检索结果-内蒙古大学图书馆

2nd International Conference on Intelligent Manufacturing and Robotics, ICIMR 2024

作者： San, Tan Jun Ajibade, Samuel-Soma M. Ajibade, Temiloluwa Iyanuoluwa Jasser, Muhammed Basheer Ayodele, Olamide Emmanuel Oyewopo, Abdulgafar Olorunleke Adediran, Anthonia Oluwatosin Majeed, Anwar P. P. Abdul Luo, Yang Department of Data Science and Artificial Intelligence Faculty of Engineering and Technology Sunway University Selangor Petaling Jaya Malaysia Department of Computer Engineering Istanbul Ticaret University Istanbul Turkey Department of Business Management Scholar School System Birmingham United Kingdom School of Engineering and Technology Sunway University Selangor Darul Ehsan Petaling Jaya47500 Malaysia Department of Banking and Finance Ekiti State University Ekiti State Ado Ekiti Nigeria Department of Business Administration Kwara State University Malete Nigeria Department of Real Estate Faculty of Built Environment Universiti Malaya Kuala Lumpur Malaysia Suzhou Taicang215400 China

ISBN: (纸本)9789819639489

The rise of deep learning algorithms has sparked interest in the financial domain. The foreign exchange market (FOREX) is the globally leading financial market with millions of active stakeholders. Research in deep learning for forecasting price movements has shown its efficacy in financial markets. Notably, LSTM have empirically proven the best performance among other machine learning techniques. However, studies have shown the lack of deep learning hybrid comparisons to fortify empirical claims, especially in the FX market characterized for its high volatility and variance among currency pairs. This study develops a generalized LSTM model to forecast the major pairs and conducts a comparative analysis with a secondary hybrid deep learning model to assess and solidify the robustness of deep learning methods in forex forecasting. The empirical scenario simulates a classification problem employing cross-validation techniques to optimize the models’ generalization rigorously. Evaluation of the model utilized the accuracy, precision, recall, and f1-score metrics. Results indicated the performance of the models from best to worst were LSTM, SRNN and followed by CNN indicating the importance of testing deep learning approaches in different empirical setups. Conclusively, this study highlights the need challenges in forex forecasting and raises the need for more robust assessments on machine learning models forecasting capabilities. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Exams Item Analysis, Online Examination, and Education Evaluation system Via Internet

Exams Item Analysis, Online Examination, and Education Evalu...

引用

International Conference on Electrical Engineering/Electronics, computer, Telecommunications and Information technology, ECTI-CON

作者： Kamonlak Chaidee Kanchana Boontasri Ekkachai Chaidee Kittichai Punthura Narong Kumtip Yotsanan Pankham Department of Computer Information System Faculty of Business Administration And Liberal Arts Rajamangala University of Technology Lanna Chiangrai Chiang Rai Thailand Department of Information Technology Faculty of Science and Agricultural Technology Rajamangala University of Technology Lanna Chiangrai Chiang Rai Thailand Department of Electrical Engineering Faculty of Electrical Engineering Rajamangala University of Technology Lanna Chiangrai Chiang Rai Thailand

The objective of this study is to develop an exams item bank management system on the internet. The exam item analysis system is used to determine the reliability of the exams using K-R 20 and K-R 21 formulas. The difficulty and power of discrimination values are determined using a choice analysis and percentages of high and lower groups technique. The create exams set system can be performed randomly or identified through the difficulty level. The examination can be performed online and the exam results can be immediately announced. The grading system is used to support the decision-making to evaluate learning achievement. The system’s accuracy was tested and found to be accurate compared with the hand calculation results. The system was tested with a sample group and satisfaction was assessed through questionnaires. The satisfaction of teachers and students was highest, while that of administrators was high. The developed exams item bank management system operates as a web application with a security system for supporting in learning activity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Data collection in studies on internet of things (IoT), wireless sensor networks (WSNs), and sensor cloud (SC): Similarities and differences

TechRxiv

引用

TechRxiv 2021年

作者： Ihsan, A.L.I. Department of Computer System & Technology Faculty of Computer Science & Information Technology University of Malaya Malaysia

Data collection is an essential part of sensor devices, particularly in such technologies like Internet of Things (IoT), wireless sensor networks (WSN), and sensor cloud (SC). In recent years, various literature had been published in these research areas to propose different models, architectures, and contributions in the domains. Due to the importance of efficient data collection regarding reducing energy consumption, latency, network lifetime, and general cost, a momentous literature volume has been published to facilitate data collection. Hence, review studies have been conducted on data collection in these domains in isolation. However, a lack of comprehensive review collectively identifies and analyzes the differences and similarities among the data collection proposals in IoT, WSN, and SC. The main objective of this research is to conduct a comprehensive survey to explore the current state, use cases, contributions, performance measures, evaluation measures, and architecture in the IoT, WSN, and SC research domains. The findings indicate that studies on data collection in IoT, WSN, and SC are relatively consistent with stable output in the last five years. Nine novel contributions are found with models, algorithms, and frameworks being the most utilized by the selected studies. In conclusion, key research challenges and future research directions have been identified and discussed. © 2021, CC BY.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Development of User Management in Ihya Digital Ecosystem Using Iterative Incremental Method 4

Development of User Management in Ihya Digital Ecosystem Usi...

引用

4th International Conference Advancement in Data Science, E-Learning and Information systems, ICADEIS 2022

作者： Priandhika Izzulhaq, Afif Fauzi, Rahmat Suakanto, Sinung Kadir Hassan Disina, Abdul Mahdin, Hairulnizam Anka Salihu, Ibrahim Information System Telkom University Bandung Indonesia Nigeria Army University Biu Borno State Department of Cyber Security Nigeria Universiti Tun Hussein Onn Malaysia Faculty of Computer Science and Information Technology Johor Malaysia Nile University of Nigeria Abuja Nigeria

ISBN: (纸本)9781665463874

Information systems have an essential role in the development of technology and information in Indonesia. Information systems are employed and utilized in many facets of society and organizations. Digitizing and utilizing this information system will often form an integrated relationship between several digital sectors into an ecosystem or what is commonly called a digital ecosystem. Digital ecosystem provides benefits for users by exchanging data between systems within it since only one user account could access several systems or services in the ecosystem. The development of user management in the digital ecosystem will serve as a solution to accommodate the increasing number of users of the digital ecosystem. Iterative incremental development methods are used in the development of user management in Ihya digital ecosystem. The system was also tested using scenario tests, user acceptance tests, and load tests. Based on the results of the tests, the Ihya digital ecosystem user management module has met user needs with a User Acceptance Test value of 82.5%. Further development can be done in this research, including using APIs in the data exchange process and adding a two-factor authentication feature to improve data security. © 2022 IEEE.

关键词： Information systems

来源：评论

学校读者我要写书评

暂无评论

Harnessing The Power of Random Forest in Predicting Startup Partnership Success

Harnessing The Power of Random Forest in Predicting Startup ...

引用

International Conference on Informatics and Computing (ICIC)

作者： Chandra Lukita Ninda Lutfiani Arop Ria Saulina Panjaitan Bhima Untung Rahardja Muhamad Lutfi Huzaifah Faculty of Information Systems University of Catur Insan Cendekia Cirebon Indonesia Faculty of Economics and Business University of Raharja Tangerang Indonesia Faculty of Management University of Esa Unggul Jakarta Indonesia Faculty of System Computer University of Raharja Tangerang Indonesia Faculty of Information Technology University of Raharja Tangerang Indonesia

Startups are an important element in innovation and economic growth. However, startup failure is very high, so investors, governments, and startups need to predict startup success. This research develops a startup success prediction model based on random forest with multi-layer decision analytics attributes, partnership longevity predictions, importance feature ranking, cross-industry startup evaluations, and ensemble learning benefits. This research uses secondary data from Crunchbase, AngelList, and VentureBeat. The data is processed with data cleaning, feature engineering, and feature selection. The data is divided into training data and testing data with a ratio of 80:20. The training data trains a random forest model with sci-kit-learn in Python. The model is evaluated by accuracy, precision, recall, F1-score, and ROC-AUC. The testing data tested the random forest model and compared it with other models. This study also used SmartPLS to test hypotheses in a variance-based SEM model with PLS path modelling. This study used 370 respondent data for SmartPLS with SmartPLS software. The results show that the random forest model is better than other models in predicting startup success. The model provides information about important features in predicting startup success. SmartPLS results show that all hypotheses are accepted with statistical significance. The model has high explanatory power and predictive power.

关键词：

来源：评论

学校读者我要写书评

暂无评论

BETWEEN GENERATING NOISE AND GENERATING IMAGES: NOISE IN THE CORRECT FREQUENCY IMPROVES THE QUALITY OF SYNTHETIC HISTOPATHOLOGY IMAGES FOR DIGITAL PATHOLOGY

arXiv

引用

arXiv 2023年

作者： Daniel, Nati Aknin, Eliel Larey, Ariel Peretz, Yoni Sela, Guy Fisher, Yael Savir, Yonatan Department of Physiology Biophysics and System Biology Faculty of Medicine Technion Israel Institute of Technology Haifa Israel Faculty of Industrial Engineering Technion Israel Institute of Technology Haifa Israel Faculty of Computer Science Technion Israel Institute of Technology Haifa Israel Faculty of Electrical Engineering Technion Israel Institute of Technology Haifa Israel Division of Pathology Rambam Health Care Campus Haifa Israel

Artificial intelligence and machine learning techniques have the promise to revolutionize the field of digital pathology. However, these models demand considerable amounts of data, while the availability of unbiased training data is limited. Synthetic images can augment existing datasets, to improve and validate AI algorithms. Yet, controlling the exact distribution of cellular features within them is still challenging. One of the solutions is harnessing conditional generative adversarial networks that take a semantic mask as an input rather than a random noise. Unlike other domains, outlining the exact cellular structure of tissues is hard, and most of the input masks depict regions of cell types. However, using polygon-based masks introduce inherent artifacts within the synthetic images - due to the mismatch between the polygon size and the single-cell size. In this work, we show that introducing random single-pixel noise with the appropriate spatial frequency into a polygon semantic mask can dramatically improve the quality of the synthetic images. We used our platform to generate synthetic images of immunohistochemistry-treated lung biopsies. We test the quality of the images using a three-fold validation procedure. First, we show that adding the appropriate noise frequency yields 87% of the similarity metrics improvement that is obtained by adding the actual single-cell features. Second, we show that the synthetic images pass the Turing test. Finally, we show that adding these synthetic images to the train set improves AI performance in terms of PD-L1 semantic segmentation performances. Our work suggests a simple and powerful approach for generating synthetic data on demand to unbias limited datasets to improve the algorithms' accuracy and validate their robustness. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Colon and lung cancer classification from multi-modal images using resilient and efficient neural network architectures

引用

Heliyon 2024年第9期10卷 e30625页

作者： Uddin, A. Hasib Chen, Yen-Lin Akter, Miss Rokeya Ku, Chin Soon Yang, Jing Por, Lip Yee Department of Computer Science and Engineering Khwaja Yunus Ali University Enayetpur Chouhali Sirajganj 6751 Bangladesh Department of Computer Science and Information Engineering National Taipei University of Technology Taipei 106344 Taiwan Department of Computer Science Universiti Tunku Abdul Rahman Kampar 31900 Malaysia Department of Computer System and Technology Faculty of Computer Science and Information Technology Universiti Malaya Kuala Lumpur 50603 Malaysia

Automatic classification of colon and lung cancer images is crucial for early detection and accurate diagnostics. However, there is room for improvement to enhance accuracy, ensuring better diagnostic precision. This study introduces two novel dense architectures (D1 and D2) and emphasizes their effectiveness in classifying colon and lung cancer from diverse images. It also highlights their resilience, efficiency, and superior performance across multiple datasets. These architectures were tested on various types of datasets, including NCT-CRC-HE-100K (set of 100,000 non-overlapping image patches from hematoxylin and eosin (H&E) stained histological images of human colorectal cancer (CRC) and normal tissue), CRC-VAL-HE-7K (set of 7180 image patches from N = 50 patients with colorectal adenocarcinoma, no overlap with patients in NCT-CRC-HE-100K), LC25000 (Lung and Colon Cancer Histopathological Image), and IQ-OTHNCCD (Iraq-Oncology Teaching Hospital/National Center for Cancer Diseases), showcasing their effectiveness in classifying colon and lung cancers from histopathological and Computed Tomography (CT) scan images. This underscores the multi-modal image classification capability of the proposed models. Moreover, the study addresses imbalanced datasets, particularly in CRC-VAL-HE-7K and IQ-OTHNCCD, with a specific focus on model resilience and robustness. To assess overall performance, the study conducted experiments in different scenarios. The D1 model achieved an impressive 99.80 % accuracy on the NCT-CRC-HE-100K dataset, with a Jaccard Index (J) of 0.8371, a Matthew's Correlation Coefficient (MCC) of 0.9073, a Cohen's Kappa (Kp) of 0.9057, and a Critical Success Index (CSI) of 0.8213. When subjected to 10-fold cross-validation on LC25000, the D1 model averaged (avg) 99.96 % accuracy (avg J, MCC, Kp, and CSI of 0.9993, 0.9987, 0.9853, and 0.9990), surpassing recent reported performances. Furthermore, the ensemble of D1 and D2 reached 93 % accuracy (J, MCC, Kp, and

关键词： Cancer image classification Colon cancer CT-Scan imaging Dense neural networks (DNN) Histopathological imaging Lung cancer Multi-modal network

来源：评论

学校读者我要写书评

暂无评论

Economic and environmental analysis of a solar-powered ev charging system in india—a case study 2nd

Economic and environmental analysis of a solar-powered ev ch...

引用

2nd International Conference on Electrical and Electronics Engineering, ICEEE 2021

作者： Shrivastava, Prashant Soon, Teykok Mekhilef, Saad Ahmad, Furkan Department of Computer System and Technology Faculty of Computer Science and Information Technology University of Malaya Kuala Lumpur50603 Malaysia Power Electronics and Renewable Energy Laboratory Department of Electrical Engineering Faculty of Engineering University of Malaya Kuala Lumpur50603 Malaysia School of Software and Engineering Faculty of Science Engineering and Technology Swinburne University of Technology MelbourneVIC3122 Australia Indian Institute of Technology New Delhi Delhi110016 India

ISBN: (纸本)9789811607486

With the growing environmental concern, the demand for electric vehicle is increasing in India. However, the limited existing charging facilities slow down the rate of adoption in the market. Presently, the solar-based charging system is gaining popularity, due to its low greenhouse gas emission. In this study, a case study for different solar charging systems suited in Delhi is presented. The economic and environmental analysis of different solar-based EV charging systems utilized for charging three types of commercial EVs such as 2, 3, and 4-W is explained. The cost of energy required for 100 km drive is lower with vehicle integrating PV charging system;however, it can act as a supportive system for driving range improvement. The analysis shows that the economically solar rooftop charging system is suitable for all types of EVs. The CO2 emission produced by all types of solar-based EV charging systems is lower than coal-based charging systems. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2021.

关键词： Solar energy

来源：评论

学校读者我要写书评

暂无评论

A Smart City Application Design for Efficiently Tracking Missing Person in Large Gatherings in Madinah Using Emerging IoT Technologies 1

A Smart City Application Design for Efficiently Tracking Mis...

引用

1st Mohammad Ali Jinnah University International Conference on Computing, MAJICC 2021

作者： Nadeem, Adnan Rizwan, Kashif Mehmood, Amir Qadeer, Nauman Noor, Fazal Alzahrani, Ali Islamic University of Madinah Faculty of Computer and Information System Madinah Saudi Arabia Federal Urdu University of Arts Science and Technology Department of Computer Science Islamabad Pakistan Muhammad Ali Jinnah University Department of Computer Science Karachi Pakistan

ISBN: (纸本)9781665424134

Ensuring the safety of residents and visitors is one of the major priorities of the Kingdom of Saudi Arabia (KSA). There are some residents in Madinah who are vulnerable or prone to getting lost in crowded areas, including children, the elderly, and people with certain diseases and disorders. Besides, the Kingdom receives millions of visiting pilgrims in Madinah and Makkah and thousands of them get lost every year around Masjid-e-Nabavi and Masjid Al Haram. Considering the importance of the safety of residents and visiting pilgrims in Madinah, in this paper, we propose a smart city application design for tracking and locating the missing person using an emerging Internet of Things (IoT) based system. We propose to evaluate the performance of Bluetooth low energy (BLE), low power wide area network (LPWAN), technologies, both individually and as a hybrid solution. We propose an IoT based system with a proactive approach to help security officials in Madinah and the Department of lost and found in Masjid e Nabavi in two major safety issues: 1) Tracking the companion of missing person found by a security official and 2) Tracking the missing person using reported location via IoT based system. We present our proposed smart city application design and its implementation scenarios in Madinah. © 2021 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Metaheuristic with Deep Learning Enabled Biomedical Bone Age Assessment and Classification Model

引用

computers, Materials & Continua 2022年第12期73卷 5473-5489页

作者： Mesfer Al Duhayyim Areej A.Malibari Marwa Obayya Mohamed K.Nour Ahmed S.Salama Mohamed I.Eldesouki Abu Sarwar Zamani Mohammed Rizwanullah Department of Computer Science College of Sciences and Humanities-AflajPrince Sattam bin Abdulaziz UniversitySaudi Arabia Department of Industrial and Systems Engineering College of EngineeringPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Biomedical Engineering College of EngineeringPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Sciences College of Computing and Information SystemUmm Al-Qura UniversitySaudi Arabia Department of Electrical Engineering Faculty of Engineering&TechnologyFuture University in EgyptNew Cairo11845Egypt Department of Information System College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityAlKharjSaudi Arabia Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam bin Abdulaziz UniversityAlKharjSaudi Arabia

The skeletal bone age assessment(BAA)was extremely implemented in development prediction and auxiliary analysis of medicinal issues.X-ray images of hands were detected from the estimation of bone age,whereas the ossification centers of epiphysis and carpal bones are important *** typical skeletal BAA approaches remove these regions for predicting the bone age,however,few of them attain suitable efficacy or *** BAA techniques with deep learning(DL)methods are reached the leading efficiency on manual and typical ***,this study introduces an intellectual skeletal bone age assessment and classification with the use of metaheuristic with deep learning(ISBAAC-MDL)*** presented ISBAAC-MDL technique majorly focuses on the identification of bone age prediction and classification *** attain this,the presented ISBAAC-MDL model derives a mask Region-related Convolutional Neural Network(Mask-RCNN)with MobileNet as baseline model to extract *** by,the whale optimization algorithm(WOA)is implemented for hyperparameter tuning of the MobileNet *** last,Deep Feed-Forward Module(DFFM)based age prediction and Radial Basis Function Neural Network(RBFNN)based stage classification approach is *** experimental evaluation of the ISBAAC-MDL model is tested using benchmark dataset and the outcomes are assessed over distinct *** experimental outcomes reported the better performances of the ISBAACMDL model over recent approaches with maximum accuracy of 0.9920.

关键词： Biomedical images bone age assessment age prediction computer vision deep learning image classification

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：