diseases and to improve the classification efficiencyby the use of taxonomy. We have trained our model using skin pictorial dataset, namely the ISIC archive and DermNet, and used the disease taxonomy, where they are available, to improve classification efficiency. At DermNet, we are establishing a new state-of-the-artmodel with a rate of 80% and an Area Under the Curve (AUC) of 98%. We have also prioritized the classification of all 622 unique sub-classes. In this data set and it also achieved 67% cure and 98% AUC. In the ISICarchives, we have classified the 7diseases with an average accuracy of 93% and an AUC of 99%. This study reveals that machine learning has very huge potential to demonstrate a different types of skin diseases with example. This plays a vital role in present diagnosis of skin diseases and help the clinicians in large-scale dermoscopic imaging. © 2024, CRC Press/Balkema. All rights reserved.

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

Advancing Water Crisis Solutions through Deep Learning 15

Advancing Water Crisis Solutions through Deep Learning

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Jaeyalakshmi, M. Vijay, K. Pradeep, R. Ram Prakash, L. Pravinesh, H. Rajalakshmi Engineering College Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350370249

Social media data is becoming more and more important for crisis and disaster management, especially when it comes to problems like urban floods and lake and pond water quality. Conventional remote sensing frequently falls short of effectively gathering this data. Our study intends to identify and classify water-related issues from social media posts by utilizing cutting-edge computer vision and deep learning techniques. ResNet is used to automatically evaluate pertinent photos, and Natural Language Processing (NLP) is used to map the locations of the concerns using metadata and summarize post descriptions. Authorities receive notifications, and direct complaints, peer review, and fact-checking are made possible through a public forum. With the help of our approach, numerous water-related problems have been successfully recognized, providing a thorough picture and enabling precise communication between the public and authorities. In order to solve these issues, this strategy promotes volunteerism and community involvement while increasing the effectiveness of disaster management. © 2024 IEEE.

关键词： Data Scraping Deep Learning Disaster Mitigation Image Classification Social Media Data

来源：评论

学校读者我要写书评

暂无评论

Disaster Management Strategies: A Systematic Review of Current Practices and Future Directions 4

Disaster Management Strategies: A Systematic Review of Curre...

引用

4th International Conference on Power, Energy, Control and Transmission Systems, ICPECTS 2024

作者： Deepika, R. Mahalakshmi, M. Nausheen Romaisa, A. Kavya, A. Sri Sai Ram Engineering College Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331508845

In India, nearly 1,38,000 people have lost their lives due to disasters between 1970 to 2021. The major challenge people face during such crisis is that there is no proper communication between the rescue team and the people due to low connectivity. To overcome this situation, we propose an app "RESCUE HUB"through which all the rescue agencies that are registered can communicate with each other and save people lives. The app promotes coordination and communication between people who are exposed to hazard and the rescue team. It is also developed in a way such that it is easy to use for everyone. The app also works in low connectivity with mesh technology and also uses GPS for real-time location tracking. Artificial Intelligence (AI) is used for finding the shortest path to reach the victim and provide them service. © 2024 IEEE.

关键词： Disaster prevention

来源：评论

学校读者我要写书评

暂无评论

PDC-ViT: source camera identification using pixel difference convolution and vision transformer

引用

Neural Computing and Applications 2025年第9期37卷 6933-6949页

作者： Elharrouss, Omar Akbari, Younes Almadeed, Noor Al-Maadeed, Somaya Khelifi, Fouad Bouridane, Ahmed Department of Computer Science and Software Engineering United Arab Emirates University Al Ain United Arab Emirates Department of Computer Science and Engineering Qatar University Doha Qatar Northumbria University Newcastle Newcastle upon Tyne United Kingdom University of Sharjah Sharjah United Arab Emirates

Source camera identification has emerged as a vital solution to unlock incidents involving critical cases like terrorism, violence, and other criminal activities. The ability to trace the origin of an image/video can aid law enforcement agencies in gathering evidence and constructing the timeline of events. Moreover, identifying the owner of a certain device narrows down the area of search in a criminal investigation where smartphone devices are involved. This paper proposes a new pixel-based method for source camera identification, integrating Pixel Difference Convolution (PDC) with a Vision Transformer network (ViT), and named PDC-ViT. While the PDC acts as the backbone for feature extraction by exploiting Angular PDC (APDC) and Radial PDC (RPDC). These techniques enhance the capability to capture subtle variations in pixel information, which are crucial for distinguishing between different source cameras. The second part of the methodology focuses on classification, which is based on a Vision Transformer network. Unlike traditional methods that utilize image patches directly for training the classification network, the proposed approach uniquely inputs PDC features into the Vision Transformer network. To demonstrate the effectiveness of the PDC-ViT approach, it has been assessed on five different datasets, which include various image contents and video scenes. The method has also been compared with state-of-the-art source camera identification methods. Experimental results demonstrate the effectiveness and superiority of the proposed system in terms of accuracy and robustness when compared to its competitors. For example, our proposed PDC-ViT has achieved an accuracy of 94.30%, 84%, 94.22% and 92.29% using the Vision dataset, Daxing dataset, Socrates dataset and QUFVD dataset, respectively. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Detection of Aphasia Using Speech Characteristics: A Comparative Analysis of Learning Models 5th

Detection of Aphasia Using Speech Characteristics: A Compara...

引用

5th International Conference on Computing and Network Communications, CoCoNet 2023

作者： Surisetty, Hima Varshini Gottimukkala, Sarayu Varma Vekkot, Susmitha Gupta, Deepa Alotaibi, Yousef A. M. Department of Computer Science and Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham Bengaluru India Department of Electronics and Communication Engineering Amrita School of Engineering Amrita Vishwa Vidyapeetham Bengaluru India Department of Computer Engineering College of Computer and Information Sciences King Saud University Riyadh11451 Saudi Arabia

ISBN: (纸本)9789819747108

Aphasia is one of the brain disorders that affects the part of the brain that is responsible for communication. This work deals with the detection of aphasia from speech features. The features extracted from the speech samples are MFCC, mel spectrogram, zero crossing rate, chroma, energy, spectral centroid, spectral roll-off, fundamental frequency and utterance duration. These different speech features were then ranked based on the SHapley Additive exPlanations (SHAPs), and the most important features were retained in an optimized feature set that was given to various machine learning models like support vector machine and decision trees and deep learning models like LSTM, LSTM with GRU, Bi-LSTM and Bi-LSTM with GRU. These models were then evaluated based on their train and test set accuracy, F1 score, recall, precision, plots of training loss and validation loss and confusion matrix. Based on the analysis of the performance metrics, Bi-LSTM with GRU was found to be the best model among all the models used. The model’s performance was evaluated using metrics like accuracy, F1 score, recall and precision when trained and tested with the optimal feature set which were 87.5%, 79.7%, 90% and 75%, respectively. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Improving Fault Tolerance of LoRaWAN With Predicting Packet Collision 28

Improving Fault Tolerance of LoRaWAN With Predicting Packet ...

引用

28th International computer Conference, computer Society of Iran, CSICC 2023

作者： Rezazadeh, Reza Sedaahat, Yasser Ghodsollahee, Ismail Azizi, Farzad Laboratory Department of Computer Engineering Mashhad Iran Amirkabir University of Technology Department of Computer Engineering Tehran Iran

ISBN: (纸本)9798350338195

the dependability of IIoT functionality is strongly influenced by its communication protocols. One of the most popular communication standards for the Internet of Things, whose features make it attractive in the IIoT field, is LoRaWAN. LoRaWAN can be considered a low-consumption competitor to cellular networks. This protocol has important features such as long-range coverage, low energy consumption, and a low implementation cost. Although the LoRaWAnfeatures make it a good choice for IoT applications, the existence of real-time constraints and a harsh environment in the IIoT field make it a challenge for network designers to guarantee the dependability of IIoT networks with LoRaWAN. Therefore, in this paper, to overcome this challenge, a novel method is presented for improving energy consumption efficiency, latency, and fault tolerance of the LoRaWAN protocol. The evaluation results show that the proposed method improves packet delivery and latency rate by 11% and 21% compared to standard LoRaWAn. © 2023 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Cloud Security: Upgradation in CSPM Configuration Setting 4

Cloud Security: Upgradation in CSPM Configuration Setting

引用

4th IEEE International Conference on Data engineering and Communication Systems, ICDECS 2024

作者： Jeya Suriya, B. Amarnath, B.K. Raghuraman, A.R. Arumugam, Chamundeswari Sri Sivasubramaniya Nadar College of Engineering Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350393354

In recent days, lot of companies are migrating to the cloud (AWS, GCP, and Azure). Compared to on-premises servers, cloud infrastructure would be easy to set up, scale-up, cost-effective, and easy to maintain as it fits to current business requirements. This work attempts in solving the problem of cloud security settings that arise due to compliance violations and misconfigurations issues when sharing cloud resources. It adds rules and provide solutions for handlings these issues in improving the business productivity. New rules for protecting cloud environment was achieved using CSPM tools (Scout suite) and monitoring & reporting the vulnerabilities visually was carried out through splunk tool. © 2024 IEEE.

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Retention: A Hybrid Approach to Employee Turnover Prediction 9

AI-Driven Retention: A Hybrid Approach to Employee Turnover ...

引用

9th International Conference on Communication and Electronics Systems, ICCES 2024

作者： Ponmalar, S. Affrin Fowmiya, N. Nandhini, C. Velammal College of Engineering and Technology Department of Computer Science and Engineering Tamilnadu Madurai India

ISBN: (纸本)9798350377972

Predictive analytics by combining ensemble learning and deep learning techniques. The first step normalizes the feature space with MinMaxScaler, which improves the performance of the algorithms. To tackle class imbalances, the Synthetic Minority Over-sampling Technique (SMOTE) is used, ensuring strong predictive modeling. An empirical study shows the effectiveness of various algorithms, including ensemble methods like CatBoost, AdaBoost, LightGBM, and Gradient Boosting Machine (GBM), whicheffectively capture complex interactions and nonlinear relationships in employee data. Furthermore, Long Short- Term Memory (LSTM) networks are employed to identify temporal dependencies in longitudinal records. The findings emphasize the approach's capability to detect subtle signals of potential turnover. By integrating these methodologies, this research provides HR professionals with valuable tools for proactive retention strategies. Ultimately, it advances HR analytics, assisting organizations in reducing attrition risks and promoting an engaged workforce. © 2024 IEEE.

关键词： Predictive analytics

来源：评论

学校读者我要写书评

暂无评论

DeepQ Based Automated Irrigation Systems Using Deep Belief WSN

引用

Intelligent Automation & Soft Computing 2023年第3期35卷 3415-3427页

作者： E.Gokulakannan Department of Computer Science and Engineering MRK Institute of TechnologyCuddalore608301TamilnaduIndia

Deep learning is the subset of artiﬁcial intelligence and it is used for effective decision *** Sensor based automated irrigation system is proposed to monitor and cultivate *** system consists of Distributed wire-less sensor environment to handle the moisture of the soil and temperature *** is automated process and useful for minimizing the usage of resources such as water level,quality of the soil,fertilizer values and controlling the whole *** mobile app based smart control system is designed using deep belief *** system has multiple sensors placed in agriculturalﬁeld and collect the *** collected transmitted to cloud server and deep learning process is applied for making *** residue analysis method is proposed for analyzing auto-mated and sensor captured ***,we used 512×512×3 layers deep belief network and 10000 trained data and 2500 test data are taken for *** is automated process once data is collected deep belief network is *** performance is compared with existing results and our process method has 94%of accuracy ***,our system has low cost and energy consumption also suitable for all kind of agriculturalﬁelds.

关键词： Wireless sensor network deepq residue automation deep belief network tensorﬂow

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：