This paper presents an intelligent model for stock market signal prediction using Multi Layer Perceptron (MLP) Artificial Neural Networks (ANN). Blind source separation technique, from signal processing, is integrated with the learning phase of the constructed baseline MLP ANN to overcome the problems of prediction accuracy and lack of generalization. Kullback Leibler Divergence (KLD) is used, as a learning algorithm, because it converges fast and provides generalization in the learning mechanism. Both accuracy and efficiency of the proposed model were confirmed through the Microsoft stock, from wall-street market, and various data sets, from different sectors of the Egyptian stock market. In addition, sensitivity analysis was conducted on the various parameters of the model to ensure the coverage of the generalization issue.

In the present research, stabilized rice bran (SRB) of an Egyptian variety was used for the preparation of corn flakes and tortilla chips with and without fortification with rich protein sources. SRB was used as 10, 20 and 30% replacements of gelatinized corn flour. Doughs of different blends were evaluated rheologically. Color quality, sensory parameters and proximate composition of the products were assessed. Results showed that the maximum and breakdown viscosity and color quality was affected by the presence of SRB. Some sensory parameters of tortilla chips and corn flakes containing RB showed decline. Percentage protein of 30% SRB corn flakes and tortilla chips that were not fortified with protein‐rich sources was 10.57 and 11.2, while that of fat was 3.65 and 23.21; crude fibers were 0.775 and 0.631, and ash was 0.24 and 1.71, respectively. Fortified tortilla chips and corn flakes contain 11.5 and 13.7% protein, respectively. PRACTICAL APPLICATIONS The present research aimed at production of functional foods containing both rice bran and corn flour so as to be marketed.

The present study aims to evaluate the antioxidant and anti-cancer activities of nutraceuticals prepared from apricot kernel and grape seeds extracts. Different bioactive compounds were determined in the prepared nutraceuticals (total phenolic compounds, flavonoids, β-carotene, phytosterols and fatty acids). Acute toxicity of these nutraceuticals was evaluated. Apricot kernel showed the highest content of protein and fat, while grape seeds were rich in carbohydrates. Apricot kernel nutraceutical (AKN) showed the highest content of hydrocarbons, while grape seeds nutraceutical (GSN) showed the highest phytosterol content. Stigmasterol was the major phytosterol present in both nutraceuticals. Oleic acid and linoleic acid were the major unsaturated fatty acids present in AKN and GSN, respectively. GSN showed the highest content of phenolic compounds and total flavonoids, while AKN showed the highest content of β-carotene (2.91mg/100g). GSN showed the highest antioxidant activity in all the studied methods (DPPH, reducing power and ferric thiocynate) compared with apricot kernel nutraceutical. Both nutraceuticals showed anti-cancer activity against liver carcinoma cells (HEPG2), breast cancer cells (MCF7) and lung cell cancer (H460). GSN was the most promising in all types of cancer cells. GSN showed complete safety, while AKN was completely safe up to 6 g/kg mice body weight.

Introduction: Protection of brain against accelerated aging helps avoiding the occurrence of neurodegenerative diseases. So, the current work was conducted to evaluate the rescuing role of kumquat fruits crude ethanol extract, carrot seeds ethanol and petroleum ether extracts against the brain aging induced by D-galactose in rats. Methods: Forty male Sprague Dawley rats were divided equally into five groups. Group I was served as normal control, rats of group II were daily injected intraperitoneally (i.p.) with 150 mg/kg BW of D-galactose. Rats of group III, IV and V were daily injected i.p. with the same dose of D-galactose and administered orally with 250 mg/kg BW/day of kumquat fruits crude ethanol extract, carrot seeds ethanol extract and carrot seeds petroleum ether extract, respectively. After 6 weeks the rats were scarified, brain tissues were analyzed for malondialdehyde (MDA), catalase (CAT) as well as histological examination. Also, the plasma was analyzed for MDA, tumor necrosis factor-α (TNF-α), creatinine and urea levels, as well as CAT, butyrylcholinesterase (BChE), aspartate transaminase (AST) and alanine transaminase (ALT) activities. Results: From the results, it was elucidated that the tested extracts suppressed both the reduction in CAT and the elevation in MDA either in brain or plasma and the increase in plasma TNF-α, BChE as well as liver and kidney parameters. Conclusion: The tested extracts can be served as potent protective agents against the accelerated aging parameters which may be due to anti-oxidant and anti-inflammatory activities.

This paper presents an intelligent model for stock market signal prediction using Multi-Layer Perceptron (MLP) Artificial Neural Networks (ANN). Blind source separation technique, from signal processing, is integrated with the learning phase of the constructed baseline MLP ANN to overcome the problems of prediction accuracy and lack of generalization. Kullback Leibler Divergence (KLD) is used, as a learning algorithm, because it converges fast and provides generalization in the learning mechanism. Both accuracy and efficiency of the proposed model were confirmed through the Microsoft stock, from wall-street market, and various data sets, from different sectors of the Egyptian stock market. In addition, sensitivity analysis was conducted on the various parameters of the model to ensure the coverage of the generalization issue. Finally, statistical significance was examined using ANOVA test.