检索结果-内蒙古大学图书馆

IET Blockchain 2024年第2期4卷 101-123页

作者： Wu, Hanjie Yao, Qian Liu, Zhenguang Huang, Butian Zhuang, Yuan Tang, Huayun Liu, Erwu School of Cyber Science and Technology Zhejiang University Hangzhou China ZJU-Hangzhou Global Scientific and Technological Innovation Center Hangzhou China China Securities Regulatory Commission Beijing China Hangzhou Yunphant Network Technology Co. Ltd. Hangzhou China College of Computer Science and Technology Harbin Engineering University Harbin China Institute of Chinese Finance Studies Southwestern University of Finance and Economics Chengdu China College of Electronics and Information Engineering Tongji University Shanghai China

As an innovative technology for enhancing authenticity, security, and risk management, blockchain is being widely adopted in trade and finance systems. The unique capabilities of blockchain, such as immutability and transparency, enable new business models of distributed data storage, point-to-point transactions, and decentralized autonomous organizations. Here, the authors focus on blockchain-based securities trading, in which blockchain technology plays a vital role in financial services as it ultimately lifts trust and frees the need for third-party verification by using consensus-based verification. The 12 most popular blockchain platforms are investigated and 6 platforms that are related to finance are elaborated on, seeking to provide a panorama of securities trading practices. Meanwhile, this survey provides a comprehensive summary of blockchain-based securities trading applications. Numerous practical applications of blockchain-based securities trading are gathered and they are categorized into four distinct categories. For each category, a typical example is introduced and how blockchain contributes to solving the key problems faced by FinTech companies and researchers explained. Finally, interesting observations are provided ranging from mainstream blockchain-based financial institutions to security issues of decentralized finance applications, aiming to picture the current blockchain ecosystem in finance. © 2024 The Authors. IET Blockchain published by John Wiley & Sons Ltd on behalf of The Institution of engineering and Technology.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Human Blood Cell (Haematologicalimages) Recognition by Applying Deep Convolution Methods 9

Human Blood Cell (Haematologicalimages) Recognition by Apply...

引用

9th IEEE International Conference for Convergence in Technology, I2CT 2024

作者： Krishna Kumar, N. Sarada, Ch. Mallika, S. Suguna Subhashini, P. Sai Kumar, K. Zearah, Sajad Ali Gnitc Department of Cse Hyderabad India Cvr College of Engineering Department of Cse Telangana Hyderabad India Mlr Institute of Technology Department of Computer Science And Information Technology Telangana Hyderabad India Malla Reddy University School of Engineering Computer Science Dulapally Maisammaguda Telangana Hyderabad500100 India Al-Ayen University Scientific Research Center Thi-Qar Iraq

ISBN: (纸本)9798350394474

Utilizing Deep Convolution Strategies to Perceive Human Platelets (Hematological Pictures): Deep Learning is rapidly becoming seen as a preferable method for learning over conventional ML models. This is on the grounds that it has previously been demonstrated to have the option to manage continuous issues in numerous application regions. Convolutional neural networks (CNNs), a sort of deep learning calculation, have a few advantages in the field of well-being, where a ton of pictures should be handled and inspected. The objective of the review is to make a deep learning model to take care of the issue of placing platelets into gatherings. It is one of the hardest things to sort out while checking blood out. A CNN-based framework has been made that consequently sorts pictures of platelets into various kinds of cells, like MONOCYTE, LYMPHOCYTE, NEUTROPHIL, and EOSINOPHIL. To further develop CNN innovation, specialists have investigated thoughts like the utilization of numerous initiation and misfortune capabilities, regularization, boundary advancement, and plan development. Be that as it may, changes to CNN's design have made it feasible for it to show much more. A block of layers can likewise be utilized as a structure block. This concentrates first glances at the inward scientific classifications of recently declared deep CNN frameworks. This is done so that new CNN configuration patterns can be placed into classes. The seven regions are channel gain, utilization of room, utilization of element maps, multipath, profundity, width, and consideration. Overall information on CNN's parts, its ongoing issues, and how it tends to be utilized is likewise given. © 2024 IEEE.

关键词： Platelets

来源：评论

学校读者我要写书评

暂无评论

Channel Allocation in 5G Networks using Ant Colony Optimization Algorithm 6

Channel Allocation in 5G Networks using Ant Colony Optimizat...

引用

6th International Youth Conference on Radio Electronics, Electrical and Power engineering, REEPE 2024

作者： Hussein, Areej Anbar, Mohammad Molhem, Mohammed Oudeh, Atheer Yousif Nassr, Mohammad Fardoun, Habib University of Tartous Dept. of Communication Technology Engineering Tartous Syria Al-Ayen University Thi-Qar Dept. of Computer Engineering Technology Iraq College of Education for Pure Science University of Thi-Qar Scientific Research Center Al-Ayen University Thi-Qar Dept. of Computer Science Iraq Canadian University Dubai United Arab Emirates

ISBN: (纸本)9798350382891

Efficient channel allocation is crucial for enabling concurrent calls and data sessions within a cellular network in general. When channels are inefficiently allocated, network congestion may occur leading to call blocking due to a lack of available channels. In this research, an Ant Colony Optimization (ACO) algorithm-based model has been proposed to tackle channel allocation problem in 5G cellular networks. The proposed model has been simulated using Python. The experimental study focused on minimizing Call Block Probability (CBP) by optimizing channel allocation as the number of network users increase. © 2024 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

A survey and recent advances in black widow optimization: variants and applications

引用

Neural Computing and Applications 2024年 1-21页

作者： Shehab, Mohammad Shambour, Mohd Khaled Yousef Abu Hashem, Muhannad A. Al Hamad, Husam Ahmad Shannaq, Fatima Mizher, Manar Jaradat, Ghaith Sh. Daoud, Mohammad Abualigah, Laith College of Computer Sciences and Informatics Amman Arab University Amman11953 Jordan The Custodian of the Two Holy Mosques Institute for Hajj and Umrah Research Umm Al-Qura University Makkah Saudi Arabia Department of Geomatics Architecture and Planning Faculty King Abdulaziz University Jeddah Saudi Arabia College of Engineering Al Ain University Abu Dhabi United Arab Emirates Research Center University of Tabuk Tabuk71491 Saudi Arabia Computer Science Department Al al-Bayt University Mafraq25113 Jordan Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman19328 Jordan MEU Research Unit Middle East University Amman11831 Jordan Department of Electrical and Computer Engineering Lebanese American University Byblos13-5053 Lebanon School of Computer Sciences Universiti Sains Malaysia Pulau Pinang11800 Malaysia School of Engineering and Technology Sunway University Malaysia Petaling Jaya27500 Malaysia Applied science research center Applied science private university Amman11931 Jordan College of Engineering Yuan Ze University Taoyuan32003 Taiwan

Artificial Intelligence techniques, such as optimization algorithms, have become essential for success in many fields. Therefore, most researchers, especially in computer and engineering sciences, focused their efforts and abilities on adapting the optimization algorithms for solving various problems. This review introduces one of the recent nature-inspired optimization algorithms, called black widow optimization (BWO). This review highlights the main procedures of BWO, its strengths and weaknesses, the growth of BWO, the variants of BWO (i.e., binary, modification, and hybridization), and the efficiency of BWO in different fields and applications (i.e., feature selection, medical, image processing, engineering, IoT, power and energy, and networks). As a result, the review seeks to assist researchers who are interested in using the BWO to address their challenges. For instance, it could help manage large pilgrim crowds, enabling smoother ritual performances and overcoming potential difficulties they encounter. Also, it suggests new possible ways of enhancing the efficiency of the basic BWO. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Applied intelligence with deep learning assisted automated sarcasm recognition in twitter data

引用

Alexandria engineering Journal 2025年 128卷 79-91页

作者： Alzaidi, Muhammad Swaileh A. Alsudais, Taghreed Ali Eltahir, Majdy M. Ebad, Shouki A. Alshuhail, Asma Alshahrani, Mohammed Alanazi, Sultan Department of English Language College of Language Sciences King Saud University P. O. Box 145111 Riyadh Saudi Arabia Department of Teaching and Learning College of Education and Human Development Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia Department of Information Systems Applied College at Mahayil King Khalid University Saudi Arabia Center for Scientific Research and Entrepreneurship Northern Border University Arar73213 Saudi Arabia Department of Information Systems College of Computer Sciences & Information Technology King Faisal University Saudi Arabia Computer Department Applied College Najran University Najran66462 Saudi Arabia Department of Computer Science College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz University Al-Kharj16273 Saudi Arabia

Sarcasm is essential in human interaction, particularly on social networking, where individuals share their feelings through criticism, humour, and satire. Sarcasm detection is vital in understanding the context of communication and the sentiment on platforms such as Twitter. This presents sarcasm detection as a complex problem in natural language processing (NLP). The challenges and importance upsurge, particularly in languages such as Arabic and Urdu, where resources for NLP are inadequate. The classical rule-based techniques need to improve performance owing to sarcasm's context-based and subtle nature. On the other hand, the current developments in deep learning (DL) and NLP offer efficient solutions. Therefore, this study presents an Applied Intelligence with Deep Learning Assisted Automated Sarcasm Recognition Approach (AIDL-ASRA) on Twitter Data. The presented AIDL-ASRA technique concentrates on identifying sarcastic and non-sarcastic contexts in tweets. In the AIDL-ASRA technique, the initial pre-processing stage is executed with different subprocesses. Next, Global Vectors for Word Representation (GloVe)-based word embedding process occurs. The AIDL-ASRA technique utilizes the Discriminative Deep Belief Networks (DDBN) method for sarcasm recognition. The DBN model's effectiveness is improved using the cat swarm optimization (CSO) model. A set of experiments were involved in evaluating the performance of the AIDL-ASRA method under the Arabic sarcastic dataset comprising 10,000 tweets. The experimental validation of the AIDL-ASRA method attained a superior accuracy value of 91.25 % over existing techniques under distinct measures. © 2025 The Authors

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

WHO IS YOUR RIGHT MIXUP PARTNER IN POSITIVE AND UNLABELED LEARNING 10

WHO IS YOUR RIGHT MIXUP PARTNER IN POSITIVE AND UNLABELED LE...

引用

10th International Conference on Learning Representations, ICLR 2022

作者： Li, Changchun Li, Ximing Feng, Lei Ouyang, Jihong College of Computer Science and Technology Jilin University China College of Computer Science Chongqing University China Imperfect Information Learning Team RIKEN Center for Advanced Intelligence Project Japan Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education China

Positive and Unlabeled (PU) learning targets inducing a binary classifier from weak training datasets of positive and unlabeled instances, which arise in many real-world applications. In this paper, we propose a novel PU learning method, namely Positive and unlabeled learning with Partially Positive Mixup (P3Mix), which simultaneously benefits from data augmentation and supervision correction with a heuristic mixup technique. To be specific, we take inspiration from the decision boundary deviation phenomenon observed in our preliminary experiments, where the learned PU boundary tends to deviate from the fully supervised boundary towards the positive side. For the unlabeled instances with ambiguous predictive results, we select their mixup partners from the positive instances around the learned PU boundary, so as to transform them into augmented instances near to the boundary yet with more precise supervision. Accordingly, those augmented instances may push the learned PU boundary towards the fully supervised boundary, thereby improving the classification performance. Comprehensive experimental results demonstrate the effectiveness of the heuristic mixup technique in PU learning and show that P3Mix can consistently outperform the state-of-the-art PU learning methods. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

关键词： Heuristic methods

来源：评论

学校读者我要写书评

暂无评论

A Dynamic Approach to Cyber Risk Assessment for Critical Information Infrastructure 3

A Dynamic Approach to Cyber Risk Assessment for Critical Inf...

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Chadalawada, Rajendra Rao, K. Srinivas Khlaif, Abbas Mahdi Kumar, Bodla. Ashwin Babu, B. Sankara Saikumar, K. Narayana Engineering College Department of Cse Nellore India Mlr Institute of Technology Department of Computer Science and Engineering Hyderabad India Scientific Research Center Al-Ayen University Thi-Qar64001 Iraq Cvr College of Engineering Department of Computer Science and Engineering Hyderabad India Dept. of Cse Telangana Bachupally India Koneru Lakshmaiah Education Foundation Dept of Cse Telangana Hyderabad500075 India

ISBN: (纸本)9798350319125

In this study, a sophisticated cyberattack model was created for real-time DDoS & MITM attacks. Clouds, servers, big data, and networks are only a few of the modern infrastructures where cyber threats have proliferated. Threats to these platforms mean that private information may have been compromised within their applications. Cyber security experts could choose from a plethora of tried-and-true static models, but they all fell short when faced with dynamic attacks and other, more complicated threats. Furthermore, earlier cybersecurity models had problems with both high-ToC and target-attack scalability. Using machine learning methods, this study develops a sophisticated model for evaluating cyber risks. The recommended Lite RFO model was built using a top-notch Python programming utility. This architecture has been used to monitor cyberattacks on any network and locate the specific attack with a reduced Tree of Controls (ToC). There was a substantial improvement in performance metrics like detection rate (98.43% ), accuracy (98.23% ), sensitivity (96.89%), and recall (94.56%). © 2023 IEEE.

关键词： attacks critical infromation of cyber-attacks cyber risk cybersecurity

来源：评论

学校读者我要写书评

暂无评论

computer Network-Assisted Technology-Based English Teaching Method with Artificial Intelligence

Computer Network-Assisted Technology-Based English Teaching ...

引用

2023 Annual International Conference on Emerging Research Areas: International Conference on Intelligent Systems, AICERA/ICIS 2023

作者： Zearah, Sajad Ali Ettyem, Sajjad Ali Adile, Mohaned Abed, Ansam Mohammed Hussian, Ahmed Al-Shaikhli, Taha Raad Al-ayen University Scientific Research Center Thi-Qar Iraq National University of Science and Technology Department of Medical Devices Engineering Technologies Nasiriyah Dhi Qar Iraq Al-farahidi University Medical Instruments Engineering Techniques Baghdad Iraq Al-Turath University College Computer Technologies Engineering Baghdad Iraq Al-Kunooze University College Technical Computer Engineering Department Basrah Iraq Al-Nisour University College Computer Engineering Techniques Baghdad Iraq

ISBN: (纸本)9798350303452

the increased need for well-rounded proficiency in oral, written, and read-aloud communication directly results from the recent educational revolution and its focus on education quality, particularly in English. The networked environment and the new reading model for English that it has spawned are products of the application of cutting-edge science and technology connected with teaching tools using artificial intelligence (AI). Hence, this paper proposes computer Network-assisted English Teaching Framework (CNETF) based on artificial intelligence. computer-assisted learning approaches can present the learning utilizing different media either video or picture that can support the effective learning progression and simplify the learners to handle the learning speed since it is joined with the multimedia. Compared to other popular methods, the results reveal that computer-assisted English teaching and test can better reflect the student's true level, performance, and outcome. The experimental result suggests that the proposed method CNETF achieves the highest performance rate of 98.78%, Level of discrepancy rate of 40.2%, regression analysis of 90.2%, path analysis of 97.7%, error rate of 5.1%, learning rate of 93.4%, correlation rate of 95.6% compared to other methods. © 2023 IEEE.

关键词： Teaching

来源：评论

学校读者我要写书评

暂无评论

Internet of Things and wearable device-basedtracking of an elderly person's physical activity 1

Internet of Things and wearable device-basedtracking of an e...

引用

1st IEEE International Conference on Emerging Research in computational science, ICERCS 2023

作者： Ali Zearah, Sajad Mohammed Abed, Ansam Hussian, Ahmed Ali Ettyem, Sajjad Hussam, Ragheed Matti, Imad Alayen University Scientific Research Center Thi-Qar Iraq Al-Turath University College Computer Technologies Engineering Baghdad Iraq Al-Kunooze University College Technical Computer Engineering Department Basrah Iraq Technologies National University of Science and Technology Department of Medical Devices Engineering Nasiriyah Dhi Qar Iraq Al-Farahidi University Medical Instruments Engineering Techniques Baghdad Iraq Al-Maamoun University College Computer Technology Engineering Baghdad Iraq

ISBN: (纸本)9798350359756

The potential for real-time activity tracking (R- TAT) to shed light on the health and habits of the elderly is a major reason why it should be widely adopted. This strategy allows for the unobtrusive collecting and analysis of data connected to a person's day-to-day physical activities by deploying wearable devices equipped with sensors and leveraging the connectivity of IoT. These details can be crucial in the early diagnosis of health problems, allowing for prompt interventions and individualized healthcare plans. Ethical constraints, data privacy, and the requirement for userfriendly gadgets offer considerable challenges to mainstream adoption. To facilitate real-time monitoring while giving top priority to data integrity and confidentiality, a new algorithm called the IoT-Enabled Data Transmission Privacy Recognition Algorithm (IoT-DTPRA) has been suggested in the present research. Provides fine-grained control over data sharing options and uses strong measures like encryption and anonymization to preserve the privacy of senior citizens' personal information. Caretakers, healthcare professionals, and family members all benefit from the actionable information provided by IoT-DTPRA since it provides a comprehensive and privacy-conscious way to monitoring the physical activity of the elderly. The suggested methodology is verified using simulation analysis, which use actual situations and synthetic datasets to assess the IoT-DTPRA system's performance in a range of environments. The methodology's reliability and robustness across a wide range of physical activities and environmental circumstances have been verified by this thorough validation. © 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

Target Detection in Complex Environments using UAV and Deep Learning-based Focal Pruning Method 1

Target Detection in Complex Environments using UAV and Deep ...

引用

1st IEEE International Conference on Emerging Research in computational science, ICERCS 2023

作者： Thejeel, Sara H. Hussian, Ahmed Hussian, Ahmed Ahmed, Wasan Saad Ali Zearah, Sajad Ali, Mohsin National University of Science and Technology Department of Medical Devices Engineering Technologies Nasiriyah Dhi Qar Iraq Al-Farahidi University Medical Instruments Engineering Techniques Baghdad Iraq Al-Kunooze University College Technical Computer Engineering Department Basrah Iraq AlTurath University College Computer Technologies Engineering Baghdad Iraq Al-Ayen University Scientific Research Center Thi-Qar Iraq Computer Technology Engineering Al-Maamoun University College Baghdad Iraq

ISBN: (纸本)9798350359756

Applications from computer vision that use deep learning for target detection have become incredibly popular recently. The requirement for future applications includes monitoring, visual navigation, object identification, and sensor-based preventative planning, together with the growing UAV industry advances, which hold great potential for deep learning. Deep learning techniques for object detection have swiftly evolved into a rendering tool for photos taken by flying drones. This paper's primary goal is to present a comprehensive overview of contemporary deep learning-based object recognition algorithms and to explore their most recent contributions to UAV low-altitude datasets. As opposed to standard or remote-sensor datasets, which comprise a smaller percentage of the literature, low-level UAV datasets are the focus of the research. To conduct real-time bridge crack diagnosis with Unmanned Aerial Vehicles (UAV), a deep learning system dubbed the You Only Look Once version-4 Focal Pruning Method (YOLOv4-FPM) is suggested based on the YOLOv4 model. For YOLOv4-FPM, focal loss architecture is utilized to streamline the loss feature, improve accuracy and colour transmission, and solve issues with dynamic context. A pruning method is used to speed up detection and facilitate the network. The outcomes show that the model can successfully handle the difficulty given by various backdrops, and the detection velocity is 97.2% effective enough for the real-time detection mission. The YOLOv4-FPM of deep learning technology guarantees 96.3% detection accuracy compared to current drone detection methods. © 2023 IEEE.

关键词： Object recognition

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：