Solar cell defect detection is a crucial assurance for the dependably functioning of solar panels. The artificial feature selection required, the excessive number of training parameters, and the subpar detection perfo...
详细信息
ISBN:
(纸本)9798350386783;9798350386776
Solar cell defect detection is a crucial assurance for the dependably functioning of solar panels. The artificial feature selection required, the excessive number of training parameters, and the subpar detection performance for particular defect kinds are some of the issues with the machinelearning defect detection approach based on computer vision technology. Deep convolutional neural network (DCNN)-based fault detection for solar cells is proposed. This method builds a deep network with three convolution layers, one pooling layer, one fully connected layer, and one output layer using solar cell photos as the input and a distinguishing defect category as the detection goal. The parameter number optimization technique, the parameter adjustment algorithm, and measures to address the overfitting issue are proposed during the training of network parameters. The experimental findings on the dataset demonstrate that the DCNN method's detection accuracy for solar cell faults can reach more than 97% and its F value can reach 0.690. This method's real-time detection speed can satisfy the needs of practical production, and its detection accuracy in each defect category is higher than that of previous approaches.
machinelearning is an important research area belonging to artificial intelligence technology. machinelearning has potent data processing and prediction ability. This paper uses machinelearning to build a data anal...
详细信息
With the development of big data technology, machinelearning is more and more widely used in the financial field, especially in the stock market prediction. Through machinelearning algorithms, it is possible to pred...
详细信息
The artificial intelligence-based systems are getting smarter and more intelligent and find widespread applications on crossing various research fields. The data mining is being increasingly focused currently on the S...
详细信息
Aiming at the problems of evolutionary learning of user preferences and high-dimensional sparse data processing in personalized recommendation systems. Inspired by the structural features of Hidden Markov Model, a per...
详细信息
ISBN:
(纸本)9781665416061
Aiming at the problems of evolutionary learning of user preferences and high-dimensional sparse data processing in personalized recommendation systems. Inspired by the structural features of Hidden Markov Model, a personalized recommendation algorithm considering contextaware two-stage user preference set reasoning strategy) is proposed. By processing the historical scoring information of the system, the extraction process of user preferences is abstracted into a hidden Markov model to perform the first stage of user preference set learning and reasoning. Then, the occurrence probability of these scoring objects is weighted with the traditional item similarity calculation method to obtain the new similarity, and finally the recommendation result is generated. In the simulation experiment, the important parameters of the algorithm are trained, and compared with other algorithms, it is proved that the improved algorithm is effective.
After implementing the Jaminan Kesehatan Nasional (JKN) in Indonesia, health system inequity, payment non-compliance and additional expenditure still exists. To better deal with the problems in their healthcare system...
详细信息
Causal structures in the real world often exhibit cycles naturally due to equilibrium, homeostasis, or feedback. However, causal discovery from observational studies regarding cyclic models has not been investigated e...
详细信息
Causal structures in the real world often exhibit cycles naturally due to equilibrium, homeostasis, or feedback. However, causal discovery from observational studies regarding cyclic models has not been investigated extensively because the underlying structure of a linear cyclic structural equation model (SEM) cannot be determined solely from observational data. Inspired by the Bayesian information Criterion (BIC), we construct a score function that assesses both accuracy and sparsity of the structure to determine which linear Gaussian SEM is the best when only observational data is given. Then, we formulate a causal discovery problem as an optimization problem of the measure and propose the Filter, Rank, and Prune (FRP) method for solving it. We empirically demonstrate that our method outperforms competitive cyclic causal discovery baselines.
One of the important application of natural language processing (NLP) is Name Entity Recognition (NER). It automatically recognise and categorise named entities in a document. Named Entities can be the name of an indi...
详细信息
In multi-party machinelearning scenarios involving sensitive data, safeguarding user and model privacy holds utmost importance. Current approaches often disclose model parameters to expedite training, but this poses ...
详细信息
Federated learning is a novel machinelearning paradigm in which the model is trained on local data by distributed clients. Most of the current research on federated learning assumes that clients are unconditionally p...
详细信息
ISBN:
(纸本)9798350349184;9798350349191
Federated learning is a novel machinelearning paradigm in which the model is trained on local data by distributed clients. Most of the current research on federated learning assumes that clients are unconditionally providing data and training models, and little consideration has been given to how to incentivize clients with high-quality data to participate in the model training task. Therefore, this paper proposes a blockchain-based federated learning incentive mechanism combining data quality verification and reverse auction. Firstly, by verifying the quality of client data, the client with high-quality data that meets the task requirements is selected, and then the client sends its bid for the task to the reverse auction smart contract. Secondly, some clients with the best performance in different training phases are selected to participate in the task training using smart contracts, and a certain number of clients are selected to form a committee among the unselected participants. The committee members are responsible for validating the local model parameters of the clients while receiving validation rewards. Finally, we conduct simulation experiments on two datasets separately, and the experimental results demonstrate the effectiveness of our proposal.
暂无评论