检索结果-内蒙古大学图书馆

3rd International Conference on Innovative Practices in Technology and Management, ICIPTM 2023

作者： Dath, Mogalraj Kushal Nazir, Nahida Lovely Professional University Division of Computer Science and Engineering Phagwara India Lovely Professional University Division of Computer Science Phagwara India

ISBN: (纸本)9798350336238

This research seeks to investigate the possibility of using deep learning strategies in the process of diagnosing malaria, a virus that affects billions of people all over the world. Standard lab tests for malaria require the services of a qualified laboratory technician as well as an in-depth analysis of blood samples. This process can be expensive, time-consuming, and prone to errors caused by humans. This work attempts to enhance the accuracy of malaria diagnosis while also increasing the rate at which it can be performed by utilizing the capabilities of deep learning. We evaluate the performance of various methods for identifying the Plasmodium parasite in thin blood smear images by using deep learning models such as CNN, ResNet50, and VGG19 in accordance with noise reduction techniques and image segmentation methods. This allows us to compare the accuracy of the various methods. According to the findings of our research, the VGG19 model had the greatest overall performance. It had an accuracy of 0.9286 as well as a low false-positive and losing rate. The model is also tiny, making it easy to transport and use in a variety of contexts due to its portability. This study gives an overview of the current advancements in deep learning for malaria diagnosis. It also illustrates the potential for ai to increase both the accuracy and speed of malaria diagnosis. © 2023 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Malware Classification Using Deep Learning 2

Malware Classification Using Deep Learning

引用

2nd International Conference on Artificial Intelligence Trends and Pattern Recognition, ICaiTPR 2024

作者： Devika, P. Surya Narayana Reddy, V. Ramya Krishna, Dhulipalla Rampilla, Chiranjeevi Charan Yadav, B Simha and Ai&ds Telangana Hyderabad500090 India Bvrit Hyderabad College of Engineering for Women Department of Computer Science and Engineering Telangana Hyderabad500090 India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Telangana Hyderabad500043 India Department of Computer Science and Engineering Telangana Hyderabad India

ISBN: (纸本)9798350368000

Malware detection and classification is a critical aspect of cybersecurity, given the increasing sophistication and prevalence of malicious software. In this study, we propose a novel approach utilizing deep learning architectures for the task of malware classification detection. These architectures are renowned for their ability to extract intricate features from complex data, making them suitable for identifying subtle patterns indicative of malware behavior. With the swift expansion of technology and the internet, the menace of malware has escalated into a pivotal apprehension for individuals, organizations, and society overall. Comprising viruses, trojans, worms, and ransomware, malware poses a formidable hazard to information security and privacy. Conventional signature-based approaches for malware detection are faltering in coping with the expanding diversity and intricacy of malware. Overall, our study contributes to the advancement of malware detection techniques by leveraging state-of-the-art deep learning architectures, providing a reliable and scalable solution to combat the evolving landscape of cyber security threats. © 2024 IEEE.

关键词： computer worms

来源：评论

学校读者我要写书评

暂无评论

Enhancing intrusion detection in IIoT: optimized CNN model with multi-class SMOTE balancing

引用

Neural Computing and Applications 2024年第24期36卷 14643-14659页

作者： Eid, Abdulrahman Mahmoud Soudan, Bassel Nassif, Ali Bou Injadat, MohammadNoor Department of Computer Engineering College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates Department of Data Science and AI Faculty of Information Technology Zarqa University Zarqa Jordan

This work introduces an intrusion detection system (IDS) tailored for industrial internet of things (IIoT) environments based on an optimized convolutional neural network (CNN) model. The model is trained on a dataset that was balanced using a novel multi-class implementation of synthetic minority over-sampling technique (SMOTE) that ensures equal representation of all classes. Additionally, systematic optimization will be used to fine tune the hyperparameters of the CNN model and mitigate the effects of the increased size of the training dataset. Evaluation results will demonstrate substantial improvement in performance when the optimized CNN model is trained on the balanced dataset. The proposed IDS will be evaluated using the IIoT-specific WUSTL-IIOT-2021 dataset, and then its generalization capability will be verified using the non-domain specific UNSW_NB15 dataset. The model’s performance will be evaluated using accuracy, precision, recall, and F1-score metrics. The results will demonstrate that the proposed IDS is highly effective with performance exceeding 99.9% on all performance metrics. The IDS is also highly effective in detecting intrusion for generic IT networks achieving improvements in excess of 30% compared to the default baseline model. The results emphasize the versatility and effectiveness of the proposed IDS model, making it a reliable and adaptable solution for enhancing network security across diverse network environments. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Smart Interaction: Merging Augmented Reality and Internet of Things for Seamless Device Control

Smart Interaction: Merging Augmented Reality and Internet of...

引用

2025 International Conference on Intelligent Computing and Control Systems, ICICCS 2025

作者： Jeny, J.R.V. Sai Mahitha, B. Shashank, M. Vamsi Krishna, N. Vignan Institute of Technology and Science Department of Computer Science and Engineering(AI & ML) 508284 India

ISBN: (纸本)9798331512088

The combination of Augmented Reality (AR) and Internet of Things (IoT), often referred to as AR + IoT, offers exciting possibilities for future research and development. IoT serves as a platform for communication and remote control of connected devices, while AR provides an intuitive interface for visualizing and managing these devices through enhanced, information-rich displays. This research aims to develop an interactive and accessible home automation system that integrates IoT and AR technologies, enabling seamless remote control of electrical devices. Utilizing an ESP32/NodeMCU board interfaced with the Blynk IoT platform, the system supports device management through a mobile application and an AR interface designed in Unity. The AR interface facilitates intuitive interactions via URL-based signals, which are transmitted to the IoT hardware for execution. This dual-control mechanism enhances user flexibility and convenience, making smart home automation more accessible to users with varying technical expertise. The proposed system not only improves user interaction and control efficiency but also demonstrates the potential of AR in augmenting IoT applications, bridging the gap between physical and virtual control environments. Future enhancements could include advanced AR features, voice control, and cloud-based analytics to further optimize system performance and scalability. © 2025 IEEE.

关键词： Augmented Reality ESP32 Board Internet of Things Serial Communication Wi-Fi Connectivity

来源：评论

学校读者我要写书评

暂无评论

Detection of Faults in Solar Grids Using Convolutional Neural Network 10

Detection of Faults in Solar Grids Using Convolutional Neura...

引用

10th International Conference on Advanced Computing and Communication Systems, ICACCS 2024

作者： Chinthaguntla, Madhuri Mahima Priyadharsini, C. Karunya Institute of Technology and Sciences Computer Engineering Division of Data Science and Cybersecurity Tamil Nadu Coimbatore India Karunya Institute of Technology and Sciences Division of Computer Science and Engineering Tamil Nadu Coimbatore India

ISBN: (纸本)9798350384369

The imperative need to guarantee the reliability and efficiency of solar energy systems inspired the development of a novel method for solar panel defect identification. As solar panels increasingly become a significant contributor to the global energy grid, it becomes crucial to address the challenges associated with their maintenance and performance optimization. Issues such as reduced efficiency due to external factors like weather, shading, and debris, as well as internal faults within the panels themselves, underscored the necessity for a more effective and reliable defect identification system. Additionally, the growing demand for clean and sustainable energy sources further emphasized the importance of maximizing the potential of solar power generation through improved maintenance practices. Therefore, the need to overcome the limitations of conventional detection techniques and enhance the reliability of solar energy production served as the primary inspiration for developing the novel method for solar panel defect identification. This research introduces an innovative approach utilizing the Visual Geometry Group (VGG16) Convolutional Neural Network (CNN) model, renowned for its efficacy in computer vision tasks. By critically reviewing existing literature and methodologies, and leveraging machine learning and deep learning techniques, the study demonstrates the potential of deep learning models like VGG16 to significantly improve solar panel fault detection accuracy to 99% during training and 90% during validation indicating its effectiveness in addressing critical challenges in solar panel maintenance and performance optimization. © 2024 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

BERTing Emotions: Exploring Textual Emotion Recognition using NLP

BERTing Emotions: Exploring Textual Emotion Recognition usin...

引用

2025 International Conference on Intelligent Computing and Control Systems, ICICCS 2025

作者： Praveen Kumar, R. Ramya, Pannala Sai Teja, G. Rama Krishna, V. Vignan Institute of Technology and Science Department of Computer Science and Engineering(AI & ML) 508284 India

ISBN: (纸本)9798331512088

Emotion recognition in text is a crucial area within Natural Language Processing (NLP), serving diverse applications such as sentiment analysis, mental health assessment, and human-computer interaction. This study explores the use of Bidirectional Encoder Representations from Transformers (BERT) for this purpose, capitalizing on its bidirectional transformer architecture to grasp intricate contextual relationships in text. By fine tuning a pretrained BERT model on a dataset annotated with emotional categories like happiness, sadness, anger, surprise, and fear, the model achieves precise emotion classification. BERT's pre-trained linguistic knowledge and ability to interpret complex semantic and syntactic patterns provide a strong foundation for this task. Experimental results demonstrate that BERT surpasses traditional machine learning approaches, including Support Vector Machines (SVM) and logistic regression, in terms of accuracy, owing to its advanced contextual embeddings. Additionally, the model exhibits excellent generalization capabilities across diverse emotional expressions, highlighting its effectiveness for emotion-aware NLP applications. This project also leverages Streamlit to develop interactive web applications that integrate NLP-based emotion detection, showcasing its practicality and accessibility for real-world use cases. © 2025 IEEE.

关键词： Contextual embeddings Emotion detection Generalization capabilities Streamlit integration Syntactic patterns

来源：评论

学校读者我要写书评

暂无评论

3D Printing of Zinc Oxide Nanoparticles Embedded Transparent Sheet for Solar Panel Encapsulation and Thermal Management 1

3D Printing of Zinc Oxide Nanoparticles Embedded Transparent...

引用

1st Middle East and North Africa Solar Conference, MENA-SC 2023

作者： Alam, Fahad El-Atab, Nazek Electrical and Computer Engineering Computer Electrical Mathematical Science and Engineering Division Thuwal23955-6900 Saudi Arabia

ISBN: (纸本)9781665491464

The current work demonstrates 3D printing of transparent sheets embedded with zinc oxide (ZnO) nanoparticles for the encapsulation of solar panels for protection and thermal management. Thin transparent sheets were prepared via a vat-photopolymerization-based 3D printing technique. The optimized sheet showed >90% transparency with a UV ray preventing capability from the range of 200-400 nm. Due to blocking of UV rays from the solar spectrum, reduction in around 8°C in the temperature from the surface of the solar panel was observed when the solar panel coated with ZnO embedded resin was exposed to sunlight for 30 min as compared to the surface temperature from the reference panel with resin coating only. The demonstrated sheet would thus be promising as an encapsulant and in assisting in the thermal management of the solar panel. © 2023 IEEE.

关键词： II-VI semiconductors

来源：评论

学校读者我要写书评

暂无评论

Synoptic: Query-Driven Multimodal Product Review Summarization System

Synoptic: Query-Driven Multimodal Product Review Summarizati...

引用

2025 CHI Conference on Human Factors in Computing Systems, CHI EA 2025

作者： Ria, Nushrat Jahan Jasim, Mahmood Division of Computer Science and Engineering Louisiana State University Baton RougeLA United States

ISBN: (纸本)9798400713958

Product reviews play a critical role in making purchase decisions. A recent shift toward multimodal reviews highlights the preference for visual and audio information over texts. While long-form review videos are information-rich, viewers often skip to find what they need, resulting in missing information. Moreover, videos are difficult to search for specific content, leading to ineffective information gathering. In this work, we surveyed 177 people to learn about the challenges and strategies to gather information from product review videos before making purchase decisions. Based on our findings, we designed and developed Synoptic, an interactive multimodal video player that allows users to search within videos and generate video summaries based on customized queries. Our initial evaluation with 40 participants suggests that Synoptic helped viewers gather personalized information from product review videos effectively and efficiently. It also enables purchase decision-making while maintaining user agency and prioritizing their preferences. © 2025 Copyright held by the owner/author(s).

关键词： interactive transcripts multimodal Product review videos video summarization

来源：评论

学校读者我要写书评

暂无评论

Early-Stage Detection of Colorectal Cancer Using Image Classification 4

Early-Stage Detection of Colorectal Cancer Using Image Class...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Santhosh, Ashlin Anusha Bamini, A.M. Rajeswari, M. Brindha, D. Chitra, R. Stewart Kirubakaran, S. Karunya Institute of Technology and Sciences Division of Computer Science and Engineering Tamil Nadu Coimbatore India

ISBN: (纸本)9798331523923

Early detection of colorectal cancer is important as it is one of the most common and deadliest types of cancer worldwide. This project proposes an image classification model based on deep learning architecture that could detect colorectal cancer in its preliminary stages by using an EfficientNetB0. By using the Colorectal Cancer Whole Slide Images (WSI) dataset, a classification model using the WSI dataset to classify tissue samples into six distinct categories of varying grades of cancerous growths and normal. In this model, transfer learning is included to maintain computational efficiency while enhancing accuracy. A user interface with Streamlit, which has real-time image upload, analysis, and prediction display, was also developed. The predictions come with confidence scores, and the Interface also provides educational content for each cancer stage to help raise awareness and prevent the disease. Applications with potential for medical diagnosis and as an educational tool for early detection of colorectal cancer are possible for this system. © 2025 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Voice of the Unheard: Conversational Challenges Between Signers and Non-Signers and Design Interventions for Adaptive SLT Systems

Voice of the Unheard: Conversational Challenges Between Sign...

引用

2025 CHI Conference on Human Factors in Computing Systems, CHI EA 2025

作者： Joseph, Vimal Thomas Jasim, Mahmood Division of Computer Science and Engineering Louisiana state university Baton RougeLA United States

ISBN: (纸本)9798400713958

Communication barriers remain a significant challenge for the D/deaf community, affecting social interactions, access to services, and overall quality of life. Despite advancements in sign language technology, existing solutions fall short of addressing the unique needs of the D/deaf community. We explore these needs and challenges by conducting a survey with 200 signers and non-signers. Our findings reveal that while the D/deaf community utilizes technology for communication, obstacles including limited translation accuracy, higher costs, and a lack of learning options persist. Additionally, varied proficiency levels, regional dialects, and the lack of visual cues further complicate interactions. We identified key barriers and design approaches that emphasize inclusivity, adaptability, and usability. By incorporating feedback from the D/deaf community, our work provides insights for developing user-centered sign language systems. Our study highlights the importance of bridging the gap between technological innovation and real-world application, paving the way for accessible and transformative communication tools. © 2025 Copyright held by the owner/author(s).

关键词： User centered design

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：