检索结果-内蒙古大学图书馆

2nd International Conference on Advanced Innovations in Smart Cities, ICAISC 2025

作者： Ibrahiem, Soha S. El-Sayed Mohammed, Bahy Ibrahim El Sayed Ahmed, Mohammed Ahmed Elbahnasy, Khaled Menofia University Computality R&D System Analyst & Nlp Researcher Faculty of Science Menofia Egypt Web Developer Cairo Egypt Software Engineer Ekad Soft Cairo Egypt Jeddah International College Computer Science and Information Technology Department Jeddah Saudi Arabia

ISBN: (纸本)9798331506995

Natural language in social media is often ambiguous, carrying diverse perspectives that are critical for opinion analysis. With vast amounts of unstructured data, particularly on platforms like Twitter, it is impractical to manually analyse relevant insights. This rapid data growth has highlighted the need for intelligent filtering and mining techniques in decision support systems to help organizations build brand reputation, foster online communities, and enhance profitability. Multi-Emotion detection is key for capturing implicit user opinions and specific emotional states;however, challenges such as text bipolarity, limited representative feature vectors, and inadequate annotated lexicons often hinder accuracy. This research aims to improve multi-emotion detection accuracy by extracting emotion implied tokens and converting them into feature vectors that capture semantic relevance. Using annotated lexicons, word embeddings, unigrams, and term frequency, these vectors are trained across five machine learning models, which are Naïve Bayes (NB), Logistic Regression (LR), Support Vector Machine (SVM), K- nearest neighbor (KNN), and Multi- layer Percepton (MLP). Finally, two ensemble techniques are applied to refine model outputs, achieving an improvement accuracy over previous work worked. The proposed system, evaluated on a real dataset, achieves a hamming score of 0.55 and an average F1 score of 0.68, demonstrating its potential for effective multi-label emotion detection. © 2025 IEEE.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

From Competition to Classroom: A Hands-on Approach to Robotics Learning

From Competition to Classroom: A Hands-on Approach to Roboti...

引用

IEEE International Conference on Autonomous Robot systems and Competitions (ICARSC)

作者： Maria S. Lopes Jorge Diogo Ribeiro António Paulo Moreira Claudia D. Rocha João G. Martins José Maria Sarmento José Pedro Carvalho Paulo G. Costa Ricardo B. Sousa Faculty of Engineering University of Porto (FEUP) Porto Portugal INESC TEC - Institute for Systems and Computer Engineering Technology and Science Porto Portugal University of Tras-os-Montes and Alto Douro (UTAD) Vila Real Portugal SYSTEC-ARISE Research Center for System and Technologies Porto Portugal

ISBN: (数字)9798331538606

ISBN: (纸本)9798331538613

Robotics education plays a crucial role in developing STEM skills. However, university-level courses often emphasize theoretical learning, which can lead to decreased student engagement and motivation. In this paper, we tackle the challenge of providing hands-on robotics experience in higher education by adapting a mobile robot originally designed for competitions to be used in laboratory classes. Our approach integrates real-world robot operation into coursework, bridging the gap between simulation and physical implementation while maintaining accessibility. The robot's software is developed using ROS, and its effectiveness is assessed through student surveys. The results indicate that the platform increases student engagement and interest in robotics topics. Furthermore, feedback from teachers is also collected and confirmed that the platform boosts students' confidence and understanding of robotics.

关键词： Surveys Education Software Mobile robots Robots Autonomous robots

来源：评论

学校读者我要写书评

暂无评论

Brain Tumor Auto-Segmentation on Multimodal Imaging Modalities Using Deep Neural Network

引用

computers, Materials & Continua 2022年第9期72卷 4509-4523页

作者： Elias Hossain Md.Shazzad Hossain Md.Selim Hossain Sabila Al Jannat Moontahina Huda Sameer Alsharif Osama S.Faragallah Mahmoud M.A.Eid Ahmed Nabih Zaki Rashed Department of Software Engineering Daffodil International UniversityDhaka 1207Bangladesh Department of Computing and Information System Daffodil International UniversityDhaka 1207Bangladesh Department of Computer Science&Engineering BRAC UniversityDhaka 1212Bangladesh Department of Information and Communication Engineering Bangladesh University of Professionals(BUP)Dhaka 1216Bangladesh Department of Computer Engineering College of Computers and Information TechnologyTaif UniversityP.O.Box 11099Taif 21944Saudi Arabia Department of Information Technology College of Computers and Information TechnologyTaif UniversityP.O.Box 11099Taif 21944Saudi Arabia Department of Electrical Engineering College of EngineeringTaif UniversityP.O.Box 11099Taif 21944Saudi Arabia Electronics and Electrical Communications Engineering Department Faculty of Electronic EngineeringMenouf 32951Egypt

Due to the difficulties of brain tumor segmentation, this paper proposes a strategy for extracting brain tumors from three-dimensional MagneticResonance Image (MRI) and Computed Tomography (CT) scans utilizing3D U-Net Design and ResNet50, taken after by conventional classificationstrategies. In this inquire, the ResNet50 picked up accuracy with 98.96%, andthe 3D U-Net scored 97.99% among the different methods of deep *** is to be mentioned that traditional Convolutional Neural Network (CNN)gives 97.90% accuracy on top of the 3D MRI. In expansion, the imagefusion approach combines the multimodal images and makes a fused image toextricate more highlights from the medical images. Other than that, we haveidentified the loss function by utilizing several dice measurements approachand received Dice Result on top of a specific test case. The average mean scoreof dice coefficient and soft dice loss for three test cases was 0.0980. At thesame time, for two test cases, the sensitivity and specification were recordedto be 0.0211 and 0.5867 using patch level predictions. On the other hand,a software integration pipeline was integrated to deploy the concentratedmodel into the webserver for accessing it from the software system using theRepresentational state transfer (REST) API. Eventually, the suggested modelswere validated through the Area Under the Curve–Receiver CharacteristicOperator (AUC–ROC) curve and Confusion Matrix and compared with theexisting research articles to understand the underlying problem. ThroughComparative Analysis, we have extracted meaningful insights regarding braintumour segmentation and figured out potential gaps. Nevertheless, the proposed model can be adjustable in daily life and the healthcare domain to identify the infected regions and cancer of the brain through various imagingmodalities.

关键词： Brain cancer segmentation 3D U-Net ResNet50 Dice measurement ROC-AUC

来源：评论

学校读者我要写书评

暂无评论

QiMINT: Quantum-Inspired Mobile Intelligence - Advancing Complex Signal Processing with Machine Learning

QiMINT: Quantum-Inspired Mobile Intelligence - Advancing Com...

引用

International Conference on Trends in Electronics and Informatics (ICEI)

作者： Vinothkumar Kolluru E. Helen Parimala Kokilavani T Sunil Raj Y Bastin Jesuraj Afrig Aminuddin Department of Data Science Stevens Institute of Technology NJ USA Department of Computer Science Gitam Deemed to be University Bangalore India Department of Computer Science School of Sciences Christ (Deemed) University Bangalore India Department of Data Science St. Xavier's College (Autonomous) Palayamkottai India Department of Computer Science Mother Theresa Arts and Science College Theni Tamilnadu India Department of Information System Faculty of Computer Science Universitas Amikom Yogyakarta Sleman Indonesia

ISBN: (数字)9798331544607

ISBN: (纸本)9798331544614

Integrating mobile intelligence with quantum-inspired machine learning (QiML) opens space for challenging mobile signal processing tasks. By utilizing superposition and entanglement, quantum computing principles, QiML boosts the agility of mobile devices by allowing real-time data processing, pattern recognition, and decision making. This work introduces Quantum-Inspired Mobile Intelligence (QiMINT) a new mobile computing framework that integrates quantum-inspired designs with classical machine learning, which increases mobile devices' accuracy, latency, and energy efficiency. Results show that medical QiML based models exceeded traditional machine learning methods in most key performance indicators. The quantum convolutional neural network (QCNN) achieved an accuracy of 92.3% in contrast with the CNNs' 87.5%, but with a processing time of 80 ms as to 120 ms, energy consumption of 10 mJ in comparison to the CNNs' 15mJ. Also, quantum-inspired random forests lowered processing delay by 40%, sustaining superior accuracy than the classical-base system. These results demonstrate that QiML can effectively balance computation complexity while making it suitable for edge computing, IoT, and mobile intelligence systems.

关键词： Quantum computing Accuracy Decision making Machine learning Signal processing Real-time systems Mobile handsets Pattern recognition Optimization Edge computing

来源：评论

学校读者我要写书评

暂无评论

Abnormal Image Classification Using Vision Transformer for Smart Agriculture

Abnormal Image Classification Using Vision Transformer for S...

引用

IEEE International Conference on Engineering Technologies and Applied Sciences (ICETAS)

作者： Talha Hafeez Muhammad Farrukh Shahid Tariq J.S. Khanzada Fast School of Computing FAST-NUCES Karachi Pakistan Department of Information System Faculty of Computing and Information Technology King Abdulaziz University Jeddah Saudi Arabia Computer Systems Engineering Departments Mehran UET Jamshoro Pakistan

Smart agriculture is an emerging innovative sector that harnesses technological advancements like sensor monitoring, image processing, soil quality evaluation, and automated water systems, all of which contribute towards enhanced crop yields and superior quality of produce. With the progression towards automated systems in smart agriculture, the need for a robust data infrastructure that assures data integrity is critical. This demands an integrated approach with anomaly detection algorithms and a robust classification technique to ensure an error-free data pipeline. This study employs two distinct datasets to achieve abnormal image classification using a vision transformer (ViT) and a convolutional neural network (CNN). The primary dataset, obtained through direct collection from cotton fields in Karachi and Balochistan, Pakistan, comprises high-resolution agricultural images captured using specialised cameras and Unmanned Aerial Vehicles (UAVs). The secondary dataset was sourced from a publicly available database. The two classification models, ViT and CNN, were applied to both datasets. These supervised models are primarily used to classify images as normal or abnormal. The results of the two classification models were also compared, with the ViT model surpassing the CNN model in performance and achieving the highest accuracy on both datasets. The Vision Transformer model proved to be robust for supervised data, showing remarkable accuracy of 96.00% on the public dataset, 99.18% on both camera based images and 97.56% on UAV images of collected dataset as compared to the CNN model's accuracy that are 82.00% on the public dataset and 98.36% on camera and 95.12% on UAV images of collected dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hybridization of deep learning models with crested porcupine optimizer algorithm-based cybersecurity detection on industrial IoT for smart city environments

引用

Alexandria Engineering Journal 2025年 127卷 239-250页

作者： Alzakari, Sarah A. Aljebreen, Mohammed Asiri, Mashael M. MANSOURI, Wahida Alahmari, Sultan Alqahtani, Mohammed Sorour, Shaymaa Bedewi, Wafi Department of Computer Sciences College of Computer and Information Sciences Princess Nourah bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia Department of Computer Science Community College King Saud University P.O. Box 28095 Riyadh11437 Saudi Arabia Department of Computer Science Applied College at Mahayil King Khalid University Saudi Arabia Department of Computer Science and Information Technology Faculty of Sciences and arts Turaif Northern Border University Arar91431 Saudi Arabia Cybersecurity Institute Riyadh Saudi Arabia Department of Information System and Cyber Security College of Computing and Information Technology University of Bisha Bisha61922 Saudi Arabia Department of Management Information Systems School of Business King Faisal University Al-Ahsa31982 Saudi Arabia Department of Information Systems Faculty of Computing and Information Technology King Abdulaziz University Jeddah Saudi Arabia

Smart cities have attracted extensive coverage from multidisciplinary studies, and many artificial intelligence (AI) solutions have been designed. Conversely, cybersecurity has constantly been a crucial issue and is becoming gradually dangerous in smart cities. The attack defence models are inappropriate for perceiving multistep assaults as the recognition rules are restricted, and efficacy is partial due to many false security alarms. Therefore, an innovative solution is immediately required to progress cybersecurity defence ability. Machine learning (ML) methods are commonly employed to recognize numerous attacks because they could help network administrators grab analogous initials to avert intrusion. This study presents Cybersecurity using a Crested Porcupine Optimizer Algorithm with Hybrid Deep Learning Models (CCPOA-HDLM). The foremost intention of this study is to improve cybersecurity detection and classification in smart city environments. To accomplish that, the CCPOA-HDLM method comprises distinct processes such as min-max normalization, improved Salp swarm algorithm (ISSA)-based feature selection, Multi-Channel Convolutional Neural Network - Recurrent Neural Network (MCNN-RNN)-based cybersecurity detection, and crested porcupine optimizer (CPO)-based parameter selection process. Primarily, data normalization utilizing min-max normalization is implemented. Next, the CCPOA-HDLM method utilizes ISSA based feature selection method to select optimum features. The CCPOA-HDLM technique employs a hybrid of the MCNN-RNN model for the cybersecurity detection and classification process. Moreover, the hyperparameter range of the hybrid of DL techniques occurs using the CPO technique. The experimental validation of the CCPOA-HDLM approach is performed on the UNSW-NB15 dataset, and the outcome portrayed a superior accuracy value of 99.04 % over other recent approaches under various measures. © 2025 The Authors

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Multiple-Criteria Decision Analysis Clustering and Cluster Head Selection Algorithm in Vehicular Network 8

A Multiple-Criteria Decision Analysis Clustering and Cluster...

引用

8th IEEE R10 Humanitarian technology Conference, R10-HTC 2020

作者： Nandy, Tarak Idris, Mohd Yamani Idna Bin Noor, Rafidah Md Ahmedy, Ismail Bhattacharyya, Sananda University of Malaya Faculty of Computer Science and Information Technology Department of Computer System and Technology Kuala Lumpur Malaysia Maldives Business School Department of Information Technology Male' Maldives

ISBN: (纸本)9781728111100

Vehicle ad-hoc network (VANET) faces heavy traffic with communication burden to connect with various nodes in the network, uses clustering techniques with neighboring vehicles, and elects a powerful and efficient vehicle as a cluster head. Cluster head vehicle collects all the information and pass them out and transmit outside data to other members in the cluster. However, clustering faces issues such as the inability of choosing feasible and stable clusters for a long time. On the other hand, the nomination of cluster heads fails to adhere to real-world parameters. To address these issues, in this paper, a k-means algorithm and direction vector-based clustering techniques and a cluster head selection method with the utilization of fuzzy-based PROMETHEE multi-criteria decision techniques are proposed. Moreover, mathematical and rational analysis shows that the method is implementable and achievable. Finally, a range of future directions of the study is shown. © 2020 IEEE.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Two-factor Authentication Protocol for V2V Communication in VANETs 20

An Enhanced Two-factor Authentication Protocol for V2V Commu...

引用

3rd International Conference on Information Science and system, ICISS 2020

作者： Nandy, Tarak Idris, Mohd Yamani Idna Bin Noor, Rafidah Md Ahmedy, Ismail Bhattacharyya, Sananda Department of Computer System and Technology Faculty of Computer Science and Information Technology University of Malaya Kuala Lumpur Malaysia Department of Information Technology Maldives Business School Male Maldives

ISBN: (纸本)9781450377256

The objective of the vehicular ad-hoc network (VANET) is to mobilize transportation systems along with the enhancement of safeguard and efficiency. Security and anonymity are important aspects of VANET too. Vehicle-to-vehicle (V2V) communication fulfills most of the requirements in VANET except the security breaches. Authentication protocols are designed to improve security by validating legitimate users in V2V communication. In this research, we proposed a two-factor authentication protocol using user biometric-based and password-based, which can support minimum or no VANET infrastructure environments. Furthermore, we performed an informal security analysis on the aforesaid protocol and shown the security features of it. We further discussed the future scope of the research in the field of VANET authentication. © 2020 ACM.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

An Investigation of IOT-Based Consumer Analytics to Assist Consumer Engagement Strategies in Evolving Markets 3

An Investigation of IOT-Based Consumer Analytics to Assist C...

引用

3rd International Conference on Advance Computing and Innovative Technologies in Engineering, ICACITE 2023

作者： Jayadeva, Sujay Mugaloremutt Prasad Krishnam, Nagendra Raja Mannar, B. Prakash Dabral, Amar Buddhi, Dharam Garg, Neha Jss Academy of Higher Education & Research Department of Health System Management Studies Faculty of Management Studies India Telangana Hyderabad India St. Theresa Intl College Business Administration Thailand Graphic Era Deemed to Be University Department of Hospitality Management Uttarakhand Dehradun India Uttaranchal University Uttaranchal Institute of Technology India Graphic Era Deemed to Be University Department of Computer Science & Engineering Uttarakhand Dehradun248002 India

ISBN: (纸本)9798350399264

In order to establish sustainable operations, Internet innovation has been widely adopted in the retail sector;however, certain operational difficulties, such as security and confidentiality have been uncovered in practise. As a result, linked fields must do more thorough theoretical study. In order to compete with online merchants and promote sustainable growth, this study examines how traditional brick and mortar stores might use IoT technology. First, by taking into account the costs of customer inconvenience associated with shopping through various retail partners and the influence of technology, pricing Plans were created for the store and the retailer of concrete blocks, respectively. Furthermore, by contrasting different scenarios, the benefits of internet to retail shops and consumer excess are analysed. After that, the basic models were expanded to take into account consumer - perceived sensitivity regarding IoT technology and price competitiveness in order to test the robustness of the analytical conclusions. Additionally, actual data-based numerical analyses are performed. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

A New Technique of Soluble NPK Nutrient Detection system Using Deep Learning-Based Recurrent Neural Networks (RNN)

A New Technique of Soluble NPK Nutrient Detection System Usi...

引用

International Electrical Engineering Congress (iEECON)

作者： Wallop Tipwong Adisorn Sirikham Jessada Konpang Putthiphong Kirdpipat Yutana Chongjarearn Oradee Preutisrunyanont Department of Electrical and Telecommunication Engineering Rajamangala University of Technology Krungthep Bangkok Thailand Department of Electrical and Computer Engineering Faculty of Engineering Thammasat School of Engineering Thammasat University Pathum Thani Thailand Department of Robotic Engineering and Automation System Dhurakij Pundit University Bangkok Thailand

ISBN: (数字)9798350383591

ISBN: (纸本)9798350383607

Modern agriculture relies heavily on effective process monitoring, control, and remote data collection, making accurate and cost-effective sensors crucial for innovation. This research focuses on the development of a spectroscopy-based device for real-time and remote monitoring of nutrient levels in hydroponic systems. The device utilizes IoT architecture, incorporating principles of light absorbance to quantify concentrations of essential nutrients during crop growth. Three deep learning techniques, Artificial Neural Networks (ANN), Convolutional Neural Networks (CNN), and Recurrent Neural Networks (RNN) were adopted for data analysis. Results demonstrate that tailored implementation of deep learning can significantly enhance the performance of sensor network system (SNS). Specifically, the RNN format achieved an impressive 98% model accuracy during both training and testing phases. The technological advancements in addressing contract variation and photometric levels contribute to increased accuracy as more sensors become available. The findings serve as a comprehensive guide for collecting extensive agricultural data, encompassing environmental factors throughout the entire cultivation period, using state-of-the-art remote control sensor equipment. This work provides a practical, efficient, and cost-effective solution for precise nutrient control and continuous data monitoring in agricultural production.

关键词： Deep learning Training Recurrent neural networks Sensor phenomena and characterization Sensor systems Environmental factors Convolutional neural networks

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：