检索结果-内蒙古大学图书馆

SSRN 2025年

作者： Aini, Mohammad Affaiq Bin Leong, Siow Hoo Yong, Yueh Tiam Lee, Beng Yong Zhao, Xiaomin Manaf, Sharifah Raina Abdullah, Firdaus Khong, Heng Yen College of Computing Informatics and Mathematics Universiti Teknologi MARA Sarawak Kota Samarahan94300 Malaysia College of Automotive Engineering Guangdong Polytechnic of Industry and Commerce Guangzhou510000 China Faculty of Plantation and Agrotechnology Universiti Teknologi MARA Sarawak Mukah96400 Malaysia Faculty of Business and Management Universiti Teknologi MARA Selangor42300 Malaysia Faculty of Applied Sciences Universiti Teknologi MARA Sarawak Kota Samarahan94300 Malaysia

In soft-shell crab farming, collecting the moulted crabs within a narrow window of one hour is crucial to meet the quality of high-graded paper shell crab. This paper incorporates IoT-based computer vision technology and deep learning techniques in greenhouse soft-shell crab farming to detect moulted crabs. The challenges arise in accurately detecting underwater crabs due to wide-angle distortion and reflections in images captured by cameras installed on rails within the greenhouse. Image enhancement methods are proposed to address these challenges and improve the performance of crab detection using the YOLOv7 deep-learning algorithm. Specifically, the performance of two methods for rectifying wide-angle distortion and two methods for removing reflections are compared, respectively. Data augmentation techniques are also applied to overcome the limitation of annotated underwater crab targets for deep-learning training. Results show that the fisheye flattening method outperforms the stretch flattening method for rectifying wide-angle distortion, while 2D-image flat field correction yields better results than the non-local mean filter for reducing reflections. Furthermore, data augmentation significantly enhances crab detection performance. Application of the best image enhancement methods and data augmentation techniques shows a successful rate of 92% in detecting the moulted crabs in greenhouse soft-shell crab farming.. © 2025, The Authors. All rights reserved.

关键词： Shellfish

来源：评论

学校读者我要写书评

暂无评论

Experiments of Crowd Detection for Crowd Digital Twins

Experiments of Crowd Detection for Crowd Digital Twins

引用

Consumer Communications and Networking Conference, CCNC IEEE

作者： Kuan Pok Chong Chon Hou Lai Weibo Ling Zhuoqian Lu Rui Wang Ruoqi Wang Yanjun Yu Alex Testa Chan-Tong Lam Su-Kit Tang Giovanni Delnevo Roberto Casadei Roberto Girau Silvia Mirri Bachelor of Science in Computing Macao Polytechnic University Macao SAR China Guangdong University of Foreign Studies China Dept. of Computer Science and Engineering University of Bologna Italy Faculty of Applied Sciences Macao Polytechnic University Macao SAR China

ISBN: (数字)9798331508050

ISBN: (纸本)9798331508067

The development of a crowd digital twin offers significant potential for enhancing public safety, urban planning, and event management. A key challenge in creating such a digital twin lies in the efficient and accurate acquisition of crowd-related data, particularly through object detection models deployed on resource-constrained devices. Through a series of experiments, we compare TinyML and Edge approaches in terms of detection accuracy, inferencing time, and resource utilization. Our findings highlight the trade-offs inherent in selecting detection models for crowd digital twin applications, underscoring the importance of aligning model choice with specific deployment needs.

关键词： Accuracy Tiny machine learning Image edge detection Urban planning Object detection Public security Data models Digital twins Resource management

来源：评论

学校读者我要写书评

暂无评论

Automatic melanoma and non-melanoma skin cancer diagnosis using advanced adaptive fine-tuned convolution neural networks

引用

Discover Oncology 2025年第1期16卷 1-27页

作者： Khan, Muhammad Amir Mazhar, Tehseen Ali, Muhammad Danish Khattak, Umar Farooq Shahzad, Tariq Saeed, Mamoon M. Hamam, Habib School of Computing Sciences College of Computing Informatics and Mathematics Universiti Teknologi MARA Shah Alam 40450 Malaysia School of Computer Science National College of Business Administration and Economics Lahore 54000 Pakistan Department of Computer Science COMSATS University Islamabad Abbottabad Campus Abbottabad 22060 Pakistan School of Information Technology UNITAR International University Kelana Jaya Petaling Jaya 47301 Malaysia Department of Computer Engineering COMSATS University Islamabad Sahiwal Campus Sahiwal 57000 Pakistan Department of Communications and Electronics Engineering Faculty of Engineering University of Modern Sciences (UMS) Yemen Sana’a 00967 Yemen Faculty of Engineering University de Moncton Moncton E1A3E9 NB Canada School of Electrical Engineering Department of Electrical and Electronic Engineering Science University of Johannesburg Johannesburg South Africa Hodmas University College Taleh Area Mogadishu Banadir 521376 Somalia Bridges for Academic Excellence—Spectrum Tunis Centre-Ville 1002 Tunisia Department of Computer Science School Education Department Government of Punjab Layyah 31200 Pakistan

Skin Cancer is an extensive and possibly dangerous disorder that requires early detection for effective treatment. Add specific global statistics on skin cancer prevalence and mortality to emphasize the importance of early detection. Example: “Skin cancer accounts for 1 in 5 diagnosed cancers globally, with melanoma causing over 60,000 deaths annually. Manual skin cancer screening is both time-intensive and expensive. Deep learning (DL) techniques have shown exceptional performance in various applications and have been applied to systematize skin cancer diagnosis. However, training DL models for skin cancer diagnosis is challenging due to limited available data and the risk of overfitting. Traditionally approaches have High computational costs, a lack of interpretability, deal with numerous hyperparameters and spatial variation have always been problems with machine learning (ML) and DL. An innovative method called adaptive learning has been developed to overcome these problems. In this research, we advise an intelligent computer-aided system for automatic skin cancer diagnosis using a two-stage transfer learning approach and Pre-trained Convolutional Neural Networks (CNNs). CNNs are well-suited for learning hierarchical features from images. Annotated skin cancer photographs are utilized to detect ROIs and reset the initial layer of the pre-trained CNN. The lower-level layers learn about the characteristics and patterns of lesions and unaffected areas by fine-tuning the model. To capture high-level, global features specific to skin cancer, we replace the fully connected (FC) layers, responsible for encoding such features, with a new FC layer based on principal component analysis (PCA). This unsupervised technique enables the mining of discriminative features from the skin cancer images, effectively mitigating overfitting concerns and letting the model adjust structural features of skin cancer images, facilitating effective detection of skin cancer features. The sys

关键词： Advanced adaptive fine-tuned Convolution neural networks Melanoma and non-melanoma skin cancer

来源：评论

学校读者我要写书评

暂无评论

Elevated levels of butyric acid in the jejunum of an animal model of broiler chickens: from early onset of Clostridium perfringens infection to clinical disease of necrotic enteritis

引用

Journal of Animal Science and Biotechnology 2025年第2期16卷 758-776页

作者： Hemlata Gautam Noor Ahmad Shaik Babajan Banaganapalli Shelly Popowich Iresha Subhasinghe Lisanework EAyalew Rupasri Mandal David S.Wishart Suresh Tikoo Susantha Gomis Department of Veterinary Pathology Western College of Veterinary MedicineUniversity of Saskatchewan52 Campus DriveSaskatoon S7N 5B4Canada Department of Genetic Medicine Faculty of MedicineKing Abdulaziz UniversityJeddah 21589Saudi Arabia Department of Pathology and Microbiology Atlantic Veterinary CollegeUniversity of Prince Edward Island550 University AveCharlottetownPE C1A 4P3Canada Departments of Biological Sciences and Computing Science University of AlbertaEdmontonAB T6G 2E9Canada Vaccinology and Immunotherapy School of Public HealthUniversity of SaskatchewanSaskatoon 7N 5E3Canada

Background Necrotic enteritis(NE)is an economically important disease of broiler chickens caused by Clostridium perfringens(CP).The pathogenesis,or disease process,of NE is still not *** study aimed to identify the alterations of metabolites and metabolic pathways associated with subclinical or clinical NE in CP infected birds and to investi-gate the possible variations in the metabolic profile of birds infected with different isolates of *** Using a well-established NE model,the protein content of feed was changed abruptly before expos-ing birds to CP isolates with different toxin genes combinations(cpa,cpb2,netB,tpeL;cpa,cpb2,netB;or cpa,cpb2).Metabolomics analysis of jejunal contents was performed by a targeted,fully quantitative LC-MS/MS based *** This study detected statistically significant differential expression of 34 metabolites including organic acids,amino acids,fatty acids,and biogenic amines,including elevation of butyric acid at onset of NE in broiler *** analysis of broilers infected with CP isolates with different toxin gene combinations confirmed an eleva-tion of butyric acid consistently among 21 differentially expressed metabolites including organic acids,amino acids,and biogenic amines,underscoring its potential role during the development of ***,protein-metabolite network analysis revealed significant alterations in butyric acid and arginine-proline *** This study indicates a significant metabolic difference between CP-infected and non-infected broiler *** all the metabolites,butyric acid increased significantly in CP-infected birds compared to non-infected healthy *** regression analysis revealed a positive association between butyric acid(coefficient:1.23,P<0.01)and CP infection,while showing a negative association with amino acid *** findings suggest that butyric acid could be a crucial metabolite linked to the occurrence of NE in b

关键词： Broiler chickens Butyric acid Gut health Metabolic pathways Necrotic enteritis Toxin genes

来源：评论

学校读者我要写书评

暂无评论

Exploration and Exploitation Mechanism in Pairwise Test Case Generation: A Systematic Literature Review

引用

IEEE Access 2025年 13卷 82342-82377页

作者： Yahaya, Muhammad Sabo Hashim, Ahmad Sobri B. Balogun, Abdullateef Oluwagbemiga Muazu, Aminu Aminu Usman, Fatima Sabo Aliyu, Dahiru Adamu Muhammad, Abdullahi Uwaisu Universiti Teknologi PETRONAS Faculty of Science and Information Technology Computer and Information Sciences Department Perak 32610 Malaysia Federal Polytechnic Daura Faculty of Engineering and Technology Computer Engineering Technology Department Katsina824101 Nigeria Umaru Musa Yar’adua University Faculty of Natural and Applied Sciences Computer Science Department Katsina820102 Nigeria Gombe State University Faculty of Science Computer Science Department Gombe760101 Nigeria Federal University Dutse Faculty of Computing Computer Science Department Jigawa 720223 Nigeria

Software systems are essential in modern life, requiring rigorous testing to ensure reliability. Pairwise testing, a combinatorial testing methodology, optimizes test case generation by minimizing redundancy while maintaining defect detection effectiveness. This review systematically examines the role of metaheuristic algorithms in pairwise test case generation, focusing on their exploration and exploitation mechanisms to address local optima challenges. Covering research from 2014 to 2024, the review evaluates hybrid and metaheuristic strategies, including Pairwise Migrating Birds Optimization-Based Strategies (PMBOS), Pairwise Gravitational Search Algorithm Strategy (PGSAS), Pairwise hybrid Artificial Bee Colony (PhABC), Genetic and Particle Swarm Optimization (GAPSO) algorithm, Hybrid Optimization Algorithm (HOA), and Parameter Free Choice Function based Hyper-Heuristic (PCFHH), among others. These methods consistently outperform traditional techniques by reducing test suite sizes and enhancing fault detection capabilities. The findings underscore the growing adoption of the one-test-at-a-time (OTAT) approach over the one-parameter-at-a-time (OPAT) approach and identify key challenges in scalability, hyperparameter tuning, and constraint handling, highlighting the need for hybrid strategies and adaptive optimization techniques. This review offers valuable insights into advancing software testing methodologies and presents recommendations for future research to improve efficiency, scalability, and fault detection in pairwise testing. © 2013 IEEE.

关键词： Software reliability

来源：评论

学校读者我要写书评

暂无评论

Dual Fuel-Based Multi-Energy System for Australian Renewable Energy Zones at Country Scale

SSRN

引用

SSRN 2025年

作者： Tariq, Abdul Haseeb Amin, Uzma Shafie-Khan, Miadreza Dehghanian, Payman Senjyu, Tomonobu National University of Sciences and Technology Pakistan School of Electrical Engineering Computing and Mathematical Sciences Curtin University Australia Research and Innovation Division Nowocert Dublin Ireland School of Engineering and Applied Science The George Washington University United States Faculty of Engineering University of the Ryukyus Japan University of Vaasa Finland

The multi-energy system (MES) is an attractive option for producing multi-energy for remote areas. This paper aims to optimize dual-fuel green hydrogen and blended natural gas (BNG) facilitated heterogeneous off-/on-grid MES integrated with renewable sources for different Renewable Energy Zones (REZs) of Australia at the country scale. The main objective is to develop a novel MES for green hydrogen production and BNG for remote housing applications, like combi boilers and gas stoves. The proposed study generates green hydrogen via a proton exchange membrane (PEM) electrolyzer and blends it with natural gas (NG). The blending process involves 20% hydrogen and 80% NG in the overall volume. The optimal sizing of the components, economic-energy-environmental, and performance analyses are performed to examine a feasible solution for each REZ. The results indicate that the North Queensland REZs have the lowest levelized cost of energy (LCE) of 1.28 A$/kWh and 0.1003 A$/kWh, and the net present cost (NPC) of A$0.311 million and A$0.219 million for off-grid and on-grid configurations. The off-grid system has 99.99% and the on-grid system has 95.27% fewer carbon emissions than the NG-fuelled combustion energy system. Therefore, the proposed on-grid dual-fuel-based MES is both more reliably feasible and economically beneficial. © 2025, The Authors. All rights reserved.

关键词： Clean energy

来源：评论

学校读者我要写书评

暂无评论

UNeLF: Unconstrained Neural Light Field for Self-Supervised Angular Super-Resolution

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Zhao, Mingyuan Sheng, Hao Chen, Rongshan Cong, Ruixuan Cui, Zhenglong Yang, Da Beihang University State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beijing100191 China Beihang University Data Science and Intelligent Computing Laboratory Hangzhou International Innovation Institute Hangzhou311115 China Macao Polytechnic University Faculty of Applied Sciences 999078 China

Compared to supervised learning methods, self-supervised learning methods address the domain gap problem between light field (LF) datasets collected under varying acquisition conditions, which typically leads to decreased performance when differences exist in the distribution between the training and test sets. However, current self-supervised light field angular super-resolution (LFASR) techniques primarily focus on exploiting discrete spatial-angular features while neglecting continuous LF information. In contrast to previous work, we propose a self-supervised unconstrained neural light field (UNeLF) to continuously represent LF for LFASR. Specifically, any LF can be described as the camera pose for each sub-aperture image (SAI) and the two-plane that captures these SAIs. To describe the former, we introduce a SAIs-dependent pose optimization method to solve the issue that arises from the narrow baseline of most LF data, which hinders robust camera pose estimation. This mechanism reduces the number of trainable camera parameters from a quadratic to a constant scale, thereby alleviating the complexity of joint optimization. For the latter, we propose a novel adaptive two-plane parameterization strategy to determine the two-plane that captures these SAIs, facilitating refocusing. Finally, we jointly optimize the camera parameters, near-far planes and neural light field, efficiently mapping each adaptive two-plane parameterized ray to its correspondence color in a continuous manner. Comprehensive experiments demonstrate that UNeLF achieves faster training and inference with fewer computational resources while exhibiting superior performance on both synthetic and real-world datasets. © 1991-2012 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Ocular Disease Classification: A Study on ODIR-5K Dataset

Deep Learning for Ocular Disease Classification: A Study on ...

引用

Artificial Intelligence, Applications, Innovation and Ethics (AI2E), International Conference for

作者： Suresh Rasappan S. Ahamed Nishath Sathish Kumar Kumaravel Regan Murugesan Kala Raja Mohan Nagadevi Bala Nagaram Mathematics Department University of Technology and Applied Sciences-Ibri Ibri Sultanate of Oman Information Technology Department College of Computing and Information Sciences University of Technology and Applied Sciences-Ibri Ibri Sultanate of Oman Department of Mathematics Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Mathematics Panimalar Engineering College Chennai Tamil Nadu India

ISBN: (数字)9798331513733

ISBN: (纸本)9798331513740

This research investigates the utilization of deep learning methodologies for classifying ocular dis-eases using the ODIR-5K dataset. A tailored convolutional neural network (CNN) architecture is developed to categorize fundus images into five distinct classes: diabetes, glaucoma, cataract, age-related macular de-generation, and normal. Notably, experimental outcomes achieve a 96.32 % accuracy rate, underscoring the effi-cacy of deep learning in ocular disease diagnosis.

关键词： Deep learning Glaucoma Technological innovation Accuracy Systematics Feature extraction Convolutional neural networks Medical diagnosis Optimization Diseases

来源：评论

学校读者我要写书评

暂无评论

Tensile Strength, Cellular Content and Degradation properties in three generations of concentrated growth factors

引用

BMC Oral Health 2025年第1期25卷 1-14页

作者： Alshirah, Akram A. Elnaem, Mohamed H. Al-Ani, Ziad Hudieb, Malik Hamilton, Jeremy Lowry, Deborah McCarron, Paul A. Periodontology Department College of Medicine and Dentistry School of Pharmacy and Pharmaceutical Sciences Faculty of Life & Health Sciences Ulster University Coleraine BT52 1SA United Kingdom School of Pharmacy and Pharmaceutical Sciences Faculty of Life & Health Sciences Ulster University Coleraine BT52 1SA United Kingdom School of Medicine Dentistry & Nursing Glasgow Dental Hospital & School G14 Level 5 378 Sauchiehall Street Glasgow G2 3JZ United Kingdom Department of Advanced Prosthodontics Tokyo Medical and Dental University 1-5-45 Yushima Bunkyo-Ku Tokyo 113-8549 Japan School of Engineering Faculty of Computing Engineering and Built Environment Ulster University 25-51 York Street Belfast BT15 1ED United Kingdom

Background: Concentrated growth factors (CGF) is a biomaterial with regenerative potential, enriched with platelets, leukocytes, growth factors, and fibrin, but it degrades within 2–3 weeks. Albumin extends CGF stability, while silver nanoparticles (SNP) improve its mechanical and antibacterial properties. This in vitro and ex vivo study investigates the impact of albumin (Alb-CGF) and albumin with SNP (Alb-CGF-SNP) on CGF’s mechanical properties, degradation rate, and cellular bioactivity. Methods: Blood samples were collected from 15 healthy volunteers who met specific inclusion criteria, with the sample size determined using G*Power software for power calculation. Three groups were prepared: control CGF, experimental Alb-CGF, and Alb-CGF-SNP. Membranes were produced using a Medifuge MF200 centrifuge and activated plasma albumin gel (APAG) device following standard settings. In experimental groups, the superficial 2.5 ml of plasma layer was heated at 75 °C for 10 min before combining with the buffy coat layer of CGF. Mechanical properties were tested using a texture analyzer, degradation rates were measured by weight loss percentage, and cellular bioactivity was evaluated with a Sysmex hematology analyzer. Data analysis was conducted using GraphPad Prism 8.0. Group differences were assessed via one-way ANOVA and Welch ANOVA, with Tukey’s HSD test for post hoc paired group comparisons. Results: The control (CGF) showed the highest mechanical properties, with Ultimate Tensile Strength (UTS) (95.6 kPa), Modulus of Toughness (55.55 kJ/m³), and Young’s Modulus (75.73 kPa;(P < 0.01). No significant differences were observed in the strain at break across groups (P > 0.90). Alb-CGF-SNP displayed superior degradation resistance, with 45.2% weight loss at day 60 versus 84.2% in CGF (P < 0.01). CGF had the highest WBC and platelet levels, with amounts of 2.25 and 3.11-fold, respectively (P < 0.01). Conclusion: The modification of CGF with albumin and silver nanopa

关键词： Albumin, Silver Nanoparticles (SNP) Biodegradation Cell Count Concentrated Growth Factors (CGF) Tensile Strength

来源：评论

学校读者我要写书评

暂无评论

SmarTeeth: Augmenting Manual Toothbrushing with In-ear Microphones 25

SmarTeeth: Augmenting Manual Toothbrushing with In-ear Micro...

引用

Proceedings of the 2025 CHI Conference on Human Factors in computing Systems

作者： Qiang Yang Yang Liu Jake Stuchbury-Wass Kayla-Jade Butkow Emeli Panariti Dong Ma Cecilia Mascolo Department of Computer Science and Technology University of Cambridge Cambridge United Kingdom Faculty of Dentistry Oral and Craniofacial Sciences King's College London London United Kingdom School of Computing and Information Systems Singapore Management University Singapore Singapore

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：