Investigation and characterization of changes in potato peels by thermochemical acidic pre-treatment for extraction of various compounds.

Potato peel waste (PPW) is an underutilized substrate which is produced in huge amounts by food processing industries. Using PPW a feedstock for production of useful compounds can overcome the problem of waste management as well as cost-effective. In present study, potential of PPW was investigated using chemical and thermochemical treatment processes. Three independent variables i.e., PPW concentration, dilute sulphuric acid concentration and liberation time were selected to optimize the production of fermentable sugars (TS and RS) and phenolic compounds (TP). These three process variables were selected in the range of 5-15 g w/v substrate, 0.8-1.2 v/v acid conc. and 4-6 h. Whole treatment process was optimized by using box-behnken design (BBD) of response surface methodology (RSM). Highest yield of total and reducing sugars and total phenolic compounds obtained after chemical treatment was 188.00, 144.42 and 43.68 mg/gds, respectively. The maximum yield of fermentable sugars attained by acid plus steam treatment were 720.00 and 660.62 mg/gds of TS and RS, respectively w.r.t 5% substrate conc. in 0.8% acid with residence time of 6 h. Results recorded that acid assisted autoclaved treatment could be an effective process for PPW deconstruction. Characterization of substrate before and after treatment was checked by SEM and FTIR. Spectras and micrographs confirmed the topographical variations in treated substrate. The present study was aimed to utilize biowaste and to determine cost-effective conditions for degradation of PWW into value added compounds.

Amylase and Cellulase Production from Newly Isolated Bacillus subtilis Using Acid Treated Potato Peel Waste.

Species belonging to the genus Bacillus produce many advantageous extracellular enzymes that have tremendous applications on a commercial scale for the textile, detergent, feed, food, and beverage industries. This study aimed to isolate potent thermo-tolerant amylolytic and cellulolytic bacterium from the local environment. Using the Box-Behnken design of response surface methodology, we further optimized the amylase and cellulase activity. The isolate was identified by 16S rRNA gene sequencing as Bacillus subtilis QY4. This study utilized potato peel waste (PPW) as the biomaterial, which is excessively being dumped in an open environment. Nutritional status of the dried PPW was determined by proximate analysis. All experimental runs were carried out in 250 mL Erlenmeyer flasks containing acid treated PPW as a substrate by the thermos-tolerant Bacillus subtilis QY4 incubated at 37 °C for 72 h of submerged fermentation. Results revealed that the dilute H2SO4 assisted autoclaved treatment favored more amylase production (0.601 IU/mL/min) compared to the acid treatment whereas high cellulase production (1.269 IU/mL/min) was observed in the dilute acid treatment and was found to be very effective compared to the acid assisted autoclaved treatment. The p-value, F-value, and coefficient of determination proved the significance of the model. These results suggest that PPW could be sustainably used to produce enzymes, which offer tremendous applications in various industrial arrays, particularly in biofuel production.

A Hybrid Technique for Diabetic Retinopathy Detection Based on Ensemble-Optimized CNN and Texture Features.

One of the most prevalent chronic conditions that can result in permanent vision loss is diabetic retinopathy (DR). Diabetic retinopathy occurs in five stages: no DR, and mild, moderate, severe, and proliferative DR. The early detection of DR is essential for preventing vision loss in diabetic patients. In this paper, we propose a method for the detection and classification of DR stages to determine whether patients are in any of the non-proliferative stages or in the proliferative stage. The hybrid approach based on image preprocessing and ensemble features is the foundation of the proposed classification method. We created a convolutional neural network (CNN) model from scratch for this study. Combining Local Binary Patterns (LBP) and deep learning features resulted in the creation of the ensemble features vector, which was then optimized using the Binary Dragonfly Algorithm (BDA) and the Sine Cosine Algorithm (SCA). Moreover, this optimized feature vector was fed to the machine learning classifiers. The SVM classifier achieved the highest classification accuracy of 98.85% on a publicly available dataset, i.e., Kaggle EyePACS. Rigorous testing and comparisons with state-of-the-art approaches in the literature indicate the effectiveness of the proposed methodology.