检索结果-内蒙古大学图书馆

International conference of Electronics, Communication and Aerospace Technology (ICECA)

作者： R Suguna S Deepa T Kanimozhi M Chandru G Arun Harshini M Department of Computer Science and Engineering Bannari Amman Institute of Technology Sathyamangalam Erode Tamilnadu India Department of Computer Technology - PG Kongu Engineering College Perundurai Erode Tamilnadu Department of Artificial Intelligence and Data Science Sri Eshwar College of Engineering Coimbatore Department of Computer Science VET-Institute of Arts and Science (Co-Education) College Erode Department of Computer Science and Engineering School of Computing Vel Tech Rangarajan Dr Sagunthala R&D Institute of Science and Technology Chennai M.Sc (Software Systems) Kongu Engineering College Perundurai Erode Tamilnadu

ISBN: (数字)9798350367904

ISBN: (纸本)9798350367911

Agriculture is the backbone of India’s economy, supporting a large portion of the population and establishing the country as a key global player in food production. India ranks as the second-largest producer of both paddy and wheat. However, agricultural productivity is highly susceptible to various plant diseases, which can significantly reduce crop yields and quality. Paddy, one of the most important staple crops, is particularly vulnerable to diseases caused mainly by viral and bacterial related diseases. The climate conditions are also play a vital role in paddy plant diseases. This research work proposes a deep learning-based approach for early detection and classification of paddy diseases. The proposed research devises a hybrid model that combines the VGG19 and ResNet50 algorithms, the system analyses images of both healthy and disease-affected paddy leaves, sourced from the Kaggle repository. This research focuses on predicting four major paddy diseases that can cause yield losses of up to 80%, and in severe cases, can destroy an entire crop: (i) Paddy Blast, (ii) Bacterial Leaf Blight, (iii) Sheath Blight, and (iv) Ufra Disease. The proposed model achieves a high accuracy rate of 98% in predicting paddy diseases and offers a rapid classification process, showcasing the potential of advanced image processing and deep learning techniques to mitigate the impact of paddy plant diseases on agricultural productivity.

关键词： Deep learning Productivity Plant diseases Microorganisms Accuracy Prediction algorithms Real-time systems Classification algorithms System analysis and design Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

Highly Sensitive Real-Time Detection of Surface Texture Changes

Highly Sensitive Real-Time Detection of Surface Texture Chan...

引用

International Conference on Modern Problems of Radio engineering, Telecommunications and computer Science

作者： Andrii Yarmilko Inna Rozlomii Yuliia Mysiura Department of Automated Systems Software Bohdan Khmelnytsky National University of Cherkasy Cherkasy Ukraine Department of Information Security and Computer Engineering Cherkasy State Technological University Cherkasy Ukraine Department of Information Technologies Bohdan Khmelnytsky National University of Cherkasy Cherkasy Ukraine

ISBN: (数字)9798331520564

ISBN: (纸本)9798331520571

Real-time surface analysis is becoming increasingly important in various fields, including industry, medicine, and transportation. This article examines the problem of remote monitoring of surface texture in real time. The authors review the methods and techniques used for this task, focusing on high-precision technologies such as computer vision, laser scanning, and image processing techniques. The paper examines the importance of this real-time approach to support accurate and rapid decisions in industrial processes and medical diagnostics. The authors propose a method for detecting texture artifacts with machine learning and analyze the performance and quality of possible variations of its application. Based on the discussion, the authors draw conclusions regarding the effectiveness and prospects of the proposed approach in real-time remote monitoring of surface textures. They emphasize the importance of further research in this direction and the use of innovative technologies to improve the accuracy and speed of the monitoring process. This article will be a valuable source of information for scientists, engineers and professionals in the field of industrial control and automation.

关键词： Industries computer vision Sensitivity Accuracy Clustering algorithms Machine learning Real-time systems Surface texture Surface treatment Remote monitoring

来源：评论

学校读者我要写书评

暂无评论

Security and Efficiency Models for Cyber-Physical systems in Medical Devices

Security and Efficiency Models for Cyber-Physical Systems in...

引用

International computer Sciences and Information Technologies (CSIT)

作者： Inna Rozlomii Andrii Yarmilko Serhii Naumenko Department of Information security and computer engineering Cherkasy State Technological University Cherkasy Ukraine Department of Automated Systems Software Bohdan Khmelnytsky National University of Cherkasy Cherkasy Ukraine Department of Information Technologies Bohdan Khmelnytsky National University of Cherkasy Cherkasy Ukraine

ISBN: (数字)9798331542634

ISBN: (纸本)9798331542641

The article explores security and efficiency models applied in cyber-physical systems of medical devices, which are increasingly integrated into the IoT framework. It provides a detailed analysis of key threats to the confidentiality, integrity, and availability of data generated and processed by such devices, considering them as critical components of patient safety. Additionally, the article examines approaches to enhancing the efficiency of medical cyber- physical systems under constraints of limited energy consumption, low computational power, and restricted memory capacity. Solutions are proposed based on the implementation of lightweight cryptographic algorithms, such as lightweight block ciphers and digital signature algorithms, which help reduce energy consumption while ensuring a high level of security. The proposed models aim to ensure the secure processing and transmission of personal medical data, particularly in scenarios of limited network bandwidth and the need to minimize transmission delays. Moreover, the article discusses aspects of the real-time efficient operation of cyber- physical systems, which is critical for the uninterrupted and reliable functioning of medical devices. The article also includes a comparative analysis of existing protection methods and suggests new approaches to improving the overall reliability and efficiency of medical cyber-physical systems.

关键词： Energy consumption Analytical models Medical devices Computational modeling Memory management Cyber-physical systems Real-time systems Encryption Reliability Protection

来源：评论

学校读者我要写书评

暂无评论

Nanoinformatics: Opportunities and challenges in the development and delivery of healthcare products in developing countries 4

Nanoinformatics: Opportunities and challenges in the develop...

引用

4th International Conference on Science and Sustainable Development: Advances in Sciences and Technology for Sustainable Development, ICSSD 2020

作者： Nwankwo, Wilson Ukhurebor, Kingsley Eghonghon Software Engineering and Cyberphysical Systems Unit Department of Computer Science Edo University Iyamho Edo State Nigeria Environmental AndTelecommunication Unit Department of Physics Edo University Iyamho Edo State Nigeria

The world is witnessing sustained effects of information technologies across all works of life. Though some of these influences are markedly negative and detrimental to the socio-economic prospects and progress of the society, the positive effects are often impressive especially where they are integrated for the betterment and greater good of the larger society. One of the fastest growing technologies is nanotechnology. Nanotechnology has numerous prospects and applicability across various sectors ranging from electronics, telecommunications, agriculture and food production, biotechnology and genetics, oil prospecting and production, remote sensing, drug production, to name a few. This novel technology readily finds usefulness and several researches are ongoing, geared at developing new tools and techniques that would improve its acceptance across the concerned domains. It is this quest that has culminated into the ongoing effort in nanoinformatics, an interdisciplinary study and a subdomain of informatics simply regarded as the conscientious application of informatics tools and technologies to the analysis, design and development of systems on the broad spectrum of nanomaterials including their physicochemical and environmental characteristics as well as their interactions, interrelationships, and applications within a given domain. This paper presents a review of some opportunities for individuals, experts, and the society especially in the production of cost-effective nanotechnology-based healthcare products. Notwithstanding the aforesaid opportunities which could be harnessed and sustained in any developing country like Nigeria, this paper identifies and buttresses core challenges that could confront the adoption of good nanoinformatics methodologies. This paper concludes that a developing country (Nigeria in perspective) could benefit from nanoinformatics if there are stronger ties among the key stakeholders involved in healthcare products delivery in the socie

关键词： Developing countries

来源：评论

学校读者我要写书评

暂无评论

Hybrid Convolutional Neural Networks for Enhanced Detection of Mango Leaf Diseases

Hybrid Convolutional Neural Networks for Enhanced Detection ...

引用

Cybernetics, Cognition and Machine Learning Applications (ICCCMLA), IEEE International Conference on

作者： Shweta Bhattacharjee Porna Md Firoz Kabir Md Imran Chowdhury Rana Md Saiful Islam Sajol Tonmoy Roy Mohammad Aman Ullah Khan Md Al Adnan Girigula Durga Bhavani Department of Computer Science and Engineering Ahsanullah University of Science and Technology Dhaka Bangladesh Master’s in Information Technology University of the Cumberlands USA Bachelor of Business Administration International American university Los Angeles California USA Department of Computer Science and Engineering Louisiana State University Louisiana USA Data Analytics & Information Systems Utah State University Logan USA Department of Computer Science and Engineering School of Data and Sciences BRAC University Dhaka Bangladesh Bsc in software engineering Noakhali Science And Technology University School of Computer Science & Engineering (SCOPE) VIT-AP University Amaravati Andhra Pradesh India

ISBN: (数字)9798331505790

ISBN: (纸本)9798331505806

The classification of mango leaf diseases is critical for effective disease management and ensuring high-quality yields in mango cultivation. This paper presents a comprehensive study on using deep learning techniques to classify various mango leaf diseases, leveraging convolutional neural networks (CNNs) and hybrid models. A total of 7,524 images were used in our study. These included 4,000 training samples and 3,524 testing samples. The images were split into eight groups, which were powdery mildew, cutting weevil, anthracnose, bacterial canker, sooty mold, gall midge, healthy, and die back. The suggested method starts with feature extraction using VGG19 and MobileNetB1, then classification using both standalone models (ResNet50V2 + EfficientNetB1 and VGG16 + MobileNetB1). We employed data augmentation techniques like random brightness adjustment, rotation, and flipping to enhance the robustness of the model. We conducted hyperparameter tuning using hyperband and Bayesian optimization to optimize the model’s performance. Experimental results demonstrate that the hybrid models achieved superior performance, with ResNet50V2 and EfficientNetB1 attaining a perfect accuracy of $100 \%$ on the test set. These findings highlight the potential of deep learning techniques to improve the accuracy and reliability of mango leaf disease diagnosis, contributing significantly to the advancement of precision agriculture.

关键词： Deep learning Training Precision agriculture Accuracy Robustness Convolutional neural networks Tuning Optimization Diseases Testing

来源：评论

学校读者我要写书评

暂无评论

Intelligent Synthesis of Individual Rehabilitation Plans for Patients after Joint Endoprosthesis Based on computer Vision Technologies 7

Intelligent Synthesis of Individual Rehabilitation Plans for...

引用

7th International Conference on Information Technologies in engineering Education, Inforino 2024

作者： Arseniev, D.G. Borisov, V.V. Misnik, A.E. Gomzhina, E.A. Shalukhova, M.A. Scientific Innovation Institute 'Mathematical Modeling and Intelligent Control Systems' Peter the Great St. Petersburg Polytechnic University St. Petersburg Russia National Research University 'MPEI' Branch in Smolensk Department of Computer Engineering Smolensk Russia Information Technology Software Inter-State Educational Institution of Higher Education 'Belarusian-Russian University' Mogilev Belarus Early Medical Rehabilitation FSBI 'FCTOE' The Ministry of Health of the Russian Federation Smolensk Russia Inter-State Educational Institution of Higher Education 'Belarusian-Russian University Peter the Great St. Petersburg Polytechnic University Information Technology Software Mogilev Belarus

ISBN: (纸本)9798350371369

The article presents an innovative approach to the rehabilitation process for patients with joint endoprosthetics, focusing on the integration of a specialized software module based on computer vision technologies and the ontological approach. Developed for the Federal Centre for Traumatology, Orthopaedics, and Endoprosthesis in Smolensk, Russia, this system is designed to improve the quality of life for patients by offering personalized rehabilitation plans. The core of the study lies in the application of ontological models and meta-associative graphs for synthesizing individual rehabilitation plans, which streamline the recovery process and reduce the workload on healthcare professionals. This method allows for the processing of large amounts of information, providing detailed conclusions and recommendations for functional correction of the musculoskeletal system. The software utilizes computer vision to analyze patient movement and develop tailored rehabilitation strategies, overcoming the limitations of traditional diagnostic tools like MRI, which may not be suitable for all patients. By incorporating artificial intelligence and augmented reality, the system enhances the accuracy of patient assessments and the effectiveness of rehabilitation plans. Furthermore, the article discusses the application of this technology in the educational process at the Belarusian-Russian University, where students are introduced to cutting-edge software tools that assist in creating personalized rehabilitation plans. This educational integration not only enriches the students' learning experience but also fosters innovation in the development of new applications for computer vision in medical rehabilitation. The ontological approach, combined with modern technology, represents a significant advancement in the management of musculoskeletal system diseases, offering a more efficient, personalized approach to rehabilitation and recovery. © 2024 IEEE.

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

Simple Image-level Classification Improves Open-vocabulary Object Detection

arXiv

引用

arXiv 2023年

作者： Fang, Ruohuan Pang, Guansong Bai, Xiao School of Computer Science and Engineering Beihang University China School of Computing and Information Systems Singapore Management University Singapore State Key Laboratory of Software Development Environment Jiangxi Research Institute Beihang University China

Open-Vocabulary Object Detection (OVOD) aims to detect novel objects beyond a given set of base categories on which the detection model is trained. Recent OVOD methods focus on adapting the image-level pre-trained vision-language models (VLMs), such as CLIP, to a region-level object detection task via, e.g., region-level knowledge distillation, regional prompt learning, or region-text pre-training, to expand the detection vocabulary. These methods have demonstrated remarkable performance in recognizing regional visual concepts, but they are weak in exploiting the VLMs' powerful global scene understanding ability learned from the billion-scale image-level text descriptions. This limits their capability in detecting hard objects of small, blurred, or occluded appearance from novel/base categories, whose detection heavily relies on contextual information. To address this, we propose a novel approach, namely Simple Image-level Classification for Context-Aware Detection Scoring (SIC-CADS), to leverage the superior global knowledge yielded from CLIP for complementing the current OVOD models from a global perspective. The core of SIC-CADS is a multi-modal multi-label recognition (MLR) module that learns the object co-occurrence-based contextual information from CLIP to recognize all possible object categories in the scene. These image-level MLR scores can then be utilized to refine the instance-level detection scores of the current OVOD models in detecting those hard objects. This is verified by extensive empirical results on two popular benchmarks, OV-LVIS and OV-COCO, which show that SIC-CADS achieves significant and consistent improvement when combined with different types of OVOD models. Further, SIC-CADS also improves the cross-dataset generalization ability on Objects365 and OpenImages. Code is available at https://***/mala-lab/SIC-CADS. Copyright © 2023, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

FireXnet: an explainable AI-based tailored deep learning model for wildfire detection on resource-constrained devices

引用

Fire Ecology 2023年第1期19卷 1-19页

作者： Ahmad, Khubab Khan, Muhammad Shahbaz Ahmed, Fawad Driss, Maha Boulila, Wadii Alazeb, Abdulwahab Alsulami, Mohammad Alshehri, Mohammed S. Ghadi, Yazeed Yasin Ahmad, Jawad Faculty of Engineering and Technology Multimedia University Melaka Malaysia School of Computing Engineering and the Built Environment Edinburgh Napier University Edinburgh UK Department of Cyber Security Pakistan Navy Engineering College NUST Karachi Pakistan Robotics and Internet of Things Laboratory Prince Sultan University Riyadh Saudi Arabia RIADI Laboratory National School of Computer Sciences University of Manouba Manouba Tunisia Department of Computer Science College of Computer Science and Information Systems Najran University Najran Saudi Arabia Department of Software Engineering Computer Science Al Ain University Abu Dhabi United Arab Emirates

Forests cover nearly one-third of the Earth’s land and are some of our most biodiverse ecosystems. Due to climate change, these essential habitats are endangered by increasing wildfires. Wildfires are not just a risk to the environment, but they also pose public health risks. Given these issues, there is an indispensable need for efficient and early detection methods. Conventional detection approaches fall short due to spatial limitations and manual feature engineering, which calls for the exploration and development of data-driven deep learning solutions. This paper, in this regard, proposes 'FireXnet', a tailored deep learning model designed for improved efficiency and accuracy in wildfire detection. FireXnet is tailored to have a lightweight architecture that exhibits high accuracy with significantly less training and testing time. It contains considerably reduced trainable and non-trainable parameters, which makes it suitable for resource-constrained devices. To make the FireXnet model visually explainable and trustable, a powerful explainable artificial intelligence (AI) tool, SHAP (SHapley Additive exPlanations) has been incorporated. It interprets FireXnet’s decisions by computing the contribution of each feature to the prediction. Furthermore, the performance of FireXnet is compared against five pre-trained models — VGG16, InceptionResNetV2, InceptionV3, DenseNet201, and MobileNetV2 — to benchmark its efficiency. For a fair comparison, transfer learning and fine-tuning have been applied to the aforementioned models to retrain the models on our dataset. The test accuracy of the proposed FireXnet model is 98.42%, which is greater than all other models used for comparison. Furthermore, results of reliability parameters confirm the model’s reliability, i.e., a confidence interval of [0.97, 1.00] validates the certainty of the proposed model’s estimates and a Cohen’s kappa coefficient of 0.98 proves that decisions of FireXnet are in considerable accordance with t

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Recognition of Unknown Objects for Open-World Object Detection

arXiv

引用

arXiv 2023年

作者： Fang, Ruohuan Pang, Guansong Zhou, Lei Bai, Xiao Zheng, Jin School of Computer Science and Engineering State Key Laboratory of Software Development Environment Jiangxi Research Institute Beihang University China School of Computing and Information Systems Singapore Management University Singapore School of Computer Science and Artificial Intelligence Wuhan University of Technology China

Open-World Object Detection (OWOD) extends object detection problem to a realistic and dynamic scenario, where a detection model is required to be capable of detecting both known and unknown objects and incrementally learning newly introduced knowledge. Current OWOD models, such as ORE and OW-DETR, focus on pseudo-labeling regions with high objectness scores as unknowns, whose performance relies heavily on the supervision of known objects. While they can detect the unknowns that exhibit similar features to the known objects, they suffer from a severe label bias problem that they tend to detect all regions (including unknown object regions) that are dissimilar to the known objects as part of the background. To eliminate the label bias, this paper proposes a novel approach that learns an unsupervised discriminative model to recognize true unknown objects from raw pseudo labels generated by unsupervised region proposal methods. The resulting model can be further refined by a classification-free self-training method which iteratively extends pseudo unknown objects to the unlabeled regions. Experimental results show that our method 1) significantly outperforms the prior SOTA in detecting unknown objects while maintaining competitive performance of detecting known object classes on the MS COCO dataset, and 2) achieves better generalization ability on the LVIS and Objects365 datasets. Code is available at https://***/frh23333/mepu-owod. Copyright © 2023, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Hidden high-risky states identification from routine urban traffic

arXiv

引用

arXiv 2024年

作者： Liu, Shiyan Bai, Mingyang Guo, Shengmin Gao, Jianxi Sun, Huijun Gao, Ziyou Li, Daqing School of Reliability and Systems Engineering Beihang University Beijing100191 China State Key Laboratory of Software Development Environment Beihang University Beijing100191 China Department of Computer Science Rensselaer Polytechnic Institute TroyNY12180 United States School of Systems Science Beijing Jiaotong University Beijing100044 China

One of the core risk management tasks is to identify hidden high-risky states that may lead to system breakdown, which can provide valuable early warning knowledge. However, due to high dimensionality and nonlinear interaction embedded in large-scale complex systems like urban traffic, it remains challenging to identify hidden high-risky states from huge system state space where over 99% of possible system states are not yet visited in empirical data. Based on maximum entropy model, we infer the underlying interaction network from complicated dynamical processes of urban traffic, and construct system energy landscape. In this way, we can locate hidden high-risky states that have never been observed from real data. These states can serve as risk signals with high probability of entering hazardous minima in energy landscape, which lead to huge recovery cost. Our finding might provide insights for complex system risk management. Significance Statement Hidden high-risky states are lethal system states with catastrophic consequences for large-scale complex systems. Existing methods for identifying hidden high-risky states face challenges in routine urban traffic, where over 99% of possible system states are not yet visited in empirical data. Based on large-scale traffic-speed data, we build a least-structured network entropy model that captures intricate traffic interactions. This model can generate the entire state space and help the identification of hidden high-risky states that may lead to extreme events. Our results suggest a new way to provide reliable early warning signals for system breakdown based on critical risk scenarios. Copyright © 2024, The Authors. All rights reserved.

关键词： Large scale systems

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：