检索结果-内蒙古大学图书馆

2024 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2024

作者： Horng, Mong-Fong Yang, Wen-Rong Chi, Po-Cheng Zhuang, Qian-Yi Hung, Ya-Chung Su, Te-Jen Wang, Shih-Ming Department of Electronic Engineering National Kaohsiung University of Sciences and Technology Kaohsiung Taiwan Department of Computer Science and Information Engineering Cheng Shiu University Kaohsiung Taiwan

ISBN: (纸本)9798350389210

This study aims to explore the feasibility and effectiveness of applying Fuzzy Theory to the risk assessment of Human Immunodeficiency Virus (HIV) infection. In recent years, the global number of infections has rapidly expanded, with many patients unaware of their own infection status, leading to potential carriers around them. Due to the complexity and diversity of HIV infection, traditional risk assessment methods often fall short. Therefore, Fuzzy Theory is introduced as a mathematical tool to address this issue. This research uses data from a case study in a tertiary hospital in Henan Province, published in a journal on dermatology and venereology in mainland China. Firstly, variables related to HIV infection are analyzed, including Viral Load, Cluster of Differentiation 4 (CD4+) cell concentration, and protein 24 (P24) antigen, which are important indicators for measuring the extent and risk of HIV infection. Then, a risk assessment model for HIV infection is developed using Fuzzy Theory, and the risk of HIV infection is evaluated through fuzzy logic operations. The results show that the assessment model based on Fuzzy Theory can effectively quantify and assess the risk of HIV infection in different individuals, providing scientific evidence for the prevention and control of HIV epidemics. It also assists physicians in quickly understanding patients' conditions, thereby reducing the risk of HIV transmission. © 2024 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

A deep learning-based compression and classification technique for whole slide histopathology images

引用

International Journal of information technology (Singapore) 2024年第7期16卷 4517-4526页

作者： Barsi, Agnes Nayak, Suvendu Chandan Parida, Sasmita Shukla, Raj Mani Computing and Information Science Anglia Ruskin University Cambridge United Kingdom Department of Computer Science & amp Engineering Silicon University Bhubaneswar India Department of Computer Science & amp Engineering SoA University Bhubaneswar India

This paper presents an autoencoder-based neural network architecture to compress histopathological images while retaining the denser and more meaningful representation of the original images. Current research into improving compression algorithms is focused on methods allowing lower compression rates for Regions of Interest (ROI-based approaches). Neural networks are great at extracting meaningful semantic representations from images and, therefore can select the regions to be considered of interest for the compression process. In this work, we focus on the compression of whole slide histopathology images. The objective is to build an ensemble of neural networks that enables a compressive autoencoder in a supervised fashion to retain a denser and more meaningful representation of the input histology images. Our proposed system is a simple and novel method to supervise compressive neural networks. We test the compressed images using transfer learning-based classifiers and show that they provide promising accuracy and classification performance. © The Author(s) 2024.

关键词： Compression Deep learning Image classification Whole slide histopathology images

来源：评论

学校读者我要写书评

暂无评论

Improving Online Job Authenticity Detection Using Deep Learning and Focal Loss 2

Improving Online Job Authenticity Detection Using Deep Learn...

引用

2nd IEEE International Conference on Data science and Network Security, ICDSNS 2024

作者： Akhila, K. Sofi, Mukhtar Ahmad Reddy, Ch. Likitha Sarayu, A. Sannitya, M. Bvrit Hyderabad College of Engineering for Women Department of Information Technology Hyderabad India Bvrit Hyderabad College of Engineering for Women Department of Computer Science Hyderabad India

ISBN: (纸本)9798350373110

The rise of fake job postings in online job marketplaces presents a significant challenge for job seekers, necessitating robust detection methods. Existing methods often struggle to adapt to evolving fraudulent tactics, leading to suboptimal accuracy. This project introduces a novel Deep Learning approaches which are Recurrent Neural Network (RNN) variants leveraging Bi-LSTM and Bi-GRU architectures to enhance fake job detection and used a loss function for removing the imbalanced class distribution which is called 'Focal Loss'. Using the EMSCAD dataset, we trained and evaluated the performance of the proposed model against state-of-the-art methods, aiming for broader accessibility through integration into a user-friendly webserver for real-time job posting analysis which will help jobseekers to identify whether the job posting is Genuine/Fake. In this project we got accuracy of value 98.6% with precision of 85%, recall of 84% and f1-score of 85%. © 2024 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

A Review on Malware Analysis for IoT and Android System

引用

SN computer science 2023年第2期4卷 118页

作者： Yadav, Chandra Shekhar Gupta, Sangeeta STQC Ministry of Electronics and Information Technology Delhi India Department of Computer Science and Engineering Chaitanya Bharathi Institute of Technology Hyderabad India

Today all humankind is willing to avail more facilities and hopes everything should be available with a click of the button. In order to offer different services, the developers have come with inbuilt modules of several systems. This make easy system develoment and services may be offered intantly. These services are connected to the internet and accessible via Android phones and IoT devices. But this inbuilt module suffers from a lot of vulnerabilities, bugs, and default settings which may be difficult to change, as happened at the time of changing the password of home-based Wi-Fi router, which require external applications and OTP verifications, etc. Due to these issues and new hacking tools and techniques, security is a major challenge today. The basic framework to provide adequate security of the system comprises five following principles: integrity, confidentiality, availability, privacy, and nonrepudiation. The attacker may leverage advantage of any shortcomings that may lead to several issues. This work explores the cause of threads/vulnerability particularly for IoT, IIoT, SCADA, and Android application systems. The structure of this work is divided in different sections like, a short introduction to Malware, how it infects the system, and a detailed malware exploitation plan that is generally followed by expert attackers to exploit the vulnerabilities related to critical infrastructure or to defame the organization or countries is presented. In addition, General framework based introduction on IoT and Android is also presented with common vulnerabilities at every stage and respective mitigation strategies. Both static and dynamic analyses are evaluated in this work. It is identified that, for a better model design and evaluation, both are highly recommended for the implementation of effective malware detection strategies. Along with these models in order to protect the infra-structure Honeynet, IDS, IPS, Hardware-based securities like CPU and Memory and for

关键词： Android IDS IIoT IoT IPS Malware SCADA Virus

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Maize Crop Disease Classification Model in Telangana Region of South India

IEEE Transactions on AgriFood Electronics

引用

IEEE Transactions on AgriFood Electronics 2024年第2期2卷 627-637页

作者： Nagaraju, M. Chawla, Priyanka Hyderabad500043 India National Institute of Technology Department of Computer Science and Engineering Warangal506004 India

One of India's main crops, maize, accounts for 2-3% of global production. Disease detection in maize fields has become increasingly difficult due to a lack of knowledge about disease symptoms. Furthermore, manual disease detection methods take a lot of time and are not effective. Recent developments in convolutional neural networks (CNNs) have exhibited remarkable performance in disease recognition and classification. A CNN is a deep learning technique that extracts the features from an image and performs the disease classification effectively. The optimization of hyperparameters is a tedious problem that impacts the performance of a model. The main purpose of the present research is to support future research to configure suitable hyperparameters to a model. In the present work, a deep CNN is proposed for the classification of seven different diseases of maize crop. Several hyperparameters, such as image size, batch size, number of epochs, optimizers, learning rate, kernel size, and number of hidden layers, were tested with various values in the experimental approach. The obtained results show that running the model for 200 epochs improved the classification accuracy with 87.44%. It also states that choosing input image sizes of 168 × 168 and 224 × 224 resulted in a good classification accuracy of 84.66% and 85.23%, respectively. The proposed deep CNN model has attained 85.83% classification accuracy with the Adam optimizer and a learning rate of 0.001. However, the results achieved by other optimizers, such as root-mean-square propagation (81.95%) and stochastic gradient descent (79.66%), are not better when compared with the Adam optimizer. Finally, the results have provided a better knowledge in selecting appropriate hyperparameters to the application of plant disease classification. © 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

NAARI- A Portable Sanitary Napkin Vending Machine 2

NAARI- A Portable Sanitary Napkin Vending Machine

引用

2nd International Conference on Self Sustainable Artificial Intelligence Systems, ICSSAS 2024

作者： Shetty, Chinmai Malathi, S.Y. Sarojadevi, H. Ranjan Kumar, H.S. Suchetha, G. Debnath, Sanjoy Kumar Dept of Information Science and Engineering Nitte India Kle Institute of Technology Dept of Computer Science and Engineering Hubballi India Nitte Meenakshi Institute of Technology Department of Computer Science and Engineering Bangalore India Shri Madhwa Vadiraja Institute of Technology and Management Bantakal Udupi India Sahyadri College of Engineering and Management-Affiliated to Vtu Department of Information Science and Engineering Mangalore India Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura India

ISBN: (纸本)9798350368413

In an effort to address the challenges of menstrual hygiene management in developing countries, a portable sanitary pad vending machine was developed. The vending machine is powered by an Arduino Uno microcontroller and a power source that ranges between 5 to 12 volts. It features an liquid-crystal display (LCD) keypad, token acceptor with an Radio Frequency Identification (RFID) scanner for validation, and a L298d motor driver that powers two DC Servo motors to turn the spring coil system that delivers the sanitary pads or disposable bags to the user. The entire system is enclosed in a metal box for protection against damage. The LCD keypad serves as an input and output device, displaying information about the vending machine and providing instructions for its use. With the token acceptor and RFID scanner, only authorized users are granted access to the vending machine. The scanner reads the user's RFID card, which has a unique identification number, to confirm their authorization. The portable vending machine is designed to be cost-effective and easy to use, providing an innovative solution to menstrual hygiene management challenges. It is also portable and can be relocated to various locations. Overall, the vending machine serves as a critical resource in promoting menstrual hygiene and addressing the challenges that come with it. Its use ensures that individuals have access to essential sanitary products that they need to live healthy lives. © 2024 IEEE.

关键词： Liquid crystal displays

来源：评论

学校读者我要写书评

暂无评论

Study on Screw Filtration System

Study on Screw Filtration System

引用

2023 IET International Conference on engineering Technologies and Applications, ICETA 2023

作者： Chuang, Ching-Chun Lin, Bo-Yu Department of Electrical Engineering National Kaohsiung University of Science and Technology Taiwan Department of Computer Science & Information Engineering National Formosa University Taiwan

ISBN: (纸本)9781839539848

This research focuses on developing a screw detection system using Yolo series object detection models and the OpenCV module. The plan uses a camera to detect and identify different types of screws on various production lines in real time. The Yolo series object detection models allow training custom objects to see corresponding screws. The performance of three models, yolov5s, yolov7-tiny, and yolov8n, is compared based on precision, recall, mAP, and loss to determine suitability. The study used four types of screws, namely screw_1, screw_2, screw_3, and screw_4, as examples of screw detection. Over 1000 images were collected for each type of screw, resulting in 5208 images used for training. In terms of screw detection, a GUI was developed using Python modules to control the detection system. The system provides visual confirmation of recognized screw patterns and displays errors if incorrect screws are detected. The experimental results indicate that in terms of precision, yolov7-tiny achieves the highest score among the Yolo models, followed by yolov8n and yolov5s. Regarding mAP, both yolov5s and yolov8n demonstrate high scores, while yolov7-tiny's mAP falls between 0.5 and 0.6, relatively lower than the other two models. In terms of loss, yolov7-tiny and yolov5s exhibit lower loss values, indicating better prediction results, while yolov8n has a higher loss, leading to poorer recognition performance. Regarding speed, yolov5s performs at 2.6ms, yolov7-tiny at 0.38ms, and yolov8n at 4.2ms. © The Institution of engineering & technology 2023.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Enhancing Speech-to-Text Transcription Accuracy for the Bahraini Dialect

Enhancing Speech-to-Text Transcription Accuracy for the Bahr...

引用

2024 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies, 3ICT 2024

作者： Almahmood, Abdulla Al-Ammal, Hesham Albalooshi, Fatema College of Information Technology University of Bahrain Sakhir Bahrain Department of Computer Science University of Bahrain Sakhir Bahrain Department of Computer Engineering University of Bahrain Sakhir Bahrain

ISBN: (纸本)9798331533137

This study investigates means of enhancing the accuracy of Automated Speech Recognition (ASR) systems for the Bahraini dialect, a variant that has received minimal attention in natural language processing research. This is achieved through increasing the accuracy of the OpenAI Whisper model’s transcription for the Bahraini dialect. Two tailored audio datasets were created: one with a local Bahraini audio which was manually transcribed, and another that included a wider range of audio sources such TV broadcasts, podcasts, and parliament sessions. To optimize the Whisper model, several methods were used, such as sequential training on both datasets, data augmentation, and hyperparameter optimization with Optuna. The Word Error Rate (WER) significantly decreased from 181.608% to 13.54% in the results, demonstrating the efficacy of the fine-tuning techniques in raising the model’s accuracy above its original benchmarks. ©2024 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Modelling of intrusion detection using sea horse optimization with machine learning model on cloud environment

引用

International Journal of information technology (Singapore) 2024年第3期16卷 1981-1988页

作者： Jansi Sophia Mary, C. Mahalakshmi, K. Department of Computer Science and Engineering Idhaya Engineering College for Women Tamil Nadu Kallakurichi India Department of Computer Science and Engineering KIT-Kalaignarkarunanidhi Institute of Technology Tamil Nadu Coimbatore India

The growing reliance on cloud services necessitates a heightened focus on security measures to protect the integrity and privacy of crucial business data. Privacy preservation techniques, incorporating cryptographic and optimization methods, are instrumental in securely storing data in the cloud. The development of Intrusion Detection Systems (IDS) is crucial for pinpointing anomalies in data, playing a pivotal role in fortifying the reliability, confidentiality, and availability of cloud-based systems. The current surge in interest from research communities towards leveraging machine learning (ML) methods for IDS reflects a strategic shift in addressing anomaly detection within network traffic to enhance overall cloud security. Thus, this study introduces a sea horse optimization with deep echo state network-based intrusion detection (SHO-DESNID) method on the cloud environment. The goal of the SHO-DESNID technique is to accomplish security in the cloud environment via an intrusion detection process. To accomplish this, the SHO-DESNID technique undergoes a min–max normalization approach as a pre-processing step. Moreover, the SHO-DESNID approach uses the DESN model for the identification and classification of intrusions into multiple classes. To enhance the intrusion detection rate of the DESN method, the SHO algorithm is utilized for optimal hyperparameter selection. The simulation outcome of the SHO-DESNID system is tested on a benchmark IDS database and the experimental values state the supremacy of the SHO-DESNID technique compared with other approaches. © The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Cloud computing Deep learning Intrusion detection system Machine learning Privacy Security

来源：评论

学校读者我要写书评

暂无评论

Comparing Boosting and Bagging Algorithms for Image Classification

Comparing Boosting and Bagging Algorithms for Image Classifi...

引用

2024 International Conference on Optimization Computing and Wireless Communication, ICOCWC 2024

作者： Chaudhary, Chetan Gupta, Arun Murugan, R. Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India College of Engineering Teetthanker Mahaveer University Uttar Pradesh Moradabad India Department of Computer Science and Information Technology Bangalore India

ISBN: (纸本)9798350383348

Boosting and bagging are famous ensembles gaining knowledge of algorithms for photo classes. Each algorithm depends upon combining a couple of classifiers to enhance generalization accuracy, at the same time as using specific techniques to generate a final model and boosting works by using training more than one vulnerable classifier iteratively, deciding on new classifiers that concentrate on miscategorized examples from earlier rounds. Bagging then uses the same classifier with extraordinary subsets of the education dataset to generate more than one classifiers that are then blended. In phrases of generalization accuracy, boosting algorithms outperform bagging due to their capability to focus more on tough-to-classify examples. However, boosting can be more computationally intensive in phrases of education time than bagging because it continually updates and trains new vulnerable classifiers. Furthermore, boosting algorithms can also be afflicted by low bias and low variance problems, making them vulnerable to overfitting. In conclusion, boosting and bagging are effective strategies for picture type, with boosting algorithms presenting superior generalization accuracy and bagging algorithms being computationally greener. Relying on the task, the perfect method may be determined. © 2024 IEEE.

关键词： algorithm computationally generalization miscategorized vulnerable

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：