Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
440
result(s) for
"Ashok Kumar, J"
Sort by:
Development of a mobile application for Pacific white shrimp (Penaeus vannamei) farming and evaluation of its efficiency in technology communication and feedback
Shrimp farming is a technology-driven and risk-intensive food production system. Shrimp farms are remotely located and farmers need customized farm advisories, which the conventional extension systems are not able to provide. To provide technology advisories to the stakeholders, an android mobile application, CIBA ShrimpApp, was developed in 2018, based on the information and format requirements of the shrimp farmers using Java language as front end and the data bases were created as back end through Structured Query Language (MySQL). The app contains eight modules, viz. better management practices of shrimp farming, quantification of inputs, on-farm disease diagnosis, on-farm risk assessment, Frequently Asked Questions (FAQs) in shrimp farming, regulations, advisories and updates and posting queries which were integrated as a mobile application. The app has more than 27,500 cumulative downloads and has a rating of 4.5 out of 5.0. The application was found to have improved the knowledge level of end users to the tune of 20–37%. The Google firebase application data showed that 98.4% of users of CIBA ShrimpApp were free from errors and crashes. An evaluation study conducted among sample regular users indicated that the app aided in farm decision-making and its design functionality and extension service function were perceived to be efficient. Considering the all-pervading mobile phone connectivity and affordability, smart phone-based mobile applications and data analytics can play a significant role in shrimp farm advisory services and its sustainability.
Journal Article
Phylogenetic Relationship Among Brackishwater Vibrio Species
Vibriosis is regarded as an important disease of penaeid shrimps affecting larvae in hatcheries. Among the Vibrio species, Vibrio parahaemolyticus, Vibrio vulnificus, Vibrio furnissii, Vibrio campbellii, Vibrio harveyi, Vibrio alginolyticus, and Vibrio anguillarum are often associated with diseases in finfish and shellfish of brackishwater ecosystem. Accurate species differentiating methods for the organisms present in an ecosystem are required for precise classification of the species and to take steps for their management. Conventional methods like 16s rRNA phylogeny and multilocus sequence typing (MLST) have often failed to correctly identify Vibrio species. This has necessitated a comprehensive investigation on methodologies available to distinguish Vibrio species associated with brackishwater aquaculture system. To achieve this, 35 whole genomes belonging to 7 Vibrio species were subjected to phylogenetic analysis based on 16s rRNA gene, MLST genes, single-copy orthologous genes, and single-nucleotide polymorphisms. In addition, genome-based similarity indices like average nucleotide identity (ANI) and in silico DNA-DNA hybridization (DDH) were computed as confirmatory tests to verify the phylogenetic relations. There were some misclassifications occurred regarding phylogenetic relations based on 16s rRNA genes and MLST genes, while phylogeny with single-copy orthologous genes produced accurate species-level clustering. Study reveals that the species identification based on whole genome-based estimates or genome-wide variants are more precise than the ones done with single or subset of genes.
Journal Article
Assessment of perceived farming risks, communication of risk management practices, and evaluation of their efficiency in Pacific white shrimp (Penaeus vannamei) farming—a survey-based cross-sectional study
Pacific white shrimp (Penaeus vannamei) farming is an important commercial aquaculture production system contributing substantially to the economic and societal development in India. Though technically efficient, shrimp farming is potentially susceptible to production risks. A risk assessment study was undertaken to ascertain the potential risks in P. vannamei shrimp farming by developing a framework consisting of risk perception and assessment, communication of risk management practices, and evaluation of their efficiency in tackling the risks. The primary data collected from a proportionate randomly chosen 604 shrimp farmers across the coastal states revealed that P. vannamei shrimp farming was prone to twenty-seven risks having very low to very high probability of occurrence with marginally negative to a catastrophic impact on production and income. Appropriate risk-preventive and management measures were proposed and suitably communicated to the shrimp farmers through training workshops, farmer handbooks in vernacular languages, and launching a mobile app module on on-farm risk assessment. A follow-up study conducted among a random subset of the original sample indicated that 76% of the farmers adopted the proposed risk management practices and experienced that the practices were highly efficient (up to 80%) in tackling the risks associated with shrimp farming. Furthermore, it was observed that adoption of risk management practices is essential to have a successful shrimp production of marketable size and an additional expenditure for adoption of these practices was estimated to be 0.5 USD per kg of shrimp produced. Shrimp farming is a delicate and dynamic production system, and it is unrealistic to avoid the emergence of hazards in the production cycle. Therefore, it is imperative to train the farmers on better management practices (BMP) and develop a certification plan to accredit the farms for the adoption of BMPs that would ensure an economically viable shrimp production in India.
Journal Article
Ensemble application of bidirectional LSTM and GRU for aspect category detection with imbalanced data
E-commerce websites produce a large number of online reviews, posts, and comments about a product or service. These reviews are used to assist consumers in buying or recommending a product. However, consumers are expressing their views on a specific aspect category of a product. In particular, aspect category detection is one of the subtasks of aspect-based sentiment analysis, and it classifies a given text into a set of predefined aspects. Naturally, a class imbalance problem occurs in real-world applications. The class imbalance is studied over the last two decades using machine learning algorithms. However, there is very little empirical research in deep learning with the class imbalance problem. In this paper, we propose bidirectional LSTM and GRU networks to deal with imbalance aspect categories. The proposed method applies a data-level technique to reduce class imbalance. Specifically, we employ the stratified sampling technique to deal with imbalanced classes. Moreover, we create word vectors with the corpus-specific word embeddings and pre-trained word embeddings. This word representations fed into the proposed method and their merge modes such as addition, multiplication, average, and concatenation. The performance of this method is evaluated with a confusion matrix, precision, recall, F1-score with micro-average, macro-average, and weighted average. The experimental result analysis suggests that the proposed method outperforms with pre-trained word embeddings.
Journal Article
First Report of a Complete Genome Sequence of White spot syndrome virus from India
ABSTRACTWhite spot syndrome virus is a major pathogen of shrimp, causing economic loss to the aquaculture industry. For the first time, a complete de novo genome of an Indian isolate of this virus has been deciphered using Illumina and Nanopore sequencing technologies. The genome has 280,591 bp with 442 predicted coding genes.
Journal Article
Radiomic Texture Analysis Mapping Predicts Areas of True Functional MRI Activity
Individual analysis of functional Magnetic Resonance Imaging (fMRI) scans requires user-adjustment of the statistical threshold in order to maximize true functional activity and eliminate false positives. In this study, we propose a novel technique that uses radiomic texture analysis (TA) features associated with heterogeneity to predict areas of true functional activity. Scans of 15 right-handed healthy volunteers were analyzed using SPM8. The resulting functional maps were thresholded to optimize visualization of language areas, resulting in 116 regions of interests (ROIs). A board-certified neuroradiologist classified different ROIs into Expected (E) and Non-Expected (NE) based on their anatomical locations. TA was performed using the mean Echo-Planner Imaging (EPI) volume, and 20 rotation-invariant texture features were obtained for each ROI. Using forward stepwise logistic regression, we built a predictive model that discriminated between E and NE areas of functional activity, with a cross-validation AUC and success rate of 79.84% and 80.19% respectively (specificity/sensitivity of 78.34%/82.61%). This study found that radiomic TA of fMRI scans may allow for determination of areas of true functional activity, and thus eliminate clinician bias.
Journal Article
A Convolutional Stacked Bidirectional LSTM with a Multiplicative Attention Mechanism for Aspect Category and Sentiment Detection
Traditionally, sentiment analysis is a binary classification task that aims to categorize a piece of text as positive or negative. This approach, however, can be too simplistic when the text under scrutiny contains more than one opinion target. Hence, aspect-based sentiment analysis provides fine-grained sentiment understanding of the product, service, or policy. Machine learning and deep learning algorithms play an important role in this kind of task. Also, attention mechanism has shown breakthrough in the field of natural language processing. Therefore, we propose a convolutional stacked bidirectional long short-term memory with a multiplicative attention mechanism for aspect category and sentiment polarity detection. More specifically, we treat the proposed model as a multiclass classification problem. The proposed model is evaluated using SemEval-2015 and SemEval-2016 dataset. Our proposed model outperforms state-of-the-art results in aspect-based sentiment analysis.
Journal Article
Pre-operative MRI radiomics model non-invasively predicts key genomic markers and survival in glioblastoma patients
Purpose
Although glioblastoma (GBM) is the most common primary brain malignancy, few tools exist to pre-operatively risk-stratify patients by overall survival (OS) or common genetic alterations. We developed an MRI-based radiomics model to identify patients with
EGFR
amplification,
MGMT
methylation, GBM subtype, and OS greater than 12 months.
Methods
We retrospectively identified 235 patients with pathologically confirmed GBMs from the Cancer Genome Atlas (88; TCGA) and MD Anderson Cancer Center (147; MDACC). After two neuroradiologists segmented MRI tumor volumes, we extracted first-order and second-order radiomic features (gray-level co-occurrence matrices). We used the Maximum Relevance Minimum Redundancy technique to identify the 100 most relevant features and validated models using leave-one-out-cross-validation and validation on external datasets (i.e., TCGA). Our results were reported as the area under the curve (AUC).
Results
The MDACC patient cohort had significantly higher OS (22 months) than the TCGA dataset (14 months). On both LOOCV and external validation, our radiomics models were able to identify EGFR amplification (all AUCs > 0.83),
MGMT
methylation (all AUCs > 0.85), GBM subtype (all AUCs > 0.92), and OS (AUC > 0.91 on LOOCV and 0.71 for TCGA validation).
Conclusions
Our robust radiomics pipeline has the potential to pre-operatively discriminate common genetic alterations and identify patients with favorable survival.
Journal Article
Is the price volatility risk in shrimp farming manageable and can profitability be sustained?
Shrimp price volatility vis-a-vis increased production costs puts the shrimp farmers in debt, reduces further investments, and threatens the sustainability of shrimp farming. The cost and price analysis using the time series data drawn from primary and secondary sources substantiated that the production cost per kg of shrimp has increased gradually whereas the corresponding prices reveal a declining trend across the years. Further analyses indicated that shrimp price instability was higher for the largely supplied 21–30 g shrimp size vis-a-vis small- (15–20 g) and large-sized shrimps (> 30 g) over a period of time. Moreover, price trend scrutiny revealed that the price of small- and large-sized shrimps were higher in January, February, September and November months across the years. Likewise, higher price trends were observed in winter, spring, and monsoon seasons, whereas in summer, the price tended to decline. The ARIMA model fitted to predict the shrimp prices for the immediate future, forecasted an increasing price trend for 15 to 20 g size shrimps. Therefore, market based farming with phase-wise stocking of ponds with the adoption of on-farm nursery that would supply quality seed for a scattered stocking and produce different sized shrimps meeting the market demand is the prudent strategy to minimize the price risk. Similarly, partial harvesting of shrimps at 15 g size and its sale in the domestic markets could secure the investments made and continuing the crop for large size shrimps for the niche market would minimize the price risk and sustain the profitability. Further, insurance cover for shrimp price volatility and social capital development in the form of fish farmer producer organizations for collectively procuring inputs and sale of shrimps are suggested as strategies towards reducing the price risk and sustain the profitability of shrimp farming in India.
Journal Article