Poultry productions have shifted towards larger farms and often cluster in certain regions. However, many of the smaller farms with a considerable amount of production are not considered concentrated animal feeding op...
详细信息
Most of the recent works on Human Gesture Recognition (HGR) using motion data rely on gathering a dataset, that faces two major challenges: $a)$ the datasets are originally stored on the smart devices at the end-users...
详细信息
ISBN:
(数字)9798350315790
ISBN:
(纸本)9798350315806
Most of the recent works on Human Gesture Recognition (HGR) using motion data rely on gathering a dataset, that faces two major challenges: $a)$ the datasets are originally stored on the smart devices at the end-users, and gathering them in one place is not feasible due to communication limitations, and $b)$ clients are reluctant to share their private data with a central server due to privacy concerns. In this paper, we address these issues and propose a privacy-preserving framework based on Federated Learning (FL) for HGR using motion data. Furthermore, we consider data heterogeneity which have destructive effects on the performance of the global model. Accordingly, we propose a communication and computation-efficient client selection method, mitigating the impact of data heterogeneity in the FL process. In the proposed framework, clients are not requested to share sensitive information about their local datasets with the edge server. Simulation results show that the proposed MoFLeuR algorithm improves the performance of the global model in the presence of different degrees of data heterogeneity, and it outperforms the baseline algorithms in terms of different metrics, namely accuracy, convergence speed, and communication and computation efficiency.
This work considers the synthesis of state feedback controllers established as deep artificial feed-forward neural networks for the control of discrete-time nonlinear but input-affine systems. The idea is to design ou...
This work considers the synthesis of state feedback controllers established as deep artificial feed-forward neural networks for the control of discrete-time nonlinear but input-affine systems. The idea is to design output layers of particular structure to guarantee the satisfaction of state constraints in form of control-invariant ellipsoids. Since an analytical expression can be derived for the resulting neural network controller, the latter can be stored and evaluated efficiently. Moreover, the proposed output layer guarantees the satisfaction of the considered state constraints for each specification of the parameter vector. Numerical examples are provided for illustration and evaluation of the approach, in which the approximation of a nonlinear model predictive control law is considered as application.
technology for motor rehabilitation faces challenges in uncontrolled settings, such as at home. In these real-world scenarios, robust signals like electromyographic (EMG) and inertial measurement unit (IMU) data are c...
详细信息
The COVID-19 pandemic among other radical changes it imposed onto our typical way of living, working, and interacting, established online education in both synchronous and asynchronous forms. This in many cases has gi...
详细信息
Machine learning is an extremely efficient technique for solving complex problems without the use of traditional programming but rather enabling machines to learn from an input of data and train them to cope with vari...
详细信息
Annotated images are required as ground truth for deep learning. Bacterial segmentation is requires a lot of time and effort when done manually. The autosegmentation task gets more challenging since bacterial images c...
详细信息
ISBN:
(数字)9798350319545
ISBN:
(纸本)9798350319552
Annotated images are required as ground truth for deep learning. Bacterial segmentation is requires a lot of time and effort when done manually. The autosegmentation task gets more challenging since bacterial images contain low light properties, which have an important effect on auto annotating tasks. In order to solve this issue, we present a system that includes a fuzzy-based clustering method that enhances bacterial object segmentation performance by utilizing the multicluster idea. The State Transform Algorithm (STA) is used to obtain starting centroids in order to increase stability, because the Kernel of Intuitionistic Fuzzy C- Means (KIFCM) is sensitive to starting centroids and hence sensitive to being stuck in local optima. The accuracy of KIFCM-STA with bicluster is poor in low-light images. To boost performance, the multicluster technique (MKIFCM-STA) is presented as a continuation hybrid of KIFCM-STA. This framework allows for the ideal amount of clusters (Silhouette) and cluster ranking to provide clusters containing bacterial objects (Topsis). In order to compare our method against.four prior approaches (IFCM, KFCM, KIFCM, and KIFCM-STA), we compare its qualitative aspects (visualization of images) and quantitative aspects (average IOU, Dice, HD, ASD, and Accuracy). In low light image clustering tasks, our model significantly improves and achieves great results in terms of accuracy, with a score of 89.438%. This accomplishment highlights how crucial it is that our framework tackles the problem of low-light image clustering in images of bacteria, eventually improving the image auto-annotation procedure.
In the era of modern agriculture, real-time monitoring of soil conditions is crucial for increasing productivity and efficiency. This research proposes an agricultural soil monitoring system that utilizes the AWS Clou...
详细信息
ISBN:
(数字)9798350365191
ISBN:
(纸本)9798350365207
In the era of modern agriculture, real-time monitoring of soil conditions is crucial for increasing productivity and efficiency. This research proposes an agricultural soil monitoring system that utilizes the AWS Cloud platform to capture, analyze, and present real-time soil data. This system is designed to integrate various sensors that can measure humidity, pH, temperature and soil nutrients, all connected via the Internet of Things (IoT). The data collected by these sensors is sent to the AWS Cloud, where it is processed using cloud computing services such as AWS Lambda and Amazon EC2. The use of the AWS Cloud enables high scalability, reliability, and data security, and facilitates big data analysis using Amazon S3 and Amazon RDS. By using an intuitive dashboard, farmers can see soil analysis results in real-time and make informed decisions based on the data. Additionally, this system is equipped with machine learning algorithms that run on the AWS Cloud to predict soil needs and provide optimal fertilizer recommendations. This research shows how implementing AWS Cloud in agriculture can bring digital transformation to agriculture, enabling farmers to increase crop yields while reducing waste and operational costs.
Given a set of bus stops and a set of employees, the commuting bus routing problem with latest arrival time constraint (CBRP-LATC) aims to determine routes of buses to carry every employee from the company to one of t...
详细信息
The growth of e-commerce has altered how consumers shop, providing a digital space where convenience, vast product offerings, and competitive pricing converge. In today’s world, e-commerce websites are transitioning ...
The growth of e-commerce has altered how consumers shop, providing a digital space where convenience, vast product offerings, and competitive pricing converge. In today’s world, e-commerce websites are transitioning from traditional search-driven methods to customized and intuitive approaches via product suggestions. Product recommendation systems are vital in e-commerce, from bringing new business to retaining existing ones. Our three-part recommendation system is designed so that new users have a great and engaging experience as the Product Popularity -Based System shows them carefully chosen products that are in demand. Collaborative Filtering Recommendations are highly personalized recommendations given to people who have already made their first purchases based on their prior actions and preferences. The K-Means Clustering-Based Recommendation System uses textual clustering analysis to deliver contextually relevant recommendations. We use a variety of evaluation metrics, such as click-through rates, user engagement, and the Silhouette Score, to assess the effectiveness and accuracy of our recommendation systems. Our findings show significant increases in user engagement, conversion rates, and relevant recommendations. Our findings demonstrate the transformative power of well-designed recommendation systems, which improve user experiences and retention and provide invaluable solutions for businesses entering the e-commerce space. This paper provides an in-dept. examination of the multifaceted landscape of e-commerce recommendations, shedding light on their far-reaching implications for customer acquisition and retention in this dynamic digital era.
暂无评论