检索结果-内蒙古大学图书馆

International Conference on Informatics and Computing (ICIC)

作者： Mendarissan Aritonang Adi Setiawan Krismiyati Theophilus Wellem Dept of Computer Science Faculty of Information Technology Satya Wacana Christian University Salatiga Indonesia Dept. Mathematics and Data Science Faculty of Science and Mathematics Satya Wacana Christian University Salatiga Indonesia Dept. Informatics & Computer Engineering Education Faculty of Information Technology Satya Wacana Christian University Salatiga Indonesia Department of Informatics Satya Wacana Christian University Salatiga Indonesia

ISBN: (数字)9798331517601

ISBN: (纸本)9798331517618

The number of woven fabric on the island of Timor is very large and varied, making it difficult to distinguish between types and origins. Many woven fabric motifs appear similar but represent different types. Therefore, this classification was used to perform pattern recognition of woven fabric in the system. The process allowed the system’s ability to be tested by applying the pattern recognition algorithm to woven images. In this context, the feature extraction method used was gray level co-occurrence matrix (GLCM), while the method used for classification was artificial neural network (ANN). The results showed an accuracy of $87.5 \%$ in the system. Finally, GUI system was developed, enabling tests to be performed on woven images for the identification of Timor Weaving image patterns.

关键词： Training Accuracy Social networking (online) Neurons Artificial neural networks Feature extraction Weaving Fabrics Pattern recognition Web sites

来源：评论

学校读者我要写书评

暂无评论

Multi-biometric fusion for enhanced human authentication in information security

引用

Measurement: Sensors 2024年 31卷

作者： Vekariya, Vipul Joshi, Manish Dikshit, Sukanya Manju bargavi, S.K. Department of Computer Science and Engineering Faculty of Engineering and Technology Parul Institute of Engineering and Technology Parul University Gujarat Vadodara India Department of College of Computing Sciences and Information Technology Teerthanker Mahaveer University Uttar Pradesh Moradabad India ISME - School of Management & Entrepreneurship ATLAS SkillTech University Maharashtra Mumbai India University Karnataka 562112 India

In the digital age, information security has taken on greater importance, necessitating the development of strong and trustworthy human authentication techniques. Traditional single-factor authentication schemes, such passwords or PINs, are prone to a number of security flaws. Multi-biometric fusion approaches have become a possible remedy to these restrictions. In comparison to other fusion techniques, feature level fusion is a very popular technique. Features are taken from every biometric attribute in this fusion. Then, the retrieved features are concatenated to create a high dimension final feature vector. In this study, we present a novel method for feature-level fusion employing optimal feature level fusion. The essential features are chosen and identified using a Binary chimp optimized adaptive kernel support vector machine (BCO-AKSVM). According to f1-score (99 %), recall (98 %), accuracy (97 %), precision (88 %), and time computation (1000 ms), the experimental results of the suggested method are analyzed. When compared to current methods, it can show that the proposed BCO-AKSVM achieves the highest performance of information security in human biometric authentication. Multi-biometric fusion is anticipated to play a significant role as technology develops in maintaining secure access control and safeguarding sensitive information in numerous sectors. © 2024 The Authors

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

First principle calculation of electronic structures and hole concentration of YBCO family compounds

引用

Materials Today: Proceedings 2024年 96卷 94-99页

作者： Choon Min Cheong Soo Kien Chen School of Engineering INTI International Collge Penang 11900 Pulau Pinang Malaysia Faculty of Computer Science & Information Technology Universiti Malaya 57100 Kuala Lumpur Malaysia Department of Physics Faculty of Science Universiti Putra Malaysia 43300 Serdang Selangor Darul Ehsan Malaysia

Yttrium barium copper oxide (YBCO) family compounds are similar in structure but have different superconducting temperatures. It is well known that superconducting properties arise from the crystal lattice and electronic structure of compounds. This work reveals and discusses the electronic structures of YBCO family compounds (YBa 2 Cu 3 O 6 , YBa 2 Cu 3 O 6.5 , YBa 2 Cu 3 O 7 , and YBa 2 Cu 4 O 8 ) based on density functional theory (DFT). The electronic structure results show that Cu–O chains are the trigger components for conduction, and only Cu–O chains and Cu-O 2 planes play important roles in electronic and superconducting properties. The results also reveal that additional hole doped will be non-trivially distributed between the Cu–O chains and the Cu-O 2 planes, and hence a more comprehensive method is required to calculate the hole concentration in the Cu-O 2 plane. This work also demonstrates the calculation of hole concentrations using DFT. By DFT calculation, the Y1236 has hole concentration of 0.5 and the hole doped of Y12365, Y1237 and Y124 are 0.09, 0.16 and 0.10, respectively. The results are consistent with the cuprate-superconductor phase diagram and the bond-valence sum (BVS) calculations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Approach for Text Pattern Diagnosis of Mental Disorders in Online Health Consultation

SSRN

引用

SSRN 2025年

作者： Juanita, Safitri Daeli, Anisah Hasratniwati Syafrullah, Mohammad Anggraeni, Wiwik Purnomo, Mauridhi Hery Faculty of Information Technology Universitas Budi Luhur Jakarta12260 Indonesia Department of Information Systems Institut Teknologi Sepuluh Nopember Surabaya60117 Indonesia Departement of Computer Engineering Institut Teknologi Sepuluh Nopember Surabaya60117 Indonesia

Online health consultation (OHC) services provide broad access to mental health consultations, particularly in densely populated countries, enabling accessibility anytime and anywhere. However, responses in OHC often rely on human medical expertise, leading to delays and queues. This study aims to develop a Machine Learning (ML) model to predict patterns in doctors' answer texts on mental health topics, allowing OHC applications to recommend automated responses, reducing doctors' response time. The methodology includes collecting datasets from OHC sites on anxiety, depression, and stress, preprocessing the data, verifying it with a medical team, extracting features, and modeling using ML algorithms: Naïve Bayes (NB), K-Nearest Neighbor (KNN), Random Forest (RF), Neural Network (NN), and Gradient Boosting (GB). Additionally, Optimized ML models with combining ML algorithms with bagging classifiers (BC) and genetic algorithms (GA) or hybridML were proposed. Models were tested, compared, and evaluated to identify the best predictor. Results showed that GB was the most effective standalone model, while the optimized GB with GA outperformed others among hybridML models. N-Gram and Bag-of-Words (BOW) were identified as optimal feature extraction methods. Train-test ratios of 90:10 and 70:30 yielded the best performance. This research supports OHC services by providing fast, accurate recommendations, enhancing efficiency for mental health information seekers and providers © 2025, The Authors. All rights reserved.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Predicting Employees' Turnover in IT Industry using Classification Method with Feature Selection 2

Predicting Employees' Turnover in IT Industry using Classifi...

引用

2nd International Conference on computer Science and engineering, IC2SE 2021

作者： Mohamad, Mas Rahayu Hanum Nasaruddin, Fariza Hamid, Suraya Bukhari, Sarah Ijab, Mohamad Taha University Malaya Faculty of Computer Science and Information Technology Kuala Lumpur Malaysia National Fertilizer Corporation Institute of Engineering and Technology Computer Science Department Multan Pakistan Selangor Malaysia

ISBN: (纸本)9781665400459

Nowadays many IT companies are concerned about retaining their employees due to the competitiveness of employment landscape where highly skilled and quality IT knowledge workers are in huge demand. However, the growing pace of technological change and the socio-economic factors have transmuted employees in various organizations on how best to make their skills and talents proffered to be more attractive toward employers. Challenges pertaining to the turnover rate can be attributed to several factors such as failure employees to meet the company's objectives, less motivating work environment, employees losing out to their employers, their skills are not put to best use, low wages, and many other turnover factors. On the other hand, the growing interest of machine learning (ML) lead to the prediction of the turnover factors. This research aims to explore the factors contributing to high turnover rate based on employee productivity using ML. For this purpose, dataset of 1,470 employees with 26 variables undergo feature selection processing which is to identify the correlation between employees' productivity and turnover features which are (i) Pearson's Square for categorical value and (ii) Correlation for numerical value have been applied to the dataset. The analysis shows higher accuracy after going through feature selection (18 variables) instead of without feature selection (26 variables). Thus, the best algorithm that can be used for the prediction of employees' turnover is Random Forest with a model accuracy value of 87.76%, precision 0.643, recall 0.75, and F1-Score of 0.692. © 2021 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Pre-Impact Fall Detection Based on Wearable Inertial Sensors using Hybrid Deep Residual Neural Network 6

Pre-Impact Fall Detection Based on Wearable Inertial Sensors...

引用

6th International Conference on information technology, InCIT 2022

作者： Mekruksavanich, Sakorn Jantawong, Ponnipa Jitpattanakul, Anuchit University of Phayao School of Information and Communication Technology Department of Computer Engineering Phayao Thailand King Mongkut's University of Technology North Bangkok Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Faculty of Applied Science Bangkok Thailand

ISBN: (纸本)9781665489126

Falls are the primary cause of fatal and nonfatal injuries among the elderly. Consequently, pre-impact fall detection that identifies a fall before the body's collision with the ground is of essential importance. In the latest days, academics have moved their attention from post-impact fall detection to pre-impact fall detection. Pre-impact fall detection systems typically use either a threshold-based or machine learning-based approach, and the thresholding is challenging to determine accurately for threshold-based methods. In addition, while additional features can sometimes assist in categorizing falls and non-falls more precisely, the value computation of prominent features will be too time-intensive, using too much of the algorithm's operating time. We proposed a pre-impact fall detection method employing wearable inertial sensors and a deep residual model to address the limitations of feature extraction, threshold definition, and algorithm sophistication. After training on a large-scale motion dataset known as the KFall, the suggested deep learning model could identify with 91.87% accuracy in 0.5 second. © 2022 IEEE.

关键词： Fall detection

来源：评论

学校读者我要写书评

暂无评论

A New Hybrid Fault-Tolerant Converter Based on Five-Level Active Neutral Point Clamped Inverter 6

A New Hybrid Fault-Tolerant Converter Based on Five-Level Ac...

引用

6th IEEE International Conference on Computing, Communication and Automation, ICCCA 2021

作者： Bikdeli, Efaf Islam, Md. Rabiul Babol Noshirvani University of Technology Department of Electrical and Computer Engineering Babol Iran University of Wollongong Faculty of Engineering and Information Sciences NSW2522 Australia

ISBN: (纸本)9781665414739

Performance of converters in the event of a fault in the semiconductor devices is very important in many critical applications. If one of their semiconductor devices is defective, the converter will not be able to continue operating, and this will cause a lot of damage in various sectors, including industry. Therefore, having converters with fault tolerance is very important. This paper presents a new hybrid fault tolerant structure to maintain the performance of the active neutral point clamped (ANPC) five-level (5L) inverter. To achieve this, a modified T-type converter has been added to the traditional ANPC 5L inverter. In the proposed structure, by increasing the number of switching states and creating redundant switching states for all output voltage levels, it is possible to continue the operation of the main inverter in the conditions of short-circuit fault and open-circuit of the switches. In this case, in the event of a fault, all output voltage levels are maintained. Evaluation of the proposed converter performance in case of faulty switches is performed in MATLAB/Simulink environment and its results are presented in this paper. © 2021 IEEE.

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Action Recognition for Pedestrian Indoor Localization using Smartphone Inertial Sensors 7

Deep Learning-based Action Recognition for Pedestrian Indoor...

引用

7th International Conference on Digital Arts, Media and technology, DAMT 2022 and 5th ECTI Northern Section Conference on Electrical, Electronics, computer and Telecommunications engineering, NCON 2022

作者： Mekruksavanich, Sakorn Jantawong, Ponnipa Jitpattanakul, Anuchit University of Phayao School of Information and Communication Technology Department of Computer Engineering Phayao Thailand King Mongkut's University of Technology North Bangkok Faculty of Applied Science Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Bangkok Thailand

ISBN: (纸本)9781665495103

For decades, the identification of human action has been one of the most critical study areas in artificial intelligence research. The study in human activity recognition aims to classify people's behavior based on data that is already accessible, such as pictures, visual, sensing, or stream recorded data, among other things. A common distinction made by most human activity recognition methods is between daily tasks such as walking and specific behaviors like standing or sitting. More specialized functions targeted to the use-case of pedestrian interior navigation are investigated in this study. These activities include several types of stationary and movement activities and various other activities. A deep learning-based human activity recognition framework is presented that can be used to recognize people's actions inside an indoor localization situation by analyzing smartphone inertial sensor data. Furthermore, we introduced a 1D-ResNet-SE model in the framework and assessed it using a publicly available dataset known as the Activity Logs dataset. According to the experimental measurements, the 1D-ResNet-SE surpasses other standard deep learning techniques in terms of accuracy, with a maximum accuracy of 84.11% in the general scenario. © 2022 IEEE.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Blending Optimal Control and Biologically Plausible Learning for Noise-Robust Physical Neural Networks

引用

Physical Review Letters 2025年第1期134卷 017301-017301页

作者： Satoshi Sunada Tomoaki Niiyama Kazutaka Kanno Rin Nogami André Röhm Takato Awano Atsushi Uchida Faculty of Mechanical Engineering Institute of Science and Engineering Kanazawa University Kakuma-machi Kanazawa Ishikawa 920-1192 Japan Department of Information and Computer Sciences Saitama University 255 Shimo-Okubo Sakura-ku Saitama City Saitama 338-8570 Japan Department of Information Physics and Computing Graduate School of Information Science and Technology The University of Tokyo 7-3-1 Hongo Bunkyo-ku Tokyo 113-8656 Japan

The rapidly increasing computational demands for artificial intelligence (AI) have spurred the exploration of computing principles beyond conventional digital computers. Physical neural networks (PNNs) offer efficient neuromorphic information processing by harnessing the innate computational power of physical processes; however, training their weight parameters is computationally expensive. We propose a training approach for substantially reducing this training cost. Our training approach merges an optimal control method for continuous-time dynamical systems with a biologically plausible training method—direct feedback alignment. In addition to the reduction of training time, this approach achieves robust processing even under measurement errors and noise without requiring detailed system information. The effectiveness was numerically and experimentally verified in an optoelectronic delay system. Our approach significantly extends the range of physical systems practically usable as PNNs.

关键词： Continuous time systems

来源：评论

学校读者我要写书评

暂无评论

Success History Adaptive Competitive Swarm Optimizer with Linear Population Reduction: Performance benchmarking and application in eye disease detection

引用

computers in Biology and Medicine 2025年 186卷 109587-109587页

作者： Zhong, Rui Wang, Zhongmin Hussien, Abdelazim G. Houssein, Essam H. Al-Shourbaji, Ibrahim Elseify, Mohamed A. Yu, Jun Information Initiative Center Hokkaido University Sapporo Japan College of Tropical Crops Yunnan Agricultural University Yunnan China Department of Computer and Information Science Linköping University Linköping Sweden Faculty of Science Fayoum University Faiyum Egypt Faculty of Computers and Information Minia University Minia Egypt Department of Electrical and Electronics Engineering Jazan Jazan University Jazan Saudi Arabia Department of Computer Science University of Hertfordshire Hatfield United Kingdom Department of Electrical Engineering Faculty of Engineering Al-Azhar University Qena Egypt Institute of Science and Technology Niigata University Niigata Japan

Eye disease detection has achieved significant advancements thanks to artificial intelligence (AI) techniques. However, the construction of high-accuracy predictive models still faces challenges, and one reason is the deficiency of the optimizer. This paper presents an efficient optimizer named Success History Adaptive Competitive Swarm Optimizer with Linear Population Reduction (L-SHACSO). Inspired by the effective success history adaptation scheme and linear population reduction strategy in Differential Evolution (DE), we introduce these techniques into CSO to enable the automatic and intelligent adjustment of hyper-parameters during optimization thereby balancing exploration and exploitation across different phases. To thoroughly investigate the performance of L-SHACSO, we conduct extensive numerical experiments on CEC2017, CEC2020, CEC2022, and eight engineering problems. State-of-the-art optimizers including jSO and L-SHADE-cnEpSin and recently proposed metaheuristic algorithms (MAs) such as RIME and the Parrot Optimizer (PO) are employed as competitors. Experimental results confirm the superiority of L-SHACSO across various optimization tasks. Furthermore, we integrate L-SHACSO into DenseNet and Extreme Learning Machine (ELM) and propose DenseNet-L-SHACSO-ELM for eye disease detection, where the features extracted by the pre-trained DenseNet are fed into L-SHACSO-optimized ELM for classification. Experiments on public datasets confirm the feasibility and effectiveness of our proposed model, which has great potential in real-world scenarios. The source code of this research is available at https://***/RuiZhong961230/L-SHACSO. © 2024 Elsevier Ltd

关键词： Swarm intelligence

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：