This paper concentrates on reproducing face images from hand-dorsal images. This idea is adopted to enhance the biometric system outcomes. That is, best identifications can be presented by providing the face images of people as this can lead to directly recognizing the individuals. Non-linear relationships between hand-dorsal images and face images are designed and implemented. The power of Cascade-Forward Neural Network (CFN) and Back Propagation Neural Network (BPN) are employed to reproduce all face details by utilizing a hand-dorsal image. Both networks recorded interesting results in reproducing the details faces. The CFN performance is equal to 2.8571% and the BPN performance is equal to 6.4286%. Furthermore, the Average Correlation (ACORR) for the BPN which achieved 0.9874, this is lower than the ACORR for the CFN obtained to 0.9940. These performances reported that the CFN has significant ability to recognize people according to their face images.
Controlling a steam valve can be considered as a sensitive subject. It can restrict the allowance of steam through a specific controllable valve or gate. Steam valves are utilized in many steam systems such as electrical generation stations, ironing systems and heating systems. In this paper, an intelligent method based on the adoption of the Adaptive Neuron-Fuzzy Inference System (ANFIS) for Controlling a Steam Valve (CSV) is designed. The proposed method is called the Intelligent Steam Valve (ISV). In this paper, a Fuzzy Logic (FL) is firstly exploited to collect the optimum CSV values. Then, the ANFIS is exploited by combining a multiple layer Neural Network (NN) with the FL to provide the proposed ISV. The obtained results confirm the successfulness of the suggested approach.
1 February 2023 in Bulletin of Electrical Engineering and Informatics
Encryption is a substantial phase in information security. It permits only approved persons to get private information. This study suggests a signal multi-encryptions system (SMES) technique for coding and decoding signals created by a deep autoencoder network (DAN). The DAN of four layers is employed for a coding package of signals multiple times before decoding or restructuring the original signals again. The suggested SMES offers a high level of security as it can produce and exploit multiple encryptions for signals. Many statistical calculations are applied to measure the reliability of the system. The outcomes are promising where noteworthy encryptions-decryptions are obtained.
10 July 2026 in Biomedical Signal Processing and Control