检索结果-内蒙古大学图书馆

1st International Conference on computer, Power and Communications, ICCPC 2022

作者： Sangeetha, K. Gokulakrishnan, D. Sridhar, J. Shanthi, N. Vijayalakshmi, C. Muthamizhan, T. Panimalar Engineering College Department of Computer Science and Engineering India Sri Sairam Institute of Technology Department of Information Technology India Siddharth Institute of Engineering and Technology Department of Computer Science and Engineering India Sri Sairam Institute of Technology Department of Electrical and Electronics Engineering India

ISBN: (纸本)9798350397840

Gastric cancer is perhaps the most widely recognized harmful cancers with unfortunate prognostic outcome. Endoscopic assessment is primarily used for early recognition, while obsessive affirmation and computed tomography scanning are proposed for additional treatment. Gastric cancer growth stays as one of the dangerous cancers with unfortunate forecast. The overall lack of pathologists offers a one kind of chance for the utilization of artificial intelligence assistance system to help frameworks to ease the responsibility and increment diagnostic accuracy. Most gastric cancer shows hereditary instability, either micro satellite precariousness or chromosomal precariousness, which is viewed as an early stage in gastric carcinogenesis. Contemporary classification of gastric cancer in view of histological highlights, genotypes and subatomic phenotypes assists better with understanding the qualities of each subtype, and work on early analysis, anticipation and treatment. This task fosters a strategy utilizing deep learning algorithms to anticipate the health issues like ulcer, heartburn, indigestion and nausea which includes various tests to show up the end. Progressed algorithm, MIFNET is utilized to precisely analyze the presence of illness efficiently. MIFNET is a aggregation of three distinct algorithm, called as multi task net, fusion net and global net, the aggregation of which gives precise expectation of gastric cancer without any further diagnosis. A web application utilizes *** will be produced for getting the contribution from the client and then showing the anticipated outcome. Hence, this proposed system helps in powerful determination of gastric cancer with greater accuracy than the existing system. Subsequently, this proposed work helps in successful analysis of Gastric Cancer in various parts of the stomach with greater accuracy than the existing system. © 2022 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Strategy for Rapid Diabetic Retinopathy Exposure Based on Enhanced Feature Extraction Processing

引用

computers, Materials & Continua 2023年第6期75卷 5597-5613页

作者： V.Banupriya S.Anusuya Department of Computer Science and Business Systems M.Kumarasamy College of EngineeringKarur639113TamilnaduIndia Department of Information Technology Saveetha School of EngineeringSaveetha Institute of Medical and Technical SciencesSIMATSChennai602117Tamil NaduIndia

In the modern world,one of the most severe eye infections brought on by diabetes is known as diabetic retinopathy(DR),which will result in retinal damage,and,thus,lead to *** retinopathy(DR)can be well treated with early *** fundus images of humans are used to screen for lesions in the ***,detecting DR in the early stages is challenging due to the minimal ***,the occurrence of diseases linked to vascular anomalies brought on by DR aids in diagnosing the ***,the resources required for manually identifying the lesions are ***,training for Convolutional Neural Networks(CNN)is more *** proposed research aims to improve diabetic retinopathy diagnosis by developing an enhanced deep learning model(EDLM)for timely DR identification that is potentially more accurate than existing CNN-based *** proposed model will detect various lesions from retinal images in the early ***,characteristics are retrieved from the retinal fundus picture and put into the EDLM for *** dimensionality reduction,EDLM is ***,the classification and feature extraction processes are optimized using the stochastic gradient descent(SGD)*** EDLM’s effectiveness is assessed on the KAG-GLE dataset with 3459 retinal images,and results are compared over VGG16,VGG19,RESNET18,RESNET34,and *** results show that the EDLM achieves higher average sensitivity by 8.28%for VGG16,by 7.03%for VGG19,by 5.58%for ResNet18,by 4.26%for ResNet 34,and by 2.04%for ResNet 50,respectively.

关键词： Diabetic retinopathy deep learning classification retinal fundus

来源：评论

学校读者我要写书评

暂无评论

Chicken Swarm Optimization with Deep Learning Based Packaged Rooftop Units Fault Diagnosis Model

引用

computer Systems science & Engineering 2023年第10期47卷 221-238页

作者： G.Anitha N.Supriya Fayadh Alenezi E.Laxmi Lydia Gyanendra Prasad Joshi Jinsang You Department of Electronics and Instrumentation Engineering B.S.Abdur Rahman Crescent Institute of Science and TechnologyChennai600048India Department of Computer Science and Engineering University Institute of Engineering and Technology(UIET)Guru Nanak UniversityHyderabadIndia Department of Electrical Engineering College of EngineeringJouf UniversitySaudi Arabia Department of Computer Science and Engineering Vignan’s Institute of Information TechnologyVisakhapatnam530049India Department of Computer Science and Engineering Sejong UniversitySeoul05006Korea Seculayer Company Ltd.Seoul04784Korea

Rooftop units(RTUs)were commonly employed in small commercial buildings that represent that can frequently do not take the higher level maintenance that chillers *** detection and diagnosis(FDD)tools can be employed for RTU methods to ensure essential faults are addressed *** this aspect,this article presents an Optimal Deep Belief Network based Fault Detection and Classification on Packaged Rooftop Units(ODBNFDC-PRTU)*** ODBNFDC-PRTU technique considers fault diagnosis as amulti-class classification problem and is handled usingDL *** fault diagnosis in RTUs,the ODBNFDC-PRTU model exploits the deep belief network(DBN)classification model,which identifies seven distinct types of *** the same time,the chicken swarm optimization(CSO)algorithm-based hyperparameter tuning technique is utilized for resolving the trial and error hyperparameter selection process,showing the novelty of the *** illustrate the enhanced performance of the ODBNFDC-PRTU algorithm,a comprehensive set of simulations are *** comparison study described the improvement of the ODBNFDC-PRTU method over other recent FDD algorithms with maximum accuracy of 99.30%and TPR of 93.09%.

关键词： Rooftop units chicken swarm optimization hyperparameter metaheuristics deep learning fault diagnosis

来源：评论

学校读者我要写书评

暂无评论

Classification of Hidden Patterns in Cancer Genome using Deep Learning 4

Classification of Hidden Patterns in Cancer Genome using Dee...

引用

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Balamurugan, K.S. Navaneethakrishnan, Sundara Rajulu Srinivasulu, Senduru Kumutha, D. Surendran, R. Kalyani, G. Karpaga Vinayaga College of Engineering and Technology Department of Electronics and Communication Engineering Tamil Nadu Chengalpattu India Dhanalakshmi Srinivasan University Trichy Department of Computer Science and Engineering Samayapuram Campus Tiruchirappalli India Sathyabama Institute of science and Technology School of Computing Department of Computer Science and Engineering Chennai600119 India Jeppiaar Institute of Technology Department of Electronics and Communication Engg. Tamilnadu Sriperumbudur India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Chennai602105 India RuralCare Innovators Llp Tamil Nadu Madurai India

ISBN: (纸本)9798331540364

The complex structures in cancer genomes are obtained through the revolution of high-throughput technology. The major challenge involves the interpretation of complex sceneries of genomic alterations with the impact of diagnosis and prognosis. The proposed system includes deep-learning techniques that provide optimum solutions for evaluating hidden patterns of the cancer genome. They help to extract important information such as mutation and detection of therapeutic targets. The proposed system involves the aid of a Convolutional Neural Network, Recurrent Neural Network with Long Short Term Memory networks. They help in obtaining intricate genomic data. This is achieved through the spatial relationship and sequential dependencies within the genetic elements. The large-scale genomic datasets are trained which helps to learn the differentiation between the driver and passenger mutations. The genetic alterations provide information regarding the cancer progression. The deep learning model helps in the identification of desperate mutations with exclusive patterns that contribute to tumor development. The important aspect involves the prediction of prognosis. This includes the model to train and learn from the cumulative knowledge of patients in accordance with the genomic profiles. An accurate prognosis and personalized treatments are obtained by analyzing certain parameters such as gene expression, gene mutation and clinical data structures. These optimization techniques help in the identification of complex relationships in the identification of therapeutical compounds. © 2024 IEEE.

关键词： Genome

来源：评论

学校读者我要写书评

暂无评论

Sim-to-Real Grasp Detection with Global-to-Local RGB-D Adaptation

Sim-to-Real Grasp Detection with Global-to-Local RGB-D Adapt...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Haoxiang Ma Ran Qin Modi Shi Boyang Gao Di Huang State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University Beijing China Geometry Robotics and the School of Computer Science and Technology Harbin Institute of Technology Harbin China

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

This paper focuses on the sim-to-real issue of RGB-D grasp detection and formulates it as a domain adaptation problem. In this case, we present a global-to-local method to address hybrid domain gaps in RGB and depth data and insufficient multi-modal feature alignment. First, a self-supervised rotation pre-training strategy is adopted to deliver robust initialization for RGB and depth networks. We then propose a global-to-local alignment pipeline with individual global domain classifiers for scene features of RGB and depth images as well as a local one specifically working for grasp features in the two modalities. In particular, we propose a grasp prototype adaptation module, which aims to facilitate fine-grained local feature alignment by dynamically updating and matching the grasp prototypes from the simulation and real-world scenarios throughout the training process. Due to such designs, the proposed method substantially reduces the domain shift and thus leads to consistent performance improvements. Extensive experiments are conducted on the GraspNet-Planar benchmark and physical environment, and superior results are achieved which demonstrate the effectiveness of our method. Code is available at https://***/mahaoxiang822/GL-MSDA.

关键词： Training Codes Pipelines Prototypes Benchmark testing Robustness Robotics and automation

来源：评论

学校读者我要写书评

暂无评论

From Detection to Severity Estimation: A Unified CNN-SVM Strategy for Taro Leaf Blight Disease 3

From Detection to Severity Estimation: A Unified CNN-SVM Str...

引用

3rd International Conference on Technological Advancements in Computational sciences, ICTACS 2023

作者： Suryavanshi, Ankita Kukreja, Vinay Hariharan, Shanmugasundaram Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Vardhaman College of Engineering Department of Computer Science and Engineering Hyderabad India

ISBN: (纸本)9798350342338

A serious threat to the world's agricultural sector is the leaf blight disease that can affect a wide variety of plants, especially taro (Colocasia esculenta). Utilizing Deep learning techniques such as Convolutional neural networks, Support Vector Machines (SVMs), and artificial neural networks (ANNs), researchers provide a comprehensive strategy in this article for detecting leaf blight disease in Taro plants. The study focuses on Phytophthora colocasia-caused taro leaf blight particularly. To create a strong dataset, the authors gathered a wide range of taro leaf images that depicted different levels of leaf blight. Researchers used data augmentation strategies to improve model generalization in response to data shortage issues. To standardize the image set and enhance feature extraction, additional preprocessing techniques such as image scaling, color uniformity, and noise reduction were used. Farmers and agricultural professionals will profit from the suggested technique, which provides a dependable tool for disease surveillance and intervention. It offers a potentially effective way to address issues with precision farming. Moreover, by utilizing machine learning, this strategy expands crop resilience, promotes sustainable farming methods, and improves food security in areas that depend on taro cultivation and beyond. This research, if put into practice well, might lead to significant improvements in the detection and management of diseases and bring about revolutionary shifts in agricultural methods worldwide. © 2023 IEEE.

关键词： CNN image preprocessing Leaf blight precision SVM

来源：评论

学校读者我要写书评

暂无评论

Identification of risk genes and biological pathways influencing myopia via transcriptome association study and biomedical ontology methods

Identification of risk genes and biological pathways influen...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Shizheng Qiu Yadong Wang Ying Zhang Yang Hu School of Computer Science and Technology Harbin Institute of Technology Harbin China Beidahuang Industry Group General Hospital Harbin China

Refractive error remains one of the most common eye diseases in the world, which causes great burden on public health and economy every year. Although genome-wide association studies (GWAS) have identified susceptibility loci for refractive error, the credible causal genes associated with gene expression in brain are still unclear. In addition, the influence of RNA splicing events on refractive error in brain remains unknown. Here, we identified candidate refractive error gene targets and biological pathways. In stage 1, we carried out gene-based association analysis to identify refractive error risk genes. In stage 2, by using transcriptome-wide association studies (TWAS) and colocalization analysis, we identified cis-regulated genes in brain tissues that were positively related to refractive error from the whole gene region and the exon region after RNA splicing, respectively. In stage 3, we reveal biological pathways influencing refractive error using biological ontology and knowledge base methods. We identified 367 risk genes passed gene-based association test. A total of 43 genes in brain could be considered as causal genes using TWAS and colocalization analysis, and 27 were novel. After RNA splicing, RCBTB1 significantly affected refractive error. Risk genes for refractive error significantly enriched in biological processes related to synaptic transmission and acetylcholine. In conclusion, our analysis provides a better understanding of potential therapeutic targets and biological pathways for refractive error.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development of Healthcare Monitoring System with Pollution Control in Industrial Sectors Using the Internet of Things 5

Development of Healthcare Monitoring System with Pollution C...

引用

5th International Conference on Inventive Research in Computing Applications, ICIRCA 2023

作者： Rajeswari, N Raja Arunkumar, G. Vadivu, M Senthil Gupta, Manish Sethuraman, R. Rajkumar, M. Saveetha Engineering College Department of Mechanical Engineering Tamil Nadu Chennai India Madanapalle Institute of Technology and Science Department of Computer Science and Engineering Andhra Pradesh Madanapalle India Sona College of Technology Department of Electronics and Communication Engineering Tamil Nadu Salem India Lovely Professional University Division of Research and Development Punjab Phagwara India Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu Chennai India School of Information Technology & Engineering Vellore Institute of Technology Vit University Department of Smart Computing Tamil Nadu Vellore India

ISBN: (纸本)9798350321425

Rapid improvement in industrialization and urbanization leads to various impacts on environmental conditions. This leads to a rise in pollution that causes various constraints on human health. Earlier prediction and maintenance of pollution is the solution to obtain a greener ecosystem. This is done through machine learning techniques adopting the Internet of Things. The Internet of Things helps to obtain a smarter environment through real-time monitoring with the control system. Thus machine learning helps to analyze the amount of toxic substances that are emitted from the industries and recorded periodically. They are represented as online controlling and monitoring systems. The sensors and actuators with control devices are used to record the external environmental conditions. The prior intimation of the healthcare is monitored appropriately and intimated to solve earlier. The classification and detection of infections and diseases are done through image processing techniques. Thus the proposed system helps to obtain automatic detection of healthcare and pollution detection systems through machine learning with computational systems. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Development of a Virtual Reality Model Using Digital Twin for Real-Time Data Analysis

引用

SN computer science 2023年第5期4卷 1-12页

作者： Sahoo, Santosh Kumar Nalinipriya, G. Srinivasan, P. Santhosh Ramesh, J.V.N. Ramamoorthy, K. Soleti, Navya Department of EIE CVR College of Engineering Telangana Hyderabad India Department of IT Saveetha Engineering College Tamil Nadu Chennai India Department of Mathematics Panimalar Engineering College Tamil Nadu Chennai India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram A.P. Guntur India Department of ECE PSNA College of Engineering and Technology Dindigul 624622 India Computer Science and Information Technology MLR Institute of Technology Hyderabad India

Digital Twin (DT) machining technology enables real-time monitoring of machining operations, ensuring precision in the process. The virtual–real separation display method utilizes advanced DT systems, but it hinders the effective transmission of essential data to local technicians, thereby limiting the utilization of field processing supported by DT systems. Augmented Reality (AR) is employed to address the issue of monitoring the machining process, which is facilitated by a DT system. First, a dynamic multi-view for AR is created by incorporating data from various sources. Second, ongoing observation of the intermediate processing in AR promotes collaboration between the DT machining system and operators, particularly for complex products, preventing irreparable errors when the final product is nearly complete. The framework includes a module for data representation and detailed explanations are provided for the modules focused on data management and data organization. In a case study, the application of cutting tool wear prediction demonstrates the feasibility and the effectiveness of the proposed method for data construction. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Augmented reality Digital twin Implementation Machining technology Monitoring

来源：评论

学校读者我要写书评

暂无评论

Exploring the Potential of AI-Driven Systems for Automating Data science

Exploring the Potential of AI-Driven Systems for Automating ...

引用

2023 IEEE International Conference on Paradigm Shift in Information Technologies with Innovative Applications in Global Scenario, ICPSITIAGS 2023

作者： Srivastava, Adarsh Katyal, Ashu Srisainath, R. Kshirsagar, Pranali S. Singh, Akhilendra Pratap Rajesh, A. Vivekananda Global University Department of Computer Science & Engineering Jaipur India Centre of Interdisciplinary Research in Business and Technology Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Prince Shri Venkateshwara Padmavathy Engineering College Department of Mechanical Engineering Chennai India Vishwakarma Institute of Information Technology Department of Computer Engineering Pune India Maharishi School of Engineering and Technology Maharishi University of Information Technology UP India Faculty of Engineering and Technology Department of Computer Science Engineering Karnataka Bangalore India

ISBN: (纸本)9798350329773

this paper discusses the capacity of artificial intelligence (AI)-pushed structures for automating records technological know-how duties including records cleaning, function engineering, and version improvement. We argue that those systems provide a promising opportunity to automate the hard work-extensive and time-ingesting venture of data technological know-how, enabling records scientists to recognition on the more creative factors of the paintings. We begin by using offering a brief evaluation of AI and its capacity packages after which study the existing AI-driven data technology gear on the market. We then describe a few revolutionary applications of AI and discuss their capability to improve existing facts technology approaches. Ultimately, we talk the demanding situations and barriers of AI-driven structures and advocate approaches to address them. We finish by using emphasizing the importance of responsibly integrating AI into the statistics science field and highlighting the capacity of collaboration between AI and facts technological know-how specialists. © 2023 IEEE.

关键词： technology transfer

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：