检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Feizi-Derakhshi, Ali-Reza Feizi-Derakhshi, Mohammad-Reza Ramezani, Majid Nikzad-Khasmakhi, Narjes Asgari-Chenaghlu, Meysam Akan, Taymaz Ranjbar-Khadivi, Mehrdad Zafarni-Moattar, Elnaz Jahanbakhsh-Naghadeh, Zoleikha Computerized Intelligence Systems Laboratory Department of Computer Engineering University of Tabriz Tabriz Iran Department of Software Engineering Ayvansaray University Istanbul Turkey Clinical Informatics Louisiana State University Health Sciences Center Shreveport Shreveport United States Department of Computer Engineering Shabestar Branch Islamic Azad University Shabestar Iran Department of Computer Engineering Tabriz Branch Islamic Azad University Tabriz Iran Department of Computer Engineering Naghadeh Branch Islamic Azad University Naghadeh Iran

Personality detection is an old topic in psychology and Automatic Personality Prediction (or Perception) (APP) is the automated (computationally) forecasting of the personality on different types of human generated/exchanged contents (such as text, speech, image, video). The principal objective of this study is to offer a shallow (overall) review of natural language processing approaches on APP since 2010. With the advent of deep learning and following it transfer-learning and pre-trained model in NLP, APP research area has been a hot topic, so in this review, methods are categorized into three;pre-trained independent, pre-trained model based, multimodal approaches. Also, to achieve a comprehensive comparison, reported results are informed by datasets. © 2021, CC BY-NC-SA.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

FEDCSD: A FEDERATED LEARNING BASED APPROACH FOR CODE-SMELL DETECTION

arXiv

引用

arXiv 2023年

作者： Alawadi, Sadi Alkharabsheh, Khalid Alkhabbas, Fahed Kebande, Victor Awaysheh, Feras M. Palomba, Fabio Awad, Mohammed Center for Applied Intelligent Systems Research School of Information Technology Halmstad University Halmstad Sweden Department of Software Engineering Prince Abdullah bin Ghazi Faculty of Information and Communication Technology Al-Balqa Applied University Jordan Internet of Things and People Research Center Malmö University Sweden Department of Computer Science Blekinge Institute of Technology Sweden Institute of Computer Science Delta Research Centre University of Tartu Estonia SeSa Lab University of Salerno Italy Arab American University Palestine Palestine

software quality is critical, as low quality, or "Code smell," increases technical debt and maintenance costs. There is a timely need for a collaborative model that detects and manages code smells by learning from diverse and distributed data sources while respecting privacy and providing a scalable solution for continuously integrating new patterns and practices in code quality management. However, the current literature is still missing such capabilities. This paper addresses the previous challenges by proposing a Federated Learning Code Smell Detection (FedCSD) approach, specifically targeting "God Class," to enable organizations to train distributed ML models while safeguarding data privacy collaboratively. We conduct experiments using manually validated datasets to detect and analyze code smell scenarios to validate our approach. Experiment 1, a centralized training experiment, revealed varying accuracies across datasets, with dataset two achieving the lowest accuracy (92.30%) and datasets one and three achieving the highest (98.90% and 99.5%, respectively). Experiment 2, focusing on cross-evaluation, showed a significant drop in accuracy (lowest: 63.80%) when fewer smells were present in the training dataset, reflecting technical debt. Experiment 3 involved splitting the dataset across 10 companies, resulting in a global model accuracy of 98.34%, comparable to the centralized model’s highest accuracy. The application of federated ML techniques demonstrates promising performance improvements in code-smell detection, benefiting both software developers and researchers. Copyright © 2023, The Authors. All rights reserved.

关键词： computer software selection and evaluation

来源：评论

学校读者我要写书评

暂无评论

Distributed Trust Management for Secured Localization Systems in Mobile Cloud Services

Distributed Trust Management for Secured Localization System...

引用

IEEE International Conference on Utility and Cloud Computing (UCC)

作者： Farouq Aliyu Mustafa Ghaleb Saud Mohammad Mostafa Sani Umar AbdalRahman Aburakhia Center of Excellence in Dev of NPO King Fahd University of Petr. & Min. Dhahran Saudi Arabia IRC for Intelligent Secure Systems King Fahd University of Petr. & Min. Dhahran Saudi Arabia Computer Engineering Department King Fahd University of Petr. & Min. Dhahran Saudi Arabia Dept. of Electrical Engr. and Computer Sci. Khalifa University Abu Dhabi UAE Information & Computer Science King Fahd University of Petr. & Min. Dhahran Saudi Arabia

ISBN: (数字)9798350367201

ISBN: (纸本)9798350367218

The market for the Internet of Things (IoT) is expanding at an exponential rate. As IoT devices increasingly rely on cloud computing for data processing, storage, and management, the security of cloud-based IoT services becomes paramount. Many of these services depend on the IoT device’s location. Therefore, secured localization systems are necessary. However, traditional security techniques are resource-consuming. An alternative method for detecting localization attacks in IoT is through trust models. This paper proposes a distributed trust management technique for localization in Mobile IoT, specifically designed to enhance the security and trustworthiness of cloud-based IoT services. The trust of a node is computed based on its availability and service quality. Nodes use this information to calculate their neighbors’ and anchor nodes’ trust values. We simulated the proposed system using the Cooja simulator. The results show that the proposed trust-based localization technique can help unknown nodes mobilize and reach a target location, reducing the control group’s error by 186.4% at the cost of 4.8 μJ only. The system finds application in indoor localization for location-based cloud services, such as locating shops of items in shopping malls.

关键词： Location awareness Cloud computing Costs Computational modeling Data processing Internet of Things Security Trust management

来源：评论

学校读者我要写书评

暂无评论

Online identification of nonlinear systems using neo-fuzzy supported brain emotional learning network

Online identification of nonlinear systems using neo-fuzzy s...

引用

作者： Farooq, Umar Gu, Jason Asad, Muhammad Usman Abbas, Ghulam Hanif, Athar Balas, Marius Department of Electrical Computer Engineering Dalhousie University Halifax Canada Department of Automatics and Applied Software University 'Aurel Vlaicu' Arad Romania Deparment of Electrical Engineering University of Lahore Pakistan Center for Automotive Research Ohio State University ColumbusOH United States Department of Electrical Engineering University of the Punjab Pakistan

This paper proposes an online algorithm for identifying the nonlinear dynamical systems and is termed as neo-fuzzy based brain emotional learning plant identifier (NFBELPI). As the name suggests, the proposed identifier is a combination of brain emotional learning network and neo-fuzzy neurons. The integration of these two networks is realized in a way that retains the characteristics of both the networks while an enhanced performance is achieved at the same time. Precisely, the orbitofrontal cortex section of the brain emotional learning network is fused with neo-fuzzy neurons with a view to equip it with more knowledge than does the amygdala section possesses. The proposed identifier accepts n-input and m-output samples to generate an estimate of the plant output and employs a brain emotional learning algorithm to lower the estimation error by adjusting a total of ((n + m + 1) × p) + (n + m + 2) weights, with p being the number of neo-fuzzy neurons. The proposal is validated in a MATLAB programming environment using a simulated Narendra dynamical plant as well as against the data recorded from real forced duffing oscillator. Comparison with a brain emotional learning plant identifier (BELPI) and some other state-of-the art identifiers in terms of root mean squared error (RMSE) criterion reveals the improved performance of the proposed identifier. © 2020 - IOS Press and the authors. All rights reserved.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

Distributed Control Scheme for Solar-Powered Serial Water Pumps based on Hidden Markov Model

Distributed Control Scheme for Solar-Powered Serial Water Pu...

引用

International Symposium on Wireless Personal Multimedia Communications (WPMC)

作者： Roungsan Chaisricharoen Wanus Srimaharaj Centre of Excellence on Industry 4.0 Computer and Communication Engineering for Capacity Building Research Center School of Information Technology Mae Fah Luang University Chiang Rai Thailand Department of Information Technology The International College Payap University Chiang Mai Thailand

This study proposes the solar Photovoltaic (PV) pump system in a non-communication grid along with Hidden Markov model to solve the problem of the delayed propagation of serial water pumps that resulted in missing data and a lost package. This distribution system improved the efficiency in communication and system status update throughout the prediction of the light state of neighbor and central station by the probability of the combination via the n-state Markov chain. As a result, the proposed method promised to improve the accuracy of prediction in non-communication states of solar-powered serial water pumps and reduce the communication loss over average time compared to previous work.

关键词： Photovoltaic systems Wireless communication System performance Decentralized control Hidden Markov models Markov processes Packaging

来源：评论

学校读者我要写书评

暂无评论

SGDA: Towards 3D Universal Pulmonary Nodule Detection via Slice Grouped Domain Attention

arXiv

引用

arXiv 2023年

作者： Xu, Rui Liu, Zhi Luo, Yong Hu, Han Shen, Li Du, Bo Kuang, Kaiming Yang, Jiancheng The School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Hubei Luojia Laboratory Wuhan China The Department of Computer and Network Engineering The University of Electro-Communications 1-5-1 Chofugaoka Chofushi Tokyo182-8585 Japan The School of Information and Electronics Beijing Insititute of Technology Beijing100081 China The JD Explore Academy Beijing China The Dianei Technology Shanghai200120 China The Shanghai Jiao Tong University Shanghai China Dianei Technology Shanghai China EPFL Lausanne Switzerland

Lung cancer is the leading cause of cancer death worldwide. The best solution for lung cancer is to diagnose the pulmonary nodules in the early stage, which is usually accomplished with the aid of thoracic computed tomography (CT). As deep learning thrives, convolutional neural networks (CNNs) have been introduced into pulmonary nodule detection to help doctors in this labor-intensive task and demonstrated to be very effective. However, the current pulmonary nodule detection methods are usually domain-specific, and cannot satisfy the requirement of working in diverse real-world scenarios. To address this issue, we propose a slice grouped domain attention (SGDA) module to enhance the generalization capability of the pulmonary nodule detection networks. This attention module works in the axial, coronal, and sagittal directions. In each direction, we divide the input feature into groups, and for each group, we utilize a universal adapter bank to capture the feature subspaces of the domains spanned by all pulmonary nodule datasets. Then the bank outputs are combined from the perspective of domain to modulate the input group. Extensive experiments demonstrate that SGDA enables substantially better multi-domain pulmonary nodule detection performance compared with the state-of-the-art multi-domain learning methods. © 2023, CC BY.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Air Quality Monitoring At Urban Scale Using PRISMA Hyperspectral Data: the ‘Primary’ Project

Air Quality Monitoring At Urban Scale Using PRISMA Hyperspec...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Davide De Santis Sarathchandrakumar T. Sasidharan Marco Di Giacomo Gianmarco Bencivenni Fabio Del Frate Gabriele Curci Ana Carolina Amarillo Francesca Barnaba Luca Di Liberto Ferdinando Pasqualini Cristiana Bassani Silvia Scifoni Stefano Casadio Alessandra Cofano Massimo Cardaci Giorgio Licciardi Department of Civil Engineering and Computer Science Engineering "Tor Vergata" University of Rome Italy Department of Civil Construction and Environmental Engineering Sapienza University of Rome Italy Department of Physical and Chemical Sciences Università Degli Studi Dell’Aquila Italy Center of Excellence in Telesensing of Environment and Model Prediction of Severe Events (CETEMPS) Università Degli Studi Dell’Aquila Italy CNR-ISAC National Research Council - Institute of Atmospheric Sciences and Climate Rome Italy CNR-IIA National Research Council - Institute of Atmospheric Pollution Research Rome Italy Serco Italia S.p.A. Rome Italy Viale del Politecnico snc Agenzia Spaziale Italiana (ASI) Rome Italy

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

The PRIMARY (PRIsma for Monitoring AiR quality) project objective is to address air quality monitoring, especially in urban areas, exploiting the PRISMA (PRecursore IperSpettrale della Missione Applicativa) mission. Utilizing PRISMA's hyperspectral data, the project aims to gain insights into atmospheric aerosol content and composition, crucial for understanding environmental and health impacts, especially in urban areas. Overcoming spatial resolution limitations and the inverse problem's complexity in satellite-based characterization, PRISMA's decametric spatial resolution and artificial intelligence play crucial roles. A synthetic PRISMA-like dataset, relying on data provided by the Copernicus Atmosphere Monitoring service (CAMS), was generated for training neural networks for estimating aerosol characteristic exploiting PRISMA data. Preliminary results are encouraging. Properly field campaigns were performed in Rome (autumn 2022) and Milan (winter to summer 2023) to support the validation of the PRIMARY project's outcomes. In addition, drone-based campaigns are currently ongoing.

关键词： Training Atmospheric modeling Neural networks Urban areas Aerosols Air quality Data models

来源：评论

学校读者我要写书评

暂无评论

An Integrated Model to Evaluate the Transparency in Predicting Chronic Kidney Disease Using a Trio-Embedded Explainable Model

SSRN

引用

SSRN 2022年

作者： Gaur, Loveleen Biswas, Milon Bakshi, Sumedha Gupta, Pranshi Si, Tapas Mallik, Saurav Maulik, Ujjwal Amity International Business School Amity University India Bangladesh University of Business and Technology Bangladesh Ernst & Young Prospecta Software India Bankura Unnayani Institute of Engineering West Bengal Bankura India The University of Texas Health Science Center Tyler United States Department of Computer Science and Engineering Jadavpur University India

Why do clinicians doubt the applicability of artificial intelligence in the medical field? One of the primary challenges to implementation is a lack of transparency, as clinicians must be confident that the AI system can be trusted. Explainable AI has the ability to solve this problem and is a step toward AI that is trustworthy. Explainability improves learning for educational and research objectives by allowing comparisons of learned procedures with existing knowledge. This research proposes an explainable artificial intelligence (XAI) archetype utilizing shapely additive values (SHAP), local interpretable model-agnostic explanation (LIME), and DALEX to provide a qualitative knowledge of the association between the model and the parameters utilized in the model. Firstly five machine learning models (Logistic Regression, Random Forest, Gradient Boosting Machine, Support Vector Machine, and Multilayer Perceptron Classifier) are being interpreted with local models called LIME, SHAP, and DALEX and then a global model called EBM. This research also compares the performance of five classifiers with Explainable Boosting Machine (EBM), while EBM achieved the highest accuracy of 98.57%. Lastly, we use the XAI model to determine the most important factors that influence those predictions. © 2022, The Authors. All rights reserved.

关键词： Transparency

来源：评论

学校读者我要写书评

暂无评论

Innovation, Research and Development in engineering Education. Activities of the Spanish Chapter of the IEEE Education Society: Directive Board of the IEEE Education Society Spanish Chapter 2020-2021

Innovation, Research and Development in Engineering Educatio...

引用

Technologies Applied to Electronics Teaching (TAEE)

作者： Ó scar Martí nez Bonastre Cristina Ferná ndez Lluí s Vicent Francisco Mur Manuel Castro Gabriel Diaz Jose Carpio Elio Sancristobal Sergio Martin Jose Sá nchez Francisco Javier Arcega Solsona Juan Suardiaz Muro Manuel Caeiro-Rodrí guez Martí n Llamas Inmaculada Plaza Baltasar Ferná ndez Manjó n Pedro Muñ oz-Merino Edmundo Tovar Telmo Zarraonandia Ayo Javier Garcia Zubia José Antonio Delgado Pení n Department of Statistics Mathematics and Computing Science Operations Research Centre Universidad Miguel Hern&#x00E1 ndez Elche Spain Department of Electronic Technology Universidad Carlos III de Madrid Madrid Spain UPF Barcelona School of Management Barcelona Spain Department of Electrical Electronic and Control Engineering UNED Madrid Spain Department of Electrical Engineering Universidad de Zaragoza Zaragoza Spain Department of Automatics Electrical Engineering and Electronic Technology Technical University of Cartagena Cartagena Spain atlanTTic Research Center University of Vigo Vigo Spain Department of Electronics and Communication Universidad de Zaragoza Zaragoza Spain Department of Software Engineering and Artificial Intelligence Complutense University of Madrid Madrid Spain Department of Telematic Engineering Universidad Carlos III de Madrid Madrid Spain Department of Computer Languages and Systems and Software Engineering Universidad Polit&#x00E9 cnica de Madrid Madrid Spain Department of Computer Science and Engineering Universidad Carlos III de Madrid Madrid Spain Department of Electronic Engineering Universidad de Deusto Bilbao Spain Universitat Polit&#x00E8 cnica de Catalunya Barcelona Spain

ISBN: (数字)9781665421614

ISBN: (纸本)9781665421621

The Technical Committee of the CESEI (Spanish Chapter of the IEEE Education Society) is focused on the Innovation, Research and Development (I+R+D) of the education in engineering, mainly Electric and computer engineering. As in other interdisciplinary fields, the I+R+D involves several sources of information and different stakeholders, each one with its own focus and purpose. As a result, sometimes it may be complex for practitioners and researchers to identify the more appropriate entities for their interests. This paper shows how the CESEI Technical Committee tries to solve this difficulty by providing updated information regarding the main publications (journals), events (conferences) and awards to the best academic works. The paper focuses special attention on the activities held during 2020–2021.

关键词： Technological innovation Collaboration Stakeholders engineering education Research and development

来源：评论

学校读者我要写书评

暂无评论

SmartEdge: Smart Healthcare End-to-End Integrated Edge and Cloud Computing System for Diabetes Prediction Enabled by Ensemble Machine Learning

SmartEdge: Smart Healthcare End-to-End Integrated Edge and C...

引用

IEEE International Conference on Cloud Computing Technology and Science (CloudCom)

作者： Alain Hennebelle Qifan Dieng Leila Ismail Rajkumar Buyya Independent Researcher in Information Technology Systems and Artificial Intelligence Applications Abu Dhabi United Arab Emirates Cloud Computing and Distributed Systems (CLOUDS) Lab School of Computing and Information Systems University of Melbourne Melbourne Australia Department of Computer Science and Software Engineering Intelligent Distributed Computing and Systems (INDUCE) Lab College of Information Technology Emirates Center for Mobility Research National Water and Energy Center UAE University Al-Ain Abu Dhabi United Arab Emirates

ISBN: (数字)9798331507589

ISBN: (纸本)9798331507596

The Internet of Things (IoT) revolutionizes smart city domains such as healthcare, transportation, industry, and education. The Internet of Medical Things (IoMT) is gaining prominence, particularly in smart hospitals and Remote Patient Monitoring (RPM). The vast volume of data generated by IoMT devices should be analyzed in real-time for health surveillance, prognosis, and prediction of diseases. Current approaches relying on Cloud computing to provide the necessary computing and storage capabilities do not scale for these latency-sensitive applications. Edge computing emerges as a solution by bringing cloud services closer to IoMT devices. This paper introduces SmartEdge, an AI-powered smart healthcare end-to-end integrated edge and cloud computing system for diabetes prediction. This work addresses latency concerns and demonstrates the efficacy of edge resources in healthcare applications within an end-to-end system. The system leverages various risk factors for diabetes prediction. We propose an Edge and Cloud-enabled framework to deploy the proposed diabetes prediction models on various configurations using edge nodes and main cloud servers. Performance metrics are evaluated using, latency, accuracy, and response time. By using ensemble machine learning voting algorithms we can improve the prediction accuracy by 5% versus a single model prediction.

关键词： Cloud computing Accuracy Smart cities Computational modeling Transportation industry Surveillance Machine learning Predictive models Diabetes Time factors

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：