No abstract

Cancer is a dreadful disease. Millions of people died every year because of this disease. Neural networks are currently a burning research area in medical scienc It is very essential for medical practitioners to opt a proper treatment for cancer patients. Therefore, cancer cells should be identified correctly. Current developments in biological as well as in the computer science encouraged more studies to examine the role related to computational techniques in broad sphere regarding certain researches related to cancer. Using different AI approaches with regard to the disease’s medical diagnosis has been more general in recent times. Furthermore, there is more concentration on shown advantages of machine learning and AI methods. Cancer can be considered as one of the terrible diseases. Yearly, a lot of humans are dying from cancer. It is very essential for the practitioners of medical field to use suitable treatment regarding patients experiencing cancer. The data on cancer is specified as collection regarding thousands of genes. Thus, the cells of cancer must be properly detected. Currently, neural networks are considered as very significant area of research in the medical science, particularly in urology, radiology, cardiology, oncology, and a lot more. The presented work will survey different techniques of neural networks to classify lymph, neck and head, as well as breast cancer. The major goal of this work in the medical diagnostics has been guiding a lot of studies for developing user-friendly as well as inexpensive techniques, processes, as well as systems for the clinicians.

This paper introduces a study to Blue Monkey (BM) algorithm, which is a new metaheuristic algorithm optimization based on the performance of blue monkey swarms in nature. The BM algorithm identifies how many males in one group. Normally, outside the season of the breeding, the groups of blue monkeys have only one adult male like other forest guenons. In addition to related patas monkeys (Erythrocebus patas). Forty-three of well-known test functions, which used in the area of optimization are used as benchmark to check BM algorithm, in addition, BM verified by a comparative performance check with Artificial-Bee-Colony (ABC), Gravitational Search Algorithm (GSA), Biogeography-Based Optimizer (BBO), and Particle Swarm Optimization (PSO). The obtained results demonstrated that BM algorithm is competitive compared with the selected metaheuristic algorithms; also, BM is able to converge towards the global optimal through optimization problems. Further, this algorithm is very efficient in field of dissolving real problems with restrictions and unidentified search space. It should be mentioned that the BM algorithm has some variables and it can obtain better results. in many test functions comparing with other algorithms.

Timetabling problems are specific types of scheduling problems that deal with assigning certain events to the timeslots. This assigning is subject to certain hard constraints that should be achieved to get a feasible timetable and soft constraints that must meet as many as possible during forming a feasible schedule. This paper introduces an adaptive tabu search. Eleven benchmark datasets of the year 2002 are applied to show the effectiveness of the introduced algorithm. These datasets consist of 5-small, 5-medium, and 1-large dataset. As compared to other methods from previous works, the proposed algorithm produces excellent timetables, in comparison with the algorithms as well as the current results, the mathematical results showed the high effectiveness of the suggested algorithm. It has a minor deficit on the medium or the small problem adaptive Tabu, and the tabu search relies on the tabu list and penalty cost when the change in the penalty cost is checked; if it is still unchanged for the period of iterations (1,000 iterations), the tabu list reduces automatically by (−2); furthermore, the tabu list remains constant.

Multimedia Information Retrieval (MIR) is an important field due to the great amount of information going through the Internet. Multimedia data can be considered as raw data or the features that compose it. Raw multimedia data consists of data structures with diverse characteristics such as image, audio, video, and text. The big challenge of MIR is a semantic gap, which is the difference between the human perception of a concept and how it can be represented using a machine-level language. The aim of this paper is to use different algorithms through two stages one for training and the other for testing. The first algorithm depends on the nature of the query language to retrieve the text document using two models, Vector Space Model (VSM) and Latent Semantic Index (LSI). The second algorithm is based on the extracted features using curvelet decomposition and the statistic parameters such as mean, standard deviation and energy of signals. The other algorithm is based on the discrete wavelet transform (DWT) and features of signals to retrieve audio signals, then the neural network is applied to describe the information retrieval model which retrieves the information from the multimedia. The neural network model, based on multiplayer perceptron and spreading activation network type, accepts the structure of conceptually and linguistically oriented model.