检索结果-内蒙古大学图书馆

4th International Conference on Ubiquitous Computing and Intelligent Information systems, ICUIS 2024

作者： Hossain, Javed Alam, Md. Nur Akib, Mohammad Yasin Nur Kogoya, Krisdahim Nanjing University of Information Science and Technology Dept. of Artificial Intelligence Nanjing China Nanjing University of Information Science and Technology Dept. of Computer Science and Technology Nanjing China

ISBN: (纸本)9798331529635

The incorporation of modern technologies into education has transformed how learning is seen and assessed, with a rising emphasis on understanding student behavior using facial expression recognition (FER). Recognizing students' emotional and cognitive states can provide vital insights into their engagement and learning styles, allowing teachers to adjust their teaching tactics in real time. Traditional machine learning algorithms have been used to solve this problem, but they frequently struggle with the complexity of facial expressions and big datasets, resulting in limitations in accuracy and processing efficiency. This study explores the potential of quantum computing in addressing these challenges through the development of a Deep Quantum Convolutional Neural Network (QCNN) architecture. By combining the advanced image processing capabilities of convolutional neural networks (CNNs) with the computational power of quantum features such as superposition and entanglement, we aim to enhance the detection of facial expressions that reflect students' engagement, concentration, frustration, and satisfaction. Finally, the result demonstrates a classification accuracy of 91.58 © 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

Active Element Arrangement and Prediction Model for Channel Estimation in IRS-Assisted systems

Active Element Arrangement and Prediction Model for Channel ...

引用

2024 IEEE Region 10 Conference, TENCON 2024

作者： Tsuchiya, Yoshihiko Suga, Norisato Uruma, Kazunori Fujisawa, Masaya Tokyo University of Science Dept. of Information and Computer Technology Tokyo Japan Shibaura Institute of Technology Dept. of Information and Communication Engineering Tokyo Japan Kogakuin University Dept. of Computer Science Tokyo Japan

ISBN: (纸本)9798350350821

Intelligent reflecting surfaces (IRS) that can dynamically control the phase of radio waves and reflect them are attracting attention to realize non line-of-sight communication in the high-frequency band. Channel state information (CSI) is estimated to properly control the phase, however the overhead of the estimation reduces communication efficiency. To reduce the overhead, IRS systems with active elements that perform channel estimation are considered. One approach treats the partial CSI obtained from the active elements as an image and utilizes a super-resolution technique to predict the entire CSI. However, because the active elements are arranged in grid, prediction is difficult when the active elements spacing and the CSI fluctuation period match. In this study, we propose a new arrangement that gathers the active elements in the center of the IRS. Furthermore, we regard prediction as an image-inpainting problem that recovers missing pixels from known pixel values, and we propose applying the U-Net to solve this problem. Numerical experiments show that the proposed method outperforms conventional methods in prediction accuracy and spectral efficiency. © 2024 IEEE.

关键词： Channel estimation

来源：评论

学校读者我要写书评

暂无评论

Leveraging XAI and Breakthrough Machine Learning Techniques for Trigeminal Neuralgia Severity Classification

Leveraging XAI and Breakthrough Machine Learning Techniques ...

引用

2024 IEEE Region 10 Symposium, TENSYMP 2024

作者： Abhijna, M.B. Akul, P. Kodipalli, Ashwini Global Academy of Technology Dept. of Information Science and Engineering India Global Academy of Technology Dept. of Computer Science and Engineering India Global Academy of Technology Dept. of Artificial Intelligence and Data Science India

ISBN: (纸本)9798350364866

Trigeminal Neuralgia (TN) is a debilitating chronic pain disorder that significantly diminishes overall well-being, making diagnosis and therapy more challenging. The quick and precise categorization of TN severity is critical to therapy effectiveness. To assess the severity of TN, this study makes use of advanced machine learning techniques and explainable AI (XAI) approaches. We use a range of bagging and boosting strategies, including AdaBoost, Random Forest, Decision Tree, K-Nearest Neighbours (KNN), Gradient Boosting, and Logistic Regression. Random Forest was 95.2% accurate, whereas AdaBoost and Gradient Boosting were 92% and 97.2% in terms of their accuracy. The Decision Tree classifier obtained an accuracy of 84.62%, while K-Nearest Neighbours and Logistic Regression also achieved 92.31% accuracy. F1- score, precision, and recall metrics were used to assess performance on a dataset that included patient demographics and medical histories. XAI techniques, such as LIME and SHAP values, were used to improve the models' readability and transparency, which helped to progress the creation of cutting-edge diagnostic tools and increase clinician and researcher confidence. © 2024 IEEE.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Techniques for Predicting Ovarian Cancer in its Early Stages Using Biomarkers 6

Machine Learning Techniques for Predicting Ovarian Cancer in...

引用

6th International Conference on Electrical Engineering and Information and Communication technology, ICEEICT 2024

作者： Alam, Mir Jafikul Anawar, Jannat-E Mohi Uddin, Khandaker Mohammad Rahman, Md. Hasibur Rahman, Md. Mahbubur Dhaka International University Dept. of Computer Science and Engineering Dhaka Bangladesh Southeast University Dept. of Computer Science and Engineering Dhaka Bangladesh Bangladesh University of Business and Technology Dept. of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798350385779

The deadliest gynecological cancer affecting women is ovarian cancer, currently incurable with no effective medication treatments. The key focus of this research is to assess insights for early diagnosis using statistical analysis and machine learning techniques on data from clinical trials obtained from 349 patients. Several techniques, including Random Forest, Decision Tree, Gaussian NB, AdaBoost, and Logistic regression, were applied to find the most reliable factor for ovarian cancer prediction. A clinically evaluated raw dataset of benign samples and malignant ovarian tumor patient data set is used to develop early-stage ovarian cancer predictions, and the effectiveness of ML models was examined utilizing metrics including F1-score, Accuracy, Precision, and Recall. The proposed study shows better outcomes, with the Random Forest classifier exhibiting the highest accuracy for validation at 99% based on the test data of ovarian cancer predictions. Even though early-stage ovarian cancer detection is generally unavailable, cancer diagnosis may be greatly aided by machine learning. © 2024 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

IRS Controlling Method With Machine Learning Based on Position Information 13

IRS Controlling Method With Machine Learning Based on Positi...

引用

13th IEEE Global Conference on Consumer Electronic, GCCE 2024

ISBN: (纸本)9798350355079

Intelligent Reflecting Surfaces (IRS) is attracting attention for wireless communications at high-frequency band. IRS can control radio propagation by reflecting radio waves and shifting their phase. As one of the methods to control IRS, location-based methods have been proposed. However, to achieve highly accurate IRS control by the methods, the assumed propagation model must match the actual propagation environment. This study proposes a method to control the IRS from location information adapted to the propagation environment by using machine learning. Numerical experiments confirm that the proposed method can appropriately control IRS regardless of the propagation environment. © 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

Deep Learning Assisted Intelligent Human computer Interaction for Next Generation Internet Applications

Informatica (Slovenia)

引用

Informatica (Slovenia) 2024年第2期48卷 145-146页

作者： Hasan, Al Mehedi Hwang, Yong Seok Shin, Jungpil Dept. of Computer Science and Engineering Rajshahi University of Engineering and Technology Bangladesh Kwangwoon University Seoul Korea Republic of School of Computer Science and Engineering The University of Aizu Aizuwakamatsu Japan

来源：评论

学校读者我要写书评

暂无评论

LeXNet++: Layer-wise eXplainable ResUNet++ framework for segmentation of colorectal polyp cancer images

引用

Neural Computing and Applications 2025年第1期37卷 213-229页

作者： Das, Surajit Khan, Soumya Suvra Sengupta, Diganta Debashis, De Dept. of Information Technology Meghnad Saha Institute of Technology Behind Urbana Complex Near Ruby General Hospital Anandapur Rd Uchhepota Kolkata700150 India Dept. of Computer Science & Engineering Meghnad Saha Institute of Technology Behind Urbana Complex Near Ruby General Hospital Anandapur Rd Uchhepota Kolkata700150 India Dept. of Computer Science & Engineering Heritage Institute of Technology Chowbaga Road West Bengal Anandapur Kolkata700107 India Dept. of Computer Science & Engineering Maulana Abul Kalam Azad University of Technology West Bengal NH-12 Simhat Haringhata West Bengal Nadia741249 India

Colorectal polyps are benign lesions that develop in the colon and can progress to cancer if left untreated. Clinical observations from medical images are often preferred over computational results due to the lack of trust in the machine learning models, thereby posing serious challenge for the explainability of the results. In order to computationally diagnose colorectal polyps from cancerous images and explain the results, we propose a Layer-wise eXplainable ResUNet++ (LeXNet++) framework for segmentation of the cancerous images, followed by layer-wise explanation of the results. We utilize a publicly accessible dataset that contains of 612 raw images with a resolution of 256×256×3 and an additional 612 clinically annotated and labeled images with a resolution of 256×256×1, which includes the infected region. The LeXNet++ framework comprises of three components—encoder, decoder and the bridge. The encoder and the decoder components each comprise of four layers. Each of the four layers in the encoder and the decoder comprises of 14 and 11 internal sub-layers, respectively. Among the sub-layers of the encoder and the decoder, there are three 3×3 convolutional layers with an additional 3×3 convolution-transpose layer in the decoder. The output of each of the sub-layers has been explained through heatmap generation after each iteration which have been further explained. The encoder and the decoder are connected by the bridge which comprises of three sub-layers. The results obtained from these three sub-layers have also been explained to inculcate trust in the findings. In this study, we have used three models to segment the images, namely UNet, ResUNet, and proposed LeXNet++. LeXNet++ exhibited the best result among the three models in terms of performance;hence, only LeXNet++ was explained layer-wise. Apart from explanation of the results fetched in this study, the performance of the proposed explainable model has been observed to be 2% greater than the existing poly

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Attention-Based AdaptSepCX Network for Effective Student Action Recognition in Online Learning 5

Attention-Based AdaptSepCX Network for Effective Student Act...

引用

5th International Conference on Innovative Data Communication Technologies and Application, ICIDCA 2024

作者： Dey, Arnab Anand, Anubhav Samanta, Subhajit Sah, Bijay Kumar Biswas, Samit Dept. of Computer Science and Technology Indian Institute of Engineering Science and Technology Shibpur Howrah711103 India

In the realm of online learning and distance education, the issue of inadequate supervision looms large, posing a significant obstacle. This paper delves into the challenges posed by the lack of supervision in online learning environments and proposes an innovative solution to understand and recognize students' behaviors. This study's primary objective is to detect and recognize students' actions in images captured through webcam. This task distinguishes itself from the well-established video-based student action recognition domain, which relies on temporal cues. Recognizing student actions from images intensifies the complexity of the problem. To meet this challenge, a novel deep learning model named AdaptSepCX Attention, specifically designed for student action recognition in online learning environments, is introduced. The proposed method exhibits exceptional performance with 92.73% validation accuracy on the Student Online Action Image dataset (SOAId), a carefully curated collection comprising 2029 student-centric images. The proposed model outperforms well-established models such as DenseNet121, NASNet Mobile, ConvXNet, DELVS1 and MobileNetV2 in student action recognition. Action recognition for students has broader implications beyond the online classroom. It has the potential to revolutionize educational technology, making online learning more interactive and engaging. Enabling machines to understand and respond to student actions enhances education, personalizes learning, and supports students' academic success and well-being. This research enhances the understanding of student involvement in online learning and offers an effective solution for recognizing actions from images. © 2024 The Authors. Published by Elsevier B.V.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Using Ant Colony Optimised Algorithms for Shortest Path Exploration by Robots 2

Using Ant Colony Optimised Algorithms for Shortest Path Expl...

引用

2nd IEEE International Conference on Interdisciplinary Approaches in technology and Management for Social Innovation, IATMSI 2024

作者： Singh, Aashdeep Dhawan, Sakshi Verma, Jyoti Singh, Gurpreet Kaur, Amanpreet Dept. of Computer Science & Engineering Punjab Rajpura India Dept. of Computer Application Punjab Rajpura India Chitkara University Institute of Engineering & Technology Dept. of Computer Science & Engineering Punjab Rajpura India

ISBN: (纸本)9798350360523

In the realm of robotics and autonomous systems, efficient path planning is a critical aspect for optimizing resource utilization and achieving mission objectives. This study explores the application of Ant Colony Optimized (ACO) algorithms to enhance the efficiency of robots in navigating and exploring unknown environments. Inspired by the foraging behavior of ants, ACO algorithms are employed to find the shortest paths by leveraging pheromone communication and decentralized decision-making. Ant Colony Optimization is then introduced as a bio-inspired solution to address these challenges. The experimental results demonstrate the capability of the ACO algorithm to efficiently explore complex environments, adapt to changes in the surroundings, and converge to optimal paths. Insights gained from these analyses contribute to the refinement of the ACO algorithm for diverse robotic applications. The findings of this research have practical implications for the development of autonomous robots operating in real-world scenarios, such as search and rescue missions, environmental monitoring, and surveillance. This study provides a valuable foundation for the integration of bio-inspired algorithms in robotics, advancing the state-of-the-art in autonomous exploration and path planning. © 2024 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Harnessing Big Data for Economic Transformation in a Digitalized World 3

Harnessing Big Data for Economic Transformation in a Digital...

引用

3rd International Conference on Creative Communication and Innovative technology, ICCIT 2024

作者： Tarigan, Riswan Efendi Triyono Mahyuni Agustian, Harry Nurfaizi, Rifky Zahra, Achani Rahmania Az Pelita Harapan University Dept. of Information Systems Tangerang Indonesia University of Raharja Dept. of Information Technology Tangerang Indonesia University of Mataram Dept. of Teacher Training and Education Science Mataram Indonesia Sesindo Dept. of Computer Systems Tangerang Indonesia Bosindo Dept. of Information Technology Tangerang Indonesia Pandawan Sejahtera Indonesia Dept. of Information Systems Tangerang Indonesia

ISBN: (纸本)9798350367492

Air is essential to life and health, with oxygen (20.94%) and the ozone layer protecting against ultraviolet radiation. Depletion of oxygen reduces the ozone layer, increasing UV exposure. Good air quality is crucial for living organisms. In 2022, Indonesia's PM 2.5 pollution ranked 26th worst globally, exceeding WHO standards, yet awareness and trust in air quality devices remain low. This study aims to implement and evaluate an AI-based machine learning system to predict the Air Quality Index (AQI) in healthcare services. Using Structural Equation Modeling with Partial Least Square analysis via SmartPLS 4.0, the research involves 120 participants and historical air quality data. Comparative analysis of machine learning algorithms assesses accuracy, robustness, and efficiency, highlighting their potential in forecasting AQI and its implications for public health and urban planning. The study demonstrates the effectiveness of these algorithms in predicting AQI, with a significant value of 0.874 for forecasting accuracy. © 2024 IEEE.

关键词： Ozone layer

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：