Improved tomato leaf disease classification through adaptive ensemble models with exponential moving average fusion and enhanced weighted gradient optimization.

Tomato is one of the most popular and most important food crops consumed globally. The quality and quantity of yield by tomato plants are affected by the impact made by various kinds of diseases. Therefore, it is essential to identify these diseases early so that it is possible to reduce the occurrences and effect of the diseases on tomato plants to improve the overall crop yield and to support the farmers. In the past, many research works have been carried out by applying the machine learning techniques to segment and classify the tomato leaf images. However, the existing machine learning-based classifiers are not able to detect the new types of diseases more accurately. On the other hand, deep learning-based classifiers with the support of swarm intelligence-based optimization techniques are able to enhance the classification accuracy, leading to the more effective and accurate detection of leaf diseases. This research paper proposes a new method for the accurate classification of tomato leaf diseases by harnessing the power of an ensemble model in a sample dataset of tomato plants, containing images pertaining to nine different types of leaf diseases. This research introduces an ensemble model with an exponential moving average function with temporal constraints and an enhanced weighted gradient optimizer that is integrated into fine-tuned Visual Geometry Group-16 (VGG-16) and Neural Architecture Search Network (NASNet) mobile training methods for providing improved learning and classification accuracy. The dataset used for the research consists of 10,000 tomato leaf images categorized into nine classes for training and validating the model and an additional 1,000 images reserved for testing the model. The results have been analyzed thoroughly and benchmarked with existing performance metrics, thus proving that the proposed approach gives better performance in terms of accuracy, loss, precision, recall, receiver operating characteristic curve, and F1-score with values of 98.7%, 4%, 97.9%, 98.6%, 99.97%, and 98.7%, respectively.

Supplemental phosphorus can be completely replaced with microbial phytase in White Leghorn layer diets.

1. A study was conducted to assess the possibility of totally replacing supplemental phosphorus sources in White Leghorn (WL) layer diets (aged 28 to 45 weeks of age) with microbial phytase supplementation. One thousand commercial layers (HyLine White) of 28 weeks of age were housed in California cages fitted in open-sided poultry shed at the rate of 20 layers in each replicate. Ten replicates were randomly allotted to each treatment, and the respective diet was fed from 28 to 45 weeks of age.2. A control diet (CD) containing the recommended levels of non-phytate phosphorus (3.6 g/kg NPP) and four other test diets (2-5) having sub-optimal levels of NPP (2.4, 2.0, 1.6 and 1.2 g/kg), but with supplemental microbial phytase (600 FTU/kg) were prepared and fed for the trial duration.3. The layers fed with lower levels of NPP with phytase had the same laying performance as the group fed the CD. Egg production, feed efficiency, egg mass, shell defects, egg density, shell weight, shell thickness, ash content and breaking strength of the tibia and sternum were not affected by feeding the lowest concentration of NPP (1.2 g/kg) plus microbial phytase.4. Phytase supplementation in diets with sub-optimal levels of NPP (2.4, 2 and 1.6 g/kg) significantly improved the Haugh unit score compared to those fed the CD.5. It was concluded that supplemental phosphorus can be completely replaced with microbial phytase (600 FTU/kg) in a diet without affecting egg production, shell quality or bone mineral variables in WL layers (28 to 45 weeks).

Phase III randomized clinical studies to evaluate the immunogenicity, lot-to-lot consistency, and safety of ROTAVAC® liquid formulations (ROTAVAC 5C & 5D) and non-inferiority comparisons with licensed ROTAVAC® (frozen formulation) in healthy infants.

The WHO pre-qualified rotavirus vaccine, ROTAVAC®, is derived naturally from the neonatal 116E rotavirus strain, and stored at -20°C. As refrigerator storage is preferable, immunogenicity and safety of liquid formulations kept at 2-8°C, having excipients to stabilize the rotavirus, with or without buffers, were compared with ROTAVAC® in different clinical studies. Study-1, the pivotal trial for this entire product development work, was a randomized, single-blind trial with two operationally seamless phases: (i) an exploratory phase involving 675 infants in which two formulations, ROTAVAC 5C (LnHRV-1.5 mL and LnHRV-2.0 mL) containing buffer and excipients to stabilize the virus against gastric acidity and temperature, were compared with ROTAVAC®. As the immune response of ROTAVAC 5C (LnHRV-2.0 mL) was non-inferior to ROTAVAC®, it was selected for (ii) confirmatory phase, involving 1,302 infants randomized 1:1:1:1 to receive three lots of LnHRV-2.0 mL, or ROTAVAC®. Primary objectives were the evaluation of non-inferiority and lot-to-lot consistency. The secondary objectives were to assess the safety and interference with the concomitant pentavalent vaccine. As it was separately established that buffers are not required for ROTAVAC®, in Study-2, the safety and immunogenicity of ROTAVAC 5D® (with excipients) were compared with ROTAVAC® and lot-to-lot consistency was assessed in another study. All lots elicited consistent immune responses, did not interfere with UIP vaccines, and had reactogenicity similar to ROTAVAC®. ROTAVAC 5C and ROTAVAC 5D® were immunogenic and well tolerated as ROTAVAC®. ROTAVAC 5D® had comparable immunogenicity and safety profiles with ROTAVAC® and can be stored at 2-8°C, leading to WHO pre-qualification.Clinical Trials Registration: Clinical Trials Registry of India (CTRI): CTRI/2015/02/005577CTRI/2016/11/007481 and CTRI/2019/03/017934.

Evaluation of Salivary Opiorphin, pH and Flow Rate in Oral Submucous Fibrosis - A Case - Control Observational Study.

Aim and Objectives: The aim of the study was to evaluate the salivary pH, flow rate and opiorphin in Oral submucous fibrosis patients and to compare them with healthy individuals. Materials and Methods: A comparative study was conducted to evaluate the salivary opiorphin levels, pH and flow rate among 78 patients (39 Oral submucous fibrosis + 39 control). Burning sensation was assessed using VAS score. Opiorphin levels were assessed using Cusabio Human Salivary Opiorphin ELISA kit. Salivary flow rate was assessed using graduated syringes and salivary pH was assessed using Hydrion salivary pH strips. Kolmogorov-Smirnov and Shapiro Wilk test were assessed for normality testing and distribution. Inferential statistics was done by using Unpaired t test/Independent sample t test to compare the mean values of variables included in the study among the OSMF and healthy patients. Results: There was statistically significant difference in pH and flow rate with a reduction in the mean pH (p=0.024) and flow rate (p<0.01) among the oral submucous fibrosis patients compared to the control group. A statistically significant increase (p<0.01) in salivary opiorphin levels was noted in the oral submucous fibrosis patients. Majority of the study participants had mild to moderate burning sensation. Conclusion: This study was a pilot evaluation of salivary opiorphin in OSMF. Salivary opiorphin could be used as an objective marker for chronic subjective conditions The pre-treatment and post treatment evaluation of salivary opiorphin could provide more insight on its role.

Meningioma brain tumor detection and classification using hybrid CNN method and RIDGELET transform.

The detection of meningioma tumors is the most crucial task compared with other tumors because of their lower pixel intensity. Modern medical platforms require a fully automated system for meningioma detection. Hence, this study proposes a novel and highly efficient hybrid Convolutional neural network (HCNN) classifier to distinguish meningioma brain images from non-meningioma brain images. The HCNN classification technique consists of the Ridgelet transform, feature computations, classifier module, and segmentation algorithm. Pixel stability during the decomposition process was improved by the Ridgelet transform, and the features were computed from the coefficient of the Ridgelet. These features were classified using the HCNN classification approach, and tumor pixels were detected using the segmentation algorithm. The experimental results were analyzed for meningioma tumor images by applying the proposed method to the BRATS 2019 and Nanfang dataset. The proposed HCNN-based meningioma detection system achieved 99.31% sensitivity, 99.37% specificity, and 99.24% segmentation accuracy for the BRATS 2019 dataset. The proposed HCNN technique achieved99.35% sensitivity, 99.22% specificity, and 99.04% segmentation accuracy on brain Magnetic Resonance Imaging (MRI) in the Nanfang dataset. The proposed system obtains 99.81% classification accuracy, 99.2% sensitivity, 99.7% specificity and 99.8% segmentation accuracy on BRATS 2022 dataset. The experimental results of the proposed HCNN algorithm were compared with those of the state-of-the-art meningioma detection algorithms in this study.

Higher concentrations of folic acid reduced the dietary requirements of supplemental methionine for commercial broilers.

Objective: An experiment was conducted to study the effect of supplementing DL methionine (DL Met) at graded concentrations on performance, carcass variables, immune responses and antioxidant variables in broiler chicken fed folic acid (FA) fortified (4mg/kg) low-methionine diet. Methods: A basal diet (BD) without supplemental DL Met, but with higher level (4 mg/kg) of FA and a control diet (CD) with the recommended concentration of methionine (Met) were prepared. The BD was supplemented with DL Met at graded concentrations (0, 10, 20, 30, 40 and 50% supplemental DL Met of CD). Each diet was fed ad libitum to 10 replicates of 5 broiler male chicks in each from 1 to 42 d of age. Results: Body weight gain (BWG) reduced, and feed conversion ratio (FCR) increased in broilers fed low-Met BD. At 30 and 20% inclusion of DL Met, the BWG and FCR were similar to those fed the CD. Similarly, supplementation of 10% DL Met to the BD significantly increased ready to cook meat yield and breast meat weight, which were similar to those of the CD fed broilers. Lipid peroxidation reduced, the activity of antioxidant enzymes (GSHPx and GSHRx) in serum increased and lymphocyte proliferation increased with increased supplemental DL Met level in the BD. The concentrations of total protein and albumin in serum increased with DL Met supplementation to the BD. Conclusion: Based on the data, it can be concluded that supplemental Met can be reduced to less than 50% in broiler chicken diets (4.40, 3.94 and 3.39g/kg, respectively in pre-starter, starter and finisher phases) containing 4 mg/kg FA.

Evaluating the expression of microRNA-15a-5p and YAP1 gene in oral squamous cell carcinoma in comparison with normal tissue: A cross-sectional study.

BACKGROUND: MicroRNAs (miRNAs) play crucial regulatory roles in cancer progression, including oral cancer (OC). However, the biological mechanisms of miRNA-15a-5p in OC remain unclear. This study aimed to evaluate the expression of miRNA-15a-5p and the YAP1 gene in OC. METHODS: A total of 22 clinically and histologically confirmed oral squamous cell carcinoma (OSCC) patients were recruited, and their tissues were stored in a stabilizing solution. Later, RT-PCR was performed to evaluate miRNA-15a-5p and the targeting gene YAP1. The results of OSCC samples were compared with unpaired normal tissues. RESULTS: The normality tests, Kolmogorov-Smirnov and Shapiro-Wilk, revealed a normal distribution. Inferential statistics were performed using an independent sample t-test/unpaired t-test among the study intervals to compare the expression of miR-15a and YAP1. SPSS (IBM SPSS Statistics for Windows, Version 26.0, Armonk, NY: IBM Corp. Released 2019) was used to analyse the data. The significance level was set at 5% (α = 0.05), and a p-value <0.05 was considered statistically significant. The expression of miRNA-15a-5p was lower in OSCC than in normal tissue, whereas the opposite was observed for YAP1 levels. CONCLUSION: In conclusion, this study demonstrated that miRNA-15a-5p was downregulated and YAP1 was overexpressed, which had a statistically significant difference between the normal and OSCC groups. Therefore, miRNA-15a-5p may serve as a novel biomarker to better understand the pathology and as a potential target in OSCC therapy.

Intrathecal pain pumps in pain relief.

Chronic pain is a significant global health issue, described as a bio-psychosocial phenomenon that hampers the integration of body, mind, and social functions. To relieve chronic intractable pain, intrathecal drug-delivery devices (IDDDs) are the last resort after conventional treatment options have been exhausted. This article outlines the indications, pharmacological agents, types, techniques, preparation of the patient, and complications of IDDDs for the management of challenging chronic pain (non-neoplastic and cancer-related pain) conditions in patients who have not responded well to a commonly used conventional line of treatment.

The Unprecedented Role of 3D Printing Technology in Fighting the COVID-19 Pandemic: A Comprehensive Review.

The coronavirus disease 2019 (COVID-19) rapidly spread to over 180 countries and abruptly disrupted production rates and supply chains worldwide. Since then, 3D printing, also recognized as additive manufacturing (AM) and known to be a novel technique that uses layer-by-layer deposition of material to produce intricate 3D geometry, has been engaged in reducing the distress caused by the outbreak. During the early stages of this pandemic, shortages of personal protective equipment (PPE), including facemasks, shields, respirators, and other medical gear, were significantly answered by remotely 3D printing them. Amidst the growing testing requirements, 3D printing emerged as a potential and fast solution as a manufacturing process to meet production needs due to its flexibility, reliability, and rapid response capabilities. In the recent past, some other medical applications that have gained prominence in the scientific community include 3D-printed ventilator splitters, device components, and patient-specific products. Regarding non-medical applications, researchers have successfully developed contact-free devices to address the sanitary crisis in public places. This work aims to systematically review the applications of 3D printing or AM techniques that have been involved in producing various critical products essential to limit this deadly pandemic's progression.

Influence of Anaemia on Multifactorial Disease Retinopathy of Prematurity: A Prospective Observational Study.

BACKGROUND: Retinopathy of prematurity (ROP), a preventable cause of childhood blindness, is a severe complication of preterm (PT) birth treatment. PURPOSE: The purpose of this study is to analyse the risk factors (RF) associated with the development and progression of ROP. Particular focus is on the contribution of anaemia towards the development and progression of ROP. METHODS: This study is a prospective observational study done in the Department of Paediatrics at Meenakshi Mission Hospital & Research Centre, Madurai, over 12 months from May 2013 to April 2014. The study included all consecutively admitted neonates born in and out of the hospital with gestational age (GA) less than or equal to 35 weeks or birth weight (BW) less than or equal to 2 kg and assessed for the gestational, perinatal, and postnatal RF. In addition, at the time of ROP screening, haemoglobin (Hb) and haematocrit (Hct) were checked. The statistical analysis was performed by Stata 11.1 (StataCorp LLC, College Station, TX). RESULT: The incidence of ROP in our study (46.7%) is higher than previously reported in India. In our study, GA and weight of the neonate at birth have a significant association with ROP incidence. Anaemia in our study is significantly associated with ROP incidence but not as an independent RF. The outcome of various stages of ROP is statistically significant, showing early stages 1 and 2 have more chances of spontaneous regression, and stages 3 and 4 are more likely to need treatment. Two cases in our study with stage 4 ROP had no complications, and none had stage 5 disease. CONCLUSION: Anaemia should be avoided or corrected in PT newborns as it is a potential and avoidable RF for ROP development. The limitation of our study is the small sample size, and probably more extensive randomized trials will help make this association clear. We recommend ROP screening for PT babies with GA less than 35 weeks and BW less than 2 kg who have the RF amounting to screening and done as per protocol.

Effect of dietary supplementation of zinc proteinate on performance, egg quality, blood biochemical parameters, and egg zinc content in White Leghorn layers.

A study was conducted to investigate the effects of zinc proteinate (Zn-P) on laying performance, egg quality, antioxidant indices, and egg zinc content in laying hens from 38 to 49 weeks of age. A total of 150 White Leghorn layers were randomly assigned to five treatments, each with six replicates with five birds per replication. Dietary treatments included a corn-soybean meal-based basal diet with no zinc addition and basal diet supplemented with Zn-P at 40, 80, 120, or 160 mg/kg of feed for 12 weeks. The analyzed zinc concentrations of the five diets were 29.5, 70.8, 110.2, 147.5, and 187.5 mg Zn/kg, respectively. Dietary Zn-P supplementation had no effect on feed intake and egg production. However, raising the zinc level improved egg weight (P < 0.01) and egg mass (P < 0.05) and lowered the feed conversion ratio (P < 0.05) during the later (46-49 weeks) period. The Zn-P supplementation also significantly (P < 0.05) increased Haugh units, egg shell strength, and shell thickness and had no influence on other egg quality parameters. Increasing zinc levels in the diet resulted in increase in egg zinc contents and serum zinc level. The serum triglyceride and LDL-cholesterol levels significantly decreased (P < 0.05) in Zn-P-supplemented groups. Supplementation of Zn-P significantly (P < 0.05) increased serum Cu-Zn-SOD activity and reduced MDA concentration. It could be concluded that dietary supplementation of higher levels of Zn-P, more than 80 mg/kg diet, significantly improved the egg zinc content, some egg quality traits, antioxidant activity, and serum zinc levels.

NH2-MIL-125(Ti) doped CdS/Graphene composite as electro and photo catalyst in basic medium under light irradiation.

The development of active electrocatalysts and photocatalysts for hydrogen evolution reaction (HER) and for environmental remediation is a huge challenge. Research is still underway on the development of low-cost catalytic materials with appreciable efficiency for HER. In the present study, a composite of metal organic framework (MOF) with CdS and graphene (NH2-MIL-125(Ti)/CdS-graphene) composites were developed with different loadings of graphene material via solvothermal technique. Further the electrocatalytic activity of the synthesized catalysts were investigated for HER and photocatalytic degradation of dye. Results show that the synthesized catalyst with a less amount of graphene was more active. HER results showed a less Tafel slope of 70.8 and 61.9 mVdec-1 with 15.6 mA/cm2 and 15.46 mA/cm2 current densities under light on and off conditions. Further the dye degradation activity of the synthesized catalysts was tested with Rhodamine B dye and results showed that the catalyst showed excellent activity for low weight loading of graphene with a degradation efficiency of 95 % and followed pseudo first order kinetic model. Overall results showed that the synthesized composites are promising for HER and photocatalytic applications.

Simulations of argon plasma decay in a thermionic converter.

The dynamics of an argon plasma in the gap of a thermionic diode is investigated using particle-in-cell (PIC) simulations. The time-averaged diode current, as a function of the relative electrical potential between the electrodes, is studied while the plasma density depletes due to recombination on the electrode surfaces. Simulations were performed in both one and two dimensions, and significant differences were observed in the plasma decay between the two cases. Specifically, in two dimensions it was found that the electrostatic potential gradually changes as the plasma decays, while in one dimension fluctuations in the plasma led to large potential fluctuations which changed the plasma decay characteristics relative to the two-dimensional case. This creates significant differences in the time-averaged diode current. Furthermore, it was found that the maximum time-averaged current is collected when the diode voltage is set to the flat-band condition, where the cathode and anode vacuum biases are equal. This suggests a novel technique of measuring the difference in work functions between the cathode and anode in a thermionic converter.

Bubble Coalescence at Wormlike Micellar Solution-Air Interfaces.

Surfactants in aqueous solutions self-assemble in the presence of salt, to form long, flexible, wormlike micelles (WLM). WLM solutions exhibit viscoelastic properties and are used in many applications, such as for cosmetic products, drag reduction, and hydraulic fracturing. Understanding the coalescence stability of bubbles in WLM solutions is important for the development of WLM based products that require a stable dispersion of bubbles. In this paper, we investigate the thin film drainage dynamics leading up to the coalescence of bubbles at flat WLM solution-air interfaces. The salts and surfactant type and concentrations were chosen so as to have the viscoelastic properties of the tested WLM solutions span over 2 orders of magnitude in moduli and relaxation times. The various stages in drainage and coalescence, the formation of a thick region at the apex (a dimple), the thinning and washout of this dimple, and the final stages of drainage before rupture, are modified by the viscoelasticity of the wormlike micellar solutions. As a result of the unique viscoelastic properties of the WLM solutions, we also observe a number of interesting fluid dynamic phenomena during the drainage processes including elastic recoil, thin film ripping, and single-step terminal drainage.

Clinical data classification using an enhanced SMOTE and chaotic evolutionary feature selection.

Class imbalance and the presence of irrelevant or redundant features in training data can pose serious challenges to the development of a classification framework. This paper proposes a framework for developing a Clinical Decision Support System (CDSS) that addresses class imbalance and the feature selection problem. Under this framework, the dataset is balanced at the data level and a wrapper approach is used to perform feature selection. The following three clinical datasets from the University of California Irvine (UCI) machine learning repository were used for experimentation: the Indian Liver Patient Dataset (ILPD), the Thoracic Surgery Dataset (TSD) and the Pima Indian Diabetes (PID) dataset. The Synthetic Minority Over-sampling Technique (SMOTE), which was enhanced using Orchard's algorithm, was used to balance the datasets. A wrapper approach that uses Chaotic Multi-Verse Optimisation (CMVO) was proposed for feature subset selection. The arithmetic mean of the Matthews correlation coefficient (MCC) and F-score (F1), which was measured using a Random Forest (RF) classifier, was used as the fitness function. After selecting the relevant features, a RF, which comprises 100 estimators and uses the Information Gain Ratio as the split criteria, was used for classification. The classifier achieved a 0.65 MCC, a 0.84 F1 and 82.46% accuracy for the ILPD; a 0.74 MCC, a 0.87 F1 and 86.88% accuracy for the TSD; and a 0.78 MCC, a 0.89 F1and 89.04% accuracy for the PID dataset. The effects of balancing and feature selection on the classifier were investigated and the performance of the framework was compared with the existing works in the literature. The results showed that the proposed framework is competitive in terms of the three performance measures used. The results of a Wilcoxon test confirmed the statistical superiority of the proposed method.

Computer-Aided Diagnosis system for diagnosis of pulmonary emphysema using bio-inspired algorithms.

Pulmonary emphysema is a condition characterized by the destruction and permanent enlargement of the alveoli of the lungs. The destruction of gas-exchanging alveoli causes shortness of breath followed by a chronic cough and sputum production. A Computer-Aided Diagnosis (CAD) framework for diagnosing pulmonary emphysema from chest Computed Tomography (CT) slices has been designed and implemented in this study. The process of implementing the CAD framework includes segmenting the lung tissues and extracting the regions of interest (ROIs) using the Spatial Intuitionistic Fuzzy C-Means clustering algorithm. The ROIs that were considered in this work were emphysematous lesions - namely, centrilobular, paraseptal, and bullae that were labelled by an expert radiologist. The shape, texture, and run-length features were extracted from each ROI. A wrapper approach that employed four bio-inspired algorithms - namely, Moth-Flame Optimization (MFO), Firefly Optimization (FFO), Artificial Bee Colony Optimization, and Ant Colony Optimization - with the accuracy of the support vector machine classifier as the fitness function was used to select the optimal feature subset. The selected features of each bio-inspired algorithm were trained independently using the Extreme Learning Machine classifier based on the tenfold cross-validation technique. The framework was tested on real-time and public emphysema datasets to perform binary classification of lung CT slices of patients with and without the presence of emphysema. The framework that used MFO and FFO for feature selection produced superior results regarding accuracy, precision, recall, and specificity for the real-time dataset and the public dataset, respectively, when compared to the other bio-inspired algorithms.

Validity of 3-Tesla diffusion-weighted magnetic resonance imaging for distinction of reactive and metastatic lymph nodes in head-and-neck carcinoma.

OBJECTIVES: The objective was to study the relationship of 3-Tesla (3T) diffusion-weighted magnetic resonance imaging (DW-MRI) with apparent diffusion coefficient (ADC) value for distinction of reactive and metastatic lymph nodes (LNs) in head-and-neck carcinoma (HNC) patients and to determine the ADC cutoff value for metastatic LNs at various levels. MATERIALS AND METHODS: 3T DW and T1- and T2-weighted imaging sequences were done in 34 patients with biopsy-proven primary HNC of 100 cervical LNs ≥1 cm in diameter. The mean ADC values were compared with histopathologically proven LNs using the independent t-test. ADC cutoff value was evaluated with sensitivity, specificity, accuracy, positive predictive value, negative predictive value and a receiver operating characteristic curve analysis. RESULTS: The mean ADC value of reactive LN was 1.2933 × 10-3 mm2/s and metastatic LN was 0.908 × 10-3 mm2/s. An ADC cutoff value was 0.868 × 10-3 mm2/s with 84% sensitivity, 96% specificity, 93% accuracy, 87.5% positive predictive value, and 94.7% negative predictive value. A significant difference in mean ADC value between reactive and metastatic LNs was noted (P< 0.001). CONCLUSION: 3T DW-MRI is useful in differentiating reactive and metastatic cervical LNs in HNC patients. However, studies with larger sample size have to be performed to validate ADC threshold value with 3T DW-MRI in differentiating between reactive and metastatic LNs for clinical practice.

Feeding status of free-range scavenging chickens in different agro-climatic regions of India.

1. The aim of this study was to determine the nutritional status of backyard chickens reared under 4 different agro-climatic conditions (tropical, humid subtropical, cool-temperate and semi-arid) of India during different seasons of the year and to compare their nutritional status with those reared under confined feeding system (CFS). In each season, 15 adult and 15 grower chickens were slaughtered for collecting content of crop and gizzard to assess the nutritional status from different agro-climatic conditions.2. The dry matter content of crop and gizzard was higher (P < 0.01) in chickens reared under backyard conditions compared to those reared under CFS.3. Higher (P < 0.01) crop and gizzard contents were recorded during winter compared to the rainy season. The proportion of grains in the crop during summer and winter season was higher compared to rainy season. Further, there were more insects present in the crop during the rainy season and winter compared to summer.4. The proportion of insects was higher in chickens reared in humid, subtropical and cool temperate regions compared to semi-arid conditions. The consumption of grasses was higher in cool-temperate regions as compared to those reared under other areas.5. Crude protein (CP), Ca, P and gross energy (GE) content of the crop were higher in chickens reared under CFS compared to those reared in backyard systems and CP in the crop contents was lower in backyard chickens reared in humid subtropical and semi-arid regions compared to other areas. Similarly, lower (P < 0.01) Ca levels were seen in crop and gizzard contents from birds reared in semi-arid Rajasthan, and P and GE were lower in tropical wet and dry Telangana (TWT) compared to the chickens reared in the backyard conditions in other regions.6. Based on the results, the nutrient intake for birds utilising the scavenging feed resource base (SFRB) in the TWT region was below the requirements of backyard chickens from the other regions selected in the present study. GE and CP were critically deficient in the SFRB of the TWT region. Therefore, evolving location-specific supplementary diets using locally available feed resources to meet nutrient requirement of backyard chickens is required for optimising production potential.

Correlation-Based Ensemble Feature Selection Using Bioinspired Algorithms and Classification Using Backpropagation Neural Network.

A framework for clinical diagnosis which uses bioinspired algorithms for feature selection and gradient descendant backpropagation neural network for classification has been designed and implemented. The clinical data are subjected to data preprocessing, feature selection, and classification. Hot deck imputation has been used for handling missing values and min-max normalization is used for data transformation. Wrapper approach that employs bioinspired algorithms, namely, Differential Evolution, Lion Optimization, and Glowworm Swarm Optimization with accuracy of AdaBoostSVM classifier as fitness function has been used for feature selection. Each bioinspired algorithm selects a subset of features yielding three feature subsets. Correlation-based ensemble feature selection is performed to select the optimal features from the three feature subsets. The optimal features selected through correlation-based ensemble feature selection are used to train a gradient descendant backpropagation neural network. Ten-fold cross-validation technique has been used to train and test the performance of the classifier. Hepatitis dataset and Wisconsin Diagnostic Breast Cancer (WDBC) dataset from University of California Irvine (UCI) Machine Learning repository have been used to evaluate the classification accuracy. An accuracy of 98.47% is obtained for Wisconsin Diagnostic Breast Cancer dataset, and 95.51% is obtained for Hepatitis dataset. The proposed framework can be tailored to develop clinical decision-making systems for any health disorders to assist physicians in clinical diagnosis.