检索结果-内蒙古大学图书馆

IEEE International Conference on Information Reuse and Integration (IRI)

作者： Danda B. Rawat Dept of Electrical Engineering & Computer Science DoD Center of Excellence in AI/ML Howard University Washington DC USA

ISBN: (数字)9798350351187

ISBN: (纸本)9798350351194

To tackle weaknesses of traditional synchronous federated learning (FL), asynchronous FL has emerged as a solution. However, asynchronous FL also faces challenges, particularly in identifying optimal clients capable of contributing to a global model with minimal latency and loss with high accuracy, while prioritizing information freshness. This paper explores client selection strategies in asynchronous FL that takes account of computing and communication delays, freshness of the data/information being used in generating local models, and the loss while providing the best global model with high efficiency in the contested environment. Furthermore, we present formal mathematical analysis and performance evaluation using numerical results. Results show that the proposed improved asynchronous FL outperforms the other FL approaches.

关键词： Performance evaluation Accuracy Federated learning Computational modeling Data science Numerical models Delays Rough surfaces Faces

来源：评论

学校读者我要写书评

暂无评论

Reactive Multi-agent Coordination using Auction-based Task Allocation and Behavior Trees

Reactive Multi-agent Coordination using Auction-based Task A...

引用

2023 IEEE Conference on Control Technology and Applications, CCTA 2023

作者： Dahlquist, Niklas Lindqvist, Bjorn Saradagi, Akshit Nikolakopoulos, George Luleå University of Technology Robotics and Ai Group Department of Computer Science Electrical and Space Engineering LuleåSE-97187 Sweden

ISBN: (纸本)9798350335446

This article presents an architecture for multi-agent task allocation and task execution, through the unification of a market-inspired task-auctioning system with Behavior Trees for managing and executing lower level behaviors. We consider the scenario with multi-stage tasks, such as 'pick and place', whose arrival times are not known a priori. In such a scenario, a coordinating architecture is expected to be reactive to newly arrived tasks and the resulting rerouting of agents should be dependent on the stage of completion of their current multi-stage tasks. In the novel architecture proposed in this article, a central auctioning system gathers bids (cost-estimates for completing currently available tasks) from all agents, and solves a combinatorial problem to optimally assign tasks to agents. For every agent, it's participation in the auctioning system and execution of an assigned multi-stage task is managed using behavior trees, which switch among several well-defined behaviors in response to changing scenarios. The auctioning system is run at a fixed rate, allowing for newly added tasks to be incorporated into the auctioning system, which makes the solution reactive and allows for rerouting of some agents (subject to the states of the behavior trees). We demonstrate that the proposed architecture is especially well-suited for multistage tasks, where high costs are incurred when rerouting agents who have completed one or more stages of their current tasks. The proposed framework is experimentally validated in multiple scenarios in a lab environment. A video of a demonstration can be found at: https://***/ZdEkoOOlB2g. © 2023 IEEE.

关键词： Cost estimating

来源：评论

学校读者我要写书评

暂无评论

GainS: Gradient Anomaly-aware Biomedical Instance Segmentation

GAInS: Gradient Anomaly-aware Biomedical Instance Segmentati...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Liu, Runsheng Jiang, Hao Zhou, Yanning Lin, Huangjing Wang, Liansheng Chen, Hao Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong Hong Kong Tencent Ai Lab Shenzhen China Imsight Ai Research Lab Shenzhen China Xiamen University Department of Computer Science Xiamen China Hong Kong University of Science and Technology Department of Chemical and Biological Engineering Hong Kong Hong Kong Hkust Shenzhen-Hong Kong Collaborative Innovation Research Institute Shenzhen China

ISBN: (纸本)9798350386226

Instance segmentation plays a vital role in the morphological quantification of biomedical entities such as tissues and cells, enabling precise identification and delineation of different structures. Current methods often address the challenges of touching, overlapping or crossing instances through individual modeling, while neglecting the intrinsic interrelation between these conditions. In this work, we propose a Gradient Anomaly-aware Biomedical Instance Segmentation approach (GainS), which leverages instance gradient information to perceive local gradient anomaly regions, thus modeling the spatial relationship between instances and refining local region segmentation. Specifically, GainS is firstly built on a Gradient Anomaly Mapping Module (GAMM), which encodes the radial fields of instances through window sliding to obtain instance gradient anomaly maps. To efficiently refine boundaries and regions with gradient anomaly attention, we propose an Adaptive Local Refinement Module (ALRM) with a gradient anomaly-aware loss function. Extensive comparisons and ablation experiments in three biomedical scenarios demonstrate that our proposed GainS outperforms other state-of-the-art (SOTA) instance segmentation methods. The code is available at https://***/DeepGainS/GainS. © 2024 IEEE.

关键词： Adaptive Refinement Biomedical Instance Segmentation Gradient Anomaly Touching and Overlapping

来源：评论

学校读者我要写书评

暂无评论

Skin Cancer Classification of Dermoscopic Images using Deep Learning 4

Skin Cancer Classification of Dermoscopic Images using Deep ...

引用

4th International Conference on Advancement in Electronics and Communication engineering, AECE 2024

作者： Madhavi, G Bindu Sumithra, M. Devi, P Yamini Mahalaxmi, U.S.B.K. Saravanan, T. Shaker Reddy, Pundru Chandra Geethanjali College of Engineering and Technology Department of Cse -AI &ml Telangana Hyderabad India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Computer Science and Engineering School of Computing Tamil Nadu Chennai India Computer Science and Engineering Vignana Bharathi Institute of Technology Telangana Hyderabad India Electronics Communication Engineering Aditya University Andhra Pradesh Surampalem India P. S. R. Engineering College Department of Information Technology Tamil Nadu Sivakasi India School of Computer Science and Artificial Intelligence Sr University Telangana Warangal India

ISBN: (纸本)9798350364729

Pigmented skin lesions must be identified in order to detect hazardous skin-related disorders, especially cancer. To improve the correctness of skin cancer recognition, image detection strategies and classification abilities can be utilized. Based on the HAM10000 dataset, which contains 10015 photos, this research paper makes use of the dataset. An augmentation has been carried out on a subset of the dataset in the proposed work. Compared to an approach with &without data augmentation, is more likely to learn unique traits and attributes. To make the model more accurate, data augmentation is often used. However, until the model is strong, it will not be able to produce meaningful results when tested with the testing data. This work's model is robust since it makes use of the k-fold cross-validation technique. Machine learning methods and models from Convolutional Neural Networks have been evaluated for their classification accuracy. After comparing the suggested work's use of several machine learning methods, we found that Convolutional Neural Network produced the best results in terms of accuracy. We achieved a maximum accuracy of 95.53% using the CNN in the suggested setup. Early detection of seven types of skin illness is made easier by the suggested work, which may be authenticated and treated properly by medicinal professionals. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Applying Convolutional Neural Networks for Disease Detection in Crop Images 7

Applying Convolutional Neural Networks for Disease Detection...

引用

7th International Conference on Contemporary Computing and Informatics, IC3I 2024

作者： Dhasmana, Gulshan Al-Jawahry, Hassan M. Deepak, A. Aravind, K. Reddy, R. Akhilesh Yadav, Kanchan Graphic Era Deemed to be University Department of Computer Science & Engineering Dehradun India The Islamic university College of technical engineering Department of computers Techniques engineering Najaf Iraq Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Tamilnadu Chennai India New Horizon College of Engineering Department of Electronics and Communication Engineering Bangalore India Mlr Institute of Technology Department of CSE-AI&ML Telangana Hyderabad India Gla University Department of Electrical Engineering Mathura India

ISBN: (纸本)9798350350067

Ensuring agricultural production and food security relies on the early and precise identification of crop diseases. It may be tedious, error-prone, and time-consuming to use traditional approaches to identify diseases. In this study, we investigate how Convolutional Neural Networks (CNNs) may be used to improve and automate the process of identifying diseases in crop photos. Our approach use deep learning to swiftly and reliably identify and classify a broad variety of agricultural diseases. We trained our CNN model on a diverse dataset that included images of crop leaves in various states of health. The dataset covers a broad variety of common illnesses and numerous kinds of crops, which guarantess that our model is resilient and can be applied to other situations. To avoid overfitting and boost the model's performance, we used sophisticated data augmentation methods. The CNN model surpasses traditional machine learning methods in terms of accuracy, as shown by a significant reduction in false positives and false negatives. The model's capacity to process and analyse images in real-time makes it beneficial in the field of disease management. This research emphasises the possibility of incorporating convolutional neural networks (CNNs) into precision agricultural methods, giving farmers a formidable instrument for early disease detection and prompt response to reduce crop losses. Improving the model's scalability for largescale agricultural applications, adding more disease kinds to the dataset, and increasing the dataset are all areas that will be the focus of future effort. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis of Online Reviews in the Field of Tourism for Hyderabad Popular Places 2

Sentiment Analysis of Online Reviews in the Field of Tourism...

引用

2nd International Conference on Advancements in Smart, Secure and Intelligent Computing, ASSIC 2024

作者： Rani, K. Pushpa Roja, G. Lalitha, E. Deepika, B. Dastagiriah, C. Arshad, Mohammad Mlr Institute of Technology Department of Computer Science and Engineering Hyderabad Dundigal500043 India Department of Computer Science and Engineering Gnits Shaik Pet Hyderabad500104 India and Ai&ds Hyderabad India Anurag University Department of Cse Hyderabad500088 India Deccan College of Engineering and Technology Department of It TS Hyderabad500 001 India

ISBN: (纸本)9798350370188

Nowadays all most all users are using the internet for any information. The main objective of this paper is used to collecting the opinions from customers are useful for both travelers and consultants. Creating a new model of approach is profitable for business organizations and also customer satisfaction. Collecting the opinions, feelings of customer by creating online blogs, forum and website. In this model we developed a new algorithm regarding facilities such as accommodation, weather, number of places to visits, hotels. Based on this analysis the consultants improve their performance to get more profits. This algorithm extracting all features and efficiently classify the given training data by observing more hidden features in the given training data set. © 2024 IEEE.

关键词： Profitability

来源：评论

学校读者我要写书评

暂无评论

Futuristic IoT based Smart Precision Agriculture: Brief Analysis

引用

Journal of Mobile Multimedia 2022年第3期18卷 935-956页

作者： Swamidason, Iwin Thanakumar Joseph Pandiyarajan, Shanthini Velswamy, Karunakaran Leela Jancy, P. Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhrapradesh Vijayawada India Department of Electronics and Communication Engineering Karunya Institute of Technology and Sciences Tamilnadu Coimbatore India Department of Computer Science and Engineering (AI & ML) and (Cybersecurity) Jain University Karnataka Bengaluru India Department of Information Technology Sri Sai Ram Institute of Technology Tamilnadu Chennai India

Agriculture is considered as the backbone of any nation across the globe. With the advent of modern technologies, smart tools and techniques are used in the agriculture/farming to build on the quantity as well as quality of the agriculture production to feed the basic necessity of the humans. Smart technology such as Internet of Things play a vital role in monitoring and analyzing various environmental parameters such as water level, humidity, soil moisture, air quality, UV level, rain etc. which are highly essential to ensure the fruitful yield of any nutritious crops. In this research article, precision agriculture concepts are investigated widely with the focus of improving the productivity level and also the effective utilization of resources with the minimal cost while compared with the conventional methodologies. © 2022 River Publishers.

关键词： Drones Internet of things (IoT) Irrigation Precision agriculture Sensors

来源：评论

学校读者我要写书评

暂无评论

Advanced Deep Learning Approaches for Early Detection of Diabetic Retinopathy in Retinal Images

Advanced Deep Learning Approaches for Early Detection of Dia...

引用

Women in Computing (InCoWoCo), International Conference for

作者： D. Vetrithangam G. Pinki Azra Fathima Naresh Kumar Pegada V. Devi Aparajita Mukherjee Department of Computer Science and Engineering Chandigarh University Mohali India Department of CSE Methodist College of Engineering and Technology Hyderabad India Department of CSE(AI &ML) Vignana Bharathi Institute of Technology Hyderabad India Department of Computer Science and Engineering(AI &ML) Keshav Memorial Engineering College Hyderabad India Department of CSE Hindusthan College of Engineering and Technology Coimbatore India Department of CSE University of Engineering and Management Kolkata India

ISBN: (数字)9798331518943

ISBN: (纸本)9798331518950

Diabetic Retinopathy (DR) is one of the major causes of blindness worldwide and a complication of diabetes. Therefore, early identification and intervention are important to reduce the extent of vision loss and improve prognosis for patients. This paper presents an improved model for screening DR at its initial stage in retinal images using deep learning methods. The developed system employs convolutional neural networks (CNNs) to detect abnormalities in retinal images that indicate early signs of DR, thereby increasing the chances of screening in clinics. The proposed system utilizes large-scale Kaggle DR and Messidor datasets, with an optimized CNN for the analysis of retinal images. To address issues related to variations in image quality and acquisition methods, various data enhancement strategies are incorporated into the model. Additionally, an interpretability module based on Grad-CAM is included to explain the model's classifications and build trust with clinicians. Based on experimental results, it can be concluded that the proposed model demonstrates higher accuracy, sensitivity, and specificity compared to benchmark methods. This system shows potential in reducing the workload of ophthalmologists and improving early DR screening, particularly in resource-limited healthcare settings. Furthermore, it can be extended to other ophthalmic diseases, offering significant benefits to the broader healthcare system.

关键词： Deep learning Diabetic retinopathy Accuracy Computational modeling Blindness Sensitivity and specificity Retina Data models Convolutional neural networks Usability

来源：评论

学校读者我要写书评

暂无评论

Enhanced Breast Cancer Relapse Prediction using Ensemble Learning Techniques 4

Enhanced Breast Cancer Relapse Prediction using Ensemble Lea...

引用

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Tripathi, Mukesh Kumar Ananya, Meka Murthy, V.N.L.N. Shashank, Tumma Reddy, Jale Subash Attaluri, Kaushal Vardhaman college of Engineering Department of Computer Science & Engineering Hyderabad India Vardhaman college of Engineering Department of Information Technology Hyderabad India Pegasystems Worldwide India Pvt Ltd Machine Learning/AI Team Hyderabad India

ISBN: (纸本)9798331540364

Breast cancer remains a significant health concern for women, and accurate prediction of recurrence is vital for effective treatment and improved outcomes. This research investigates the application of advanced ensemble learning techniques to enhance the reliability of breast cancer recurrence predictions. By combining Deep Neural Networks (DNN) and Artificial Neural Networks (ANN) with traditional machine learning methods, the proposed approach demonstrates significant improvements in accuracy, precision, sensitivity, specificity, F1-scores, and areas under the curve (AVCs). The study utilizes two breast cancer relapse datasets, UMCIO and WPBC, to evaluate the performance of the ensemble learning models. The results highlight the effectiveness of the proposed approach in accurately predicting breast cancer recurrence. This research contributes to the advancement of breast cancer diagnosis and treatment by providing a valuable tool for clinicians to assess the risk of recurrence and tailor treatment plans accordingly. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Bridging Horizons in Diabetes Prediction: A Comparative Exploration of Machine Learning and Deep Learning Approaches in Pima Indian Women 2

Bridging Horizons in Diabetes Prediction: A Comparative Expl...

引用

2nd International Conference on Advancement in Computation and computer Technologies, InCACCT 2024

作者： Chandra Sekhar Reddy, L. Gottipalli, Monikadevi Sravanthi, P. Rajanikanth, J. Yalamarthi, Ganesh Gurrapu, Neelima Hyderabad India Sir C R Reddy College of Engineering Department of CSE Eluru India CMR College of Engineering & Technology Department of CSE Hyderabad India S R K R Engineering College Department of CSE Bhimavaram India SIR C R Ramalinga Reddy Polytechnic College Department of AI&ML Eluru India SR University Department of computer science and Artificial intelligence Warangal India

ISBN: (纸本)9798350371314

This study has demonstrated that diabetes prediction models will require powerful machine learning and anomaly detection methodologies in practice. Researchers are exploring novel outlier identification algorithms to enhance predictions. This study has addressed various concerns outlined in prior research. According to this study, diagnostic records, when combined with powerful machine learning such as Adaboost and XGBoost, can offer a precise forecast of the likelihood of diabetes. RNNs also improved deep learning, according to experts. Experts use IQR for the straightened subspace to detect outliers. The stand appears to have a highly positive impact on prediction models. IQR-boosted RNNs outperform XGBoost and AdaBoost in terms of prediction and efficiency. This suggests that combining outlier detection with advanced machine learning could potentially improve diabetes diagnosis and care. The identification of IQR outliers, using RNNs cultivated through iteration with a different line of machine learning, may improve diabetes prediction outcomes. RNN produces better results, with 93% accuracy. The study demonstrated that enhanced machine learning and outlier detection led to improvements in diabetes prediction algorithms. © 2024 IEEE.

关键词： Recurrent neural networks

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：