检索结果-内蒙古大学图书馆

Smart Optimization of Semiconductors in Photovoltaic-Thermoelectric Systems Using Recurrent Neural Networks

International Journal of Energy Research 2023年第1期2023卷

作者： Alghamdi, Hisham Maduabuchi, Chika Okoli, Kingsley Albaker, Abdullah Alatawi, Ibrahim Alsafran, Ahmed S. Alkhedher, Mohammad Chen, Wei-Hsin Electrical Engineering Department College of Engineering Najran University Najran55461 Saudi Arabia Department of Nuclear Science and Engineering Massachusetts Institute of Technology CambridgeMA United States Artificial Intelligence Laboratory University of Nigeria Nsukka Enugu Nsukka410001 Nigeria Department of Computer Science and Knowledge Discovery Saint Petersburg Electrotechnical University LETI Saint Petersburg197022 Russia Department of Electrical Engineering College of Engineering University of ha'Il Ha'il81451 Saudi Arabia Department of Mechanical Engineering College of Engineering University of ha'Il Ha'il81451 Saudi Arabia Department of Electrical Engineering College of Engineering King Faisal University Al-ahsa31982 Saudi Arabia Department of Mechanical and Industrial Engineering Abu Dhabi University Abu Dhabi59911 United Arab Emirates Department of Aeronautics and Astronautics National Cheng Kung University Tainan701 Taiwan Research Center for Smart Sustainable Circular Economy Tunghai University Taichung407 Taiwan Department of Mechanical Engineering National Chin-Yi University of Technology Taichung411 Taiwan

In the relentless pursuit of sustainable energy solutions, this study pioneers an innovative approach to integrating thermoelectric generators (TEGs) and photovoltaic (PV) modules within hybrid systems. Uniquely, it employs neural networks for an exhaustive analysis of a plethora of parameters, including a diverse spectrum of semiconductor materials, cooling film coefficients, TE leg dimensions, ambient temperature, wind speed, and PV emissivity. Leveraging a rich dataset, the neural network is meticulously trained, revealing intricate interdependencies among parameters and their consequential impact on power generation and the efficiencies of TEG, PV, and integrated PV-TE systems. Notably, the hybrid system witnesses a striking 23.1% augmentation in power output, escalating from 0.26 W to 0.32 W, and a 20% ascent in efficiency, from 14.68% to 17.62%. This groundbreaking research illuminates the transformative potential of integrating TEGs and PV modules and the paramountcy of multifaceted parameter optimization. Moreover, it exemplifies the deployment of machine learning as a powerful tool for enhancing hybrid energy systems. This study, thus, stands as a beacon, heralding a new chapter in sustainable energy research and propelling further innovations in hybrid system design and optimization. Through its novel approach, it contributes indispensably to the arsenal of clean energy solutions. © 2023 Hisham Alghamdi et al.

关键词： Hybrid systems

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study on Cyber security Technology in Big data Cloud Computing Environment

A Comparative Study on Cyber security Technology in Big data...

引用

International Conference on Contemporary Computing and Informatics (IC3I)

作者： Amit Kumar Jain Tripti Misra Neha Tyagi M V Suresh Kumar Bhasker Pant Department of Computer Science Delhi University Delhi Deutche Telecom Digital Labs Gurugram Haryana India Department of IT Knowledge Park 3 G. L Bajaj Institute of Technology & Management Greater Noida India Department of Law Koneru Lakshmaiah Education Foundation Green Fields Vaddeswaram Guntur Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun Uttarakhand Guntur

Protection of networks, programs and systems from cyberattacks is the practice of cybersecurity technology. The cyberattacks are capable of gaining access for deleting or altering of data that are sensitive, demanding money from the users and obstruction of regular operations of corporates. In the present situation many devices are getting smarter than that of the hackers and humans that makes the tasks difficult for implementing the measures of cybersecurity. In terms of cyber security, the ability of collecting huge amount of data is known as big data analytics. The functions are performed through displaying, interpretation and extraction of the insights of future that can enable early detection of catastrophic cyber threats and attacks. Organizations can better understand all the activities and acts that could potentially result in cyber-attacks by having a stronger and more effective cyber defensive posture. As offices became more remote, cloud computing became crucial for gaining access to important documents, programs, and computing resources. Although connection can be both a benefit and a curse, as easily accessible files can become an easy target for hostile actors, we expect the global economy to transfer even more into the cloud over time. Therefore, efforts in strengthening cybersecurity measures are vital to safeguard distant vaults of sensitive data. The management depends on a combination of technology and advice to secure the cloud. It involves managing the framework, information applications, safe-secure guidelines, consistency leads, and secure infrastructure data applications that pertain to cloud computing. The same principles that underpin security for modern cloud computing platforms and historic knowledge centers are secrecy, integrity, and usability. The novel method of DDoS attack detection is proposed.

关键词： Performance evaluation Cloud computing Privacy Systems operation Organizations computer crime Usability

来源：评论

学校读者我要写书评

暂无评论

GEOM-GCN: GEOMETRIC GRAPH CONVOLUTIONAL NETWORKS 8

GEOM-GCN: GEOMETRIC GRAPH CONVOLUTIONAL NETWORKS

引用

8th International Conference on Learning Representations, ICLR 2020

作者： Pei, Hongbin Wei, Bingzhe Chang, Kevin Chen-Chuan Lei, Yu Yang, Bo College of Computer Science and Technology Jilin University China Department of Electrical and Computer Engineering University of Illinois Urbana-Champaign United States Department of Computer Science University of Illinois Urbana-Champaign United States Department of Computing Hong Kong Polytechnic University Hong Kong Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education China

Message-passing neural networks (MPNNs) have been successfully applied to representation learning on graphs in a variety of real-world applications. However, two fundamental weaknesses of MPNNs' aggregators limit their ability to represent graph-structured data: losing the structural information of nodes in neighborhoods and lacking the ability to capture long-range dependencies in disassortative graphs. Few studies have noticed the weaknesses from different perspectives. From the observations on classical neural network and network geometry, we propose a novel geometric aggregation scheme for graph neural networks to overcome the two weaknesses. The behind basic idea is the aggregation on a graph can benefit from a continuous space underlying the graph. The proposed aggregation scheme is permutation-invariant and consists of three modules, node embedding, structural neighborhood, and bi-level aggregation. We also present an implementation of the scheme in graph convolutional networks, termed Geom-GCN, to perform transductive learning on graphs. Experimental results show the proposed Geom-GCN achieved state-of-the-art performance on a wide range of open datasets of graphs. © 2020 8th International Conference on Learning Representations, ICLR 2020. All rights reserved.

关键词： Message passing

来源：评论

学校读者我要写书评

暂无评论

A Revised Satellite Cloud-Derived Wind Inversion Algorithm Based on computer Cluster

引用

computers, Materials & Continua 2020年第7期64卷 373-388页

作者： Lili He Zhiwei Cai Dantong Ouyang Changshuai Wang Yu Jiang Chong Wang Hongtao Bai College of Computer Science and Technology Jilin UniversityChangchun130012China Symbol Computation and Knowledge Engineer of Ministry of Education Jilin UniversityChangchun130012China Department of Engineering Mechanics State Marine Technical University of St.PetersburgSt.Petersburg190008Russia

In view of the satellite cloud-derived wind inversion has the characteristics of large scale,intensive computing and time-consuming serial inversion algorithm is very difficult to break through the bottleneck of *** proposed a parallel acceleration scheme of cloud-derived wind inversion algorithm based on MPI cluster parallel technique in this *** divide-and-conquer idea,assigning winds vector inversion tasks to each computing unit,is identified according to a certain *** computing unit executes the assigned tasks in parallel,namely divide-and-rule the inversion task,so as to reduce the efficiency bottleneck of long inversion time caused by serial time *** the scheme of parallel acceleration based on MPI cluster,an algorithm based on performance prediction is proposed to effectively implement load balance of MPI *** the comparative analysis of experiment data using the parallel scheme of this parallel technology framework,it shows that this parallel technology has a certain acceleration effect on the cloud-derived wind inversion *** speedup of the MPI-based parallel algorithm reaches 14.96,which achieved the expected *** the same time,this paper also proposes an efficiency optimization algorithm for cloud-derived wind *** the case that the inversion of wind vector accuracy loss is minimal,the optimized algorithm execution time can be up to 13 times faster.

关键词： Cloud-derived wind wind vector inversion parallel computing MPI speedup ratio

来源：评论

学校读者我要写书评

暂无评论

Recommendation Algorithm Based on Probabilistic Matrix Factorization with Adaboost

引用

computers, Materials & Continua 2020年第11期65卷 1591-1603页

作者： Hongtao Bai Xuan Li Lili He Longhai Jin Chong Wang Yu Jiang College of Computer Science and Technology Jilin UniversityChangchun130012China Symbol Computation and Knowledge Engineer of Ministry of Education Jilin UniversityChangchun130012China Department of Engineering Mechanics State Marine Technical University of St.PetersburgSt.Petersburg190008Russia

A current problem in diet recommendation systems is the matching of food preferences with nutritional requirements,taking into account individual characteristics,such as body weight with individual health conditions,such as *** dietary recommendations employ association rules,content-based collaborative filtering,and constraint-based methods,which have several *** limitations are due to the existence of a special user group and an imbalance of non-simple *** use of traditional dietary recommendation algorithm researches,we combine the Adaboost classifier with probabilistic matrix *** present a personalized diet recommendation algorithm by taking advantage of probabilistic matrix factorization via Adaboost.A probabilistic matrix factorization method extracts the implicit factors between individual food preferences and nutritional *** this,we can make use of those features with strong influence while discarding those with little *** incorporating these changes into our approach,we evaluated our algorithm’s *** results show that our method performed better than others at matching preferred foods with dietary requirements,benefiting user health as a *** algorithm fully considers the constraint relationship between users’attributes and nutritional characteristics of *** many complex factors in our algorithm,the recommended food result set meets both health standards and users’dietary preferences.A comparison of our algorithm with others demonstrated that our method offers high accuracy and interpretability.

关键词： Recommendation probabilistic matrix factorization Adaboost characteristics correlation

来源：评论

学校读者我要写书评

暂无评论

ARCH-COMP21 Category Report: Continuous and Hybrid Systems with Nonlinear Dynamics 8th

ARCH-COMP21 Category Report: Continuous and Hybrid Systems w...

引用

8th International Workshop on Applied Verification of Continuous and Hybrid Systems, ARCH 2021

作者： Geretti, Luca Sandretto, Julien Alexandre Dit Althoff, Matthias Benet, Luis Chapoutot, Alexandre Collins, Pieter Duggirala, Parasara Sridhar Forets, Marcelo Kim, Edward Linares, Uziel Sanders, David P. Schilling, Christian Wetzlinger, Mark Department of Computer Science University of Verona Verona Italy ENSTA Paris Institut Polytechnique de Paris Palaiseau France Technische Universität München Munich Germany Mexico Department of Data Science and Knowledge Engineering Maastricht University Maastricht Netherlands Department of Computer Science University of North Carolina at Chapel Hill United States Universidad de la República Montevideo Uruguay Mexico City Mexico Department of Mathematics Massachusetts Institute of Technology CambridgeMA United States University of Konstanz Konstanz Germany Aalborg University Aalborg Denmark

We present the results of a friendly competition for formal verification of continuous and hybrid systems with nonlinear continuous dynamics. The friendly competition took place as part of the workshop Applied Verification for Continuous and Hybrid Systems (ARCH) in 2021. This year, 5 tools Ariadne, CORA, DynIbex, JuliaReach and Kaa (in alphabetic order) participated. These tools are applied to solve reachability analysis problems on five benchmark problems, two of them featuring hybrid dynamics. We do not rank the tools based on the results, but show the current status and discover the potential advantages of different tools. © 2021, EasyChair. All rights reserved.

关键词： Hybrid systems

来源：评论

学校读者我要写书评

暂无评论

Opportunities for rationalization the electricity consumption of a port complex

Opportunities for rationalization the electricity consumptio...

引用

Energy Efficiency and Agricultural engineering (EE&AE), International Conference on

作者： Neli Simeonova Ginko Georgiev Rumen Kirov Venelin Ivanov Department of Electronic Electrical Engineering Machine Knowledge University Prof. d-r. "Asen Zlatarov" Burgas Bulgaria Department of Computer Science and Engineering Burgas Free University Burgas Republic of Bulgaria Department of Electric Power Supply and Equipment Technical University - Varna Varna Republic of Bulgaria Burgas Republic of Bulgaria

The research on the different characteristics of the power supply system (PSS) of a port complex is done in order to identify measures to improve the operating modes. In general, the features and requirements for the power supply and electrical equipment of the site are presented and the main energy parameters of the main consumers are marked. A theoretical formulation of the study has been synthesized, giving the opportunity to make an analysis of the characteristic coefficients of energy consumption and the additional power losses from the unevenness of the load schedule. A total of seven power substations and 11 outputs were examined and the measurements were performed with professional network analyzers. The results are presented in tabular form and provide an opportunity to make a thorough analysis of the state of the PSS of the site. Based on them, technological solutions can be offered to rationalize the electricity supply and achieve savings in electricity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Internet of things oriented elegant parking method for smart cities

引用

Materials Today: Proceedings 2021年

作者： Bedi, Pradeep Ponnusamy, Muruganantham Ashokkumar, P. Saranya, S. Hariharan, S. Department of Computer Science and Engineering Lingaya's Vidyapeeth Haryana Faridabad India Mechanical Engineering Saintgits College of Engineering Kerala India Civil Engineering Sona College of Technology Salem India Electronics and Communication Engineering Knowledge Institute of Technology India

As of late, the idea of brilliant urban areas have picked up incredible fame. Steady actions are made in meadow of IoT to augment the competence and dependability of metropolitan framework concerns. The gridlock, restricted vehicle leaving offices and street well-being are being tended by IoT. In this paper, we present an IoT based cloud coordinated rich parking lot framework using IR sensor and ultrasonic sensor. The proposed parking scaffolds encompass of an IoT module that is exploited to VDT and signalize the circumstance of convenience of each sole parking dot. An OLED which consents an end patron to verify the openness of parking dot which is controlled by a Wi-Fi module. The paper additionally illustrates an elevated point perspective on the frame-work design. © 2021

关键词： Wireless local area networks (WLAN)

来源：评论

学校读者我要写书评

暂无评论

Contrastive Fusion of Generative and Discriminative Lesion Maps for Weakly Supervised Medical Image Segmentation

SSRN

引用

SSRN 2023年

作者： Du, Wei Huo, Yongkang Tang, Shiyi Chen, Liang Li, Ying Li, Gaoyang Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education College of Computer Science and Technology Jilin University Changchun130012 China College of Engineering Shantou University Shantou515063 China Translational Medical Center for Stem Cell Therapy Institute for Regenerative Medicine Shanghai East Hospital Bioinformatics Department School of Life Sciences and Technology Tongji University Shanghai200092 China

Medical image segmentation is a crucial computer-aided diagnosis (CAD) procedure in various clinical applications. However, most existing methods rely on pixel-level annotations, which are costly and time-consuming. We propose a novel contrastive fusion model of generative and discriminative lesion maps for weakly supervised medical image segmentation to address this limitation. The generative lesion map is generated by a lesion region-guided cycle-consistent adversarial network (CCANet), and the discriminative lesion map is produced by a class-aware-based discriminative lesion localization network (DLLNet). CCANet and DLLNet share weights at the encoder layer, which contains skip connections and channel attention modules to enhance feature embedding. In order to fully utilize and integrate the generative and discriminative lesion maps, and improve the segmentation accuracy, we design a fusion method based on contrastive loss to jointly train CCANet and DLLNet. The final lesion segmentation result is obtained by applying dense conditional random fields (Dense CRF) to the fused lesion map. Extensive experiments on three benchmark medical image datasets show that our model outperforms the state-of-the-art methods on weakly supervised medical image segmentation, especially in datasets with few samples, validating the proposed model's good generalization ability and robustness in various medical image segmentation scenarios. The source code and experiment datasets are available on GitHub: https://***/mlcb-jlu/GDC4MedSeg. © 2023, The Authors. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

A review of neuro-symbolic AI integrating reasoning and learning for advanced cognitive systems

Intelligent Systems with Applications

引用

Intelligent Systems with Applications 2025年 26卷

作者： Uzma Nawaz Mufti Anees-ur-Rahaman Zubair Saeed Knowledge and Data Science Research Centre Department of Computer and Software Engineering College of Electrical and Mechanical Engineering National University of Science and Technology Islamabad Pakistan Military College of Signals National University of Science and Technology Islamabad Pakistan Department of Electrical & Computer Engineering Texas A&M University College Station TX USA Department of Electrical and Computer Engineering Texas A&M University at Qatar Doha Qatar

Neuro-symbolic AI represents the convergence of two principal paradigms in artificial intelligence: neural networks, which are efficient in data-driven learning, and symbolic reasoning, which offers explainability and logical inference. This hybrid methodology combines the adaptability of neural networks with symbolic AI's interpretability and formal reasoning abilities, which provide a practical framework for advanced cognitive systems. This paper analyzes the present condition of neuro-symbolic AI, emphasizing essential techniques that combine reasoning and learning. We explore models such as Logic Tensor Networks, Differentiable Logic Programs, and Neural Theorem Provers. The study analyzes their impact on the advancement of cognitive systems in natural language processing, robotics, and decision-making. The paper examines the challenges faced by neuro-symbolic AI, such as scalability, integration with multimodal data, and maintaining interpretability without compromising efficiency. By evaluating the strengths and weaknesses of many methodologies, we comprehensively understand the field's development and its potential to revolutionize intelligent systems. In addition, we identify emerging research areas, including the incorporation of ethical frameworks and the development of adaptive dynamic neuro-symbolic systems that respond in real-time. This review aims to guide future research by providing insights into the potential of neuro-symbolic AI to influence the development of the next generation of intelligent, explainable, and adaptive systems.

关键词：

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：