77 research outputs found
sj-docx-2-pie-10.1177_09544089231190200 - Supplemental material for Experimental investigation to optimize machining parameters for super duplex stainless steel in spark EDM using die-sinking and MQL system
No full textSupplemental material, sj-docx-2-pie-10.1177_09544089231190200 for Experimental investigation to optimize machining parameters for super duplex stainless steel in spark EDM using die-sinking and MQL system by T Sampath Kumar, M Vignesh, Ayush Bansi Mathur and Omkar Vinay Chunamari in Proceedings of the Institution of Mechanical Engineers, Part E: Journal of Process Mechanical Engineering</p
sj-docx-1-pie-10.1177_09544089231190200 - Supplemental material for Experimental investigation to optimize machining parameters for super duplex stainless steel in spark EDM using die-sinking and MQL system
No full textSupplemental material, sj-docx-1-pie-10.1177_09544089231190200 for Experimental investigation to optimize machining parameters for super duplex stainless steel in spark EDM using die-sinking and MQL system by T Sampath Kumar, M Vignesh, Ayush Bansi Mathur and Omkar Vinay Chunamari in Proceedings of the Institution of Mechanical Engineers, Part E: Journal of Process Mechanical Engineering</p
Unusual course of interferon-related retinopathy in chronic hepatitis C
No full textInterferon Alfa retinopathy usually presents as cotton wool spots, superficial hemorrhages and macular edema. We describe a rare case of severe retinopathy involving hard exudates at macula that lead to permanent visual loss in one eye. Elderly male presented with diminution of vision in right eye of 8 month duration. He was a diagnosed case of compensated chronic hepatitis C and had received interferon Alfa therapy before. Fundus examination of both eye showed multiple hard exudates at macula with a plaque involving the foveal center in right eye. OCT and FFA confirmed the findings seen clinically. Patient was advised regular follow up and on 3 months follow up his clinical picture was same. Ours is the first case report where patient had significant visual loss secondary to hard exudate plaque at center of fovea and ischemic fovea in right eye.Presence of hard exudates at any stage of therapy of hepatitis C could be an indicator of the severity of retinopathy with possible indication for stopping the drug
Signal processing for time-of-flight imaging sensors: an introduction to inverse problems in computational 3-D imaging
No full textTime-of-flight (ToF) sensors offer a cost-effective and realtime solution to the problem of three-dimensional (3-D) imaging-a theme that has revolutionized our sceneunderstanding capabilities and is a topic of contemporary interest across many areas of science and engineering. The goal of this tutorial-style article is to provide a thorough understanding of ToF imaging systems from a signal processing perspective that is useful to all application areas. Starting with a brief history of the ToF principle, we describe the mathematical basics of the ToF image-formation process, for both time- and frequency-domain, present an overview of important results within the topic, and discuss contemporary challenges where this emerging area can benefit from the signal processing community. In particular, we examine case studies where inverse problems in ToF imaging are coupled with signal processing theory and methods, such as sampling theory, system identification, and spectral estimation, among others. Through this exposition, we hope to establish that ToF sensors are more than just depth sensors; depth information may be used to encode other forms of physical parameters, such as, the fluorescence lifetime of a biosample or the diffusion coefficient of turbid/scattering medium. The MATLAB scripts and ToF sensor data used for reproducing figures in this article are available via the author?s webpage: http://www.mit.edu/~ayush/Code
Privacy-Preserving Techniques for Machine Learning Applications in Supply Chains
No full textSupply chains are vital to the global economy, and so, increasing efficiency in supply chain management is of utmost importance. Modernizing technology has allowed for various uses of machine learning to be possible in several aspects of supply chains, specifically in demand forecasting with prediction models, and customer relations with chat-bots. While this may be the case, many organizations are reluctant to implement such solutions due to potential threats to their privacy. In addition to this, some currently existing solutions do not take special care for privacy preservation. This brings the question of, "How can privacy be preserved in machine learning based applications in supply chains?" The results of this survey show that several approaches for privacy-preservation of machine learning applications exist, and can be applied to supply chains while maintaining increased efficiency in supply chain management.CSE3000 Research ProjectComputer Science and Engineerin
Exploring Hybrid Intelligence for Topic Interpretation in Colorectal Cancer Research: A Comparative Study of GPT-3.5 and Human Expertise
No full textColorectal cancer is a widespread disease that significantly impacts the health of individuals worldwide. Understanding the needs and concerns of those affected by this disease is crucial for improving patient outcomes and enhancing the quality of care. Patient web forums have emerged as valuable platforms for individuals to openly share their experiences and thoughts related to colorectal cancer, providing unique insights into the social, physical and emotional aspects of their patient journey. These forums offer a more comprehensive and authentic portrayal of patient experiences compared to traditional patient data collection methods, such as questionnaires and interviews, which may not capture the full scope of patients experiences in the colorectal cancer carepath.However, analyzing the vast amount of unstructured data within these patient web forums presents a significant challenge. Traditional manual analysis by human experts is time-consuming, labor-intensive, and limited in scalability, making it impractical to analyze the sheer volume of patient-generated content. This is where the application of natural language processing (NLP) techniques becomes crucial. NLP enables the automated processing and analysis of textual data, allowing for efficient extraction and interpretation of the large amounts of patient forum posts.Nevertheless, relying solely on machine intelligence, such as topic modeling and natural language generation, for interpreting patient forum data carries inherent risks, including the potential for disseminating misleading information. While these machine-driven techniques offer efficient and scalable ways to analyze and generate insights from the large amount of diverse and unstructured patient forums, they may lack the necessary contextual understanding and domain expertise to ensure the accuracy, relevance, and ethical implications for interpreting colorectal cancer patient experiences.To close this gap between human experts and machine intelligence, this thesis explores the potential of hybrid intelligence (HI) for topic interpretation in colorectal cancer research. The main research question is: ``How can topic modeling, GPT-3.5 language generation and human expertise be combined to explore the interpretation of patient web forums in colorectal cancer (CRC) research?"To address the research question, three human studies were conducted. The first study employed NMF topic modeling to compare topic interpretations created independently by medical workers and GPT-3.5. This comparative analysis discovered unique observations that differentiate human-written and AI-generated interpretations on online patient stories. In the second study, it was investigated how medical researchers collaborate with GPT-3.5 to develop hybrid interpretations on patient experience topics generated by the BERTopic model. A Flask web application served as the interactive platform for combining their knowledge with the AI model. Finally, the third study made professional human evaluators assess the topic relevance of the interpretations generated by medical researchers and GPT-3.5 to determine whether the combination of GPT-3.5 and human expertise leads to improved topic interpretations compared to individual interpretations.The proposed solution to the research problem is to explore a hybrid workflow that compares, combines and validates GPT-3.5 language generation and human expertise, aiming for enhanced interpretations of topics extracted from colorectal cancer patient forums. The three studies provide opportunities for researchers and medical professionals to integrate machine intelligence from topic models and GPT-3.5 in their field of work. The hybrid workflow has conclusively demonstrated that human experts were successfully able to compare and enhance the relevance of human and GPT-3.5 interpretations of colorectal cancer patient experience topics. This allowed human experts to efficiently reach a more comprehensive understanding of patient forum data, which is essential for improving patient health in colorectal cancer research.Computer Scienc
Wind turbine gearbox fault prognosis using high-frequency monitoring SCADA data
No full textWith growing wind energy capacity, especially offshore, reliability of wind turbines (WT) becomes a relevant concern. Poor reliability directly affects their cost effectiveness due to increased operation and maintenance (O&M) costs and reduced availability to generate power because of downtime. This certainly encourages WT operators to employ advanced O&M methodologies and focus on the critical components to reduce failure rate, time to repair and maximizing WT performance. Condition monitoring (CM) of wind turbines for the purpose of prognostics and health management of critical equipments can improve the reliability and reduce maintenance costs by identifying failures at the earliest possible stage and by eliminating unnecessary scheduled maintenance. In contrast to the expensive purpose-built condition monitoring systems, a SCADA (Supervisory Control and Data Acquisition System) data-based condition monitoring system uses data already collected at the wind turbine controller and provides a cost-effective way to monitor wind turbines.This research focusses on developing a prognostics framework for WT gearboxes, which are one of the costliest subsystems to maintain during a turbine’s life. The framework follows a data-driven approach and combines two machine learning algorithms – Artificial Neural Network and Support Vector Machine to capture anomalous operations of the WT gearbox. A real-time monitoring scheme is developed to track the degradation and set a maintenance alarm as the first evident signature of failure is identified. The framework was implemented using high-frequency SCADA data and was able to detect gearbox failure, a month in advance, providing enough lead time to plan and perform required maintenance activities. Additionally, a sensitivity study is conducted to determine an optimal sampling frequency of SCADA data which can be used for CM purposes as the current industry practice of storing it as 10 min averages leads to a loss of information about the condition of a WT component. The results show that the feedforward ANN can efficiently learn the complex mapping between the input and output features. To analyse the error between ANN predictions and the in-field measurements, four residual error features maximum error, minimum error, root mean squared error and error distribution are used as inputs for the OCSVM model to understand the complex boundary between normal and anomalous operation. The percentage of anomalies computed for each week of operation, 4 months before failure, show an increasing trend as the turbine approaches failure. To determine a threshold for maintenance alert, a realtime monitoring scheme based on linear regression and bootstrapped confidence intervals is developed to track the progression of anomalies and alarm a maintenance alert as the first indication of incipient fault becomes evident. The scheme alarms for maintenance a month before the actual failure, providing enough lead time to plan and maintain the gearbox.A sensitivity study is carried out for a range of sampling periods ranging from 100 Hz to 10 min. The results demonstrate that highfrequency SCADA data is beneficial for condition monitoring of the gearbox, but only if the noise in the data can be excluded. On the other hand, despite the loss of information due to the averaging effect for large sampling periods, SCADA data aggregated over a 30 s period could be utilized to predict the gearbox failure a month in advance. Furthermore, the ANN model performance is found to be sensitive to the number of data samples available for training.Electrical Engineering | Sustainable Energy Technolog
Embedded Real Time Partial Discharge Pulse Feature Extraction
No full textPartial Discharges(PD) are commonly produced in defects within the insulation systems of high voltage equipment. These discharges are typically nanosecond current pulses in the amplitude range of milli-amperes. A long term exposure of the insulation system to these partial discharges accelerate the aging mechanisms that eventually lead to the final breakdown of the insulation system. Such insulation breakdowns in High Voltage (HV) / Medium Voltage (MV) equipment typically involve arc-flash/fire hazards, posing safety threats. Moreover probable undelivered power and huge financial losses are also associated. Early detection of PD activity can provide warnings about pending insulation/device failures and hence, maintenance or repair activities can be scheduled before breakdown occurs. Moreover, clustering of PD due to different types of sources is of practical importance as it indicates the severity of defect and provides an insight into the time available for repair activities before complete breakdown. State of the art tools for electrical PD monitoring are expensive and cannot be economically deployed over a large network of HV/MV assets. Moreover, they employ classification schemes based on less robust PD features. This thesis marks the completion of the first stage in the process of building an open source, cost-effective, automated embedded online partial discharge detection tool for feature extraction and PD classification based on new, advanced robust features of partial discharges. As an outcome of this thesis, an embedded solution for real time PD detection and feature extraction was developed to facilitate future PD classification.Electrical Engineering | Embedded System
Exploiting multi-core parallelism on optimal decision trees
No full textThis paper presents a study that discusses how multi-threading can be used to improve the runtime performance of constructing optimal classification trees. Decision trees are popular for solving classification or regression problems in machine learning. Heuristic methods are used to build decision tree algorithms that produce models of high accuracy within a short amount of time. An important limitation is that these heuristics locally optimize the decisions of the tree model. Consequently, in recent years, optimal classification tree algorithms have been introduced to strive for global optimality when learning decision trees. Unfortunately, the runtimes for constructing optimal decision trees are quite larger in comparison with the runtimes obtained from heuristic solutions. The study provides a mitigation for this by parallelizing the work of a recently invented optimal decision tree algorithm on multiple cores. There exist different parallel techniques to divide and schedule the work among processors. Our strategy follows the parallel approach that computes optimal decision trees using threads as processing elements in a shared memory space. In the end, we provide the experimental study to show that impressive runtime results of the optimal decision tree algorithm are successfully obtained with the help of the parallelization strategy.CSE3000 Research ProjectComputer Science and Engineerin
- …
