Nilesh Patel

Bio: Nilesh Patel is an academic researcher from University of Rochester. The author has contributed to research in topics: Motion estimation & Motion compensation. The author has an hindex of 17, co-authored 67 publications receiving 858 citations. Previous affiliations of Nilesh Patel include Oakland University & Universidade Federal de Juiz de Fora.

Renewable energy: Present research and future scope of Artificial Intelligence

Abstract: The existence of sunlight, air and other resources on earth must be used in an appropriate way for human welfare while still protecting the environment and its living creatures. The exploitation of sunlight and air as a substantial Renewable Energy (RE) source is an important research and development domain over past few years. The present and future overtaking in RE mainly comprises of (i) the development of novel technology for optimum production from the available natural resources (ii) environmental awareness, and (iii) the better management and distribution system. Like other domains (food, health, accommodation, safety, etc.), Artificial Intelligence (AI) could assist in achieving the future goals of the RE. Statistical and biologically inspired AI methods have been implemented in several studies to achieve common and future aims of the RE. The present study summarizes the review of reviews and the state-of-the-art research outcomes related to wind energy, solar energy, geothermal energy, hydro energy, ocean energy, bioenergy, hydrogen energy, and hybrid energy. Particularly, the role of single and hybrid AI approaches in research and development of the previously mentioned sources of RE will be comprehensively reviewed.

Comprehensive Overview of Low Voltage Ride Through Methods of Grid Integrated Wind Generator

Abstract: The wind power generation is a rapidly growing grid integrated renewable energy (RE) technology with an installed capacity of 539.291 GW. The capability of the wind energy conversion system (WECS) to remain integrated into the utility network in the case of low voltage events is called low-voltage ride-through (LVRT) capability. This paper offers a comprehensive overview of improvement techniques of the LVRT capability in WECS to increase the wind energy penetration level in the utility grid. Exhibited portrait manifests a broad spectrum of 1) wind turbines, 2) electrical generators used for wind power applications, 3) international grid codes applicable for grid integration of WECS, 4) LVRT fundamentals in WECS, 5) wind turbines LVRT methods by doubly fed induction generator (DFIG), 6) wind turbines LVRT methods by permanent magnet synchronous generators (PMSG), and 7) LVRT methods of wind turbines using squirrel cage induction generator (SCIG). This ready-reckoner paper critically reviews and classifies more than 190 research papers on LVRT issues, practices, and available technologies for grid integration in wind energy systems, and it aims to be a quick reference for the researchers, designers, manufacturers, and engineers working in the same field.

Economic data analytic AI technique on IoT edge devices for health monitoring of agriculture machines

Abstract: In the era of Internet of things (IoT), network Connection of an enormous number of agriculture machines and service centers is an expectation. However, it will be with a generation of massive volume of data, thus overwhelming the network traffic and storage system especially when manufacturers give maintenance service typically by various data analytic applications on the cloud. The situation is more complex in the context of low latency applications such as health monitoring of agriculture machines, although require emergency responses. Performing the computational intelligence on edge devices is one of the best approaches in developing green communications and managing the blast of network traffic. Due to the increasing usage of smartphone applications, the edge computation on the smartphone can highly assist the network traffic management. In connection with the mentioned point, in the context of exploiting the limited computation power of smartphones, the design of an AI-based data analytic technique is a challenging task. On the other hand, the users’ need for economic technology makes it not to be easily pierced. This research work aims both targets by presenting a bi-level genetic algorithm approach of an optimized data analytic AI technique for monitoring the health of the agriculture vehicles which can be economically utilized on smartphone end-devices using the built-in microphones instead of expensive IoT sensors.

Method and system for simplified recordkeeping including transcription and voting based verification

Abstract: A simplified method of recordkeeping is provided. The method includes capturing a document image of a transaction document; identifying a document type of the transaction document; associating the document image with a data capture template based on the document type; transmitting the document image and the data capture template to a remote system; extracting record data from the document image based on the document type; and populating the data capture template with the record data.

A Bi-Level Evolutionary Optimization for Coordinated Transmission Expansion Planning

Abstract: In this paper, a real-life application of bi-level evolutionary optimization is proposed to optimize the electricity industry infrastructure. It offers a coordinated generation and transmission expansion planning (CGTEP) from the perspective of an independent system operator (ISO). The main objective of the proposed study is to show the effect of optimizing the generators concerning capacity and location both to reduce the transmission investment and increasing the reliability of the network. The proposed framework of bi-level optimization contributes to utilize global evolutionary optimization method GA in its hybrid form in level-I to select the location of lines and energy generators. The respective capacities of the corresponding selected lines and generators are optimized in the level-II by RW. In conflicting objectives of minimizing the investment for capacity addition in the network and maximizing the reliability, a Pareto-optimal solution is achieved by using the theory of marginal value (TMV). To satisfy TMV, the total cost is minimized, which comprises the cost of investment in building new transmission and generation capacities, cost of not-served expected energy, cost of unutilized expected generation, and cost of unserved energy due to the constrained network. Proposed methodology on IEEE 24-bus power system is presented encountering the combination of N-1 and probable N-2 contingency security criteria. The comparison results show that bi-level GA-RW optimization minimizes the investment with increasing power system reliability.

Pattern Recognition and Machine Learning

Abstract: Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

When is nearest neighbor meaningful

Abstract: We explore the effect of dimensionality on the nearest neighbor problem. We show that under a broad set of conditions (much broader than independent and identically distributed dimensions), as dimensionality increases, the distance to the nearest data point approaches the distance to the farthest data point. To provide a practical perspective, we present empirical results on both real and synthetic data sets that demonstrate that this effect can occur for as few as 10-15 dimensions. These results should not be interpreted to mean that high-dimensional indexing is never meaningful; we illustrate this point by identifying some high-dimensional workloads for which this effect does not occur. However, our results do emphasize that the methodology used almost universally in the database literature to evaluate high-dimensional indexing techniques is flawed, and should be modified. In particular, most such techniques proposed in the literature are not evaluated versus simple linear scan, and are evaluated over workloads for which nearest neighbor is not meaningful. Often, even the reported experiments, when analyzed carefully, show that linear scan would outperform the techniques being proposed on the workloads studied in high (10-15) dimensionality!.

Decision trees: a recent overview

Abstract: Decision tree techniques have been widely used to build classification models as such models closely resemble human reasoning and are easy to understand. This paper describes basic decision tree issues and current research points. Of course, a single article cannot be a complete review of all algorithms (also known induction classification trees), yet we hope that the references cited will cover the major theoretical issues, guiding the researcher in interesting research directions and suggesting possible bias combinations that have yet to be explored.