This research aimed to develop a 3D Faster-R-CNN model for detecting dental restorations and treatments in panoramic view radiographs and dental intra-oral X-rays. Trained on a comprehensive collection of 2D and 3D de...
详细信息
With the rapid development of big data, Federated learning (FL) has found numerous applications, enabling machine learning (ML) on edge devices while preserving privacy. However, FL still faces crucial challenges, suc...
详细信息
With the rapid development of big data, Federated learning (FL) has found numerous applications, enabling machine learning (ML) on edge devices while preserving privacy. However, FL still faces crucial challenges, such as single point of failure and poisoning attacks, which motivate the integration of blockchain-enabled FL (BeFL). Beyond that, the efficiency issue still limits the further application of BeFL. To address these issues, we propose a novel decentralized framework: Accelerating Blockchain-Enabled Federated Learning with Clustered Clients (ABFLCC), who utilize actual training time for clustering clients to achieve hierarchical FL and solve the single point of failure problem through blockchain. Additionally, the framework clusters edge devices considering their actual training times, which allows for synchronous FL within clusters and asynchronous FL across clusters simultaneously. This approach guarantees that devices with a similar training time have a consistent global model version, improving the stability of the converging process, while the asynchronous learning between clusters enhances the efficiency of convergence. The proposed framework is evaluated through simulations on three real-world public datasets, demonstrating a training efficiency improvement of 30% to 70% in terms of convergence time compared to existing BeFL systems. IEEE
Industry 5.0 is a new way of thinking that is consistent with the ideas of Industry 4.0 but places greater emphasis on sustainability, sustainability, and human-centricity. Unlike Industry 4.0, which emphasizes the ef...
详细信息
Recently,a massive quantity of data is being produced from a distinct number of sources and the size of the daily created on the Internet has crossed two *** the same time,clustering is one of the efficient techniques...
详细信息
Recently,a massive quantity of data is being produced from a distinct number of sources and the size of the daily created on the Internet has crossed two *** the same time,clustering is one of the efficient techniques for mining big data to extract the useful and hidden patterns that exist in ***-based clustering techniques have gained significant attention owing to the fact that it helps to effectively recognize complex patterns in spatial *** data clustering is a trivial process owing to the increasing quantity of data which can be solved by the use of Map Reduce *** this motivation,this paper presents an efficient Map Reduce based hybrid density based clustering and classification algorithm for big data analytics(MR-HDBCC).The proposed MR-HDBCC technique is executed on Map Reduce tool for handling the big *** addition,the MR-HDBCC technique involves three distinct processes namely pre-processing,clustering,and *** proposed model utilizes the Density-Based Spatial Clustering of Applications with Noise(DBSCAN)techni-que which is capable of detecting random shapes and diverse clusters with noisy *** improving the performance of the DBSCAN technique,a hybrid model using cockroach swarm optimization(CSO)algorithm is developed for the exploration of the search space and determine the optimal parameters for density based ***,bidirectional gated recurrent neural network(BGRNN)is employed for the classification of big *** experimental validation of the proposed MR-HDBCC technique takes place using the benchmark dataset and the simulation outcomes demonstrate the promising performance of the proposed model interms of different measures.
In this work, we leverage state-of-the-art machine learning algorithms to predict Channel State Information (CSI), for enhancing performance of wireless communication systems. The simulation and analysis stop with tra...
详细信息
Software Testing is an important and measured/outcome-oriented field that requires an in-depth analysis for developing new methodologies. This enables the development of high-quality end product resulting in fewer mai...
详细信息
Learning causal structures from observational data is critical for causal discovery and many machine learning tasks. Traditional constraint-based methods first adopt conditional independence (CI) tests to learn a glob...
详细信息
There are several uses for information concealing today. The use of data hiding knowledge may be morally or immorally acceptable. data hiding methods, however, are difficult to classify into either the steganography o...
详细信息
In this paper, we have analyzed the secrecy performance and system operation performance for hybrid RF/FSO systems against composite Weibull-log-normal fading channel with M turbulent channels. The performance is eval...
详细信息
Breast and cervical cancers account for more than 85 percent of all cancer-related fatalities in developing nations, according to the World Cancer Research Fund. As a result, breast and cervical cancer have become one...
详细信息
Breast and cervical cancers account for more than 85 percent of all cancer-related fatalities in developing nations, according to the World Cancer Research Fund. As a result, breast and cervical cancer have become one of the leading causes of mortality among women worldwide. This field is still in its infancy, with only a few studies in gynaecology and computerscience looking into the detection of breast and cervical cancer. According to the researchers, medical records and early testing from individuals with breast and cervical cancer will be used in this study to determine the prognosis of those suffering from the diseases. To assess our cervical cancer predictions, we employed machine learning models such as Optimized Hybrid Ensemble Classifier (OHEC), which were trained on patient behavior and variables revealed to be associated with patient behavior. The datasets in this study have a substantial number of missing values, and the distribution of those values has been altered as a function of the missing values. OHEC classifier performance has been shown to improve when the number of features is reduced and the problem of high-class imbalance is resolved, because the accuracy, sensitivity, and specificity of the classifier, as well as the number of false positives, were used to demonstrate the success of feature selection in the suggested model's predictive analysis. This has been demonstrated through the use of numerous tests involving categorization challenges. The study underscores the critical significance of early detection and prognosis in combating breast and cervical cancers, which remain leading causes of mortality worldwide. Through the utilization of machine learning models like the OHEC, the authors have demonstrated the potential for improved predictive accuracy and clinical outcomes. The findings highlight the importance of addressing challenges such as missing data and class imbalance in enhancing the performance of predictive models for effective
暂无评论