检索结果-内蒙古大学图书馆

Deep learning computer vision system for estimating sheep age using teeth images

Connection Science 2025年第1期37卷

作者： Ahmad B. Hassanat Mohammad A. Al-Sarayreh Ahmad S. Tarawneh Mohammad A. Abbadi Khalid Almohammadi Mansoor Alghamdi Maha Alamri Abdulkareem Alzahrani Ghada A. Altarawneh a Faculty of Information Technology Mutah University Karak Jordan b Faculty of Information Technology American University of Madaba Amman Jordan c Department of Computer Science Applied College University of Tabuk Tabuk Saudi Arabia d Department of Systems and Networking Faculty of Computing and Information Al-Baha University Al-Baha Saudi Arabia e Department of Computer Science Faculty of Computing and Information Al-Baha University Al-Baha Saudi Arabia f Faculty of Business Mutah University Karak Jordan

This study explores the use of deep learning neural networks and transfer learning to estimate the age of sheep from their dental images. This is an important aspect of agriculture for meat quality, animal welfare, breeding, and health management. Using cutting-edge techniques, MobileNet, ResNet50, and ResNet102, we compare two deep learning approaches: fine-tuning and feature extraction using the pre-trained version of these models as part of our investigation. We collected 540 images of sheep from nearby farms, concentrating on three age groups: young, middle-aged, and elderly, for the purpose of our study. With an interesting recognition accuracy of 96.9%, the experimental results demonstrate that ResNet102 is the best performer both when fine-tuned and when employing its deep features that are retrieved from its pre-trained version. These findings highlight how cutting-edge machine learning techniques have the potential to completely transform long-standing methods in the sheep sector and pave the way for developing a novel mobile application that improves economic outcomes and cultural conformity concerning sheep age recognition.

关键词： Deep learning convolutional neural networks (CNNs) meat quality animal management smart agriculture sheep age estimation

来源：评论

学校读者我要写书评

暂无评论

Thermal Stability and Fracture Patterns of a Recently Synthesized Monolayer Fullerene Network: A Reactive Molecular Dynamics Study

arXiv

引用

arXiv 2022年

作者： Junior, Luiz Antonio Ribeiro Pereira Júnior, M.L. Giozza, W.F. Tromer, R.M. Galvão, D.S. Institute of Physics University of Brasília Brasília Brazil Department of Electrical Engineering Faculty of Technology University of Brasília Brasília Brazil Center for Computing in Engineering & Sciences Unicamp SP Campinas Brazil Applied Physics Department ‘Gleb Wataghin’ Institute of Physics Unicamp SP Campinas Brazil

New monolayer 2D carbon structures, namely qHPC60 and qTPC60, were recently synthesized by covalently bonding C60 polymers. Here, we carried out Reactive (ReaxFF) molecular dynamics simulations to study the thermodynamic stability and fracture patterns of qHPC60 and qTPC60. Our results showed that these structures present similar thermal stability, with sublimation points of 3898K and 3965K, respectively. qHPC60 and qTPC60 undergo an abrupt structural transition becoming totally fractured after a critical strain threshold. The crack propagation is linear (non-linear) for qHPC60 (qTPC60). The estimated elastic modulus for qHPC60 and qTPC60 are 175.9 GPa and 100.7 GPa, *** Codes 00-XX Copyright © 2022, The Authors. All rights reserved.

关键词： Thermodynamic stability

来源：评论

学校读者我要写书评

暂无评论

Adsorption and reversible detection of toxic halogens gases at room temperature by two-dimensional Al2SSe for occupational sustainability

引用

Materials Today Communications 2024年 39卷

作者： Chang, Yee Hui Robin Yeoh, Keat Hoe Jiang, Junke Yu, Hung Wei Chang, Edward Yi Dee, Chang Fu Tuh, Moi Hua Faculty of Applied Sciences Universiti Teknologi MARA Cawangan Sarawak Sarawak Kota Samarahan94300 Malaysia Jeffrey Sachs Center on Sustainable Development Sunway University No. 5 Jalan Universiti Selangor Bandar Sunway47500 Malaysia Materials Simulation and Modelling Department of Applied Physics Eindhoven University of Technology Eindhoven5612 Netherlands Department of Materials Science and Engineering National Yang Ming Chiao Tung University Hsinchu30010 Taiwan International College of Semiconductor Technology National Yang Ming Chiao Tung University Hsinchu30010 Taiwan Institute of Electronics Engineering National Yang Ming Chiao Tung University Hsinchu30010 Taiwan Selangor Bangi43600 Malaysia College of Computing Informatics & Mathematics Universiti Teknologi MARA Cawangan Sarawak Sarawak Kota Samarahan94300 Malaysia

Current treatment for inhalational halogens poisoning involves providing supportive care, which includes administering humidified oxygen and managing the airway. Since toxic effects of halogens cannot be reversed, sensors with high sensitivity and good reversibility for detecting the relatively lower concentration yet noxious halogens becomes particularly significant and enticing. Herein, the structural and optoelectronic properties of toxic F2 and Cl2 gas molecules adsorbed on highly stable Al2SSe monolayer have been systematically studied by means of first-principles calculations based on density functional theory (DFT). Favorable adsorption sites of said molecules on Al2SSe were carefully examined. The relatively high, negative adsorption energy for F2 and Cl2 indicate that the adsorption process is exothermic and the molecules could be stably adsorbed on Al2SSe monolayer. This characteristic, combined with the substantial charge transfer (0.15–0.55 |e|), drastic change in work function, complete reversibility due to recovery time in 10−1 s scale and distinct optical response, render Al2SSe monolayer a viable option for utilization as either surface work functions transistor or optical chemical resistor for detecting these gases. Pearson correlation coefficient (PCC) analysis of theoretical recovery time and response value indicates that band gap change and electron transfer are the primary influencing factors. Selectivity analysis reveals that common compound forms of halogens and atmospheric molecules such as HF, HCl, N2, O2, H2 and H2O are either physically adsorbed or inert with extremely low adsorption energies on Al2SSe, prompting high F2 and Cl2 selectivity. These outcomes acclaim the exciting prospects of developing Al2SSe monolayer for specific, occupational related ultrahigh-sensitivity F2 and Cl2 sensing nanodevices. © 2024 Elsevier Ltd

关键词： Optical properties

来源：评论

学校读者我要写书评

暂无评论

Identifying factors that affected student enrolment in Additional Mathematics for urban areas of Kuantan district 28

Identifying factors that affected student enrolment in Addit...

引用

28th Simposium Kebangsaan Sains Matematik, SKSM 2021

作者： Chuan, Z.L. Liong, C.-.Y. Yusoff, W.N.S.W. Aminuddin, A.S.A. Tan, E.H. Centre for Mathematical Sciences College of Computing and Applied Sciences Universiti Malaysia Pahang Lebuhraya Tun Razak Pahang DM Gambang Kuantan26300 Malaysia Department of Mathematical Sciences Faculty of Science and Technology Universiti Kebangsaan Malaysia UKM Bangi Selangor DE43600 Malaysia Sekolah Menengah Kebangsaan Semambu Depan Qtrs Loji Air Semambu Pahang DM Kuantan25350 Malaysia

The skilful and qualified Science, technology, Engineering and Mathematics (STEM) workforces are expected to be in high demand in the 21st digital economy. In Malaysia public education system, the principal key to STEM education is Additional Mathematics. However, the statistics depicted that the number of upper secondary students enrolled in Additional Mathematics have been severely delineated. Furthermore, the prerequisite to enrol in STEM and Technical and Vocational Education and Training (TVET) courses in tertiary education is achieving a minimum grade C for Additional Mathematics. Therefore, the principal objective of this article is to identify the significant factors that affected the upper secondary students enrolled in Additional Mathematics using Pearson's chi-square test without Yates continuity correction and unadjusted odds ratio (OR). A validated questionnaire comprised nine potential factors that affected enrolment in additional mathematics was distributed to 389 Form Four students' cohort 2020 from four selected urban government schools to pursue this objective. Based on the finding of this article, several initiatives might be taken by the policymakers, such as the teachers may enhancing and throughout the broad of STEM and TVET careers in the 21st digital economy era, while the students' parents can participate in schools in building the communicating and coordinating mechanism. Consequently, the number of upper secondary enrolled in STEM education might be increased to pipeline the future STEM and TVET human capitals in sustaining and stabilising the national economy in the digital era. © Published under licence by IOP Publishing Ltd.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Applications in Home Improvement Retailer, Koctas

Applications in Home Improvement Retailer, Koctas

引用

Business Analytics for technology and Security (ICBATS), International Conference on

作者： Nahia Mourad Hammad Raza Muhamamd Amjad Muhammed Ubaid Ullah Nouh Sabri Elmitwally College of Engineering & IT British University in Dubai Dubai United Arab Emirates Department of Computer Science National College of Business Administration and Economics Lahore Pakistan School of Computer Science NCBA&E Lahore Pakistan Applied Science Research Center Applied Science Private University Amman Jordan Minhaj University Lahore Paksitan School of Computing and Digital Technology Birmingham City University Birmingham B4 7XG UK Department of Computer Science Faculty of Computers and Artifcial Intelligence Cairo University Giza

It sounds like Koçtaş is a leader in the home improvement sector in Turkey, and they are focused on providing the best service and customer experience possible. They are also actively working to accelerate their digital investments and use their vast amount of customer data to innovate in the industry. One way they are using this data is by collecting and analyzing video camera images using AI. This allows them to detect humans and identify which products and shelves are most viewed in their stores. This information can then be used to optimize store layout and product placement for a better customer experience. Another way Koçtaş is innovating is through the implementation of kiosks that use Natural Language Processing (NLP) to interact with customers. These kiosks can understand and respond to questions asked by customers using AI, providing a more personalized and human-like ***, Koçtaş is using Dynamic Creative Optimization to create personalized advertisements for their customers. This method allows them to optimize the content and format of their ads based on the individual preferences and behavior of their customers, leading to more effective ***, Koçtaş is using technology and data to drive innovation and provide a better customer experience in the home improvement industry.

关键词： Industries Technological innovation Layout Cameras Natural language processing Security Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Semi-automatic construction of word-formation networks (for Polish and Spanish) 11

Semi-automatic construction of word-formation networks (for ...

引用

11th International Conference on Language Resources and Evaluation, LREC 2018

作者： Lango, Mateusz Ševčíková, Magda Žabokrtský, Zdeněk Poznan University of Technology Faculty of Computing Institute of Computing Science United States Charles University Faculty of Mathematics and Physics Institute of Formal and Applied Linguistics Czech Republic

ISBN: (纸本)9791095546009

The paper presents a semi-automatic method for the construction of derivational networks. The proposed approach applies a sequential pattern mining technique in order to construct useful morphological features in an unsupervised manner. The features take the form of regular expressions and later are used to feed a machine-learned ranking model. The network is constructed by applying resulting model to sort the lists of possible base words and selecting the most probable ones. This approach, besides relatively small training set and a lexicon, does not require any additional language resources such as a list of alternations groups, POS tags etc. The proposed approach is applied to the lexeme sets of two languages, namely Polish and Spanish, which results in the establishment of two novel word-formation networks. Finally, the network constructed for Polish is merged with the derivational connections extracted from the Polish WordNet and those resulting from the derivational rules developed by a linguist, resulting in the biggest word-formation network for that language. The presented approach is general enough to be adopted for other languages. © LREC 2018 - 11th International Conference on Language Resources and Evaluation. All rights reserved.

关键词： Morphology

来源：评论

学校读者我要写书评

暂无评论

Security & Privacy Issues in IoT Using Blockchain and ML

Security & Privacy Issues in IoT Using Blockchain and ML

引用

International Conference on Image Information Processing

作者： Muna Muhammad Ahthasham Sajid Gunjan Chhabra Hamed Taherdoost Inam Ullah Khan Keshav Kaushik Engineering and Management Sciences Balochistan University of Information Technology Balochistan Pakistan Faculty of Computing Capital University of Science and Technology Islamabad Pakistan Department of CSE Graphic Era Hill University Dehradun Uttarakhand India Q Minded | Quark Minded Tehnology Inc. University Canada West Vancouver Canada Department of Electronic Engineering School of Engineering and Applied Sciences (SEAS) Isra University Islamabad Campus Pakistan School of Computer Science University of Petroleum and Energy Studies Dehradun India

ISBN: (数字)9798350371406

ISBN: (纸本)9798350371413

As Internet of Things (IoT) devices are being involved in abundant applications, security, and privacy of the IoT users have been of more concern. The security threats are rapidly growing making the solutions of security and privacy not inadequate. Thereby, each thing on the internet can be a point of target for hackers. Accordingly, ML algorithms are utilized for producing accurate outputs by using large and complex databases in which the produced outputs could be used in the prediction and detection of weaknesses in IoT systems. Additionally, BC methods are also being used for providing security and privacy solutions in IoT networks. Many existing studies have been carried out on BC techniques or ML algorithms or both. Though, these existing studies focus on either providing privacy or security issues by using BC techniques or ML algorithms, therefore, give rise to need for aa combined survey on solutions made recently which address both privacy and security issues by using BC techniques and ML algorithms. In this paper, we give a summarized survey of research works that happened in the last four years by addressing privacy and security issues by using BC techniques and ML algorithms in IoT networks. Different literatures have been categorized on privacy and security of BC techniques and ML algorithms in IoT. Then at last, some research challenges and future works are highlighted by using BC techniques and ML algorithms for addressing security and privacy issues in IoT networks.

关键词： Surveys Threat modeling Privacy Databases Computer hacking Information processing Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Application of Kronecker convolutions in deep learning technique for automated detection of kidney stones with coronal CT images

引用

Information Sciences 2023年 640卷

作者： Patro, Kiran Kumar Allam, Jaya Prakash Neelapu, Bala Chakravarthy Tadeusiewicz, Ryszard Acharya, U Rajendra Hammad, Mohamed Yildirim, Ozal Plawiak, Pawel Department of Electronics and Communication Engineering Aditya Institute of Technology and Management AP Tekkali532201 India Department of Electronics and Communication Engineering National Institute of Technology Rourkela Odisha Rourkela769008 India Department of Biotechnology and Medical Engineering National Institute of Technology Rourkela Odisha Rourkela769008 India AGH University of Science and Technology Department of Biocybernetics and Biomedical Engineering Krakow Poland School of Mathematics Physics and Computing University of Southern Queensland Springfield Australia EIAS Data Science Lab College of Computer and Information Sciences Prince Sultan University Riyadh11586 Saudi Arabia Department of Information Technology Faculty of Computers and Information Menoufia University Shibin El Kom32511 Egypt Department of Software Engineering Firat University Elazig Turkey Department of Computer Science Faculty of Computer Science and Telecommunications Cracow University of Technology Warszawska 24 Krakow31-155 Poland Institute of Theoretical and Applied Informatics Polish Academy of Sciences Baltycka 5 Gliwice44-100 Poland

Kidney stone disease is a serious public health concern that is getting worse with changes in diet, obesity, medical conditions, certain supplements etc. A kidney stone also called a renal calculus, is a hard buildup of urine minerals that form in the kidneys. Computed tomography (CT) is one of the imaging models used to identify kidney stones by clinical experts. Due to the low resolution of these images, sometimes detecting kidney stones is tedious with the naked eye, which may lead to false alarms. In this work, a computer-based diagnosis system with a deep learning technique has been developed as a practical solution to aid clinicians in their diagnosis. The traditional convolutional neural network (CNN)-based deep learning technology can detect stones in the kidney. Still, it suffers from the performance and standard implementation of the convolution operations in convolution layers. A Kronecker product-based convolution technique is incorporated in the proposed deep learning architecture to reduce the redundancy in feature maps without convolution overlapping. Our proposed method helps to make the network more effective by extracting abstract and in-depth features from the input images. The publicly available GitHub kidney stone CT scans are utilized to develop the proposed architecture. Our automated model detected kidney stones with an accuracy of 98.56% utilizing CT images. Our system is more effective than the most recent and cutting-edge techniques developed for identifying kidney stones of any size, including the smallest ones. © 2023 The Author(s)

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Classification & Detection of Epilepsy Using IEEG Application

Classification & Detection of Epilepsy Using IEEG Applicatio...

引用

Advance computing and Innovative Technologies in Engineering (ICACITE), International Conference on

作者： R. Kishore Kanna Kapil Joshi Kamreed Udham Singh Ambali Pacholi Mathar Mohideen Nagoor Thangam X.S. Blessing NimaSajai Department of Biomedical Engineering Jerusalem College of Engineering (Autonomous) Chennai India Department of CSE Uttaranchal Institute of Technology Uttaranchal University Dehradun India School of Computing Graphic Era Hill University Adjunct Professor Graphic Era Deemed to be University Dehradun Uttarakhand School of Nursing Science ITM University Gwalior (MP) India Department of Nursing Faculty of Applied Medical Sciences University of Tabuk Saudi Arabia College of Nursing Khamis MushaytKing Khalid University Kingdom Of Saudi Arabia

ISBN: (数字)9798350360165

ISBN: (纸本)9798350360172

More than only cognitive loss and impairment, epileptic seizures may seriously harm one’s intellect. Early seizure detection is essential to minimize the harm caused by their possessions. Presently, medical professionals use optical testing of electroencephalographic (EEG) data for project labeling, which may be a labor-intensive and delayed procedure. By resolving EEG data using the best spatial convolutional interconnected system-long temporary thought (1D CNNLSTM) model, this study offers a revolutionary pattern for always identifying seizures. Before the raw EEG dossier is augmented into a 1D CNN that pulls appearance data from the dossier, it is preprocessed and standardized. Hence, worldly faces are extracted using Long Short-Term Memory (LSTM) layers, which are then combined into various suitably linked coatings for capture recognition. The projected model’s representation was evaluated using the UCI epileptic capture acknowledgment dataset. For the twofold and five-class taking acknowledgment tasks, respectively, the outcomes show an exceptional acknowledgment veracity of 99.39 % and 82.00 %. The predicted model achieved better act when compared to existing machine intelligence setups and additional deep education models. These rulings highlight the promise of the proposed method for accurately diagnosing seizures in patients who are experiencing muscular spasms and acknowledge the potential for improved impartial outcomes.

关键词： Optical losses Optical interconnections Predictive models Brain modeling Electroencephalography Task analysis Spatial resolution

来源：评论

学校读者我要写书评

暂无评论

MSKI-Net: Towards modality-specific knowledge interaction for glioma survival prediction

MSKI-Net: Towards modality-specific knowledge interaction fo...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Ran Su Jin Xiao Hui Cui Ping Xuan Xikang Feng Leyi Wei Qiangguo Jin School of Computer Software College of Intelligence and Computing Tianjin University Tianjin China Department of Computer Science and Information Technology La Trobe University Melbourne Australia Department of Computer Science School of Engineering Shantou University China School of Software Northwestern Polytechnical University China AIDD Faculty of Applied Science Macao Polytechnic University Macao SAR China School of Information Xiamen University Xiamen China Yangtze River Delta Research Institute of Northwestern Polytechnical University Taicang China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Gliomas hold a prominent position in neurooncology due to their high malignancy and poor survival rates. Accurately predicting the prognosis and survival risk of glioma patients is crucial for clinical treatment. Recent advances in survival prediction methods emphasize the importance of integrating complementary information from diverse modalities while neglecting the significant modality gap between pathological images and genomic data. To address this issue, we propose a modality-specific knowledge interaction network (MSKI-Net), which integrates whole slide images (WSI), RNA-Seq gene expression data, and copy number variation (CNV) data for glioma survival analysis. The MSKI-Net consists of a modality-specific feature enhancement (MSFE) module, a modality-interactive cross-attention (MICA) module, and a modality-specific knowledge-guided representation learning (MSKR) module. The three modules collaborate by complementing modality-specific features with modality-agnostic knowledge to improve the learning capability of MSKI-Net. Furthermore, we construct a dataset named TCGA mm , which combines WSI, RNA-Seq, and CNV data from The Cancer Genome Atlas (TCGA) to address the issue of data scarcity. Extensive experiments demonstrate that MSKI-Net achieves superior performance in predicting the survival risk of glioma cancer.

关键词： Knowledge engineering Representation learning Pathology Genomics Prediction methods Data models Gene expression Bioinformatics Prognostics and health management Cancer

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：