<span>To assess different approaches to traffic light control design, a systematic literature review was conducted, covering publications from 2006 to 2020. The review’s aim was to gather and examine all studies that looked at road traffic and congestion issues. As well, it aims to extract and analyze protruding techniques from selected research articles in order to provide researchers and practitioners with recommendations and solutions. The research approach has placed a strong emphasis on planning, performing the analysis, and reporting the results. According to the results of the study, there has yet to be developed a specific design that senses road traffic and provides intelligent solutions. Dynamic time intervals, learning capability, emergency priority management, and intelligent functionality are all missing from the conventional design approach. While learning skills in the adaptive self-organization strategy were missed. Nonetheless, the vast majority of intelligent design approach papers lacked intelligent fear tires and learning abilities.</span>

No abstract

The technology of face recognition is attractive and full of technology research challenges; It is used for recognizing people by using digital images. Although face recognition has an important role in several areas such as security, face recognition technology still encounters many challenges that need to be solved with more scientific methods. One of These challenges lead can be the variations of the face of the same person due to lighting or pose. This project explores and investigates the use of combined hybrid algorithms based on neural networks and discreet wavelet transform for face recognition in order to enhance the recognition rate for a face from identified data set of faces. Two techniques have been used in this research; the First one is applying the discrete wavelet transformation method in order to improve and compress the images of the data set. The second one is implementing a well-known approach called Principal Component Analysis. The training and testing face images are selected from ORL database, which contains 400 images for 40 different persons and have minimum pose variation. The experimental results confirmed that the proposed methodology provides a feasible and effective solution for recognizing faces.

No abstract