The exploration of deep learning techniques for multimodal predictive maintenance in automated production lines is undertaken, presenting a hybrid model that synergizes Convolutional Neural Networks (CNNs) for visual ...
详细信息
With the help of machinelearning, a winning Formula One (F1) race prediction model is what this project hopes to create. The model is trained using historical data from F1 races, such as lap times, sector times, qual...
详细信息
Federated learning (FL) has been widely used in edge computing that enables artificial intelligence at the network edge as a distributed machinelearning paradigm. In contrast to traditional cloud-based distributed tr...
详细信息
ISBN:
(纸本)9798350358261;9798350358278
Federated learning (FL) has been widely used in edge computing that enables artificial intelligence at the network edge as a distributed machinelearning paradigm. In contrast to traditional cloud-based distributed training, the heterogeneity in edge computing may cause federated learning taking long training time. In this paper, we adapt control parameter (i.e., local epoch size) across devices to minimize wall-clock convergence time with joint consideration of resource heterogeneity and statistical heterogeneity. To analyze the influence of statistical heterogeneity, we derive a convergence upper bound for synchronous FL algorithm and establish the relationship between the number of training rounds and local epoch size under heterogeneous data distribution. Based on the convergence bound, we can solve the non-convex problem of minimizing FL training time with accuracy constraint and obtain near-optimal local epoch size. We develop a scheduling algorithm that estimates the statistical heterogeneity in initial training rounds and subsequently guides adaptive local training across devices. Practically, we evaluate our algorithm in a variety of heterogeneous scenarios. Extensive simulation results demonstrate that our algorithm performs high convergence speed over wall-clock time and spends less time reaching target accuracy compared with benchmark approaches.
Around the world, diabetes is a common chronic (long-lasting) disease. One of the best approaches to analyzing early-stage symptoms is machinelearning. This paper proposed an approach to predict diabetes type 2 form ...
详细信息
The proceedings contain 39 papers. The special focus in this conference is on Cognitive computing and Cyber Physical Systems. The topics include: Drug Recommendations Using a Reviews and Sentiment Analysis by RNN;opti...
ISBN:
(纸本)9783031488870
The proceedings contain 39 papers. The special focus in this conference is on Cognitive computing and Cyber Physical Systems. The topics include: Drug Recommendations Using a Reviews and Sentiment Analysis by RNN;optimizing Real Estate Prediction - A Comparative Analysis of Ensemble and Regression Models;estimation of Power Consumption Prediction of Electricity Using machinelearning;medical Plants Identification Using Leaves Based on Convolutional Neural Networks;An Efficient Real-Time NIDS Using machinelearning Methods;Maixdock Based Driver Drowsiness Detection System Using CNN;A Novel Approach to Visualize Arrhythmia Classification Using 1D CNN;exploring machinelearning Models for Solar Energy Output Forecasting;the Survival Analysis of Mental Fatigue Utilizing the Estimator of Kaplan-Meier and Nelson-Aalen;an Optimized Ensemble machinelearning Framework for Multi-class Classification of Date Fruits by Integrating Feature Selection Techniques;EEMS - Examining the Environment of the Job Metaverse Scheduling for Data Security;text Analysis Based Human Resource Productivity Profiling;a Novel Technique for Analyzing the Sentiment of Social Media Posts Using Deep learning Techniques;comparative Analysis of Pretrained Models for Speech Enhancement in Noisy Environments;Use of Improved Generative Adversarial Network (GAN) Under Insufficient Data;unraveling the Techniques for Speaker Diarization;LUT-Based Area-Optimized Accurate Multiplier Design for Signal Processing Applications;speaker Recognition Using Convolutional Autoencoder in Mismatch Condition with Small Dataset in Noisy Background;face Emotion Recognition Based on Images Using the Haar-Cascade Front End Approach;textRank – Based Keyword Extraction for Constructing a Domain-Specific Dictionary;harmonizing Insights: Python-Based Data Analysis of Spotify's Musical Tapestry;Enlighten GAN for Super-Resolution Images from Surveillance Car.
The medical profession currently faces a number of difficult problems, such as rising medicine and therapy costs, and society requires particular major reforms in this field. Pharmaceutical goods may now be produced w...
详细信息
The advent of COVID-19 highlights the need for big data-driven medical applications, the Internet of Medical Things, and smart healthcare. The biological information collected is strictly private. This enormous quanti...
详细信息
Deep learning falls within the realm of artificial intelligence as a subset of machinelearning. It plays a crucial role in our everyday lives. The field of Deep learning has expanded significantly in recent years and...
详细信息
machinelearning aims to extract hidden information that is present in the data using knowledge of current data on a certain subject. We can achieve machinelearning and predict results for unknown data by using speci...
详细信息
Leaf diseases can have a considerable influence on crop production and food security. Therefore, it's crucial to detect and diagnose these diseases early to prevent their spread and minimize yield losses. Image pr...
详细信息
暂无评论