Two Novel Versions of Randomized Feed Forward Artificial Neural Networks: Stochastic and Pruned Stochastic

Improving the Accuracy of Diabetes Diagnosis Applications through a Hybrid Feature Selection Algorithm

Artificial intelligence is a future and valuable tool for early disease recognition and support in patient condition monitoring. It can increase the reliability of the cure and decision making by developing useful systems and algorithms. Healthcare workers, especially nurses and physicians, are overworked due to a massive and unexpected increase in the number of patients during the coronavirus pandemic. In such situations, artificial intelligence techniques could be used to diagnose a patient with life-threatening illnesses. In particular, diseases that increase the risk of hospitalization and death in coronavirus patients, such as high blood pressure, heart disease and diabetes, should be diagnosed at an early stage. This article focuses on diagnosing a diabetic patient through data mining techniques. If we are able to diagnose diabetes in the early stages of the disease, we can force patients to stay home and care for their health, so the risk of being infected with the coronavirus would be reduced. The proposed method has three steps: preprocessing, feature selection and classification. Several combinations of Harmony search algorithm, genetic algorithm, and particle swarm optimization algorithm are examined with K-means for feature selection. The combinations have not examined before for diabetes diagnosis applications. K-nearest neighbor is used for classification of the diabetes dataset. Sensitivity, specificity, and accuracy have been measured to evaluate the results. The results achieved indicate that the proposed method with an accuracy of 91.65% outperformed the results of the earlier methods examined in this article.

Bidirectional stochastic configuration network for regression problems

To adapt to the reality of limited computing resources of various terminal devices in industrial applications, a randomized neural network called stochastic configuration network (SCN), which can conduct effective training without GPU, was proposed. SCN uses a supervisory random mechanism to assign its input weights and hidden biases, which makes it more stable than other randomized algorithms but also leads to time-consuming model training. To alleviate this problem, we propose a novel bidirectional SCN algorithm (BSCN) in this paper, which divides the way of adding hidden nodes into two modes: forward learning and backward learning. In the forward learning mode, BSCN still uses the supervisory mechanism to configure the parameters of the newly added nodes, which is the same as SCN. In the backward learning mode, BSCN calculates the parameters at one time based on the residual error feedback of the current model. The two learning modes are performed iteratively until the prediction error of the model reaches an acceptable level or the number of hidden nodes reaches its maximum value. This semi-random learning mechanism greatly speeds up the training efficiency of the BSCN model and significantly improves the quality of the hidden nodes. Extensive experiments on ten benchmark regression problems, two real-life air pollution prediction problems, and a classical image processing problem show that BSCN can achieve faster training speed, higher stability, and better generalization ability than SCN.