Debashish Mohapatra

Bio: Debashish Mohapatra is an academic researcher from National Institute of Technology, Rourkela. The author has contributed to research in topics: Data acquisition & Perceptron. The author has an hindex of 3, co-authored 9 publications receiving 20 citations.

Design of Solar Powered Battery Charger: An Experimental Verification

Abstract: This paper presents the design and implementation details of the embedded system to design a photovoltaic based battery charger for lead-acid battery. The battery is charged in float charging mode as well as in bulk charging mode. In bulk charging mode perturb and observe maximum power point tracking algorithm is used to charge the battery. Hardware realization of the PV based battery charger has been carried out and is tested in real time scenario.

Development of a Cost-Effective IoT-Based Weather Monitoring System

Abstract: This work explores the development and deployment of a cost-effective IoT platform to monitor and archival weather data, namely temperature, humidity, atmospheric pressure, and dust particles in a residential area, using open-source technologies. The IoT device sends the data to a remote virtual private server (VPS) over the Internet. A server application runs 24x7 to collect the data and logs it into a database. The necessary steps to set up a VPS server, secure it and install the IoT server application implementing the message queuing telemetry transport protocol are also described. The complete system is verified by real-time implementation using IoT devices, namely NodeMCU ESP 8266 and Raspberry Pi Zero W, along with suitable sensors. The work demonstrates the proof-of-concept feasibility of developing and deploying a scalable weather station from scratch using open-source technologies for faster time to market and the privacy and safety concerns with the end product.

Development and Hardware Implementation of a Phasor Measurement Unit using Microcontroller

Abstract: As the world continues to move towards a Smarter Grid day by day, it has become the necessity to incorporate real-time monitoring of the grid wherein the instantaneous snapshot of the health of the grid can be made available. No other parameters than the Instantaneous Phasors, considered to be the heart-beats of the Electrical Grid, can represent the complete health status of the grid. This paper discusses how an Open Hardware Platform (Arduino Due with ARM Cortex M3 Micro-controller) can be used to estimate the phasors of a three phase system in real-time. The Pulse Per Second(PPS) signal from a GPS module is used to generate the sampling pulses. These pulses synchronise the sampling process by the Analog to Digital Converters(ADC), used by the PMU throughout the globe because of the high accuracy of the atomic clocks in the GPS satellites. The microcontroller uses a 64-Point DFT algorithm to estimate the phasors. The reference time is obtained from the GPS module which is the UTC time, with which the phasors are time stamped and displayed in a real-time Graphical User Interface(GUI) designed using Python(another open source programming language)

Spline-rule ensemble classifiers with structured sparsity regularization for interpretable customer churn modeling

Abstract: An important business domain that relies heavily on advanced statistical- and machine learning algorithms to support operational decision-making is customer retention management. Customer churn prediction is a crucial tool to support customer retention. It allows an early identification of customers who are at risk to abandon the company and provides the ability to gain insights into why customers are at risk. Hence, customer churn prediction models should complement predictive performance with model insights. Inspired by their ability to reconcile strong predictive performance and interpretability, this study introduces rule ensembles and their extension, spline-rule ensembles, as a promising family of classification algorithms to the customer churn prediction domain. Spline-rule ensembles combine the flexibility of a tree-based ensemble classifier with the simplicity of regression analysis. They do, however, neglect the relatedness between potentially conflicting model components which can introduce unnecessary complexity in the models and compromises model interpretability. To tackle this issue, a novel algorithmic extension, spline-rule ensembles with sparse group lasso regularization (SRE-SGL) is proposed to enhance interpretability through structured regularization. Experiments on fourteen real-world customer churn data sets in different industries (i) demonstrate the superior predictive performance of spline-rule ensembles with sparse group lasso over a set well yet powerful benchmark methods in terms of AUC and top decile lift; (ii) show that spline-rule ensembles with sparse group lasso regularization significantly outperform conventional rule ensembles whilst performing at least as well as conventional spline-rule ensembles; and (iii) illustrate the interpretable nature of a spline-rule ensemble model and the advantage of structured regularization in SRE-SGL by means of a case study on customer churn prediction for a telecommunications company.

A New Convolutional Neural Network With Random Forest Method for Hydrogen Sensor Fault Diagnosis

Abstract: Hydrogen is considered to be a hazardous substance. Hydrogen sensors can be used to detect the concentration of hydrogen and provide an ideal monitoring means for the safe use of hydrogen energy. Hydrogen sensors need to be highly reliable, so fault identification and diagnosis for gas sensors are of vital practical significance. However, traditional machine learning methods for fault diagnosis are based on features extracted by experts, prior knowledge requirements and the sensitivity of system changes. In this study, a new convolutional neural network (CNN) using the random forest (RF) classifier is proposed for hydrogen sensor fault diagnosis. First, the 1-D time-domain data of fault signals are converted into 2-D gray matrix images; this process does not require noise suppression and no signal information is lost. Secondly, the features of the gray matrix images are automatically extracted by using a CNN, which does not rely on expert experience. Dropout and zero-padding are used to optimize the structure of the CNN and reduce overfitting. Random forest, which is robust and has strong generalization ability, is introduced for the classification of gas sensor signal modes, in order to obtain the final diagnostic results. Finally, we design and implement a prototype hydrogen sensor array for experimental verification. The accuracy of fault diagnosis in hydrogen sensors is 100% under noisy environment with the proposed method, which is superior of CNN without RF and other methods. The results show that the proposed CNN with RF method provides a good solution for hydrogen sensor fault diagnosis.

Design and Implementation of a Low-Cost Phasor Measurement Unit: A Comprehensive Review

Abstract: The complexity of the contemporary electrical power systems imposes challenges in the aspect of monitoring, protection and control. In order to obtain a high speed of response, wide area effect and prices synchronisation, the grid control functions can be benefited by the implementation of Phasor Measurement Units (PMU). The paper is aimed to make a review of the commercial implementation of Phasor Measurement Units and then open source based implementations (open architecture hardware and software). This paper focuses on standard implementations; as a consequence, the concept of virtual PMU is not discussed here.

CAFD: Context-Aware Fault Diagnostic Scheme towards Sensor Faults Utilizing Machine Learning.

Abstract: Sensors’ existence as a key component of Cyber-Physical Systems makes it susceptible to failures due to complex environments, low-quality production, and aging When defective, sensors either stop communicating or convey incorrect information These unsteady situations threaten the safety, economy, and reliability of a system The objective of this study is to construct a lightweight machine learning-based fault detection and diagnostic system within the limited energy resources, memory, and computation of a Wireless Sensor Network (WSN) In this paper, a Context-Aware Fault Diagnostic (CAFD) scheme is proposed based on an ensemble learning algorithm called Extra-Trees To evaluate the performance of the proposed scheme, a realistic WSN scenario composed of humidity and temperature sensor observations is replicated with extreme low-intensity faults Six commonly occurring types of sensor fault are considered: drift, hard-over/bias, spike, erratic/precision degradation, stuck, and data-loss The proposed CAFD scheme reveals the ability to accurately detect and diagnose low-intensity sensor faults in a timely manner Moreover, the efficiency of the Extra-Trees algorithm in terms of diagnostic accuracy, F1-score, ROC-AUC, and training time is demonstrated by comparison with cutting-edge machine learning algorithms: a Support Vector Machine and a Neural Network