Explore the vast range of titles available.

Handwritten character recognition is currently getting the attention of researchers because of possible applications in assisting technology for blind and visually impaired users, human–robot interaction, automatic data entry for business documents, etc. In this work, we propose a technique to recognize handwritten Devanagari characters using deep convolutional neural networks (DCNN) which are one of the recent techniques adopted from the deep learning community. We experimented the ISIDCHAR database provided by (Information Sharing Index) ISI, Kolkata and V2DMDCHAR database with six different architectures of DCNN to evaluate the performance and also investigate the use of six recently developed adaptive gradient methods. A layer-wise technique of DCNN has been employed that helped to achieve the highest recognition accuracy and also get a faster convergence rate. The results of layer-wise-trained DCNN are favorable in comparison with those achieved by a shallow technique of handcrafted features and standard DCNN.

Customer churn prediction in telecommunication industry is a very essential factor to be achieved and it makes direct impact to customer retention and its revenues. Developing a good and effective churn prediction model is very important however it is a time-consuming process. This study presents a very good review of customer churn, its effects, identification of its causes, business needs, methods, and all the techniques used for churn prediction. On the other hand, this study provides the best understanding of the telecom dataset, datasets used by past researches and features used in different researches. Also, this study shows the best techniques used for the churn prediction and describes all performance measures used in the churn prediction models. In this study a wide range of researches are added from the year 2005 to 2020. It includes variety of methods proposed by past researches and technologies used in these researches. At the end, a state of art comparison is added that gives a very good and meaningful comparison of past researches. The study indicates that machine learning techniques are mostly used and feature extraction is a very important task for developing an effective churn prediction model. Deep learning algorithm CNN itself has the capability of feature extraction and establish itself as a powerful technique for churn model, in particular for large datasets. For performance ‘Accuracy’ is a good measure however measuring performance only with ‘Accuracy’ is not sufficient because on small datasets accuracy is more predictable and will be the same. With Accuracy, researchers also need to look at other performance measures such as confusion matrix, ROC, precision. F-measure etc. This study assures that new researchers can find everything regarding their churn prediction model requirements at one place. This study provides a comprehensive view by extensively detailing work which has happened in this area and will act as a rich repositorory of all knowledge regarding churn prediction in telecom sector.

Disasters are crisis circumstances that put human life in jeopardy. During disasters, public communication infrastructure is particularly damaged, obstructing Search And Rescue (SAR) efforts, and it takes significant time and effort to re-establish functioning communication infrastructure. SAR is a critical component of mitigating human and environmental risks in disasters and harsh environments. As a result, there is an urgent need to construct communication networks swiftly to help SAR efforts exchange emergency data. UAV technology has the potential to provide key solutions to mitigate such disaster situations. UAVs can be used to provide an adaptable and reliable emergency communication backbone and to resolve major issues in disasters for SAR operations. In this paper, we evaluate the network performance of UAV-assisted intelligent edge computing to expedite SAR missions and functionality, as this technology can be deployed within a short time and can help to rescue most people during a disaster. We have considered network parameters such as delay, throughput, and traffic sent and received, as well as path loss for the proposed network. It is also demonstrated that with the proposed parameter optimization, network performance improves significantly, eventually leading to far more efficient SAR missions in disasters and harsh environments.

Lateral epicondylitis, commonly referred to as tennis elbow, is a frequent sports injury that poses diagnostic and management challenges. Players often self-treat and delay medical intervention, exacerbating the condition, which highlights the need for early identification and prevention strategies. Purpose  This study aims to enhance the understanding of tennis elbow mechanisms and identify key factors influencing its development. Method This research introduces a novel approach integrating Design of Experiments (DoE) with Response Surface Methodology (RSM) and an Expert System (ES) using both Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) for personalized injury prevention recommendations. This combined methodology provides valuable insights and empowers players to adopt safer playing practices, potentially reducing the incidence of tennis elbow. Comprehensive education for athletes, coaches, and physicians on tennis elbow management is emphasized for early diagnosis and improved treatment outcomes. Result  After analysis of the computing model, 99% accuracy was achieved using the ANFIS approach for tennis elbow injury prediction. The accuracy was validated through multi-model prediction involving training, validation, and testing phases. Conclusion  The proposed work not only offers a deeper understanding of the factors influencing tennis elbow this srisk but also provides personalized preventive strategies through the expert system.

The environmental impact of traditional construction materials has led to increasing interest in developing more sustainable alternatives. This study addresses the development of low-carbon autoclaved aerated concrete (AAC) through the complete replacement of ordinary Portland cement (OPC) with ground granulated blast furnace slag (BFS), activated with lime and, in some formulations, supplemented with calcium carbide slag (CCS). Five different AAC mixtures were prepared and evaluated in terms of workability, foaming behavior, compressive strength, phase composition, density, thermal conductivity, and life cycle assessment (LCA). The BFS-based mixtures activated with lime exhibited good workability and foaming stability. After pre-curing, the addition of CCS significantly improved the formation of tobermorite during autoclaving. As a result, the BFS–CCS formulations achieved compressive strengths comparable to the reference OPC-based mix while maintaining low densities (420–441 kg/m3) and thermal conductivities in the range of 0.111–0.119 W/(m·K). These results confirm the technical feasibility of producing structural-grade AAC with a lower environmental footprint.

Human voice or speech is a contactless, non-invasive biometric trait for human recognition, easy to use with minimal computer complexity and inexpensive to implement. Speaker recognition (SR) has turned out to be a magnificent approach using speech as the central premise since decades. Its broad range of usages, like forensic speech verification to identify culprits by law enforcement authorities and access control to mobile banking, mobile shopping, etc., has made it a lucrative area of research. Also, the ease of use and dependability of SR will significantly assist people with disabilities in securely accessing and reaping the benefits of digital-era services. Additionally, the emergence of numerous deep learning methods for feature extraction and classification, has helped SR to achieve tremendous progress. This paper presents a comprehensive study on the progression of SR for decades till the present, including integration with Blockchain and challenges. It covers most of the factors that influence SR performance such as fundamentals and structure of SR, different speech pre-processing techniques, various speech features, feature extraction techniques, traditional and neural network-based classification techniques and deep learning-based SR toolkits. As a consequence, in this digital Blockchain era, it will help to design robust and reliable recognition-based services for mankind.

Ayurveda provided many innovative solutions during the COVID-19 pandemic. It is important to explore the phytochemical constituents in effective Ayurvedic formulations. The main aim of the work is to identify active phytoconstituents from five Ayurvedic formulations employed in treating COVID-19 patients in an Ayurvedic hospital. Pharmacoinformatics technologies were employed in this study. The chemoinformatics, 3D molecular structure building, and molecular docking of 967 compounds on eight different macromolecular viral targets associated with SARS-CoV-2 were carried out using GLIDE software. Molecular dynamics simulations were also performed. SwissADME web server was employed to determine the physicochemical, lipophilicity and absorption, distribution, metabolism, and excretion (ADME) parameters. The molecular docking results indicate that quercetin-3-O-arabinoglucoside, quercetin-3,7-O-diglucoside, glycyrrhizin, calceolarioside B, mucic acid-2-gallate, protodioscin and indioside D are the phytochemicals which effectively bind to eight of the proteins of SARS-CoV-2 virus and these may be treated as new lead compounds for multi-target drug discovery for SARS-CoV-2 inhibition. MD simulations helped in identifying five leads out of seven chosen from docking analysis. Five Ayurvedic formulations were used to treat respiratory illnesses associated with COVID-19. Five phytoconstituents present in these formulations were identified as leads by employing pharmacoinformatics techniques.

To determine the therapeutic efficacy and safety of AYUSH-64 as an add-on to standard care in mild to moderate COVID-19. This open-label randomized controlled parallel-group trial was conducted at a designated COVID care centre in India in 80 patients diagnosed with mild to moderate COVID-19 and randomized into two groups. Participants in the AYUSH-64 add-on group (AG) received AYUSH-64 two tablets (500 mg each) three times a day for 30 days along with standard conventional care. The control group (CG) received standard care alone. Proportion of participants who attained clinical recovery on day 7, 15, 23 and 30, proportion of participants with negative RT-PCR assay for COVID-19 at each weekly time point, change in pro-inflammatory markers, metabolic functions, HRCT chest (CO-RADS category) and incidence of Adverse Drug Reaction (ADR)/Adverse Event (AE). Out of 80 participants, 74 (37 in each group) contributed to the final analysis. Significant difference was observed in clinical recovery in the AG (p < 0.001 ) compared to CG. Mean duration for clinical recovery in AG (5.8 ± 2.67 days) was significantly less compared to CG (10.0 ± 4.06 days). Significant improvement in HRCT chest was observed in AG (p = 0.031) unlike in CG (p = 0.210). No ADR/SAE was observed or reported in AG. AYUSH-64 as adjunct to standard care is safe and effective in hastening clinical recovery in mild to moderate COVID-19. The efficacy may be further validated by larger multi-center double-blind trials. •Randomized controlled trial assessing efficacy of AYUSH-64 as adjunct to standard care in mild to moderate COVID-19.•AYUSH-64 as an adjunct hastens clinical recovery in mild to moderate COVID-19.•AYUSH-64 as an adjunct is superior to standard care alone in mild to moderate COVID-19.•AYUSH-64 as an adjunct to standard care is safer option to manage mild to moderate COVID-19.

Ayurveda interventions have been used for prophylaxis and care during the COVID-19 pandemic in India and have shown promising results in promoting early clinical recovery from COVID-19. To assess the efficacy and safety of Ashwagandha [Withania somnifera (L.) Dunal] tablet and Shunthi (Zingiber officinale Roscoe) capsule in mild and moderate COVID-19 compared to conventional standard care. A randomized controlled exploratory trial was conducted at a designated COVID-19 care center in India with 60 participants having mild or moderate COVID-19. Ashwagandha, two tablets (250 mg each), and Shunthi, two capsules (500 mg each) twice daily for 15 days, were given orally to the participants in the Ayurveda group (AG) and the control group (CG) received conventional standard care. The outcome measures included clinical recovery rate, the proportion of participants with negative RT-PCR assay for COVID-19 on day 7 and day 15, mean time to attain clinical recovery, change in pro-inflammatory markers, serum IgG for COVID-19, HRCT chest findings, disease progression and incidence of adverse events (AE). A total of 60 participants were enrolled, and the data of 48 participants (AG = 25 and CG = 23) were considered for the statistical analysis. The mean time for clinical recovery was reduced by almost 50 % in the AG (6.9 days) compared to CG (13.0 days) (p < 0.001). The proportion of participants who attained viral clearance in AG was 76.0 % compared to 60.8 % in the CG (RR= 1.24, 95 % CI: 0.841, 1.851, p-value = 0.270). Changes in the pro-inflammatory markers, serum IgG for COVID-19, and HRCT chest findings were comparable in both groups, and no AE or disease progression was reported. The Ayurveda interventions, Ashwagandha and Shunthi, can effectively reduce the duration of clinical recovery and improve time for viral clearance in mild and moderate COVID-19. These interventions were observed to be safe and well-tolerated during the duration of the trial. Clinical Trial Registry of India - CTRI/2020/08/027224 •RCT assessing the efficacy of Withania somnifera (WS) and Zingiber officinale (ZO) in mild and moderate COVID-19.•WS and ZO hasten clinical recovery in mild and moderate COVID-19.•No disease progression was observed after WS and ZO administration in mild and moderate COVID-19.•The combination of WS and ZO is safe for managing mild and moderate COVID-19.

Arogyamrita Kwath (AMK) is a polyherbal decoction comprising ten medicinal plants, viz., Albizia lebbeck, Andrographis paniculata, Tinospora cordifolia, Adhatoda vasica, Solanum xanthocarpum, Curcuma longa, Glycyrrhiza glabra, Terminalia bellirica, Withania somnifera and Trachyspermum ammi. The plants of the AMK formulation are traditionally used for the treatment of inflammation and respiratory ailments, but no scientific evidence has been reported so far for this formulation. To evaluate anti-inflammatory activity of AMK formulation in vitro and its fractions and to predict in silico anti-viral activity of identified potential phytoconstituents. The MTT cell cytotoxicity assay, nitric oxide (NO) inhibition assay and cytokines assay were carried out at concentrations 100 and 200 μg/mL. The phytoconstituents were identified by UPLC-PDA and UPLC-HRMS analyses. For pharmacoinformatics study molecular docking and molecular dynamics methods were used. The study revealed that AMK significantly inhibited NO in comparison to dexamethasone (100 μg/mL) and pro-inflammatory cytokines in RAW264.7 cells. The three fractions, n-hexane, EtOAc and n-BuOH prepared from the AMK formulation were non-cytotoxic against RAW264.7 murine macrophage cells during MTT cytotoxicity assay and showed satisfactory results during cytokines assay. Ethyl acetate fraction contains active phytoconstituents in appreciable quantities. 16 phytoconstituents have been identified by UPLC-HRMS analysis in the formulation and four phytocompounds were quantified by UPLC-PDA. Molecular dynamics study helped in identifying two macromolecular targets (viral replicase and the membrane protein), which are relatively more important. In the present study, anti-inflammatory activity of AMK was evaluated and the claimed anti-viral property was re-confirmed by molecular modelling in this work. The results clearly established that AMK showed remarkable anti-inflammatory and anti-viral activities. •AMK formulation is a decoction used for the treatment of respiratory ailments.•Sixteen compounds were identified by UPLC-HRMS analysis in the AMK formulation.•AMK formulation significantly lowered NF-kB and TNF-α levels in concentration-dependent manner.•Quercetin and vasicine, present in AMK showed significant binding affinity against seven viral targets.•MD simulations revealed that viral replicase and membrane protein were found to be the preferred targets for AMK formulation.