Diabetes, also known as chronic illness, is a group of metabolic diseases due to a high level of sugar in the blood over a long period. The risk factor and severity of diabetes can be reduced significantly if the precise early prediction is possible. The robust and accurate prediction of diabetes is highly challenging due to the limited number of labeled data and also the presence of outliers (or missing values) in the diabetes datasets. In this literature, we are proposing a robust framework for diabetes prediction where the outlier rejection, filling the missing values, data standardization, feature selection, K-fold cross-validation, and different Machine Learning (ML) classifiers (k-nearest Neighbour, Decision Trees, Random Forest, AdaBoost, Naive Bayes, and XGBoost) and Multilayer Perceptron (MLP) were employed. The weighted ensembling of different ML models is also proposed, in this literature, to improve the prediction of diabetes where the weights are estimated from the corresponding Area Under ROC Curve (AUC) of the ML model. AUC is chosen as the performance metric, which is then maximized during hyperparameter tuning using the grid search technique. All the experiments, in this literature, were conducted under the same experimental conditions using the Pima Indian Diabetes Dataset. From all the extensive experiments, our proposed ensembling classifier is the best performing classifier with the sensitivity, specificity, false omission rate, diagnostic odds ratio, and AUC as 0.789, 0.934, 0.092, 66.234, and 0.950 respectively which outperforms the state-of-the-art results by 2.00 % in AUC. Our proposed framework for the diabetes prediction outperforms the other methods discussed in the article. It can also provide better results on the same dataset which can lead to better performance in diabetes prediction. Our source code for diabetes prediction is made publicly available.

/pdf/diabetes-prediction-using-ensembling-of-different-machine-5e1q9pirab.pdf

Diabetes Prediction Using Ensembling of Different Machine Learning Classifiers

Small millets are nutrient-rich food sources traditionally grown and consumed by subsistence farmers in Asia and Africa. They include finger millet (Eleusine coracana), foxtail millet (Setaria italica), kodo millet (Paspalum scrobiculatum), proso millet (Panicum miliaceum), barnyard millet (Echinochloa spp.), and little millet (Panicum sumatrense). Local farmers value the small millets for their nutritional and health, tolerance to extreme stress including drought, and ability to grow under low nutrient input conditions, ideal in an era of climate change and steadily depleting natural resources. Little scientific attention has been paid to these crops, hence they have been termed “orphan cereals”. Despite this challenge, an advantageous quality of the small millets is that they continue to be grown in remote regions of the world which has preserved their biodiversity, providing breeders with unique alleles for crop improvement. The purpose of this review, first, is to highlight the diverse traits of each small millet species that are valued by farmers and consumers (e.g. nutritional quality) which hold potential for selection, improvement or mechanistic study. For each species, the germplasm, genetic and genomic resources available will then be described as potential tools to exploit this biodiversity. The review will conclude with noting current trends and gaps in the literature and make recommendations on how to better preserve and utilize diversity within these species to accelerate a New Green Revolution for subsistence farmers in Asia and Africa.

/pdf/genetic-diversity-and-genomic-resources-available-for-the-4ewabz3zfi.pdf

Genetic diversity and genomic resources available for the small millet crops to accelerate a New Green Revolution.

Crop growth and productivity has largely been vulnerable to various abiotic and biotic stresses that are only set to be compounded due to global climate change. Therefore developing improved varieties and designing newer approaches for crop improvement against stress tolerance have become a priority now-a-days. However, most of the crop improvement strategies are directed towards staple cereals such as rice, wheat, maize etc. whereas attention on minor cereals such as finger millet [Eleusine coracana (L.) Gaertn.] lags far behind. It is an important staple in several semi-arid and tropical regions of the world with excellent nutraceutical properties as well as ensuring food security in these areas even during harsh environment. This review highlights the importance of finger millet as a model nutraceutical crop. Progress and prospects in genetic manipulation for the development of abiotic and biotic stress tolerant varieties is also discussed. Although limited studies have been conducted for genetic improvement of finger millets, its nutritional significance in providing minerals, calories and protein makes it an ideal model for nutrition-agriculture research. Therefore, improved genetic manipulation of finger millets for resistance to both abiotic and biotic stresses, as well as for enhancing nutrient content will be very effective in millet improvement.

/pdf/finger-millet-a-certain-crop-for-an-uncertain-future-and-a-4py2xugs7h.pdf

Finger Millet: A “Certain” Crop for an “Uncertain” Future and a Solution to Food Insecurity and Hidden Hunger under Stressful Environments

Exploration of millet models for developing nutrient rich graminaceous crops

NAC proteins (NAM (No apical meristem), ATAF (Arabidopsis transcription activation factor) and CUC (cup-shaped cotyledon)) are plant-specific transcription factors reported to be involved in regulating growth, development and stress responses. Salinity responsive transcriptome profiling in a set of contrasting finger millet genotypes through RNA-sequencing resulted in the identification of a NAC homolog (EcNAC 67) exhibiting differential salinity responsive expression pattern. Full length cDNA of EcNAC67 was isolated, characterized and validated for its role in abiotic stress tolerance through agrobacterium mediated genetic transformation in a rice cultivar ASD16. Bioinformatics analysis of putative NAC transcription factor (TF) isolated from a salinity tolerant finger millet showed its genetic relatedness to NAC67 family TFs in related cereals. Putative transgenic lines of rice over-expressing EcNAC67 were generated through Agrobacterium mediated transformation and presence/integration of transgene was confirmed through PCR and southern hybridization analysis. Transgenic rice plants harboring EcNAC67 showed enhanced tolerance against drought and salinity under greenhouse conditions. Transgenic rice plants were found to possess higher root and shoot biomass during stress and showed better revival ability upon relief from salinity stress. Upon drought stress, transgenic lines were found to maintain higher relative water content and lesser reduction in grain yield when compared to non-transgenic ASD16 plants. Drought induced spikelet sterility was found to be much lower in the transgenic lines than the non-transgenic ASD16. Results revealed the significant role of EcNAC67 in modulating responses against dehydration stress in rice. No detectable abnormalities in the phenotypic traits were observed in the transgenic plants under normal growth conditions. Results indicate that EcNAC67 can be used as a novel source for engineering tolerance against drought and salinity stress in rice and other crop plants.

/pdf/over-expression-of-a-nac-67-transcription-factor-from-finger-39odi0nyg5.pdf

Over-expression of a NAC 67 transcription factor from finger millet ( Eleusine coracana L.) confers tolerance against salinity and drought stress in rice

Finger millet (Eleusine coracana L.) is a hardy cereal known for its superior level of tolerance against drought, salinity, diseases and its nutritional properties. In this study, attempts were made to unravel the physiological and molecular basis of salinity tolerance in two contrasting finger millet genotypes viz., CO 12 and Trichy 1. Physiological studies revealed that the tolerant genotype Trichy 1 had lower Na(+) to K(+) ratio in leaves and shoots, higher growth rate (osmotic tolerance) and ability to accumulate higher amount of total soluble sugar in leaves under salinity stress. We sequenced the salinity responsive leaf transcriptome of contrasting finger millet genotypes using IonProton platform and generated 27.91 million reads. Mapping and annotation of finger millet transcripts against rice gene models led to the identification of salinity responsive genes and genotype specific responses. Several functional groups of genes like transporters, transcription factors, genes involved in cell signaling, osmotic homeostasis and biosynthesis of compatible solutes were found to be highly up-regulated in the tolerant Trichy 1. Salinity stress inhibited photosynthetic capacity and photosynthesis related genes in the susceptible genotype CO 12. Several genes involved in cell growth and differentiation were found to be up-regulated in both the genotypes but more specifically in tolerant genotype. Genes involved in flavonoid biosynthesis were found to be down-regulated specifically in the salinity tolerant Trichy 1. This study provides a genome-wide transcriptional analysis of two finger millet genotypes differing in their level of salinity tolerance during a gradually progressing salinity stress under greenhouse conditions.

Transcriptome analysis of salinity responsiveness in contrasting genotypes of finger millet (Eleusine coracana L.) through RNA-sequencing

Diabetes Mellitus is a dreadful disease characterized by increased levels of glucose in the blood, termed as the condition of hyperglycemia. As this disease is prominent among the tropical countries like India, an intense research is being carried out to deliver a machine learning model that could learn from previous patient records in order to deliver smart diagnosis. This research work aims to improve the accuracy of existing diagnostic methods for the prediction of Type 2 Diabetes with machine learning algorithms. The proposed algorithm selects the essential features from the Pima Indians Diabetes Dataset with Goldberg's Genetic algorithm in the pre-processing stage and a Multi Objective Evolutionary Fuzzy Classifier is applied on the dataset. This algorithm works on the principle of maximum classifier rate and minimum rules. As a result of feature selection with GA the number of features is reduced to 4 from 8 and the classifier rate is improved to 83.0435 % with NSGA II in training rate of 70% and 30% testing.

Genetic algorithm based feature selection and MOE Fuzzy classification algorithm on Pima Indians Diabetes dataset

In recent years, the mobile devices become popular for communication and running advanced real time applications such as face reorganization and online games. Although, mobile devices advanced for providing significant benefits for mobile users. But still, these devices suffers with limited recourses such as computation power, battery and storage space due to the portable size. However, The Cloud Technology overcome the limitations of mobile computing with better performance and recourses. The cloud technology provides enough computing recourses to run mobile applications as storage computing power on cloud platform. Therefore, the novel technology called mobile cloud computing (MCC) is introduced by integrating two technologies (Mobile Computing, Cloud Computing) in order to overcome the limitations(such as Battery life, Storage capacity, Processing capacity) of Mobile Devices by offloading application to recourse rich Remote server. This paper presents an overview of MCC, the advantages of MCC, the related concepts and the technology beyond various offloading frameworks, the architecture of the MCC, Cloudlet technology, security and privacy issues and limitations of mobile cloud computing. Finally, we conclude with feature research directions in MCC.

/pdf/a-survey-on-mobile-cloud-computing-mobile-computing-cloud-1u37tg4aem.pdf

A Survey on Mobile Cloud Computing: Mobile Computing + Cloud Computing (MCC = MC + CC)

Nowadays, the uses of mobile devices have been increasing in many aspects of our life such as playing games, sending documents, transactions, and marketing, business, and conference meetings. But this mobile device has limited the resources in terms of battery lifetime, storage, and processing capacity. The new technology known as mobile cloud computing can help users to increase utilization of mobile cloud resources. The limitation of mobile device can be overcome by MCC. The technique called as offloading can transfer the resource-intensive task to remote cloud for processing, and the result will come back to the mobile device. The mobile device connecting to remote cloud with the help of 3G (or) LTE networks causes latency-related issues bandwidth and cost. In order to overcome these problems, MCC has introduced new technology which can reduce latency problems by providing secured and efficient model based on cloudlet. In this paper, we mainly focus on healthcare applications which can be processed by new cloudlet model for reducing processing time as well as providing enough security to user’s data. Initially, the user connects to the available cloudlet; if the cloudlet is not providing required resources or services, the user will redirect to remote cloud. In our model, the cloudlet is used to analyze patient medical records.

Cloudlet Services for Healthcare Applications in Mobile Cloud Computing

Six promising rice varieties viz., CO 43, CO 47, CO 48, CO 49, ADT 43 and Improved White Ponni were treated with gamma irradiation with doses of 100Gy, 200Gy, 250Gy, 300Gy and 350Gy of gamma rays in order to study effect of gamma irradiation in seed germination of rice varieties and study the root and shoot length variation. Treated seeds were sown separately in germination paper and nursery with the two replications. The germination percentage was decreased after gamma irradiation. But the decrease was neither proportional to the increase in dosage nor definite pattern was found in all the six rice varieties. At the dose of 350Gy all the six varieties exhibited the low germination percentage especially in the variety ADT 43 is 33%. The gamma ray dose of 300Gy was causing 42–51% seedling height reductions in CO 43, CO 47, CO 48, CO 49 and ADT43. The seedling height was decreased in decreasing manner with the increase of irradiation dose in the varieties such as CO 47 and improved white ponni. The root development in seedlings was inhibited higher in the dose of 300Gy in all the six varieties. At higher dose of 350Gy root length is very much affected in the varieties viz., CO 43 with 76% reduction and 70% reduction in improved white ponni. Plant height and seed fertility percentage were decreased with increase of gamma radiation dose in linear fashion. Seed fertility decreased with increase of radiation dose was observed in CO 47, ADT 43 and improved white ponni. In ADT 43 seed fertility was reduced approximately 69% at gamma ray dose of 350Gy.

R. Sasikala

Papers

Transcriptome analysis of salinity responsiveness in contrasting genotypes of finger millet (Eleusine coracana L.) through RNA-sequencing

Genetic algorithm based feature selection and MOE Fuzzy classification algorithm on Pima Indians Diabetes dataset

A Survey on Mobile Cloud Computing: Mobile Computing + Cloud Computing (MCC = MC + CC)

Cloudlet Services for Healthcare Applications in Mobile Cloud Computing

Sensitivity of rice varieties to gamma irradiation