Search

Abstract Background Septoria tritici blotch (STB) disease causes yield losses of up to 50 per cent in susceptible wheat cultivars and can reduce wheat production. In this study, genomic architecture for adult-plant STB resistance in a Septoria Association Mapping Panel (SAMP) having 181 accessions and genomic regions governing STB resistance in a South Asian wheat panel were looked for. Results Field experiments during the period from 2019 to 2021 revealed those certain accessions, namely BGD52 (CHIR7/ANB//CHIR1), BGD54 (CHIR7/ANB//CHIR1), IND92 (WH 1218), IND8 (DBW 168), and IND75 (PBW 800), exhibited a high level of resistance. Genetic analysis revealed the presence of 21 stable quantitative trait nucleotides (QTNs) associated with resistance to STB (Septoria tritici blotch) on all wheat chromosomes, except for 2D, 3A, 3D, 4A, 4D, 5D, 6B, 6D, and 7A. These QTNs were predominantly located in chromosome regions previously identified as associated with STB resistance. Three Quantitative Trait Loci (QTNs) were found to have significant phenotypic effects in field evaluations. These QTNs are Q.STB.5A.1, Q.STB.5B.1, and Q.STB.5B.3. Furthermore, it is possible that the QTNs located on chromosomes 1A (Q.STB.1A.1), 2A (Q.STB_DH.2A.1, Q.STB.2A.3), 2B (Q.STB.2B.4), 5A (Q.STB.5A.1, Q.STB.5A.2), and 7B (Q.STB.7B.2) could potentially be new genetic regions associated with resistance. Conclusion Our findings demonstrate the importance of Asian bread wheat as a source of STB resistance alleles and novel stable QTNs for wheat breeding programs aiming to develop long-lasting and wide-ranging resistance to Zymoseptoria tritici in wheat cultivars.

Introduction: This study aimed to study on clinical outcomes of single-stage (laparoscopic cholecystectomy [LC] and laparoscopic common bile duct [CBD] exploration using flexible videobronchoscope) versus dual-stage (endoscopic retrograde cholangiopancreatography followed by laparoscopic cholecystectomy) for cholelithiasis with choledocholithiasis-prospective study in a tertiary care centre (BRACE STUDY-Bronchoscope-Assisted CBD Exploration [CBDE] Study). Patients and Methods: Between April 2022 and April 2023, patients who underwent LC with laparoscopic CBDE and endoscopic retrograde cholangiopancreatography (ERCP) followed by LC participated in this single-centre prospective research. The Institute Ethics Committee granted its approval after receiving an ethical review. The primary endpoint of the proposed research was the removal of the gall bladder and CBD stones. The secondary outcomes studied were complications using the Clavien-Dindo score, cost-effectiveness, patient satisfaction score and post-procedure duration of hospital stay. Results: A total of 168 patients were included in the study. The success rate of LC with laparoscopic CBD exploration using a flexible videobronchoscope (Group 1) was significantly higher as compared to ERCP f/b LC (Group 2) (96.4% vs. 84.5%, P value = 0.02). Out of the 84 patients in Group 1, direct choledochotomies were performed on 83 of them. Group 1 had a considerably shorter hospital stay (4.6 ± 2.4 vs. 5.3 ± 6.2 days; P = 0.03). Both the cost (P = 0.002) and the number of procedures per patient (P < 0.001) were considerably higher in Group 2. Major complications (Clavien-Dindo grade 3 and above) were significantly higher in Group 2 (P = 0.04). Patient satisfaction in Group 1 scored more favourably than those in Group 2 (2.26 ± 0.3 vs. 1.92 ± 0.7; P = 0.006). Conclusion: For concurrent gall bladder and CBD stones, single-stage management by LCBDE using a flexible videobronchoscope has a significantly better primary outcome and lower major complications than dual-stage management. The single-stage strategy also has advantages in terms of a shorter hospital stay, the need for fewer procedures, cost efficiency and patient satisfaction.

Abstract Epileptic seizure (ES) detection is an active research area, that aims at patient-specific ES detection with high accuracy from electroencephalogram (EEG) signals. The early detection of seizure is crucial for timely medical intervention and prevention of further injuries of the patients. This work proposes a robust deep learning framework called HyEpiSeiD that extracts self-trained features from the pre-processed EEG signals using a hybrid combination of convolutional neural network followed by two gated recurrent unit layers and performs prediction based on those extracted features. The proposed HyEpiSeiD framework is evaluated on two public datasets, the UCI Epilepsy and Mendeley datasets. The proposed HyEpiSeiD model achieved 99.01% and 97.50% classification accuracy, respectively, outperforming most of the state-of-the-art methods in epilepsy detection domain.

Purpose: The metal present in the implant creates artifacts during the treatment simulation, which impacts the treatment planning and delivery of the prescribed dose to the target and sparing normal tissues. This retrospective study evaluated the uncertainties in the planning and delivery of doses for prosthesis cases with dedicated phantom. Materials and Methods: In this retrospective study, 11 patients with a hip prosthesis having cervix carcinoma were selected. Two treatment plans were generated on treatment planning system (TPS) for each case. Plan_No_Res was without any beam restriction, and Plan_exit_only was the plan with restricted beam entry through the metallic implant. An indigenous phantom was utilized to verify the accuracy of the treatment. In the phantom, some groves were present, which could be filled by implants that mimic the patient’s geometries, like left, right and bilateral femur implants. The delivered doses were recorded using optically stimulated luminescence dosimeters (OSLDs), which were placed at different positions in the phantom. The plans were further calculated using megavoltage computed tomography (MVCT) scans acquired during treatment. Results: The patient data showed no significant dose changes between the two planning methods. The treatment time increases from 412.18 ± 86.65 to 427.36 ± 104.80 with P = 0.03 for Plan_No_Res and Plan_exit_only, respectively. The difference between planned and delivered doses of various points across phantom geometries was within ± 9.5% in each case as left, right, and bilateral implant. The variations between OSLDs and MVCT calculated doses were also within ± 10.8%. Conclusion: The study showed the competency of tomotherapy planning for hip prosthesis cases. The phantom measurements demonstrate the errors in dosimetry near the implant material, suggesting the need for precise methods to deal with artifact-related issues.

Abstract In recent years, the growth spurt of medical imaging data has led to the development of various machine learning algorithms for various healthcare applications. The MedMNISTv2 dataset, a comprehensive benchmark for 2D biomedical image classification, encompasses diverse medical imaging modalities such as Fundus Camera, Breast Ultrasound, Colon Pathology, Blood Cell Microscope etc. Highly accurate classifications performed on these datasets is crucial for identification of various diseases and determining the course of treatment. This research paper presents a comprehensive analysis of four subsets within the MedMNISTv2 dataset: BloodMNIST, BreastMNIST, PathMNIST and RetinaMNIST. Each of these selected datasets is of diverse data modalities and comes with various sample sizes, and have been selected to analyze the efficiency of the model against diverse data modalities. The study explores the idea of assessing the Vision Transformer Model’s ability to capture intricate patterns and features crucial for these medical image classification and thereby transcend the benchmark metrics substantially. The methodology includes pre-processing the input images which is followed by training the ViT-base-patch16-224 model on the mentioned datasets. The performance of the model is assessed using key metrices and by comparing the classification accuracies achieved with the benchmark accuracies. With the assistance of ViT, the new benchmarks achieved for BloodMNIST, BreastMNIST, PathMNIST and RetinaMNIST are 97.90%, 90.38%, 94.62% and 57%, respectively. The study highlights the promise of Vision transformer models in medical image analysis, preparing the way for their adoption and further exploration in healthcare applications, aiming to enhance diagnostic accuracy and assist medical professionals in clinical decision-making.

Zika virus (ZIKV) is a re-emerging RNA virus that is known to cause ocular and neurological abnormalities in infants. ZIKV exploits autophagic processes in infected cells to enhance its replication and spread. Thus, autophagy inhibitors have emerged as a potent therapeutic target to combat RNA viruses, with Hydroxychloroquine (HCQ) being one of the most promising candidates. In this study, we synthesized several novel small-molecule quinoline derivatives, assessed their antiviral activity, and determined the underlying molecular mechanisms. Among the nine synthesized analogs, two lead candidates, labeled GL-287 and GL-382, significantly attenuated ZIKV replication in human ocular cells, primarily by inhibiting autophagy. These two compounds surpassed the antiviral efficacy of HCQ and other existing autophagy inhibitors, such as ROC-325, DC661, and GNS561. Moreover, unlike HCQ, these novel analogs did not exhibit cytotoxicity in the ocular cells. Treatment with compounds GL-287 and GL-382 in ZIKV-infected cells increased the abundance of LC3 puncta, indicating the disruption of the autophagic process. Furthermore, compounds GL-287 and GL-382 effectively inhibited the ZIKV-induced innate inflammatory response in ocular cells. Collectively, our study demonstrates the safe and potent antiviral activity of novel autophagy inhibitors against ZIKV.

Summary: Background: Emerging research indicates growing concern over long COVID globally, although there have been limited studies that estimate population burden. We aimed to estimate the burden of long COVID in three districts of Haryana, India, using an opportunity to link a seroprevalence study to follow-up survey of symptoms associated with long COVID. Methods: We used a population-based seroprevalence survey for COVID-19 conducted in September 2021 across Haryana, India. Adults from three purposively selected districts (Rohtak, Gurugram, and Jhajjar) were eligible to participate; 2205 of 3213 consented to participate in a survey on health status. Trained investigators administered a structured questionnaire that included demographic characteristics, self-reported symptoms of illness in the last six months before the survey, mental health, and history of COVID-19. Findings: Unadjusted regression estimates indicated positive correlations between symptomatic complaints and COVID-19 exposure, suggesting lingering effects of COVID-19 in this population. The overall physical morbidity index was higher among those who tested positive for COVID-19, as was the incidence of new cases. However, both morbidity and incidence became statistically insignificant after adjustment for multiple comparisons. Cough emerged as the only statistically significant individual persistent symptom. Sex-stratified analyses indicated significant estimates only for physical morbidity in women. Interpretation: This study is one of the first from India that uses a large population-based sample to examine longer term repercussions of COVID infections. The burden of long COVID should primarily be addressed in clinical settings, where specialised treatment for individual cases continues to evolve. Our analyses also provide insight into the size and nature of studies required to assess the population-level burden of long COVID. Funding: This paper was produced under the auspices of the Lancet COVID 19 Commission India Task Force, which was supported financially by the Reliance Foundation. The Lancet COVID 19 Commission was set up in July 2020 and submitted its final report by October 2022. This report by the India Task Force was prepared during the same period.

SARS-CoV-2 has been shown to cause wide-ranging ocular abnormalities and vision impairment in COVID-19 patients. However, there is limited understanding of SARS-CoV-2 in ocular transmission, tropism, and associated pathologies. The presence of viral RNA in corneal/conjunctival tissue and tears, along with the evidence of viral entry receptors on the ocular surface, has led to speculation that the eye may serve as a potential route of SARS-CoV-2 transmission. Here, we investigated the interaction of SARS-CoV-2 with cells lining the blood-retinal barrier (BRB) and the role of the eye in its transmission and tropism. The results from our study suggest that SARS-CoV-2 ocular exposure does not cause lung infection and moribund illness in K18-hACE2 mice despite the extended presence of viral remnants in various ocular tissues. In contrast, intranasal exposure not only resulted in SARS-CoV-2 spike (S) protein presence in different ocular tissues but also induces a hyperinflammatory immune response in the retina. Additionally, the long-term exposure to viral S-protein caused microaneurysm, retinal pigmented epithelium (RPE) mottling, retinal atrophy, and vein occlusion in mouse eyes. Notably, cells lining the BRB, the outer barrier, RPE, and the inner barrier, retinal vascular endothelium, were highly permissive to SARS-CoV-2 replication. Unexpectedly, primary human corneal epithelial cells were comparatively resistant to SARS-CoV-2 infection. The cells lining the BRB showed induced expression of viral entry receptors and increased susceptibility towards SARS-CoV-2-induced cell death. Furthermore, hyperglycemic conditions enhanced the viral entry receptor expression, infectivity, and susceptibility of SARS-CoV-2-induced cell death in the BRB cells, confirming the reported heightened pathological manifestations in comorbid populations. Collectively, our study provides the first evidence of SARS-CoV-2 ocular tropism via cells lining the BRB and that the virus can infect the retina via systemic permeation and induce retinal inflammation.

Abstract Spot blotch caused by Bipolaris sorokiniana ((Sacc.) Shoemaker) (teleomorph: Cochliobolus sativus [Ito and Kuribayashi] Drechsler ex Dastur) is an economically important disease of warm and humid regions. The present study focused on identifying resistant genotypes and single‐nucleotide polymorphism (SNP) markers associated with spot blotch resistance in a panel of 174 bread spring wheat lines using field screening and genome‐wide association mapping strategies. Field experiments were conducted in Agua Fria, Mexico, during the 2019–2020 and 2020–2021 cropping seasons. A wide range of phenotypic variation was observed among genotypes tested during both years. Twenty SNP markers showed significant association with spot blotch resistance on 15 chromosomes, namely, 1A, 1B, 2A, 2B, 2D, 3A, 3B, 4B, 4D, 5A, 5B, 6A, 6B, 7A, and 7B. Of these, two consistently significant SNPs on 5A, TA003225‐0566 and TA003225‐1427, may represent a new resistance quantitative trait loci. Further, in the proximity of Tsn1 on 5B, AX‐94435238 was the most stable and consistent in both years. The identified genomic regions could be deployed to develop spot blotch‐resistant genotypes, particularly in the spot blotch‐vulnerable wheat growing areas.

Abstract Background Colonic perforation usually presents with classical signs of peritonitis. However, isolated retroperitoneal colonic perforation can present with varied clinical signs and symptoms and pose diagnostic challenges. Pneumo-mediastinum and abdominal subcutaneous emphysema can be one of the presenting signs of colonic perforation. Case report A 33-year-old male presented with abdominal distension and extensive subcutaneous emphysema over the abdomen, pneumo-mediastinum, and pneumo-scrotum secondary to sigmoid colon perforation from a foreign body. The patient did not have classical signs of peritonitis. Conclusion Being vigilant about the potential of colonic perforation is crucial when observing a significantly increasing subcutaneous emphysema across different parts of the body. Attending clinicians should always keep intraabdominal pathology in mind when a direct cause for these symptoms cannot be found and the patient’s symptoms become progressive.

Abstract Colorectal cancer is the third most common type of cancer diagnosed annually, and the second leading cause of death due to cancer. Early diagnosis of this ailment is vital for preventing the tumours to spread and plan treatment to possibly eradicate the disease. However, population-wide screening is stunted by the requirement of medical professionals to analyse histological slides manually. Thus, an automated computer-aided detection (CAD) framework based on deep learning is proposed in this research that uses histological slide images for predictions. Ensemble learning is a popular strategy for fusing the salient properties of several models to make the final predictions. However, such frameworks are computationally costly since it requires the training of multiple base learners. Instead, in this study, we adopt a snapshot ensemble method, wherein, instead of the traditional method of fusing decision scores from the snapshots of a Convolutional Neural Network (CNN) model, we extract deep features from the penultimate layer of the CNN model. Since the deep features are extracted from the same CNN model but for different learning environments, there may be redundancy in the feature set. To alleviate this, the features are fed into Particle Swarm Optimization, a popular meta-heuristic, for dimensionality reduction of the feature space and better classification. Upon evaluation on a publicly available colorectal cancer histology dataset using a five-fold cross-validation scheme, the proposed method obtains a highest accuracy of 97.60% and F1-Score of 97.61%, outperforming existing state-of-the-art methods on the same dataset. Further, qualitative investigation of class activation maps provide visual explainability to medical practitioners, as well as justifies the use of the CAD framework in screening of colorectal histology. Our source codes are publicly accessible at: https://github.com/soumitri2001/SnapEnsemFS .

Vehicle make and model recognition (VMMR) is a crucial task for developing automatic vehicle recognition (AVR) systems, and has gained significant attention in the fields of computer vision and artificial intelligence in recent years. The ability to automatically identify a vehicle's make and model has numerous practical applications, such as traffic monitoring, vehicle re-identification, etc. This survey paper provides a comprehensive overview of the state-of-the-art techniques developed for VMMR problem. The survey begins with an introduction to the problem of AVR, followed by a discussion of the various factors that affect the accuracy of recognition, including lighting conditions, viewpoint variations, and occlusions. We then discuss a solution to this problem and provide an overview of the different approaches for VMMR, such as machine learning approaches and deep learning approaches. This survey also provides a comprehensive review of publicly available datasets that have been used for evaluating VMMR methods. Finally, the paper concludes with a discussion of some of the remaining challenges in VMMR, such as the need for large-scale datasets with more diverse vehicle models, the need for more robust methods that can handle variations in lighting and viewpoint, and the need for real-time methods that can operate in a variety of settings. This survey aims to serve as a valuable resource for researchers working in the field of computer vision that includes AVR.

Background Patients with chronic-obstructive-pulmonary-disease (COPD) undergo bronchoscopy for various reasons, and are at relatively higher risk of complications. This study evaluated the efficacy of non-invasive ventilation (NIV) and high-flow-oxygen-therapy (HFOT) compared with conventional-oxygen-therapy (COT) in patients with COPD undergoing bronchoscopy, to prevent hypoxia.Methods It was a triple-arm, open-label, randomised controlled trial. Ninety patients with COPD were randomly assigned into three intervention arms in 1:1:1 ratio. The incidence of hypoxia, lowest recorded oxygen saturation measured by plethysmography (SpO2), ECG, patient vitals and comfort levels were assessed.Results Mean age of the study population was 61.71±7.5 years. Out of 90 cases enrolled, 51, 34 and 5 were moderate, severe and very-severe COPD, respectively, as per GOLD (Global Initiative for Chronic Obstructive Lung Disease) classification. Rest of the baseline characteristics were similar. SpO2 during flexible bronchoscopy (FB) was lowest in COT group (COT: 87.03±5.7% vs HFOT: 95.57±5.0% vs NIV: 97.40±1.6%, p

Abstract The productivity of rice is greatly affected by the infection of the plant pathogenic fungus Rhizoctonia solani, which causes a significant grain yield reduction globally. There exist a limited number of rice accessions that are available to develop sheath blight resistance (ShB). Our objective was to identify a good source of the ShB resistance, understand the heritability, and trait interactions, and identify the genomic regions for ShB resistance traits by genome‐wide association studies (GWAS). In the present study, a set of 330 traditional landraces and improved rice varieties were evaluated for ShB resistance and created a core panel of 192 accessions used in the GWAS. This panel provides a more considerable amount of genetic variance and found a significant phenotypic variation among the panel of rice accessions for all the agro‐morphological and disease‐resistance traits over the seasons. The infection rate of ShB and disease reaction were calculated as percent disease index (PDI) and area under the disease progress curve (AUDPC). The correlation analysis showed a significant positive association between PDIs and AUPDC and a negative association between PDI and plant height, flag leaf length, and grain yield. The panel was genotyped with 133 SSR microsatellite markers, resulting in a genome coverage of 314.83 Mb, and the average distance between markers is 2.53 Mb. By employing GLM and MLM (Q + K) models, 30 marker–trait associations (MTAs) were identified with targeted traits over the seasons. Among these QTLs, eight were found to be novel and located on 2, 4, 8, 10, and 12 chromosomes, which explained the phenotypic variation ranging from 5% to 15%. With the GWAS approach, six candidate genes were identified. Os05t0566400, Os08t0155900, and Os09t0567300 were found to be associated with defense mechanisms against ShB. These findings provided insights into the novel donors of IC283139, IC 277248, Sivappuchithirai Kar, and Bowalia. The promising genomic regions on 10 of 12 chromosomes associated with ShB would be useful in developing rice varieties with durable disease resistance.

IntroductionSheath blight caused by Rhizoctonia solani is one of the major diseases of rice, causing widespread crop losses. The use of semi-dwarf rice varieties in the ongoing nutrient-intensive rice cultivation system has further accentuated the incidence of the disease. An ideal solution to this problem would be identifying a stable sheath blight-tolerant genotype. Material and methodsA multi-environment evaluation of 32 rice genotypes against sheath blight infection was conducted over six seasons across two locations (Agricultural Research Farm, Institute of Agricultural Sciences, Banaras Hindu University (28.18° N, 38.03° E, and 75.5 masl), for four years during the wet seasons (kharif) from 2015 to 2018 and two seasons at the National Rice Research Institute (20°27’09” N, 85°55’57” E, 26 masl), Cuttack, Odisha, during the dry season (rabi) of 2019 and the kharif of 2019, including susceptible and resistant check. Percent disease index data were collected over 4 weeks (on the 7th, 14th, 21st, and 28th day after infection), along with data on other morphological and physiological traits.Result and discussionThe resistant genotypes across seasons were the ones with a higher hemicellulose content (13.93-14.64) and lower nitrogen content (1.10- 1.31) compared with the susceptible check Tapaswini (G32) (hemicellulose 12.96, nitrogen 1.38), which might explain the resistant reaction. Three different stability models—additive main effect and multiplicative interaction (AMMI), genotype + genotype x environment (GGE) biplot, and multi-trait stability index (MTSI)—were then used to identify the stable resistant genotypes across six seasons. The results obtained with all three models had common genotypes highlighted as stable and having a low area under the disease progress curve (AUDPC) values. The ideal stable genotypes with low disease incidence were IC 283139 (G19), Tetep (G28), IC 260917 (G4), and IC 277274 (G10), with AUDPC values of 658.91, 607.46, 479.69, and 547.94, respectively. Weather parameters such as temperature, rainfall, sunshine hours, and relative humidity were also noted daily. Relative humidity was positively correlated with the percent disease index.

The leaf blight diseases, Septoria nodorum blotch (SNB), and tan spot (TS) are emerging due to changing climatic conditions in the northern parts of India. We screened 296 bread wheat cultivars released in India over the past 20 years for seedling resistance against SNB (three experiments) and TS (two experiments). According to a genome-wide association study, six QTLs on chromosome arms 1BL, 2AS, 5BL, and 6BL were particularly significant for SNB across all three years, of which Q.CIM.snb.1BL, Q.CIM.snb.2AS1, Q.CIM.snb.2AS.2, and Q.CIM.snb.6BL appeared novel. In contrast, those on 5BS and 5BL may correspond to Snn3 and Tsn1, respectively. The allelic combination of tsn1/snn3 conferred resistance to SNB, whereas that of Tsn1/Snn3 conferred high susceptibility. As for TS, Tsn1 was the only stably significant locus identified in this panel. Several varieties like PBW 771, DBW 277, and HD 3319, were identified as highly resistant to both diseases that can be used in future wheat improvement programs as resistant donors.

The agriculture sector plays an essential function within the Indian economic system. Foodgrains provide almost all the calories and proteins. This paper aims to compare ARIMA, SutteARIMA, Holt-Winters, and NNAR models to recommend an effective model to predict foodgrains production in India. The execution of the SutteARIMA predictive model used in this analysis was compared with the established ARIMA, Neural Network Auto-Regressive (NNAR), and Holt-Winters models, which have been widely applied for time series prediction. The findings of this study reveal that both the SutteARIMA model and the Holt-Winters model performed well with real-life problems and can effectively and profitably be engaged for food grain forecasting in India. The food grain forecasting approach with the SutteARIMA model indicated superior performance over the ARIMA, Holt-Winters, and NNAR models. Indeed, the actual and predicted values of the SutteARIMA and Holt-Winters forecasting models are quite close to predicting foodgrains production in India. This has been verified by MAPE and MSE values that are relatively low with the SutteARIMA model. Therefore, India’s SutteARIMA model was used to predict foodgrains production from 2021 to 2025. The forecasted amount of respective crops are as follows (in lakh tonnes) 1140.14 (wheat), 1232.27 (rice), 466.46 (coarse), 259.95 (pulses), and a total 3069.80 (foodgrains) by 2025.

Abstract The Human Activity Recognition (HAR) problem leverages pattern recognition to classify physical human activities as they are captured by several sensor modalities. Remote monitoring of an individual’s activities has gained importance due to the reduction in travel and physical activities during the pandemic. Research on HAR enables one person to either remotely monitor or recognize another person’s activity via the ubiquitous mobile device or by using sensor-based Internet of Things (IoT). Our proposed work focuses on the accurate classification of daily human activities from both accelerometer and gyroscope sensor data after converting into spectrogram images. The feature extraction process follows by leveraging the pre-trained weights of two popular and efficient transfer learning convolutional neural network models. Finally, a wrapper-based feature selection method has been employed for selecting the optimal feature subset that both reduces the training time and improves the final classification performance. The proposed HAR model has been tested on the three benchmark datasets namely, HARTH, KU-HAR and HuGaDB and has achieved 88.89%, 97.97% and 93.82% respectively on these datasets. It is to be noted that the proposed HAR model achieves an improvement of about 21%, 20% and 6% in the overall classification accuracies while utilizing only 52%, 45% and 60% of the original feature set for HuGaDB, KU-HAR and HARTH datasets respectively. This proves the effectiveness of our proposed wrapper-based feature selection HAR methodology.

Background Acute respiratory failure (ARF) is commonly managed with invasive mechanical ventilation (IMV). The majority of the time that a patient spends on IMV is in the process of weaning. Prediction of the weaning outcome is of paramount importance, as untimely/delayed extubation is associated with a high risk of mortality. Diaphragmatic ultrasonography is a promising tool in the intensive care unit, and its utility in predicting the success of weaning remains understudied. Methods In this prospective-observational study, we recruited 54 ARF patients on IMV, along with 50 healthy controls. During a spontaneous breathing trial, all subjects underwent diaphragmatic ultrasonography along with a rapid shallow breathing index (RSBI) assessment. Results The mean age was 41.8±17.0 and 37.6±10.5 years among the cases and control group, respectively. Demographic variables were broadly similar in the two groups. The most common cause of ARF was obstructive airway disease. The average duration of IMV was 5.41±2.81 days. Out of 54 subjects, 45 were successfully weaned, while nine patients failed weaning. Age, body mass index, and severity of disease were similar in the successful and failed weaning patients. The sensitivity in predicting successful weaning of percent change in diaphragmatic thickness (Δtdi%) >29.71% was high (93.33%), while specificity was 66.67%. The sensitivity and specificity of mean diaphragmatic thickness (tdi) end-expiratory >0.178 cm was 60.00% and 77.78%, respectively. RSBI at 1 minute of

During and following the COVID-19 pandemic, the world has witnessed a surge in high-flow oxygen therapy (HFOT) use. The ability to provide high oxygenation levels with remarkable comfort levels has been the grounds for the same. Despite the advantages, delay in intubation leading to poor overall outcomes has been noticed in subgroup of patients on HFOT. ROX index has been proposed to be a useful indicator to predict HFOT success. In this study, we have examined the utility of the ROX index prospectively in cases of acute hypoxemic respiratory failure (AHRF) due to infective etiologies. Seventy participants were screened, and 55 were recruited for the study. The majority of participants were males (56.4%), with diabetes mellitus being the most common comorbidity (29.1%). The mean age of the study subjects was 46.27±15.6 years. COVID-19 (70.9%) was the most common etiology for AHRF, followed by scrub typhus (21.8%). Nineteen (34.5%) experienced HFOT failure and 9 (16.4%) subjects died during the study period. Demographic characteristics did not differ between either of the two groups (HFOT success versus failure and survived group versus expired group). ROX index was significantly different between the HFOT success versus failure group at baseline, 2, 4, 6, 12 and 24 h. The best cut-off of ROX index at baseline and 2 h were 4.4 (sensitivity 91.7%, specificity 86.7%) and 4.3 (sensitivity 94.4% and specificity 86.7%), respectively. ROX index was found to be an efficient tool in predicting HFOT failure in cases with AHRF with infective etiology.

IntroductionCurrently, there are no guidelines for the management of B-cell lineage acute lymphoblastic leukemia (B-ALL) from an Indian perspective. The diagnostic workup, monitoring, and treatment of B-ALL vary among different physicians and institutes.ObjectiveTo develop evidence-based practical consensus recommendations for the management of B-ALL in Indian settings.MethodsModified Delphi consensus methodology was considered to arrive at a consensus. An expert scientific committee of 15 experts from India constituted the panel. Clinically relevant questions belonging to three major domains were drafted for presentation and discussion: (i) diagnosis and risk assignment; (ii) frontline treatment; and (iii) choice of therapy (optimal vs. real-world practice) in relapsed/refractory (R/R) settings. The questionnaire was shared with the panel members through an online survey platform. The level of consensus was categorized into high (≥ 80%), moderate (60%–79%), and no consensus (< 60%). The process involved 2 rounds of discussion and 3 rounds of Delphi survey. The questions that received near or no consensus were discussed during virtual meetings (Delphi rounds 1 and 2). The final draft of the consensus was emailed to the panel for final review.ResultsExperts recommended morphologic assessment of peripheral blood or bone marrow, flow cytometric immunophenotyping, and conventional cytogenetic analysis in the initial diagnostic workup. Berlin–Frankfurt–Münster (BFM)–based protocol is the preferred frontline therapy in pediatric and adolescent and young adult patients with B-ALL. BFM/German Multicenter Study Group for Adult Acute Lymphoblastic Leukemia–based regimen is suggested in adult patients with B-ALL. Immunotherapy (blinatumomab or inotuzumab ozogamicin) followed by allogeneic hematopoietic cell transplantation (allo-HCT) is the optimal choice of therapy that would yield the best outcomes if offered in the first salvage in patients with R/R B-ALL. In patients with financial constraints or prior allo-HCT (real-world practice) at first relapse, standard-intensive chemotherapy followed by allo-HCT may be considered. For subsequent relapses, chimeric antigen receptor T-cell therapy or palliative care was suggested as the optimal choice of therapy.ConclusionThis expert consensus will offer guidance to oncologists/clinicians on the management of B-ALL in Indian settings.

Wheat, one of the most important food crops, is threatened by a blast disease pandemic. Here, we show that a clonal lineage of the wheat blast fungus recently spread to Asia and Africa following two independent introductions from South America. Through a combination of genome analyses and laboratory experiments, we show that the decade-old blast pandemic lineage can be controlled by the Rmg8 disease resistance gene and is sensitive to strobilurin fungicides. However, we also highlight the potential of the pandemic clone to evolve fungicide-insensitive variants and sexually recombine with African lineages. This underscores the urgent need for genomic surveillance to track and mitigate the spread of wheat blast outside of South America and to guide preemptive wheat breeding for blast resistance. Wheat, the most important food crop, is threatened by a blast disease pandemic. This study uses genome analyses to track the spread of a clonal lineage of the pandemic blast fungus and to reveal its potential to evolve fungicide-insensitive variants and sexually recombine with African lineages.

Abstract Human Action Recognition (HAR) is a popular area of research in computer vision due to its wide range of applications such as surveillance, health care, and gaming, etc. Action recognition based on 3D skeleton data allows simplistic, cost-efficient models to be formed making it a widely used method. In this work, we propose DSwarm-Net, a framework that employs deep learning and swarm intelligence-based metaheuristic for HAR that uses 3D skeleton data for action classification. We extract four different types of features from the skeletal data namely: Distance, Distance Velocity, Angle, and Angle Velocity, which capture complementary information from the skeleton joints for encoding them into images. Encoding the skeleton data features into images is an alternative to the traditional video-processing approach and it helps in making the classification task less complex. The Distance and Distance Velocity encoded images have been stacked depth-wise and fed into a Convolutional Neural Network model which is a modified version of Inception-ResNet. Similarly, the Angle and Angle Velocity encoded images have been stacked depth-wise and fed into the same network. After training these models, deep features have been extracted from the pre-final layer of the networks, and the obtained feature representation is optimized by a nature-inspired metaheuristic, called Ant Lion Optimizer, to eliminate the non-informative or misleading features and to reduce the dimensionality of the feature set. DSwarm-Net has been evaluated on three publicly available HAR datasets, namely UTD-MHAD, HDM05, and NTU RGB+D 60 achieving competitive results, thus confirming the superiority of the proposed model compared to state-of-the-art models.

In this current era, the identification of both known and novel cell types, the representation of cells, predicting cell fates, classifying various tumor types, and studying heterogeneity in various cells are the key areas of interest in the analysis of single-cell RNA sequencing (scRNA-seq) data. Due to the nature of the data, cluster identification in single-cell sequencing data with high dimensions presents several difficulties. In this paper, we introduce a new framework that combines various strategies such as imputed matrix, minimum redundancy maximum relevance (MRMR) feature selection, and shrinkage clustering to discover gene signatures from scRNA-seq data. Firstly, we conducted the pre-filtering of the “drop-out” value in the data focusing solely on imputing the identified “drop-out” values. Next, we applied the MRMR feature selection method to the imputed data and obtained the top 100 features based on the MRMR feature selection optimization scores for further downstream analysis. Thereafter, we employed shrinkage clustering on the selected feature matrix to identify the cell clusters using a global optimization approach. Finally, we applied the Limma-Voom R tool employing voom normalization and an empirical Bayes test to detect differentially expressed features with a false discovery rate (FDR) < 0.001. In addition, we performed the KEGG pathway and gene ontology enrichment analysis of the identified biomarkers using David 6.8 software. Furthermore, we conducted miRNA target detection for the top gene markers and performed miRNA target gene interaction network analysis using the Cytoscape online tool. Subsequently, we compared our detected 100 markers with our previously detected top 100 cluster-specified markers ranked by FDR of the latest published article and discovered three common markers; namely, Cyp2b10, Mt1, Alpi, along with 97 novel markers. In addition, the Gene Set Enrichment Analysis (GSEA) of both marker sets also yields similar outcomes. Apart from this, we performed another comparative study with another published method, demonstrating that our model detects more significant markers than that model. To assess the efficiency of our framework, we apply it to another dataset and identify 20 strongly significant up-regulated markers. Additionally, we perform a comparative study of different imputation methods and include an ablation study to prove that every key phase of our framework is essential and strongly recommended. In summary, our proposed integrated framework efficiently discovers differentially expressed stronger gene signatures as well as up-regulated markers in single-cell RNA sequencing data.

Purpose: To study the impact of different optimization methods in dealing with metallic hip implant using intensity-modulated radiotherapy (IMRT) and volumetric-modulated arc therapy (VMAT) techniques. Materials and Methods: A cohort of 16 patients having metallic implants was selected for the study. Three sets of IMRT and VMAT plans were generated. Set 1 IMRT (IM_Base), VMAT (VM_Base) without any restrictions on beam entry and exit, set 2 (IM_ENT and VM_ENT) optimizer restricts the beam entry and set 3 (IM_EXT+ENT), neither entry nor exit doses were allowed toward the metallic implant. Results: There was no significant difference in target (D95%) and organ-at-risk doses between IM_Base and IM_ENT. There were significant (P = 0.002) improvements in planning target volume (PTV) V95% and homogeneity from IM_EXT+ENT to IM_ENT. There was no significant difference in plan quality between VM_Base and VM_ENT. There were significant (P = 0.005) improvements in PTV, V95%, homogeneity from VM_EXT+ENT to VM_ENT. V40Gy, V30Gy for bladder, rectum, bowel, and bowel maximum dose decreases significantly (P < 0.005) in IM_ENT compared to IM_EXT+ENT, but not significant for VMAT plans. Similarly, there was a significant decrease in dose spill outside target (P < 0.05) comparing 40%, 50%, 60%, and 70% dose spills for IM_ENT compared to IM_EXT+ENT, but variations among VMAT plans are insignificant. VMAT plans were always superior to IMRT plans for the same optimization methods. Conclusion: The best approach is to plan hip prosthesis cases with blocked entry of radiation beam for IMRT and VMAT. The VMAT plans had more volumetric coverage, fewer hotspots, and lesser heterogeneity.

Music has been an integral part of the history of humankind with theories suggesting it is more antediluvian than speech itself. Music is an ordered succession of tones and harmonies that produce sounds characterized by melody and rhythm. Our paper proposes an ensemble deep learning musical instrument classification (MIC) framework, named as MIC_FuzzyNET model which aims to classify the dominant instruments present in musical clips. Firstly, the musical data is converted to three different spectrograms: Constant Q-Transform, Semitone Spectrogram, and Mel Spectrogram, which are then stacked to form 3 channel 2D data. This stacked spectrogram is fed to transfer learning models namely, EfficientNetV2 and ResNet18 which output the preliminary classification scores. A fuzzy rank ensemble model is finally employed that assigns the classifier ranks, on the testing data to achieve final enhanced classification scores which reduces error and biases for the constituent CNN architectures. Our proposed framework has been evaluated on the Persian Classical Music Instrument Recognition (PCMIR) dataset and Instrument Recognition in Musical Audio Signals (IRMAS) dataset. It has achieved considerably high accuracy, making our proposed framework a robust MIC model.

Abstract COVID-19 is a respiratory disease that causes infection in both lungs and the upper respiratory tract. The World Health Organization (WHO) has declared it a global pandemic because of its rapid spread across the globe. The most common way for COVID-19 diagnosis is real-time reverse transcription-polymerase chain reaction (RT-PCR) which takes a significant amount of time to get the result. Computer based medical image analysis is more beneficial for the diagnosis of such disease as it can give better results in less time. Computed Tomography (CT) scans are used to monitor lung diseases including COVID-19. In this work, a hybrid model for COVID-19 detection has developed which has two key stages. In the first stage, we have fine-tuned the parameters of the pre-trained convolutional neural networks (CNNs) to extract some features from the COVID-19 affected lungs. As pre-trained CNNs, we have used two standard CNNs namely, GoogleNet and ResNet18. Then, we have proposed a hybrid meta-heuristic feature selection (FS) algorithm, named as Manta Ray Foraging based Golden Ratio Optimizer (MRFGRO) to select the most significant feature subset. The proposed model is implemented over three publicly available datasets, namely, COVID-CT dataset, SARS-COV-2 dataset, and MOSMED dataset, and attains state-of-the-art classification accuracies of 99.15%, 99.42% and 95.57% respectively. Obtained results confirm that the proposed approach is quite efficient when compared to the local texture descriptors used for COVID-19 detection from chest CT-scan images.

Background: Health Care Workers (HCW) are among the primary stakeholders and front liners in the fight against COVID-19. They are in direct contact with the patients as primary caregivers and, therefore, are at a higher risk of infection. This Pandemic offers a unique opportunity to explore the level of knowledge among ground-level HCWs during this global health crisis. Objective: We conducted this study to assess the knowledge and awareness among HCW regarding the COVID-19 Pandemic in a tertiary care hospital. Methods: It was a cross-sectional study done on HCW comprising faculty, senior residents, junior residents, demonstrators, and nursing staff of various specialties directly involved in the care of suspected/confirmed COVID-19 patients. A pretested questionnaire consisting of 20 questions was used as a study tool and was circulated through the digital platform. Results: There were a total of 437 respondents. In the subgroup analysis, the respondents in the age group of 55–64 years had a higher mean knowledge score, followed by the respondents in the age group of 18–24 years. For years of experience, the mean knowledge score varied from 13.89 (10–20 years of experience) to 13.83 (5–10 years of experience). The mean knowledge score was the highest for consultants (14.10), followed by Resident Doctors (13.96). Conclusions: This study has shed some critical clues for further research and interventions. Firstly, as health care workers are probably learning about COVID-19 from their practical exposure rather than formal teaching, it is pertinent to address this issue through well-planned formal sessions of training workshops and lectures.

Fusarium head blight (FHB) is an economically important disease affecting wheat and thus poses a major threat to wheat production. Several studies have evaluated the effectiveness of image analysis methods to predict FHB using disease-infected grains; however, few have looked at the final application, considering the relationship between cost and benefit, resolution, and accuracy. The conventional screening of FHB resistance of large-scale samples is still dependent on low-throughput visual inspections. This study aims to compare the performance of two cost–benefit seed image analysis methods, the free software “SmartGrain” and the fully automated commercially available instrument “Cgrain Value™” by assessing 16 seed morphological traits of winter wheat to predict FHB. The analysis was carried out on a seed set of FHB which was visually assessed as to the severity. The dataset is composed of 432 winter wheat genotypes that were greenhouse-inoculated. The predictions from each method, in addition to the predictions combined from the results of both methods, were compared with the disease visual scores. The results showed that Cgrain Value™ had a higher prediction accuracy of R2 = 0.52 compared with SmartGrain for which R2 = 0.30 for all morphological traits. However, the results combined from both methods showed the greatest prediction performance of R2 = 0.58. Additionally, a subpart of the morphological traits, namely, width, length, thickness, and color features, showed a higher correlation with the visual scores compared with the other traits. Overall, both methods were related to the visual scores. This study shows that these affordable imaging methods could be effective to predict FHB in seeds and enable us to distinguish minor differences in seed morphology, which could lead to a precise performance selection of disease-free seeds/grains.

Genomic prediction combines molecular and phenotypic data in a training population to predict the breeding values of individuals that have only been genotyped. The use of genomic information in breeding programs helps to increase the frequency of favorable alleles in the populations of interest. This study evaluated the performance of BLUP (Best Linear Unbiased Prediction) in predicting resistance to tan spot, spot blotch and Septoria nodorum blotch in synthetic hexaploid wheat. BLUP was implemented in single-trait and multi-trait models with three variations: (1) the pedigree relationship matrix (A-BLUP), (2) the genomic relationship matrix (G-BLUP), and (3) a combination of the two matrices (A+G BLUP). In all three diseases, the A-BLUP model had a lower performance, and the G-BLUP and A+G BLUP were statistically similar (p ≥ 0.05). The prediction accuracy with the single trait was statistically similar (p ≥ 0.05) to the multi-trait accuracy, possibly due to the low correlation of severity between the diseases.

Abstract COVID-19 has crippled the world’s healthcare systems, setting back the economy and taking the lives of several people. Although potential vaccines are being tested and supplied around the world, it will take a long time to reach every human being, more so with new variants of the virus emerging, enforcing a lockdown-like situation on parts of the world. Thus, there is a dire need for early and accurate detection of COVID-19 to prevent the spread of the disease, even more. The current gold-standard RT-PCR test is only 71% sensitive and is a laborious test to perform, leading to the incapability of conducting the population-wide screening. To this end, in this paper, we propose an automated COVID-19 detection system that uses CT-scan images of the lungs for classifying the same into COVID and Non-COVID cases. The proposed method applies an ensemble strategy that generates fuzzy ranks of the base classification models using the Gompertz function and fuses the decision scores of the base models adaptively to make the final predictions on the test cases. Three transfer learning-based convolutional neural network models are used, namely VGG-11, Wide ResNet-50-2, and Inception v3, to generate the decision scores to be fused by the proposed ensemble model. The framework has been evaluated on two publicly available chest CT scan datasets achieving state-of-the-art performance, justifying the reliability of the model. The relevant source codes related to the present work is available in: GitHub.

Abstract COVID-19, a viral infection originated from Wuhan, China has spread across the world and it has currently affected over 115 million people. Although vaccination process has already started, reaching sufficient availability will take time. Considering the impact of this widespread disease, many research attempts have been made by the computer scientists to screen the COVID-19 from Chest X-Rays (CXRs) or Computed Tomography (CT) scans. To this end, we have proposed GraphCovidNet, a Graph Isomorphic Network (GIN) based model which is used to detect COVID-19 from CT-scans and CXRs of the affected patients. Our proposed model only accepts input data in the form of graph as we follow a GIN based architecture. Initially, pre-processing is performed to convert an image data into an undirected graph to consider only the edges instead of the whole image. Our proposed GraphCovidNet model is evaluated on four standard datasets: SARS-COV-2 Ct-Scan dataset, COVID-CT dataset, combination of covid-chestxray-dataset, Chest X-Ray Images (Pneumonia) dataset and CMSC-678-ML-Project dataset. The model shows an impressive accuracy of 99% for all the datasets and its prediction capability becomes 100% accurate for the binary classification problem of detecting COVID-19 scans. Source code of this work can be found at GitHub-link .

The limited availability of effective treatment against SARS-CoV-2 infection is a major challenge in managing COVID-19. This scenario has augmented the need for repurposing anti-virals for COVID-19 mitigation. In this report, the anti-SARS-CoV-2 potential of anti-HCV drugs such as daclatasvir (DCV) or ledipasvir (LDP) in combination with sofosbuvir (SOF) was evaluated. The binding mode and higher affinity of these molecules with RNA-dependent-RNA-polymerase of SARS-CoV-2 were apparent by computational analysis. In vitro anti-SARS-CoV-2 activity depicted that SOF/DCV and SOF/LDP combination has IC50 of 1.8 and 2.0 µM, respectively, comparable to remdesivir, an approved drug for COVID-19. Furthermore, the clinical trial was conducted in 183 mild COVID-19 patients for 14 days to check the efficacy and safety of SOF/DCV and SOF/LDP compared to standard of care (SOC) in a parallel-group, hybrid, individually randomized, controlled clinical study. The primary outcomes of the study suggested no significant difference in negativity after 3, 7 and 14 days in both treatments. None of the patients displayed any worsening in the disease severity, and no mortality was observed in the study. Although, the post hoc exploratory analysis indicated significant normalization of the pulse rate showed in SOF/DCV and SOF/LDP treatment vs. SOC. The current study highlights the limitations of bench side models in predicting the clinical efficacy of drugs that are planned for repurposing.

The problem of gender and age identification has been addressed by many researchers, however, the attention given to it compared to the other related problems of face recognition in particular is far less. The success achieved in this domain has not seen much improvement compared to the other face recognition problems. Any language in the world has a separate set of words and grammatical rules when addressing people of different ages. The decision associated with its usage, relies on our ability to demarcate these individual characteristics like gender and age from the facial appearances at one glance. With the rapid usage of Artificial Intelligence (AI) based systems in different fields, we expect that such decision making capability of these systems match as much as to the human capability. To this end, in this work, we have designed a deep learning based model, called GRA_Net (Gated Residual Attention Network), for the prediction of age and gender from the facial images. This is a modified and improved version of Residual Attention Network where we have included the concept of Gate in the architecture. Gender identification is a binary classification problem whereas prediction of age is a regression problem. We have decomposed this regression problem into a combination of classification and regression problems for achieving better accuracy. Experiments have been done on five publicly available standard datasets namely FG-Net, Wikipedia, AFAD, UTKFAce and AdienceDB. Obtained results have proven its effectiveness for both age and gender classification, thus making it a proper candidate for the same against any other state-of-the-art methods.

Background: Hospitals are at the forefront of dealing infectious public health emergencies. Recently, COVID-19 has been declared as pandemic by the World Health Organization. Dealing with COVID-19 pandemic requires high intensity of administrative activity. Objective: We conducted this study to assess and compare, objectively, hospital preparedness with available Centre of Disease Control and Prevention (CDC) standards. Methods: CDC has issued checklist for the assessment of hospital preparedness for COVID-19 pandemic, globally. This list contains 10 elements with sub-sections. We objectified the same and scored the hospital preparations accordingly. Various financial efforts made by the hospital to procure COVID19-specified items was also recorded.Results: As per the CDC checklist, the hospital scored 197 points (72.06%) out of 270 points with highest points in element two and eight. Element two is for the development for written COVID-19 plan. Element eight consists of addressing the occupational health of healthcare workers. Lowest scoring was in the element seven represented visitor access and movement within facility. During the study period, the hospital procured items of approximately 55 lakhs. In the study period, doctors, nursing staff, housekeeping staff, and security staff were channelized for doing COVID-19 duties. Conclusions: We obtained a score above 70% (good) which is quite encouraging, and we concluded that pandemic preparations in hospitals are necessary and it can be assessed objectively against prevailing standards. It is important in poor countries like India where spending on healthcare is minimal compared to other countries. Additionally, this assessment can be used to guide us further changes in policies and identifying the gaps in pandemic preparedness in hospitals which require special attention.

Human speech is not only a verbose medium of communication but it also conveys emotions. The past decade has seen a lot of research going on with speech data which becomes especially important for human-computer interaction and also healthcare, security, and entertainment. This paper proposes the TLEFuzzyNet model, a three-stage pipeline for emotion recognition from speech. The first stage includes feature extraction by data augmentation of speech signals and extraction of Mel spectrograms, followed by the use of three pretrained transfer learning CNN models namely, ResNet18, Inception_v3, and GoogleNet whose prediction scores are fed to the third stage. In the final stage, we assign Fuzzy Ranks using a modified Gompertz function which gives the final prediction scores after considering the individual scores from the three CNN models. We have used the Surrey Audio-Visual Expressed Emotion (SAVEE), the Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS), and the Berlin Database of Emotional Speech (EmoDB) datasets to evaluate the TLEFuzzyNet model which has achieved state-of-the-art performance and is hence a dependable framework for Speech emotion recognition(SER). All the codes are available using GitHub link: https://github.com/KaramSahoo/SpeechEmotionRecognitionFuzzy

The effectiveness of herbs for the management of chemically induced hepatotoxicity has been discussed by many researchers. However, there is a paucity of compressive literature on the significance of hepatoprotective plants for the management of anti-TB drug induced toxicity. Anti-TB drugs have been reported to causes hepatic damage, due to which, many patients across the globe discontinued the treatment. Medicinal plants have multiple therapeutic effects. The assessment of biological activity of plants against Mycobacterium and its use for hepatic recovery provides an effective treatment approach. Traditionally used medicinal plants are the rich source of phytochemicals and secondary metabolites. These compounds can restore normal function, enzymatic activity and structure of hepatic cells against anti-TB drug induced hepatotoxicity. The present review covers comprehensive details on different hepatoprotective and antimycobacterial plants studied during past few decades so that potential adjuvants can be studied for Tuberculosis chemotherapy.

Background: Oleaginous yeasts can be grown on different carbon sources, including lignocellulosic hydrolysate containing a mixture of glucose and xylose. However, not all yeast strains can utilize both the sugars for lipogenesis. Therefore, in this study, efforts were made to isolate dual sugar-utilizing oleaginous yeasts from different sources. Results: A total of eleven isolates were obtained, which were screened for their ability to utilize various carbohydrates for lipogenesis. One promising yeast isolate Trichosporon mycotoxinivorans S2 was selected based on its capability to use a mixture of glucose and xylose and produce 44.86 ± 4.03% lipids, as well as its tolerance to fermentation inhibitors. In order to identify an inexpensive source of sugars, nondetoxified paddy straw hydrolysate (saccharified with cellulase), supplemented with 0.05% yeast extract, 0.18% peptone, and 0.04% MgSO4 was used for growth of the yeast, resulting in a yield of 5.17 g L−1 lipids with conversion productivity of 0.06 g L−1 h−1. Optimization of the levels of yeast extract, peptone, and MgSO4 for maximizing lipid production using Box–Behnken design led to an increase in lipid yield by 41.59%. FAME analysis of single cell oil revealed oleic acid (30.84%), palmitic acid (18.28%), and stearic acid (17.64%) as the major fatty acids. Conclusion: The fatty acid profile illustrates the potential of T. mycotoxinivorans S2 to produce single cell oil as a feedstock for biodiesel. Therefore, the present study also indicated the potential of selected yeast to develop a zero-waste process for the complete valorization of paddy straw hydrolysate without detoxification.How to cite: Sagia S, Sharma A, Singh S, et al. Single cell oil production by a novel yeast Trichosporon mycotoxinivorans for complete and ecofriendly valorization of paddy straw. Electronic Journal of Biotechnology 2020;44. https://doi.org/10.1016/j.ejbt.2020.01.009. Keywords: Biodiesel, Fatty acids, Lignocellulosic biomass, Lignocellulosic hydrolysate, Lipid production, Lipogenesis, Oleaginous yeast, Paddy straw, Single cell oil, Trichosporon mycotoxinivorans, Yeast

Feature selection (FS), an important pre-processing step in the fields of machine learning and data mining, has immense impact on the outcome of the corresponding learning models. Basically, it aims to remove all possible irrelevant as well as redundant features from a feature vector, thereby enhancing the performance of the overall prediction or classification model. Over the years, meta-heuristic optimization techniques have been applied for FS, as these are able to overcome the limitations of traditional optimization approaches. In this work, we introduce a binary variant of the recently-proposed Sailfish Optimizer (SFO), named as Binary Sailfish (BSF) optimizer, to solve FS problems. Sigmoid transfer function is utilized here to map the continuous search space of SFO to a binary one. In order to improve the exploitation ability of the BSF optimizer, we amalgamate another recently proposed meta-heuristic algorithm, namely adaptive β-hill climbing (AβHC) with BSF optimizer. The proposed BSF and AβBSF algorithms are applied on 18 standard UCI datasets and compared with 10 state-of-the-art meta-heuristic FS methods. The results demonstrate the superiority of both BSF and AβBSF algorithms in solving FS problems. The source code of this work is available in https://github.com/Rangerix/MetaheuristicOptimization.

Definitive optimization algorithms are not able to solve high dimensional optimization problems when the search space grows exponentially with the problem size, and an exhaustive search also becomes impractical. To encounter this problem, researchers use approximation algorithms. A category of approximation algorithms is meta-heuristic algorithms which have shown an acceptable degree of efficiency to solve this kind of problems. Social Mimic Optimization (SMO) algorithm is a recently proposed meta-heuristic algorithm which is used to optimize problems with continuous solution space. It is proposed by following the behavior of people in society. SMO can efficiently explore the solution space for obtaining optimal or near-optimal solution by minimizing a given fitness function. Feature selection is a binary optimization problem where the aim is to maximize the classification accuracy of a learning algorithm using minimum the number of features. To convert the continuous search space to a binary one, a proper transfer function is required. The effect a transfer function has on the binary variant of an optimization algorithm is very important since selecting a particular subset of features based on the solution values attained by the algorithm in continuous search space depends on the considered transfer function. To this end, we have proposed a new transfer function, namely X-shaped transfer function, to enhance the exploration and exploitation ability of binary SMO. The proposed X-shaped transfer function utilizes two components and crossover operation to obtain a new solution. Effect of the proposed X-shaped transfer function is compared with the effect of four S-shaped and four V-shaped transfer functions on SMO in terms of achieved classification accuracy, rate of convergence, and number of features selected over 18 standard UCI datasets. The proposed algorithm is also compared with state-of-the-art meta-heuristic feature selection (FS) algorithms. Experimental results confirm the efficiency of the proposed approach in improving the classification accuracy compared to other meta-heuristic algorithms, and the superiority of X-shaped transfer function over commonly used S-shaped and V-shaped transfer functions. The source code of the proposed method along with the datasets used can be found at https://github.com/Rangerix/SocialMimic.

Feature Selection (FS) is an important pre-processing step in the fields of machine learning and data mining, which has a major impact on the performance of the corresponding learning models. The main goal of FS is to remove the irrelevant and redundant features, resulting in optimized time and space requirements along with enhanced performance of the learning model under consideration. Many meta-heuristic optimization techniques have been applied to solve FS problems because of its superiority over the traditional optimization approaches. Here, we have introduced a new hybrid meta-heuristic FS model based on a well-known meta-heuristic Harmony Search (HS) algorithm and a recently proposed Ring Theory based Evolutionary Algorithm (RTEA), which we have named as Ring Theory based Harmony Search (RTHS). Effectiveness of RTHS has been evaluated by applying it on 18 standard UCI datasets and comparing it with 10 state-of-the-art meta-heuristic FS methods. Obtained results prove the superiority of RTHS over the state-of-the-art methods considered here for comparison.

Feature selection (FS) is mainly used as a pre-processing tool to reduce dimensionality by eliminating irrelevant or redundant features to be used for a machine learning or data mining algorithm. In this paper, we have introduced binary variant of a recently proposed meta-heuristic algorithm called Social Ski Driver (SSD) optimization. To the best of our knowledge, SSD has not been used yet in the domain of FS. Two binary variants of SSD are proposed using S-shaped and V-shaped transfer functions. Besides, the exploitation ability of SSD is improved by using a local search method, called Late Acceptance Hill Climbing (LAHC). The hybrid meta-heuristic is then converted to binary version by using said transfer functions. The proposed methods are applied on 18 standard UCI datasets and compared with 15 state-of-the-art FS methods. Also to check the robustness of the proposed method, we have applied it to 3 high dimensional microarray datasets and compared with 6 state-of-the-art methods. Achieved results confirm the superiority of the proposed methods compared to other meta-heuristic wrapper based FS methods considered here. Source code of this work is available at https://github.com/consigliere19/SSD-LAHC.

With the recent advancements in the fields of machine learning and artificial intelligence, spoken language identification-based applications have been increasing in terms of the impact they have on the day-to-day lives of common people. Western countries have been enjoying the privilege of spoken language recognition-based applications for a while now, however, they have not gained much popularity in multi-lingual countries like India owing to various complexities. In this paper, we have addressed this issue by attempting to identify different Indian languages based on various well-known features like Mel-Frequency Cepstral Coefficient (MFCC), Linear Prediction Coefficient (LPC), Discrete Wavelet Transform (DWT), Gammatone Frequency Cepstral Coefficient (GFCC) as well as a few deep learning architecture based features like i-vector and x-vector extracted from the audio signals. After comparing the initial results, it is observed that the combination of MFCC and LPC produces the best results. Then we have developed a new nature-inspired feature selection (FS) algorithm by hybridizing Binary Bat Algorithm (BBA) with Late Acceptance Hill-Climbing (LAHC) to select the optimal subset from the said feature vectors in order to reduce the model complexity and help it train faster. Using Random Forest (RF) classifier, we have achieved an accuracy of 92.35% on Indic TTS database developed by IIT-Madras, and an accuracy of 100% on the Indic Speech database developed by the Speech and Vision Laboratory (SVL) IIIT-Hyderabad. The proposed algorithm is also found to outperform many standard meta-heuristic FS algorithms. The source code of this work is available at: https://github.com/CodeChef97dotcom/Feature-Selection.

Selecting the most relevant features from a high dimensional dataset is always a challenging task. In this regard, the feature selection (FS) method acts as a solution to this problem mainly in the domain of data mining and machine learning. It aims at improving the performance of a learning model greatly by choosing the relevant features and ignoring the redundant ones. Besides, this also helps to achieve efficient use of space and time by the learning model under consideration. Though over the years, many meta-heuristic algorithms have been proposed by the researchers to solve FS problem, still this is considered as the open research problem due to its enormous challenges. Particularly, these algorithms, at times, suffer from poor convergence because of the improper tuning of exploration and exploitation phases. Here lies the importance of the hybrid meta-heuristics which help to improve the searching capability and convergence rate of the parent algorithms. To this end, the present work introduces a new hybrid meta-heuristic FS model by combining two meta-heuristics - Harmony Search (HS) algorithm and Artificial Electric Field Algorithm (AEFA), which we have named as Electrical Harmony based Hybrid Meta-heurtistic (EHHM). The proposed hybrid meta-heuristic converges faster than its predecessors, thereby ensuring its capability to search efficiently. Usability of EHHM is examined by applying it on 18 standard UCI datasets. Moreover, to prove its supremacy, we have compared it with 10 state-of-the-art FS methods. Link to code implementation of proposed method: khalid0007/Metaheuristic-Algorithms/FS_AEFAhHS.

This era is dominated by artificial intelligence and its various applications - one of which is Spoken Language Identification (S-LID) which has always been a challenging issue and an important research area in the domain of speech signal processing. This paper deals with S-LID to be used for Human-Computer Interaction (HCI) based applications by attempting to classify various languages from three multi-lingual databases namely CSS10: A Collection of Single Speaker Speech Datasets for 10 Languages, VoxForge and Indian Institute of Technology, Madras (IIT-Madras) speech corpus database by extracting their Mel-Spectrogram features and Relative Spectral Transform - Perceptual Linear Prediction (RASTA-PLP) features. A new hybrid Feature Selection (FS) algorithm have been developed using the versatile Harmony Search (HS) algorithm and a new nature-inspired algorithm called Naked Mole-Rat (NMR) algorithm to select the best subset of features and reduce the model complexity to help it train faster. This selected feature set is fed to five classifiers namely Support Vector Machine (SVM), k-Nearest Neighbor (k-NN), Multi-layer Perceptron (MLP), Naïve Bayes (NB) and Random Forest (RF). The evaluation measures used in this paper are precision, recall, f1-score, classification accuracy and number of selected features. An accuracy of 99.89% on CSS10, 98.22% on VoxForge and 99.75% on IIT-Madras speech corpus databases is achieved using RF. Furthermore, the proposed algorithm is found to outperform 15 standard meta-heuristic FS algorithms. The source code of this work is available at: https://github.com/CodeChef97dotcom/HS-NMR.git.

Speech is the most important media of expressing emotions for human beings. Thus, it has often been an area of interest to understand the emotion of a person out of his/her speech by using the intelligence of the computing devices. Traditional machine learning techniques are very much popular in accomplishing such tasks. To provide a less expensive computational model for emotion classification through speech analysis, we propose a meta-heuristic feature selection (FS) method using a hybrid of Golden Ratio Optimization (GRO) and Equilibrium Optimization (EO) algorithms, which we have named as Golden Ratio based Equilibrium Optimization (GREO) algorithm. The optimally selected features by the model are fed to the XGBoost classifier. Linear Predictive Coding (LPC) and Linear Prediction Cepstral Coefficients (LPCC) based features are considered as the input here, and these are optimized by using the proposed GREO algorithm. We have achieved impressive recognition accuracies of 97.31% and 98.46% on two standard datasets namely, SAVEE and EmoDB respectively. The proposed FS model is also found to perform better than their constituent algorithms as well as many well-known optimization algorithms used for FS in the past. Source code of the present work is made available at: https://github.com/arijitdey1/Hybrid-GREO.

Feature selection is a process to reduce the dimension of a dataset by removing redundant features, and to use the optimal subset of features for machine learning or data mining algorithms. This helps to minimize the time requirement to train a learning algorithm as well as to lessen the storage requirement by ignoring the less-informative features. Feature selection can be considered as a combinatorial optimization problem. In this paper, the authors have presented a new feature selection algorithm called Mayfly-Harmony Search (MA-HS) based on two meta-heuristics namely Mayfly Algorithm and Harmony Search. Mayfly Algorithm has not hitherto been used for feature selection problems to the best of the author’s knowledge. An S-shaped transfer function is incorporated for converting it into a binary version of Mayfly Algorithm. When different candidate solutions obtained from various regions of the search space using Mayfly Algorithm are taken into the harmony memory and processed by Harmony Search, a superior solution can be ensured. This is the primary reason for proposing a hybrid of Mayfly Algorithm and Harmony Search. Thus, combining harmony search with Mayfly Algorithm leads to an increased exploitation of the search space and an overall improvement in the performance of Mayfly-Harmony Search (MA-HS) algorithm. The proposed algorithm has been applied on 18 UCI datasets and compared with 12 other state-of-the-art meta-heuristic FS methods. Experiments have also been performed on three high-dimensional microarray datasets. The results obtained support the superior performance of the algorithm compared to the other methods. The source code of the proposed algorithm can be found using the link as follows: https://github.com/trin07/MA-HS.