Papers by Dr. Abhishek Verma
Process Safety and Environmental Protection, 2022
In this study, a novel scheme is proposed for occupational safety improvement by leveraging the c... more In this study, a novel scheme is proposed for occupational safety improvement by leveraging the concepts of Virtual Reality (VR), Safety Function Deployment (SFD), TRIZ (theory of inventive problem solving) and capital budgeting approach. This integrated approach helped in identifying safety interventions, which added a new dimension to the safety intervention design in the operational study at the workplace. By observing the effectiveness of the immersive safety training in identifying the accident path elements such as hazards and initiating mechanisms, a three-dimensional (3D) VR environment is created for safety training of Electric Overhead Travelling (EOT) crane operators of the studied manufacturing industry. This study is carried out in two phases based on accident path elements identified before and after safety training in the VR platform. Three House of Safety (HoSs) are used in this study to establish a relationship between tasks and hazards, hazards and initiating mechanism, and initiating mechanism and safety interventions. Priority weight of interventions in the last HoS is fed as input to the capital budgeting methodology for the selection of an optimal number of interventions for safety improvement. 0–1 multi-dimensional knapsack model is used in capital budgeting considering safety budget and cost of each intervention. We have introduced Z- number approach in capital budgeting methodology to characterize the reliability of experts’ opinion considered in this process. A 15% improvement in safety performance is observed after safety training. Further, it is observed that technology-based interventions (laser scanner, smart helmet, smart jacket, Radio Frequency Identification (RFID) to monitor Personal Protective Equipment (PPE), immersive safety training) are having more weightage than traditional safety interventions after safety training.
Safety Science, 2022
Occupational incidents are a major concern in steel industries due to the complex nature of job a... more Occupational incidents are a major concern in steel industries due to the complex nature of job activities. Forecasting incidents caused by various activities and determining the root cause might aid in implementing appropriate interventions. Thus, the purpose of this study is to investigate the future trend and identify the pattern of contributing factors of incident occurrences. The study focuses on an integrated steel plant where different steel-making-related operations are carried out in separate units. The incident data of 45 months is used. Initially, a unit-wise trend of incidents (e.g., injury, near-miss and property damage) is forecasted using the autoregressive integrated moving average (ARIMA) model to determine the near-future incident trends and to identify the most incident-prone unit of the plant. The model is validated using six-month holdout data, and the predicted number of incidents is compared with the actual counts. The ARIMA model indicates that the safety performance of the iron making unit is found to be underperforming. In the second phase, meaningful association rules are extracted from text data using the apriori algorithm for the underperforming unit to discover the incident-causing factors. Results from text mining-based association mining suggest that bike and car-related incidents are the leading causes of injury. Similarly, gas leakage, slag spillage, and coke-oven door malfunctioning are causing near-miss incidents. The majority of property damage incidents are reported due to derailment, loading/ unloading and dashing of the dumper vehicle. Effective implementation of the study’s specified rules can aid plant administration in formulating policies to improve safety performance by designing focused interventions.
Springer, 2022
Wireless sensor network (WSN) based applications have become regular in our daily lives, and thei... more Wireless sensor network (WSN) based applications have become regular in our daily lives, and their integration with the Internet of Things (IoT) makes them even more productive and convenient. However, the inclusion of massive devices, which form the core of IoT, raises plenty of security concerns. Many security strategies to handle data privacy have been proposed in previous work. However, very few of these schemes addressed the confidentiality of the sensor node's position. The goal of this study is to ensure source node location privacy by source location privacy preservation technique by randomized ring routing and confounding transmission (SLP-RRRCT). Random routing with confusing transmission benefits the SLP-RRRCT by distracting the adversary backtracking process. After the random routing phase expires, packets are forwarded to the base station (BS) by neighbour grid-based ring routing. During the development of SLP-RRRCT, we concentrated on the privacy of sensor node position, sensor energy usage, network lifetime, and packet routing randomization. Through a simulation experiment and theoretical analysis, we have observed that the proposed SLP-RRRCT provides better safety time, randomization in transmission delay, and large network lifetime than the compared techniques, i.e., baseline, probabilistic, phantom, source location protection protocol based on dynamic routing (SLPDR), and source location privacy protection scheme based on ring-loop routing (SLPRR).
Taylor & Francis, 2022
Data-driven approaches have noteworthy significance in managing and improving logistics in E-comm... more Data-driven approaches have noteworthy significance in managing and improving logistics in E-commerce enterprises. This study focuses on the development of an integrated framework to analyse the Brazilian E-Commerce enterprise public dataset. From the analysis, it is found that sellers of Ibitinga city of SP state had the most count of late deliveries where 42 sellers are under-performing in terms of estimated delivery time. Locations of customers and sellers were spotted on a map to get a geographical representation. The proposed framework may help E-Commerce enterprise owners and retail merchants to make better decisions related to sales and E-Commerce enterprise logistics.
Elsevier, 2019
Although analysing categorical data from incident investigation reports provides meaningful assoc... more Although analysing categorical data from incident investigation reports provides meaningful associations amongst causal factors of incidents, however, to date, no studies considered these associations in designing actionable interventions for safety improvement. We propose a methodology using descriptive analytics and axiomatic design framework. In this study, we have analysed injury, and ‘property-damage’ data, collected for 45 months from a large integrated steel plant. The data are analysed using the contingency table, Cramer’s V, Phi coefficients (ϕ) and Fisher’s exact test. The ‘wire-making division’ is the most injury-prone. Unsafe acts done by fellow workers are significantly causing injuries in ‘support services’, maintenance and ‘steel-making’. The property-damage cases are mostly reported in ‘steel-making division’, and caused by material-handling, crane-dashing, toxic-chemical, hot-metal and process-related incidents. It is also found that SOP inadequacy and non-compliance are significantly associated with ‘property-damage’ incidents. The key interventions from axiomatic design are as follows. For process-related incidents, regular inspection and maintenance of safety-critical equipment should be done. Safety-critical instrument and alarms can also be used to monitor safe operating limits of processes. Unsafe acts by fellow workers are the result of lack of coordination and communication. So, the management should identify and provide the types of safety training necessary to improve the same. The material-handling related problems can be handled through improved staff competency and communication. To address the SOP related issues, operating procedures should be reviewed, revised and communicated regularly.
Elsevier, 2019
An attempt has been made to develop a decision support system (DSS) for safety improvement using ... more An attempt has been made to develop a decision support system (DSS) for safety improvement using a multi-step knowledge discovery process involving multiple correspondence analysis (MCA), t-SNE algorithm and K-means clustering. MCA is used for dimension reduction and perceptual mapping from categorical data. Usually, the first two dimensions are used for perceptual mapping if these two dimensions explain a significant percentage of variance. Otherwise, the traditional method of two dimensional mapping, leads to loss of important categorical information involved with other dimensions. Considering the above, a novel R2-profile approach, as an alternate to inertia based approach, is adopted to obtain the desired number of dimensions to be retained without loss of significant amount of information. t-SNE technique reduces the high dimensional data into two dimensional (2D) map, which provides the associations amongst different categories. K-means clustering grouped the 2D categories in homogenous clusters as per the similarities of the categories. A novel kernel category based chi-square distance method is proposed to identify sub-clusters within a cluster which subsequently provides useful rules for safety improvement. The methodology also provides a logical approach of dimension reduction in a form called ‘funnel diagram’. Finally, the DSS is applied to analysing near miss incidents occurred in electric overhead traveling (EOT) crane operations in a steel plant. Several safety rules are identified and safety interventions are proposed.
Taylor & Francis, 2018
The purpose of this study is to develop a text clustering-based cause and effect analysis methodo... more The purpose of this study is to develop a text clustering-based cause and effect analysis methodology for incident data to unfold the root causes behind the incidents. A cause–effect diagram is usually prepared by using experts’ knowledge which may fail to capture all the causes present at a workplace. On the other hand, the description of incidents provided by the workers in the form of incident reports is typically a rich data source and can be utilized to explore the causes and sub-causes of incidents. In this study, data were collected from an integrated steel plant. The text data were analysed using singular value decomposition (SVD) and expectation-maximization (EM) algorithm. Results suggest that text-document clustering can be used as a feasible method for exploring the hidden factors and trends from the description of incidents occurred at workplaces. The study also helped in finding out the anomaly in incident reporting.
Taylor and Francis, 2018
Large integrated steel plants employ an effective safety management system and gather a significa... more Large integrated steel plants employ an effective safety management system and gather a significant amount of safety-related data. This research intends to explore and visualize the rich database to find out the key factors responsible for the occurrences of incidents. The study was carried out on the data in the form of investigation reports collected from a steel plant in India. The data were processed and analysed using some of the quality management tools like Pareto chart, control chart, Ishikawa diagram, etc. Analyses showed that causes of incidents differ depending on the activities performed in a department. For example, fire/explosion and process-related incidents are more common in the departments associated with coke-making and blast furnace. Similar kind of factors were obtained, and recommendations were provided for their mitigation. Finally, the limitations of the study were discussed, and the scope of the research works was identified.
Springer Singapore
This study aims to analyse the incident investigation reports logged after the occurrence of even... more This study aims to analyse the incident investigation reports logged after the occurrence of events from an integrated steel plant and map it with proactive safety data. From the narrative text describing the event, this study has attempted to unfold the hazards and safety factors present at the workplace. Text document clustering with expectation maximization algorithm (EM) has been used to group the different events and find key phrases from them. These key phrases are considered as the root causes of the reported events. This study shows how the mapping of the safety factors from both proactive safety data and incident reports can help in the improvement of safety performance as well as better allocation of resources. The study points out specific areas to the management where improvements are needed. The mapping also indicates the areas of improvement made by the constant effort of safety practitioners.
Springer Singapore
Prediction of occupational incidents is an important task for any industry. To do this, reactive ... more Prediction of occupational incidents is an important task for any industry. To do this, reactive data has been used by most of the previous studies in this domain. As an extension of the existing works, the present study has used the underused proactive data coupled with reactive data to establish the predictive models so that the information inherent in both data sets could be better utilized. The main aim of the study is to predict the incident outcomes using mixed data set comprising reactive and proactive data together. Two decision tree classifiers, i.e. classification and regression tree (CART) andC5.0, have been implemented with tenfold cross-validation. Furthermore, the ensemble technique, namely adaptive boosting has been implemented to increase the classification accuracy. Results show that boosted C5.0 produces higher accuracy than others for the prediction task. Furthermore, the rules obtained produce the insight of the incidents. The limitation of the present study includes the use of less amount of data and the requirement of experts’ domain knowledge for a large span of time. Future scope of the study includes the proper feature selection for preparation of the mixed dataset and building the better classification algorithm for better prediction of occurrence of accidents.The present work sets out the potential use of both types of data sources together.
Springer, 2017
Near-Miss incidents can be treated as events to signal the weakness of safety management system (... more Near-Miss incidents can be treated as events to signal the weakness of safety management system (SMS) at the workplace. Analyzing near-misses will provide relevant root causes behind such incidents so that effective safety related interventions can be developed beforehand. Despite having a huge potential towards workplace safety improvements, analysis of near-misses is scant in the literature owing to the fact that near-misses are often reported as text narratives. The aim of this study is therefore to explore text-mining for extraction of root causes of near-misses from the narrative text descriptions of such incidents and to measure their relationships probabilistically. Root causes were extracted by word cloud technique and causal model was constructed using a Bayesian network (BN). Finally, using BN’s inference mechanism, scenarios were evaluated and root causes were listed in a prioritized order. A case study in a steel plant validated the approach and raised concerns for variety of circumstances such as incidents related to collision, slip-trip-fall, and working at height.
In this study, we have analyzed a steel plant's derailment data using correspondence analysis. Th... more In this study, we have analyzed a steel plant's derailment data using correspondence analysis. The primary purpose of this analysis is to find out associations of categories of factors contributing to the derailments which ultimately lead to the development of meaningful rules for preventing derailments. 348 derailment incidents collected over a period of 42 months were analyzed considering 4 factors namely, shift of working, location, cause of derailment and department responsible. Descriptive statistics show that by shift of working there is not much difference in the occurrence of derailments. But from location, cause of derailment and responsibility (departments) points of view, 'raw material line', 'manual operations' and 'production (raw material)' accounted for 50%, 60% and 48.28% of derailments, respectively. From correspondence analysis, it is found that 'level of movements', 'level of human involvement', 'management of wagons', and 'criticality of movements' are the hidden root causes of derailments in the plant studied. In order to improve the safety of in-plant rail transport of the plant studied, the plant management should (i) collect and analyze derailment data related to 'level of movements' and 'human involvement', (ii) adopt collaborative maintenance of wagons as external agencies are also involved in rail transport, and (iii) practice risk based maintenance of the in-plant rail transportation systems.
Elsevier, 2014
The aim of this paper is to find out the patterns of incidents in a steel plant in India. Occupat... more The aim of this paper is to find out the patterns of incidents in a steel plant in India. Occupational incidents occur in steel plant mainly in form of injury, near miss, and property damage or in combination. Different factors are responsible for such incidents to occur. An incident investigation scheme is proposed. Association rule mining approach is used to discover cause-and-affect patterns (rules) using 843 incidents. Thirty-five meaningful association rules are extracted using three criteria, support (S), confidence (C) and lift (L). For example, the results show that unsafe acts done by others are more frequent in injury cases (S = 4.86%, C = 78.8%, L = 2.3). Similarly, one of the SOP (standard operating procedures) related rule: ‘SOP required, available, adequate but not complied’ led to property damage (S = 11.03%, C = 49.2%, L = 1.525). Another useful rule ‘SOP required, available but inadequate, followed’ led to near miss (S = 1.66%, C = 38.89%, L = 1.163). It is also found that for slip, trip and fall incidents, workers working alone (S = 3.91%, C = 76.74%, L = 2.239) or in a group (S = 3.20%, C = 75.00%, L = 2.188) does not make much difference. The findings pinpoint the areas of improvement such as inadequate SOPs, non-compliance of SOPs, training, and slip, trip and fall prevention to minimize incidents.
Artificial Bee Colony (ABC) optimization algorithm is a powerful stochastic evolutionary algorith... more Artificial Bee Colony (ABC) optimization algorithm is a powerful stochastic evolutionary algorithm that is used to find the global optimum solution in search space. In ABC each bee stores candidate solution; and stochastically modifies its candidate over time, based on the best solution found by neighboring bees,and based on the best solution found by the bee itself. When tested over various benchmark function and real life problems, it has performed better than a few evolutionary algorithms and other search heuristics . ABC, like other probabilistic optimization algorithms, has inherent drawback of premature convergence or stagnation that leads to loss of exploration and exploitation capability . Therefore, in order to balance between exploration and exploitation capability of ABC a new search strategy is proposed. In the proposed strategy, search process in ABC is performed by smaller group of independent swarms of bees. The experiments with 10 test functions of different complexities show that the proposed strategy has better diversity and faster convergence than the basic ABC.
Particle Swarm Optimization is a popular heuristic search algorithm which is inspired by the soci... more Particle Swarm Optimization is a popular heuristic search algorithm which is inspired by the social learning of birds or fishes. It is a swarm intelligence technique for optimization developed by Eberhart and Kennedy [1] in 1995. Inertia weight is an important parameter in PSO, which significantly affects the convergence and exploration-exploitation trade-off in PSO process. Since inception of Inertia Weight in PSO, a large number of variations of Inertia Weight strategy have been proposed. In order to propose one or more than one Inertia Weight strategies which are efficient than others, this paper studies 15 relatively recent and popular Inertia Weight strategies and compares their performance on 05 optimization test problems.
Uploads
Papers by Dr. Abhishek Verma