Data driven analysis of social capital in Farmer Producer Companies.

The Farmer Producer Company (FPC), a subset of the Farmer Producer Organization (FPO), is an important institutional form designed to organize farmer groups towards better coordinated farming and marketing. In the Indian context, as FPCs have emerged as new forms of members-led agribusiness, their ability to identify prevailing social ties and tap them effectively towards business growth needs to be better understood. Although social capital is studied broadly for its potential to drive organizational performance, it has been poorly researched in farmer collectives such as FPCs. The current work examines the effect of social capital on benefits and business performance at the level of member groups in FPCs. An empirical analysis was conducted in which two FPCs, which differed significantly in their mobilization strategies, farming methods, and supply chain linkages, were surveyed. Data collected from the surveys were visualized and clustering analysis was carried out using Self Organizing Maps (SOM), an unsupervised Artificial Neural Network (ANN) tool. Insights from clustering reveal the importance of pre-existing social ties, leadership, participation in group activities and the geographical affinity of groups in benefits realization and business performance of FPCs. The importance of bottom-up approaches in establishing robust supply chain linkages in emerging FPCs was keyed out through this work. The inferences through SOM, distilled strategies for FPCs' stakeholders in prioritizing interventions for member groups and in generating broader implications for policy makers accounting social capital in new institutional models.

A novel data-driven visualization of n-dimensional feasible region using interpretable self-organizing maps (iSOM).

Graphical optimization allows solving one or two dimensional optimization problems visually by merely plotting the objective function and constraint function contours. In addition to the discovery of optima, such a visualization-based approach enables understanding and interpretation of design variable and objective behavior with respect to feasibility and optimality, permitting intuitive decision making for designers. However, visualization of optimization problems in higher dimensions is challenging, though it is desirable. Interpretable self-organizing map (iSOM) is an artificial neural network that enables visualization of many dimensions via two-dimensional representations. We introduce iSOM to solve multidimensional optimization problems graphically. In the current work, a novel graphical representation of the n-dimensional feasible region, called B-matrix is constructed using iSOM. B-matrix is used to represent feasible range of design variables and objective function on separate plots. Consequently, dimension-wise shrinkage in the search space is also obtained. The proposed approach is demonstrated on various benchmark analytical examples and engineering examples with dimensions ranging from 2 to 30.

An Automated Approach to Differentiate Drug Resistant Tuberculosis in Chest X-ray Images Using Projection Profiling and Mediastinal Features.

In this study, an attempt has been made to differentiate Drug Resistant Tuberculosis (DR-TB) in chest X-rays using projection profiling and mediastinal features. DR-TB is a condition which is non-responsive to at least one of anti-TB drugs. Mediastinum variations can be considered as significant image biomarkers for detection of DR-TB. Images are obtained from a public database and are contrast enhanced using coherence filtering. Projection profiling is used to obtain the feature lines from which the mediastinal and thoracic indices are computed. Classification of Drug Sensitive (DS-TB) and DR-TB is performed using three classifiers. Results show that the mediastinal features are found to be statistically significant. Support vector machine with quadratic kernel is able to provide better classification performance values of greater than 93%. Hence, the automated analysis of mediastinum could be clinically significant in differentiation of DR-TB.

QR code based patient data protection in ECG steganography.

Connected health enables patient centric interventions resulting in better healthcare and hence better living. In order to accomplish this, bio-signals, medical and diagnosis information are shared and accessed by multiple actors and it is important to protect the privacy of patient data. Steganography is widely used to protect patient data by hiding it in the medical information. Current work investigates ECG steganography using Discrete Wavelet Transform (DWT) and Quick Response (QR) code. Steganography deteriorates the ECG signal and it is important to minimize this deterioration to preserve diagnosability. 1D ECG signal is converted to 2D ECG image and decomposed into sub-bands by subjecting it to DWT. The novelty of the proposed approach lies in converting the patient data into QR code and using it as watermark in ECG steganography. The QR code is embedded in the 2D image using additive quantization scheme. The performance of proposed method is measured using Peak Signal to Noise Ratio, Percentage Residual Difference and Kullback-Leibler distance. These metrics are used as a measure of imperceptibility while the data loss during retrieval is measured by Bit Retrieval Rate. The proposed method is demonstrated on normal ECG signals obtained from MIT-BIH database for different QR code versions. Metrics reveal that imperceptibility decreased for increasing patient data size and increasing scaling factors. Metrics were independent of the sub-band and the proposed method allows reliable patient data protection with full retrieval ability.

Pull out strength calculator for pedicle screws using a surrogate ensemble approach.

BACKGROUND AND OBJECTIVE: Pedicle screw instrumentation is widely used in the treatment of spinal disorders and deformities. Currently, the surgeon decides the holding power of instrumentation based on the perioperative feeling which is subjective in nature. The objective of the paper is to develop a surrogate model which will predict the pullout strength of pedicle screw based on density, insertion angle, insertion depth and reinsertion. METHODS: A Taguchi's orthogonal array was used to design an experiment to find the factors effecting pullout strength of pedicle screw. The pullout studies were carried using polyaxial pedicle screw on rigid polyurethane foam block according to American society for testing of materials (ASTM F543). Analysis of variance (ANOVA) and Tukey's honestly significant difference multiple comparison tests were done to find factor effect. Based on the experimental results, surrogate models based on Krigging, polynomial response surface and radial basis function were developed for predicting the pullout strength for different combination of factors. An ensemble of these surrogates based on weighted average surrogate model was also evaluated for prediction. RESULTS: Density, insertion depth, insertion angle and reinsertion have a significant effect (p <0.05) on pullout strength of pedicle screw. Weighted average surrogate performed the best in predicting the pull out strength amongst the surrogate models considered in this study and acted as insurance against bad prediction. CONCLUSIONS: A predictive model for pullout strength of pedicle screw was developed using experimental values and surrogate models. This can be used in pre-surgical planning and decision support system for spine surgeon.

Steganography in arrhythmic electrocardiogram signal.

Security and privacy of patient data is a vital requirement during exchange/storage of medical information over communication network. Steganography method hides patient data into a cover signal to prevent unauthenticated accesses during data transfer. This study evaluates the performance of ECG steganography to ensure secured transmission of patient data where an abnormal ECG signal is used as cover signal. The novelty of this work is to hide patient data into two dimensional matrix of an abnormal ECG signal using Discrete Wavelet Transform and Singular Value Decomposition based steganography method. A 2D ECG is constructed according to Tompkins QRS detection algorithm. The missed R peaks are computed using RR interval during 2D conversion. The abnormal ECG signals are obtained from the MIT-BIH arrhythmia database. Metrics such as Peak Signal to Noise Ratio, Percentage Residual Difference, Kullback-Leibler distance and Bit Error Rate are used to evaluate the performance of the proposed approach.

Discrete wavelet transform and singular value decomposition based ECG steganography for secured patient information transmission.

ECG Steganography provides secured transmission of secret information such as patient personal information through ECG signals. This paper proposes an approach that uses discrete wavelet transform to decompose signals and singular value decomposition (SVD) to embed the secret information into the decomposed ECG signal. The novelty of the proposed method is to embed the watermark using SVD into the two dimensional (2D) ECG image. The embedding of secret information in a selected sub band of the decomposed ECG is achieved by replacing the singular values of the decomposed cover image by the singular values of the secret data. The performance assessment of the proposed approach allows understanding the suitable sub-band to hide secret data and the signal degradation that will affect diagnosability. Performance is measured using metrics like Kullback-Leibler divergence (KL), percentage residual difference (PRD), peak signal to noise ratio (PSNR) and bit error rate (BER). A dynamic location selection approach for embedding the singular values is also discussed. The proposed approach is demonstrated on a MIT-BIH database and the observations validate that HH is the ideal sub-band to hide data. It is also observed that the signal degradation (less than 0.6%) is very less in the proposed approach even with the secret data being as large as the sub band size. So, it does not affect the diagnosability and is reliable to transmit patient information.