检索结果-内蒙古大学图书馆

2024 International Conference on computer, Electronics, Electrical engineering and their Applications, IC2E3 2024

作者： Upadhyay, Deepak Sharma, Kunj Bihari Gupta, Mridul Upadhyay, Abhay Graphic Era Hill University Dept. of Computer Science and Engineering Dehradun India Graphic Era deemed to be University Dept. of Computer Science and Engineering Dehradun India Graphic Era deemed to be University Dept. of Electronics and Communication Engineering Dehradun India

ISBN: (纸本)9798350388534

This paper presents an extraordinary method to detected melanoma, the most lethal form of skin cancer, using Involutional Neural Networks (INNs). Melanoma's early detection is crucial for effecacius treatment, yet existing diagnostic methods often lack the requiring precision and scalability. INNs offer a solve through their advanced capability to adaptively process spatial information in images, a huge different from traditional convolutional techniques. Our reaserch applies INNs to melanoma detectionair, focusing on their unique involution operations that significant enhance image analysis for accurately classification. The performance of our model, assessed across different metrics including accurate, precision, recall, and F1-scores, demonstrates its superior diagnostic capability. This investigation not only underscores the potency of INNs in medical imagining but also opens up new avenues for their application across diverse analytical needs in healthcare. By advancing melanoma detection methods, we contribute to the broader goal of improving early cancer diagnose and treatment outcomes! © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Modified Deep Neural Network Approach to Identify Heart Disease using IoMT: Artificial Neural Networks or Convolutional Neural Networks!

Modified Deep Neural Network Approach to Identify Heart Dise...

引用

2024 International Conference on Intelligent Computing and Sustainable Innovations in Technology, IC-SIT 2024

作者： Nayak, Debasish Swapnesh Kumar Priyadarshini, Arpita Mahanta, Pabani Panigrahi, Soumyarashmi Meher, Sushanta Swain, Satyananda Centurion University of Technology and Management Department of Computer Science and Engineering Bhubaneswar752050 India Utkal University Department of Statistics Bhubaneswar India University Dept. of Computer Science & Engineering Bhubaneswar752050 India

ISBN: (纸本)9798350369175

Unconventional methods of predicting and treating heart disease (HD) are required because HD is still the top mortality on a global scale. This study delves into the potential of combining deep learning (DL) methods with IoMT devices to improve HD prediction and early diagnosis. Despite their usefulness, traditional risk assessment approaches can misrepresent the intricate relationship between cardiovascular risk factors. On the other hand, DL and ML algorithms can sift through mountains of data related to lifestyle, genetics, demographics, and clinical conditions to find complex relationships. To increase generalization performance across varied patient demographics and datasets, our study is focused on designing a novel DL architecture that is specialized for HD prediction. We optimize its design and hyperparameters. With feature engineering, when selecting features, we use linear discriminant analysis (LDA). In our work, two different DL techniques neural network and convolutional neural network (CNN) for HD identification are studied. We then evaluate the studied model's efficacy with measures including recall, accuracy, precision, F1-score, and Matthews Correlation Coefficient (MCC). By attaining 96% accuracy, 97% precision, 95% specificity, 97% F1-score, and 93% MCC on chosen features, the experimental findings show that a one-dimensional (1-D) CNN performs better than other models. Our suggested method, which combines DL and IoMT, offers a powerful answer to the problems of real-time health monitoring and HD risk assessment, which in turn improves early intervention and tailors treatment plans to each patient. The findings of this study highlight the promise of cutting-edge AI-driven approaches to revolutionizing cardiovascular healthcare. © 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

Mouse Cursor Controlled by Eye Movement for Individuals with Disabilities 7

Mouse Cursor Controlled by Eye Movement for Individuals with...

引用

7th International Conference on Intelligent Computing and Control Systems, ICICCS 2023

作者： Kanakaprabha, S. Arulprakash, P. Praveena, S. Preethi, G. Hussain, Thahsin Sakkeer Vignesh, V. Rathinam Technical Campus Dept of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350397253

The research study introduces an innovative method designed to help people with physical disabilities operate a computer without having to rely on a regular mouse. The solution is a mouse cursor controlled by eye movement, utilizing eye-tracking technology to enable users to control the cursor simply by looking at the screen. This innovative technology can be a life-changer for those with disabilities like spinal cord injuries, cerebral palsy, and much more. It eliminates the need of using a conventional mouse and gives them the same user experience as any other individual. The device is designed to be lightweight, compact, and ergonomic, making it comfortable for extended use. Additionally, it is user-friendly, easy to use, and compatible with all standard operating systems, including Windows, MacOS, and Linux. Eye-controlled mouse cursors have an incredible potential to revolutionize the way people with disabilities use computers. It is a step towards greater disability inclusion in the workplace and other areas of life. It provides a new level of independence and freedom, enabling users to perform tasks efficiently and effectively. The device is responsive, ensuring the user can easily perform tasks. The implementation of this technology has the potential to increase the independence and productivity of individuals with disabilities, thus improving their quality of life. The development of an eye-tracking controlled mouse is bringing revolutionary changes to the lives of disabled individuals, allowing them to effortlessly and efficiently use computers like never before. It is an innovative tool that can provide new levels of independence and freedom, making it easier for users to perform tasks and achieve their goals. © 2023 IEEE.

关键词： Eye movements

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Techniques for Object Detection in Underwater Environments

Deep Learning Techniques for Object Detection in Underwater ...

引用

2025 IEEE International Conference on Computational, Communication and Information Technology, ICCCIT 2025

作者： Praveen, R.V.S. Maindola, Meenakshi Anandhi, R.J. Thandra, Nagarjuna Bansal, Saloni Sharma, Vishal LTIMindtree Limited Telangana Hyderabad India Graphic Era Deemed to Be University Department of Computer Science & Engineering Dehradun India New Horizon College of Engineering Department of Information Science Engineering Bangalore India MLR Institute of Technology Dept. Computer Science and Engineering Telangana Hyderabad India GLA University Department of Computer Engineering and Applications Mathura India Lovely Professional University Phagwara India

ISBN: (纸本)9798331512965

The degradation of image quality caused by things like light absorption, scattering, and distortion makes object detection in underwater environments a unique challenge. Applications like marine research, environmental monitoring, and autonomous underwater vehicles (AUVs) are restricted in their effectiveness by traditional image processing techniques, which often struggle with these complexities. Recent years have seen the rise of deep learning techniques as a potent weapon in the fight against these obstacles. In order to accurately detect objects underwater, this paper investigates the use of deep learning models, specifically convolutional neural networks (CNNs). We explore cutting-edge models and methods like attention mechanisms, transfer learning, and hybrid deep learning architectures to improve detection performance in challenging underwater environments. Furthermore, we utilize data augmentation techniques and synthetic dataset generation to tackle the critical issue of limited labeled underwater datasets. From a detection accuracy and robustness perspective, the experimental results show that our suggested deep learning method is light years ahead of the competition. Marine exploration, autonomous underwater vehicle navigation, and underwater surveillance systems can all benefit from this study's new insights into how to better detect objects in real time while submerged. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A review on investigating the role of block-chain in cyber security

引用

Materials Today: Proceedings 2022年 56卷 3312-3316页

作者： Aggarwal, Bharat Kumar Gupta, Ankur Goyal, Deepak Gupta, Pankaj Bansal, Bijender Barak, Dheer Dhwaj Dept. of Computer Science and Engineering Vaish College of Engineering Haryana Rohtak India

In the issue of cyber security, block-chain, which is best known for crypto currencies, is providing an interesting answer. Block-chain has excellent safeguards against information manipulation. It supports securing access to Internet of Things (IOT) devices. Furthermore, it enables hacked IOT network instruments to be closed and unplugged. Block-chain serves as a distributed ledger system. It is used in conjunction with IOT to enable machine-to-machine interactions. It makes use of a database that contains a collection of transactions. These transactions are double-checked and recorded in a central ledger. On each node, these ledgers have been deployed. The idea of block chain is discussed in conjunction with the Internet of Things in this research study. Several studies in the fields of block-chain and IOT are considered in this paper. The necessity for block-chain and its development have been discussed in terms of its applicability difficulties. In addition, the significance of block chain in IOT-based research for online transaction security is examined. © 2022

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Unique Approach of Contextual Uniqueness Assessment of Research Papers Using Multi-Label Classification and Similarity Detection 26

Unique Approach of Contextual Uniqueness Assessment of Resea...

引用

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

作者： Tanvir, Sifat Islam, Md. Zihadul Moon Taher, Sidrat Muztahid, Shaikh Adib Biswas, Arpon Shopnil, Md. Shahariar Brac University Dept. of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798350359015

Research papers should possess a significant amount of novelty. However, proper paraphrasing of entire paper may not be identified as plagiarism. Therefore, in this work a unique approach of similarity detection technique has been proposed. At first the abstracts are used to classify which area the paper belongs to, then papers of the same area are extracted and then contextual similarity is detected using cosine similarity. For training and testing purposes, two datasets have been created using data from IEEE Xplore. Since, almost every paper has some elements of paraphrased contents, therefore, a maximum acceptable threshold has also been proposed in this paper. Maintaining the maximum threshold, how well cosine similarity was able to distinguish the novel, paraphrased, and fully plagiarised works has also been analyzed. © 2023 IEEE.

关键词： Contextual Similarity Detection Cosine Similarity Deep Learning Multi-Label Classification

来源：评论

学校读者我要写书评

暂无评论

Job Title Prediction and Recommendation System for IT Professionals 5

Job Title Prediction and Recommendation System for IT Profes...

引用

5th International Conference on Sustainable Technologies for Industry 5.0, STI 2023

作者： Rahman, Shafika Habiba, Kazi Roy, Sourav Nur, Fernaz Narin Notre Dame University Bangladesh Dept of Computer Science and Engineering Bangladesh

ISBN: (纸本)9798350394290

In the current era of globalization, finding and searching for suitable jobs heavily relies on manual systems, which often prove to be time-consuming and fail to deliver optimal outcomes. Addressing these challenges, we present an advanced job prediction system called the Job Title Prediction and Recommendation System (JoTPaRS). Leveraging machine learning techniques, JoTPaRS offers personalized multiple job title suggestions and salary range estimations based on the user's knowledge, requirements, job description, and experience. Our research focuses on developing a robust prediction system that caters to the needs of job seekers, recruiters, and HR departments. Compared to existing approaches in the field, our proposed system demonstrates remarkable performance, achieving an accuracy score of 95.63 %. In contrast, alternative methods exhibit accuracy ranges between 60% and 85% when predicting and determining job titles based on textual job descriptions. Ad-ditionally, we incorporate experience-based salary ranges for each predicted title into our recommendations to ensure accurate and reliable suggestions for users. In alignment with the paradigm of Industry 5.0 and the principles of Sustainable Technology, our research offers a pivotal step towards enhancing the efficiency and sustainability of the modern workforce, fostering a more dynamic and eco-conscious employment landscape. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

IoT-driven automatic vehicle accident rescue system implemented with Proteus 1

IoT-driven automatic vehicle accident rescue system implemen...

引用

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

作者： Hemalatha, K. Ganga Devi, S.V.S. Deepika, V. Madanapalle Institute of Technology and Science Dept. of Computer Science & Engineering-Artificial Intelligence Andhra-Pradesh Madanapalle India Madanapalle Institute of Technology and Science Dept. of Computer Science & Engineering-Cyber Security Andhra-Pradesh Madanapalle India Sri Venkateswara College of Engineering Dept. of Computer Science & Engineering Andhra-Pradesh India

ISBN: (纸本)9798350328042

IoT-driven automatic vehicle accident rescue system implemented with Proteus is an inventive solution aimed at enhancing emergency response and rescue operations following vehicle accidents. Given the rising vehicle usage alongside population growth, the frequency of accidents has also surged over time, leading to unfortunate loss of life due to delays in ambulance arrival at accident scenes. Swift transportation of accident victims to medical facilities is of paramount importance. Upon occurrence of an accident, the proposed "IoT-driven automatic vehicle accident rescue system implemented with Proteus"immediately transmits accident details to the ambulance service, investigation unit, and designated emergency contacts. Simultaneously, the accident's precise location is shared via a Google Maps link to the users' smart devices equipped with mobile network connectivity. This facilitates efficient location identification for both ambulance services and police departments. Comprising elements such as accelerometers, GPS (Global Positioning System) modules, GSM (Global System for Mobile Communication) modules, motors, buzzers, LEDs, and more, the system seamlessly integrates these components with a central microcontroller unit using Proteus software. The core objective of this initiative revolves around two key goals: rescuing drivers involved in accidents and expediting victim recovery during the critical early stages of mishaps. © 2023 IEEE.

关键词： Global system for mobile communications

来源：评论

学校读者我要写书评

暂无评论

Survey of Stock Market Price Prediction Trends using Machine Learning Techniques

Survey of Stock Market Price Prediction Trends using Machine...

引用

2023 International Conference on Artificial Intelligence and Applications, ICAIA 2023 and Alliance Technology Conference, ATCON-1 2023

作者： Gunturu, Paul Akash Joseph, Rony Revant, Emany Sri Khapre, Shailesh Iiit Naya Raipur Dept of Computer Science Engineering Raipur India

ISBN: (纸本)9781665456272

Investing in the stock market is an essential aspect of the financial sector. However, the task of identifying lucrative stocks is a challenging one that requires careful analysis. This study aims to address this challenge by comparing various Machine Learning and Deep Learning techniques for predicting stock trends. The research evaluates and compares different models, including Long Short-Term Memory (LSTM), Prophet (Automated Forecasting Procedure), Random Decision Forest, Auto-ARIMA, k-Nearest Neighbors (KNN), Linear Regression, and Moving Average techniques like SMA and EMA. Furthermore, a new hybrid model is proposed, which outperforms existing models in terms of accuracy. The models are trained and tested on a historical dataset of stocks from different industrial sectors and evaluated based on various performance metrics. The study provides insights into the accuracy of different prediction models and can help investors, traders, and financial analysts make informed investment decisions. Additionally, the findings of this research work can serve as a benchmark for future research on stock market prediction. © 2023 IEEE.

关键词： Financial markets

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Handwritten Descriptive Responses Using Machine Learning - A Survey 2

Evaluation of Handwritten Descriptive Responses Using Machin...

引用

2nd IEEE International Conference on Futuristic Technologies, INCOFT 2023

作者： Tayal, Pankhuri Shetty, Parth Praveen Pratheeksha, P. Harshita, R. Sreenath, M.V. Pes University Dept. of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350308846

Evaluation of student performances is crucial to the process of learning in an education system. Currently, the most common approach adopted throughout the education industry is largely reliant on human resources as forms of evaluators. As the gap in student-teacher ratios increases, this process becomes complicated and cumbersome and such manual assessment techniques lead to unintentional biases and inconsistency. Technology has been playing a role in aiding evaluators in the recent trends. Instead of the traditional pen and paper-based methods, modes of assessments are being digitized and so are the correction processes. While there are several successful technologies available for grading multiple-choice questions, there is still growing research for methods of evaluating descriptive questions which need to account for a degree of variations in student answers. For the last few decades, there have been many researchers working on developing a system that would act as a bridge between traditional methods and digitized evaluation systems, by using techniques like Optical Character Recognition (OCR). Various Artificial Intelligence and Machine Learning techniques have been proposed to evaluate descriptive answers automatically. This paper provides a comprehensive survey of such systems and analyses the drawbacks of the current studies. It has been observed that these systems do not consider essay-type questions that do not have a defined answer. © 2023 IEEE.

关键词： Artificial Intelligence and Machine Learning Handwritten descriptive answer evaluation Natural Language Processing OCR

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：