检索结果-内蒙古大学图书馆

Multilingual Sentiment Analysis using DistilBert

Multilingual Sentiment Analysis using DistilBert

2024 International Conference on Artificial Intelligence and Quantum Computation-Based Sensor Applications, ICAIQSA 2024

作者： Gupta, Nishi Bhattarai, Mandip Chavan, Abhishek Pimpri Chinchwad College of Engineering Dept. of Applied Science and Humanities Maharastra Pune India Pimpri Chinchwad College of Engineering Dept. of Computer Engineering Maharastra Pune India

ISBN: (纸本)9798331517953

In today's virtual age, studying feelings and sentiments through textual content and emojis is essential. This research article explores a way to use natural language processing (NLP) techniques to interpret feelings from textual content and emoji content. We used the distilbert-base-uncased-finetuned-sst2english version, a small variant model of BERT, to categorize feelings as positive or negative. Our experiments confirmed that the version executed extraordinarily properly throughout more than one language, with especially great effects on Indonesian textual content. Our assessment confirmed that the version has an excellent accuracy of91.50% and an F1 rating of 91.44% for Indonesian, highlighting its wonderful overall performance in this language. It additionally plays properly in English, French, German, Arabic, and Italian, even though overall performance may also range through language. These effects reveal the version's effectiveness for duties, social media monitoring, client comments evaluation, and inventory marketplace fashion assessment. We finish with a conclusion about the results of those findings. © 2024 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Evaluation of the Robustness, Transparency, Reliability and Safety of AI Systems 9

Evaluation of the Robustness, Transparency, Reliability and ...

引用

9th International Conference on Advanced Computing and Communication Systems, ICACCS 2023

作者： Mahilraj, Jenifer Pandian, Manivel Subbiah, Muthuraman Kalyan, S. Vadivel, R. Nirmala, S. NPR College of Engineering Department of Computer Science and Engineering Tamilnadu India University of Technology and Applied Sciences Muscat Oman BVRIT Hyderabad College of Engineering for Women Bachupally Dept of Basic Sciences and Humanities-Management Studies Hyderabad India HKBK College of Engineering Department of Computer Science and Engineering Karnataka Bangalore India Sri Eshwar College of Engineering Department of Computer Science and Engineering TamilNadu Coimbatore India

ISBN: (纸本)9798350397376

Advances in artificial intelligence have been promising in recent years. AI-related activities such as international conferences, academic research, and technological challenges have proliferated over the globe. The technologies and applications are always being improved and expanded in the modern age. In addition, humans' studies, job, and personal lives have been greatly improved by the ongoing development of intelligent devices. Efforts have been dedicated to identify some of these issues and to present policymakers with possible remedies, which focus on reconciling the valid expectations of AI in terms of resilience and interpretability with the existing scientific environment of AI on these aspects. In this paper, the individual aims are to present an objective picture of the current environment of Artificial Intelligence (AI), emphasizing on the issues of robustness and explanability, transparency, reliability and safety. AI's present cybersecurity, security, and information security problems are discussed in detail, as well as the scientific approaches that are now being developed in the AI world to address these risks. © 2023 IEEE.

关键词： Reliability

来源：评论

学校读者我要写书评

暂无评论

Advances in AI-based genomic data analysis for cancer survival prediction

引用

Multimedia Tools and Applications 2025年第14期84卷 14139-14166页

作者： Deepali Goel, Neelam Padmavati Khandnor University Institute of Engineering and Technology Panjab University Chandigarh160014 India Chandigarh160012 India Department of Computer Science Guru Nanak College Budhlada151502 India

Problem: Cancer is one of the deadliest diseases prevalent in the world. Survivability, early diagnosis, and accurate prognosis are of utmost importance for the therapeutics and clinical management of cancer patients. To achieve accurate and timely prediction of the survival of cancer patients, several machine-learning models based on genomic data have been proposed but a comprehensive review of recent applications in cancer survival prediction is lacking. This paper represents a review of the most recent application of machine learning and deep learning on cancer survival prediction, with a particular focus on the use of genomic data. It specifically targets the most prominent cancer types such as breast cancer, glioblastoma, lung cancer, renal cell cancer, and oral cancer. Methods: A systematic review approach is employed to analyze recent studies on machine learning techniques applied to cancer survival prediction. Emphasis is placed on methodologies utilizing genomic data due to its effectiveness in predicting survival outcomes. Results: This review highlights the efficacy of different machine/deep learning-based techniques in predicting survival outcomes for different cancer types with genomic data. It also provides a summary of the contributions made by different research groups, critically examines the associated challenges, and suggests potential areas for further investigation. Conclusion: Machine learning and deep learning techniques, especially those utilizing genomic data, hold significant promise for accurate cancer survival prediction across diverse cancer types. Despite advancements, challenges such as data heterogeneity and model interpretability still persist. Further research is warranted to address these challenges and develop a comprehensive framework for cancer survival prediction applicable to various cancer types. This review lays the foundation for future investigations in the area of cancer research. © The Author(s), under exclusive licence

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Attention Based CNN to Improve Identification of Ischaemia and Infection in DFU

Attention Based CNN to Improve Identification of Ischaemia a...

引用

2023 International Conference on New Frontiers in Communication, Automation, Management and Security, ICCAMS 2023

作者： Bhowmick, Priya Revanth, K. Lakshmi, Parlapalli Das, Sujit Kumar Babu, Tina Alliance University Alliance College of Engineering and Design Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350317060

Diabetic foot ulcers (DFUs) frequently occur as complications of diabetes. Identifying infection and ischaemia in DFUs is crucial for wound assessment and treatment planning. Recent advancements in deep learning have shown promise in classifying infection and ischaemia in DFUs using computerized methods. Many modern systems for classifying DFU images rely on deep neural networks, particularly convolutional neural networks. These networks analyze distinctive features and predict class probabilities based on these features. During testing, predictions are made using individual input images and trained parameters. To harness the information in training data more effectively, this study introduces the concept of an attention layer. This layer aids neural networks in memorizing long sequences of data, mitigates issues like exploding gradients, and enhances model accuracy. Experimental results demonstrate that this proposed approach significantly improves the accuracy of DFU infection and ischaemia detection. © 2023 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Security Mechanism of MQTT Protocol Using Payload Encryption 3rd

Enhancing Security Mechanism of MQTT Protocol Using Payload...

引用

The 3rd International Conference on Frontiers in Computing and Systems (COMSYS 2022)

作者： Akshatha, P.S. Dilip Kumar, S.M. Department of Computer Science and Engineering University Visvesvaraya College of Engineering Bangalore University Bengaluru India

ISBN: (纸本)9789819926794

MQTT has become one of the most widely used IoT communication protocols due to its efficiency and simplicity. However, it does not support the desired security features;instead, it assumes the use of SSL/TLS in the lower layer. The high bandwidth consumption of SSL/TLS makes it costly to support it. This paper proposes an end-to-end payload encryption technique using the Fernet key for enhancing the security of MQTT communication. The intermediate brokers are not necessary for the proposed approach to support SSL/TLS or to obtain and install certificates. Fernet provides symmetric encryption and authentication of data. The outcomes demonstrate that the suggested approach enhances bandwidth use, requires less initial connection setup time, and minimal jitter and the slight delay introduced by Fernet’s method is acceptable for secured communication. Since the key is only generated once, less time is needed for long-lasting communications. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Object Detection Algorithms for Waste Segregation 3

Performance Analysis of Object Detection Algorithms for Wast...

引用

3rd International Conference on Artificial Intelligence and Smart Energy, ICAIS 2023

作者： Singh, Naman Sastry, Pranav Niharika, B.S. Sinha, Arka Umadevi, V. B.M.S. College of Engineering Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9781665462167

The amount of waste generated in urban cities is increasing at an alarming rate and its effective and efficient management has become nearly impossible. To combat this issue, this study has compared different object detection algorithms applied on data containing trash with no cluttered background, so as to first evaluate the different algorithms only on the basis of their inherent performance. The algorithms used for training are YOLOv5, EfficientDet and Faster RCNN. Using mAP(Mean Average Precision) as the evaluating metric, this study has found that YOLOv5 with mAP of 0.92 has outperformed EfficientDet and Faster RCNN, whose mAP was 0.846 and 0.836 respectively. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Secure Image Encryption Model for Cloud-Based Healthcare Storage Using Hyperchaos and DNA Encoding 1

引用

Proceedings of the 6th IFIP TC 12 International Conference on Computational Intelligence in Data science, ICCIDS 2023

作者： Amaithi Rajan, Arun Vetrian, Vetriselvi Gladys, Aruna Department of Computer Science and Engineering College of Engineering Guindy Anna University Chennai600025 India

ISBN: (数字)9783031382963

ISBN: (纸本)9783031382956

In recent years, security and privacy have drawn a lot of attention due to digital communications and the widespread usage of multimedia transmissions over unsecured channels. In every area of analytics, digital images are essential. Sensitive image information like fingerprints, medical records, or defense satellite images needs to be securely stored and processed in a cloud server. In this article, we come up with a novel image encryption model for medical images utilizing a combination of chaotic maps over the DNA-encoded image with bit plane scrambling. Hyperchaotic maps are used to generate confusion keys and Chaotic maps are used for diffusion keys generation. The robustness and resistance of the system to attacks like differential attacks and statistical attacks are shown and extensively analyzed in terms of the security of the proposed model. © 2023, IFIP International Federation for Information Processing.

关键词： Military satellites

来源：评论

学校读者我要写书评

暂无评论

Paddy Plant Disease Detection using Hybrid Deep Learning Algorithms 8

Paddy Plant Disease Detection using Hybrid Deep Learning Alg...

引用

8th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2024

作者： Suguna, R. Deepa, S. Kanimozhi, T. Chandru, M. Arun, G. Harshini, M. Bannari Amman Institute of Technology Department of Computer Science and Engineering Sathyamangalam Tamilnadu Erode638401 India Kongu Engineering College Perundurai Department of Computer Technology - Pg Tamilnadu Erode638060 India Sri Eshwar College of Engineering Department of Artificial Intelligence and Data Science Coimbatore641202 India College Department of Computer Science Erode India Vel Tech Rangarajan Dr Sagunthala R&d Institute of Science and Technology School of Computing Department of Computer Science and Engineering Chennai India Kongu Engineering College Tamilnadu Perundurai Erode638060 India

ISBN: (纸本)9798350367904

Agriculture is the backbone of India's economy, supporting a large portion of the population and establishing the country as a key global player in food production. India ranks as the second-largest producer of both paddy and wheat. However, agricultural productivity is highly susceptible to various plant diseases, which can significantly reduce crop yields and quality. Paddy, one of the most important staple crops, is particularly vulnerable to diseases caused mainly by viral and bacterial related diseases. The climate conditions are also play a vital role in paddy plant diseases. This research work proposes a deep learning-based approach for early detection and classification of paddy diseases. The proposed research devises a hybrid model that combines the VGG19 and ResNet50 algorithms, the system analyses images of both healthy and disease-affected paddy leaves, sourced from the Kaggle repository. This research focuses on predicting four major paddy diseases that can cause yield losses of up to 80%, and in severe cases, can destroy an entire crop: (i) Paddy Blast, (ii) Bacterial Leaf Blight, (iii) Sheath Blight, and (iv) Ufra Disease. The proposed model achieves a high accuracy rate of 98% in predicting paddy diseases and offers a rapid classification process, showcasing the potential of advanced image processing and deep learning techniques to mitigate the impact of paddy plant diseases on agricultural productivity. © 2024 IEEE.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

Dual-Axis Solar Tracker: An Efficient Budgetfriendly Way to Utilize Solar Energy 1

Dual-Axis Solar Tracker: An Efficient Budgetfriendly Way to ...

引用

1st International Conference on Computing, sciences and Communications, ICCSC 2024

作者： Guha, Shobham Ghosh, Arghya Singh, Kamakhya Narain Misra, Chinmaya Sudershana, Sadhana Goswami, Biswadev School of Computer Application KIIT Deemed University Bhubaneswar India Computer Science and Engineering Dr. B C Roy Engineering College Jamua India

ISBN: (纸本)9798350353648

In order to improve solar energy collecting, this study investigates the development of an affordable dual-axis sun tracking apparatus. This technological attempts to increase efficiency by continuously altering the orientation of solar panels to follow the course of the sun throughout the day, as solar power gains popularity worldwide as a clean alternative to fossil fuels. The study begins with a historical overview of solar energy evolution and focuses on practical implementation using basic components like solar panels, servo motors, and light sensors. By constantly adjusting based on sunlight angles, the dual-axis system boosts energy generation efficiency. Mathematical calculations optimize panel angles for maximum sunlight exposure. Its affordability and practicality provide a sustainable solution for regions with abundant solar radiation, such as India. This research highlights the dual-axis system's potential to promote sustainable energy practices, reduce fossil fuel dependence, and mitigate environmental impact. Its cost- effectiveness makes it viable for widespread adoption in residential and commercial settings, contributing to increased global solar energy use. © 2024 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Research on an Adaptive RRT Path Planning Algorithm Based on Regional Sampling 7

Research on an Adaptive RRT Path Planning Algorithm Based on...

引用

7th International Conference on computer Information science and Application Technology, CISAT 2024

作者： Su, Yu Li, Hongbing Gong, Wenbin Chen, Honghao Jiang, Yutao Long, Boxuan Chongqing Three Gorges University College of Computer Science and Engineering Chongqing Wanzhou China Chongqing Three Gorges University College of Electronic and Information Engineering Chongqing Wanzhou China Changchun University of Science and Technology College of Computer Science and Technology Jilin Changchun China

ISBN: (纸本)9798350375107

An enhanced RRT path planning algorithm based on regional sampling is proposed with the goal of addressing the issues of inadequate guidance, discontinuous sampling, and unsatisfactory path in RRT algorithm path search in complicated situations. The improved algorithm first enhances the algorithm's guidance and avoids unnecessary sampling by using a target bias strategy and a regional sampling strategy. Secondly, an adaptive step size strategy based on obstacle factors is adopted to dynamically adjust the step size by detecting the complexity of the environment around the expansion direction. Finally, the produced path is trimmed and optimized. According to simulation results, the revised algorithm reduces running time, path length, and number of path nodes by 68.65%, 18.56%, and 85.45%, respectively, in comparison to the RRT algorithm. The enhanced approach reduces the running time, path length, and number of path nodes by 14.06%, 12.91%, and 82.97%, respectively, in comparison to the Bias RRT algorithm. © 2024 IEEE.

关键词： Signal sampling

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：