检索结果-内蒙古大学图书馆

5th International Conference on Information and Communication technology for Development for Africa, ICT4DA 2023

作者： Wubineh, Betelhem Zewdu Metekiya, Biniyam Yirsaw Wroclaw University of Science and Technology Faculty of Information and Communication Technology Wroclaw Poland School of Computing and Informatics Wachemo University Department of Information Technology Hossana Ethiopia College of Informatics Department of Information System University of Gondar Gondar Ethiopia

ISBN: (纸本)9798350328486

Crime is a complex social phenomenon, and its cost continues to rise over time. Police have collected a large amount of data on criminals every day for different crimes. However, extracting valuable information from these data takes time and effort for the law enforcement organization at hand. Therefore, effective crime prevention strategies and policies are necessary to prevent crime. Criminology is one of the most important areas for data mining. The purpose of this study is to extract useful crime patterns from past data and develop a knowledge-based system to prevent crime. Different criminals commit different crimes, but we do not know which criminal commits which crime. For this purpose, the 910 criminal records are used to train and test the model. To predict a crime, the classification technique and the J48 decision tree, random forest (RF), PART, and ensemble algorithms are used. As a result, the algorithm scored an accuracy of 75.38%, 80.4%,73.7%, and 81.3% in the J48, RF, PART, and ensemble methods, respectively, in a 10-fold cross-validation. Additionally, the offender's job is the determining factor that causes and predicts crimes. Finally, we integrate the rules extracted from a data mining task into a knowledge base system using PROLOG, which is used to make decisions. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Deep Learning in Sinhala Sign Language Recognition: A Systematic Decade Review

Deep Learning in Sinhala Sign Language Recognition: A System...

引用

Image Processing, Computer Vision and Machine Learning (ICICML), International Conference on

作者： Yohan Abhishek T. G. D. K. Sumanathilaka School of Computing Informatics Institute of Technology Colombo Sri Lanka

ISBN: (数字)9798350355413

ISBN: (纸本)9798350355420

The paper reviews the progress in Sinhala Sign Language recognition (SSL) over the last decade, tracing the techniques from early image processing to advanced deep learning models, indicating methodologies involved, datasets used, and challenges. The paper shows that the evolution has progressed from basic classifiers to sophisticated machine learning techniques that integrate CNNs, RNNs, and transformer architectures. It also presents the implementation of multimodal systems using hand gestures, facial expressions, and body postures. The review identifies the limitations of current recognition in SSL, such as scarce complete datasets, technical difficulties, and a lack of robust continuous recognition. Finally, it points out future research directions, stressing that further work must focus on growing datasets, making lightweight models for edge devices, and collaboration for further growth in SSL recognition technology.

关键词： Deep learning Hands Sign language Computer vision Image recognition Systematics Reviews Transformers Research and development Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-powered Mobile App for Early Brahmi Script Decipherment in Sri Lanka

Deep Learning-powered Mobile App for Early Brahmi Script Dec...

引用

International Research Conference on Smart computing and Systems Engineering (SCSE)

作者： Sakith Gunasekara Muhammed Haleef Lafir Chavindu Dulaj Lakidu Haputhanthri Dileeka Alwis School of Computing Informatics Institute of Technology Colombo Sri Lanka

ISBN: (数字)9798350375688

ISBN: (纸本)9798350375695

This ongoing research delves into ancient Brahmi writings carved on stone surfaces, particularly focusing on early Brahmi characters which serves as critical artifacts to illuminate the island’s historical ties with India, religious and cultural practices of the era. The study aims to develop a mobile application utilizing deep learning techniques to recognize and translate ancient early Brahmi characters, ensuring enhanced efficiency and accuracy in the decipherment process. A comprehensive literature review highlighted the absence of a mobile application, challenges of contextual translation, and difficulties in accurate predicting translation for damaged inscriptions and translation to foreign languages were identified as notable research gaps. Drawing upon interdisciplinary expertise and stakeholder analysis, the research tackles these complex challenges of script recognition, linguistic translation, accurate prediction by employing a data-driven approach, cutting-edge algorithms, and user-centric design principles. After the creation of a refined, precise digitized dataset of early Brahmi characters with found variations, the research aims to utilize semantic segmentation techniques to recognize characters using TensorFlow and Keras. OpenCV for image preprocessing, Flutter framework for development of mobile application. Expected outcomes include improved recognition accuracy, linguistically faithful translations, and user-friendly interfaces, contributing to advancements in digital humanities, cultural preservation, and computational linguistics.

关键词： Semantic segmentation Linguistics Systems engineering and theory Prediction algorithms Mobile applications Character recognition Cultural differences

来源：评论

学校读者我要写书评

暂无评论

Optimization strategies for microgrid based on generation scheduling considering cost reduction and electric vehicles

引用

Soft computing 2024年第13-14期28卷 7893-7903页

作者： Jiang, Yingjie Zain, Jasni Mohamad Nasr, Arman Institute of Information Technology Changchun Automotive Vocational and Technical University Changchun130051 China School of Computing Sciences College of Computing Informatics and Media Universiti Teknologi MARA Selangor Shah Alam40450 Malaysia Universiti Teknologi MARA Selangor Shah Alam40450 Malaysia Solar Energy and Power Electronic Co Ltd Istanbul Turkey

One of the main issues in power systems relates to scheduling of energy resources. With the ever-increasing penetration of renewable energies with intermittent power output, this issue has turned into an even more significant problem. Renewable energy sources (RESs) have captured attention due to their low environmental emission and also low running cost. One drawback that may be brought into power systems is the surplus power generation by such generation technologies that should be carefully addressed in power system-related problems. This paper proposes the unscented transform modeling to consider the stochastic behavior of charge and discharge of EVs, random performance of photovoltaic, load demand and wind turbine systems. Due to the unpredictable nature of solar and wind power outputs, as well as plug-in electric vehicle owners' behavior when supplying or receiving power from the grid, a stochastic programming-based approach is proposed to operate microgrids in grid-connected configuration mode. The integration of vehicle to grid (V2G) has a good ability to minimize the operating cost of the MG. An integrated optimization model is presented in this study for optimal operation of the MG with high penetration of PEVs and RESs. Modified sunflower optimization algorithm (MSFO) algorithm is applied in this paper to address the optimization problem. The single-objective stochastic optimization is used for minimizing the total operating cost over the day taking into consideration the uncertainties due to the RESs’ power output intermittency, including wind speed and solar irradiance and load demand forecast error. Several case studies are taken into account to show the efficiency of the optimal operation with PEVs. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Operating costs

来源：评论

学校读者我要写书评

暂无评论

GreenGuard: Mobile Application for Real-Time Tea Leaves Disease Detection and Treatment Guidance

GreenGuard: Mobile Application for Real-Time Tea Leaves Dise...

引用

Advancements in computing (ICAC), International Conference on

作者： Esandu Obadaarachchi Damika Saputhanthri Pramuditha Vithanarachchi Yoosuf Zuhry Rasanjalee Rathnayake School of Computing Informatics Institute of Technology Colombo Sri Lanka

ISBN: (数字)9798331517878

ISBN: (纸本)9798331517885

Accurate tea leaves disease detection is essential in agriculture to maintain healthy crops, food security, and economic stability. Tea leaves disease identification is challenging due to traditional detection methods, frequently constrained by the knowledge gap between small-scale and general-level farmers. To alleviate this issue, the proposed study presents an Artificial Intelligence (AI)-enhanced tea plant disease detection system that can accurately identify ailments and suggest relevant treatments. The proposed Convolutional Neural Network (CNN) architecture ensures high accuracy while efficiently working in real time for disease detection and treatment suggesting. The custom CNN model surpasses the ResNet50V2 model's accuracy while achieving 94% accuracy in disease detection. Further, the study initiative promises to make a major contribution to the advancement of agricultural technology in the tea plantation sector and the support of farming-dependent people worldwide by fusing AI with traditional methods while ensuring sustainable development and food security.

关键词： Accuracy Food security Computer architecture Data augmentation Data models Real-time systems Mobile applications Convolutional neural networks Artificial intelligence Diseases

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Review of Transformer-Based Models: ChatGPT and Bard in Focus

A Comprehensive Review of Transformer-Based Models: ChatGPT ...

引用

International Conference on Artificial Intelligence and Big Data (ICAIBD)

作者： Pooja Illangarathne Nethari Jayasinghe A.B. Duweeja de Lima School of Computing Informatics Institute of Technology Colombo Sri Lanka

ISBN: (数字)9798350385106

ISBN: (纸本)9798350385113

This review paper provides a thorough analysis of transformer-based models, specifically ChatGPT and Bard, exploring their many uses, underlying difficulties, and potential future developments. Through a synthesis of current research findings, it highlights the transformational power and possible drawbacks of these models in a variety of fields. The study delves deeper into the moral issues, societal ramifications, and complex roles these models play in fields including environmental research, digital forensics, healthcare, and education. The changing field of artificial intelligence is also covered, emphasizing the necessity of domain-specific modifications as well as the significance of resolving ethical and technological issues in the ongoing creation and use of increasingly sophisticated AI systems.

关键词： Ethics Adaptation models Analytical models Reviews Computational modeling Transforms Transformers

来源：评论

学校读者我要写书评

暂无评论

LawKey — Law Constitution Chatbot

LawKey — Law Constitution Chatbot

引用

Artificial Intelligence (SLAAI-ICAI), SLAAI International Conference on

作者： W Shamini Fernando Mandinu Handapangoda Nividula Samindi Maneth Gamage Dileeka Alwis School of Computing Informatics Institute of Technology Colombo Sri Lanka

ISBN: (数字)9798331509170

ISBN: (纸本)9798331509187

In response to a pervasive lack of legal awareness among Sri Lanka, this research introduces a law constitution chatbot utilizing Natural Language Processing (NLP). The chatbot is designed to offer precise legal guidance by extracting pertinent laws from the Sri Lankan constitution based on user input. Building on existing studies at the intersection of NLP and the legal domain, this chatbot addresses the lack of relevant legal context for Sri Lanka. Reinforcement learning is integrated to refine the chatbot’s behavior through user feedback, ensuring optimal selection of the most relevant laws. An exploration of applications in countries like Canada and India, where NLP and machine learning have successfully addressed legal information gaps, focuses on various legal domains in Sri Lanka with the aim of empowering the public. The research methodology involves leveraging the Sri Lankan constitution as the dataset, extracting keywords from legal documents, and employing various NLP models, and limitations of the application. A comprehensive literature review reveals the potential energy of NLP techniques in legal chatbots. The global analysis of legal chatbots significantly contributes to the theoretical foundation of this project. In summary, this project seeks to advance legal chatbot technology in Sri Lanka, utilizing NLP and reinforcement learning techniques to empower citizens with legal knowledge and enhance overall legal awareness, thereby addressing the critical issue of legal unawareness and fostering a more informed society.

关键词： Potential energy Law Buildings Reinforcement learning Chatbots Mobile applications Encryption Security IEEE Constitution Systematic literature review

来源：评论

学校读者我要写书评

暂无评论

Lightweight 1-D Convolutional Neural Network Model for Predicting Snoring Duration

Lightweight 1-D Convolutional Neural Network Model for Predi...

引用

Sensors, Electronics and Computer Engineering (ICSECE), IEEE International Conference on

作者： Yohan Abhishek School of Computing Informatics Institute of Technology Colombo Sri Lanka

ISBN: (数字)9798350373646

ISBN: (纸本)9798350373653

This paper introduces an approach to snoring duration prediction utilizing a custom 1-D Convolutional Neural Network (CNN) implemented into TensorFlow Lite. Snoring is a prevalent symptom of sleep disorders which presents challenges in diagnosis and management due to its disruptive effects on sleep quality and potential indication of underlying health issues like obstructive sleep apnea (OSA). Despite the significance of accurate snoring prediction and monitoring, existing research lacks specific exploration of lightweight and accurate CNN models tailored for this purpose. Leveraging the advantages of 1-D CNNs, such as efficient processing of 1D signals without extensive preprocessing, this paper addresses the research gap by proposing a custom TensorFlow Lite-based model for snoring prediction. Through a comprehensive literature review, the efficiency of CNNs in predictive modeling across various domains is highlighted, underscoring the need for specialized models in healthcare applications like snoring prediction. The proposed approach not only supports the gap in existing research but also opens possibilities for lightweight, real-time snoring monitoring, potentially integrated into mobile or wearable devices for continuous assessment of sleep-related disorders.

关键词： Accuracy Computational modeling Medical services Predictive models Sleep apnea Real-time systems Sensors Convolutional neural networks Wearable devices Monitoring

来源：评论

学校读者我要写书评

暂无评论

Recent Advances in Fiber-Optic Sensors for the Detection of Inorganic Acidic Gases

引用

Photonic Sensors 2024年第4期14卷 74-100页

作者： Lingnan KONG Yuanke GONG Xiaoyu ZHONG Yang LIU Bo WAN Quanhua XIE Yuanyuan HE Xiaoling PENG Haixing CHANG Dengjie ZHONG Huiling LIU Nianbing ZHONG Chongqing Key Laboratory of Optical Fiber Sensor and Photoelectric Detection Chongqing Key Laboratory of Modern Photoelectric Detection Technology and InstrumentsChongqing Engineering Research Center of Intelligent Optical Fiber Sensing TechnologyChongqing University of TechnologyChongqing 400054China Meishan San Su Shrine Museum Meishan 620010China School of Chemistry and Chemical Engineering Chongqing University of TechnologyChongqing 400054China College of Computing and Informatics Sungkyunkwan UniversitySeoul 03060South Korea

An acidic gas is an important basic chemical raw material used for synthesizing fertilizers,insecticides,explosives,dyes,and ***,inorganic acidic gases that leak into the air have harmful effects on the human health,infrastructure,and cultural ***,the demand for inorganic acidic gas sensors for air quality monitoring and management has continuously increased,enabling the development of various sensing *** them,fiber-optic sensors are promising for acidic gas detection because of their excellent in-situ measurement,resistance to corrosion,anti-electromagnetic interference,long service life,and smart *** particular,fiber-optic sensors have proven to be very useful for the in-situ detection and distributed monitoring of multiple gas ***,the sensitivity,selectivity,repeatability,and limits of detection of these sensors can be improved to achieve acceptable performance levels for practical *** this review,we introduce fiber-optic sensors based on structured optical fibers and fiber gratings for detecting H_(2)S,SO_(2),NO_(2),CO_(2),and N_(2)*** structures of the sensing regions,gas-sensitive materials,and measurement principles of these sensors are *** sensitivity,selectivity,limit of detection,and response time of the sensors are ***,the future of fiber-optic sensors for the detection of inorganic acidic gases is discussed.

关键词： Fiber-optic sensors structured optical fibers fiber gratings inorganic acidic gases measurement principles sensing performance

来源：评论

学校读者我要写书评

暂无评论

Knee Osteoarthritis Detection Using Machine Learning on Pre-Processed X-ray Images and Treatment Recommendation

Knee Osteoarthritis Detection Using Machine Learning on Pre-...

引用

Artificial Intelligence (SLAAI-ICAI), SLAAI International Conference on

作者： Nuha Rameez G.G Dewmi Dissanayake G. A. Chanula Senindu P.M.H Liyanage Vishmi Embuldeniya School of Computing Informatics Institute of Technology Colombo Sri Lanka

ISBN: (数字)9798331509170

ISBN: (纸本)9798331509187

Osteoarthritis (OA) is a degenerative joint disease marked by the gradual breakdown of cartilage and changes in the underlying bone. The condition is most prevalent in older adults and is often exacerbated by joint injuries and mechanical stress. Knee osteoarthritis (KOA) is one of the common disability adjusted life years. There is no cure for the disease, but a combination of lifestyle changes, medications, physical therapies, and sometimes knee transplants can help manage the condition. Despite being time-consuming and highly prone to user variation, manual segmentation, diagnosis, annotation of knee joints, and personalized treatment recommendations remain common procedures for diagnosing osteoarthritis in clinical practice. This research addresses these limitations and reduces diagnostic errors and time and enhance the efficiency and accuracy of knee osteoarthritis diagnosis. The proposed KOA detection model utilizes a deep learning-based approach with Convolutional Neural Networks (CNNs) to identified knee joints in x-rays, Binary classification to determine the presence of disease, a pre trained network(VGG16) and custom CNN used to classify the Kellgren-Lawrence (KL) grades, and random forest model recommending and validating treatment options based on severity. The proposed model has shown promising results by obtaining 98% overall accuracy.

关键词： Accuracy Refining X-rays Organ transplantation Convolutional neural networks Osteoarthritis Older adults Medical diagnostic imaging Stress Random forests

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：