Browsing by Author "Sharma, A."

Now showing 1 - 20 of 22

Ageist Spider Monkey Optimization algorithm
(Elsevier B.V., 2016) Sharma, A.; Sharma, A.; Panigrahi, B.K.; Kiran, D.; Kumar, R.
Swarm Intelligence (SI) is quite popular in the field of numerical optimization and has enormous scope for research. A number of algorithms based on decentralized and self-organized swarm behavior of natural as well as artificial systems have been proposed and developed in last few years. Spider Monkey Optimization (SMO) algorithm, inspired by the intelligent behavior of spider monkeys, is one such recently proposed algorithm. The algorithm along with some of its variants has proved to be very successful and efficient. A spider monkey group consists of members from every age group. The agility and swiftness of the spider monkeys differ on the basis of their age groups. This paper proposes a new variant of SMO algorithm termed as Ageist Spider Monkey Optimization (ASMO) algorithm which seems more practical in biological terms and works on the basis of age difference present in spider monkey population. Experiments on different benchmark functions with different parameters and settings have been carried out and the variant with the best suited settings is proposed. This variant of SMO has enhanced the performance of its original version. Also, ASMO has performed better in comparison to some of the recent advanced algorithms. © 2016
An Improved ResNet-50 Neural Network Design for PV Panel Image Classification
(Springer Science and Business Media Deutschland GmbH, 2025) Kumar, A.; Kashyap, Y.; Sharma, A.
The increasing popularity of photovoltaic (PV) setups stems from their capacity to generate clean and cost-effective electricity. However, various factors can either totally or partially disrupt the production of PV panels. To address this challenge, this study proposes a ResNet-50 model with dynamically adjusted hyperparameters to classify real-time captured images of PV panels into efficient and non-efficient categories. The hyperparameter tuning within the ResNet-50 model is conducted across three distinct cases, revealing that the most optimal classification results are achieved with the following settings: 50 epochs, a learning rate of 0.001, and a batch size of 32. The highest weighted average metrics, including accuracy (96%), recall (96%), precision (97%), and F1-score (96%), were obtained under these settings. Â© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.
An investigation on CRDi engine characteristic using renewable orange-peel oil
(Elsevier Ltd, 2019) Bragadeshwaran, B.; Kasianantham, K.; Arumuga Perumal, D.A.; Babu, J.M.; Tiwari, A.; Sharma, A.
Aiming towards discovering a solution for the imminent fossil fuel crisis, the research contributes towards the utilisation of orange peel oil as a potential alternative to mineral diesel while strictly adhering to the emission norms. The study reveals the performance, combustion and emissions characteristics obtained upon operating a 20% by volume of OPO blended with diesel, in a compression ignition engine, integrated with a common rail direct injection (CRDi) system. The fuel injection pressures were varied as 400 bar, 500 bar and 600 bar. Furthermore, two stage injection strategies were employed while varying the pilot charge quantity as 10%, 20% and 30%. Subsequently, 10% EGR was employed for the test with 30% pilot injection quantity upon realising that the respective NOx emissions were the highest for the same. All the results were compared with the test results while utilising diesel at 600 bar injection pressure. For OPO20 the brake thermal efficiency at full load was observed to be 31.37% higher and the brake specific fuel consumption 5.53% lower than that for diesel. In-cylinder pressure values recorded were almost similar to diesel corresponding to brake power. Heat release rate was significantly higher in case of orange peel oil. Additionally, it was found that smoke, unburned hydrocarbons content and carbon monoxide emission decreased by 16.30%, 27.63% and 42.28% respectively in the engine exhaust. Oxides of nitrogen were recorded to be 15.46% higher than that of diesel. © 2018 Elsevier Ltd
Design and Development of Efficient Under-Drainage System for Lined Canals
(Springer Science and Business Media Deutschland GmbH, 2021) Sharma, A.; Das, B.B.
Under-drainage system for lined canal is present beneath the canal bed to drain off the water present over there. It consists of longitudinal and transverse perforated drain pipes along with the arrangement of pressure relief valves. Cases of failure of lining of canal are there due to inconsistency in under-drainage system. Performance of geocell is exceptionally well in soil compaction, slope stabilization, earth retention and as reinforcement in case of retaining structure, road construction and railway embankments. Contrary to other researches, here performance of geocell as reinforcement of buried pipe under canal bed is investigated. Experimental study is carried out on canal model and on an under-drainage system. Strain in the buried pipe is observed due to application of various loading patterns on canal model. For sustained loading, 29% increase in strain is observed in pipe buried in unreinforced soil as compared to 18% in pipe buried in reinforced soil. For maximum loading almost three times more strain is stored in pipe in unreinforced soil. Yield is also observed in pipe without geocell, whereas at same loading no such behaviour is observed in pipe with geocell. It is reported that geocell can act as reinforcement for buried drain pipes under canal bed, and this helps in making under-drainage system efficient. Â© 2021, Springer Nature Singapore Pte Ltd.
Design and Implementation of a System for Vehicle Accident Reporting and Tracking
(Institute of Electrical and Electronics Engineers Inc., 2022) Dankan Gowda, V.D.; Sharma, A.; Naik, A.S.; Meena, R.S.; Kudari, J.M.; Purushotham, S.
Population growth and per capita income have contributed to increasing vehicle ownership and presence on roads worldwide. Increasing traffic on roads is one of the prime causes of road accidents. A large proportion of people die prematurely in road accidents. It is almost impossible to predict before the accident happens. Also, there may be some accident prevention mechanisms and early warning systems, but it is hard to avert road accidents wholly. This paper has explained in detail, the designing and implementation of a crash notifier system. Â© 2022 IEEE.
Human-in-the-Loop Data Analytics for Classifying Fatal Mining Accident Causes Using Natural Language Processing and Machine Learning Techniques
(Springer Science and Business Media Deutschland GmbH, 2025) Sharma, A.; Kumar, A.; Vardhan, H.; Mangalpady, A.; Mandal, B.B.; Senapati, A.; Akhil, A.; Saini, S.
Mining remains one of the most hazardous industries globally, marked by frequent fatalities resulting from complex operational risks. While accident investigation reports hold valuable insights for improving safety practices, the manual coding of fatality narratives remains labor-intensive, inconsistent, and impractical for large datasets. Although natural language processing (NLP) and machine learning (ML) techniques have gained traction for automating the analysis of safety narratives in other high-risk industries, their application to mining accident data, particularly within the Indian context, remains limited. Addressing this gap, the present study proposes a ML framework for the semi-automated classification of fatal accident causes from unstructured text narratives reported by the Directorate General of Mines Safety (DGMS) between 2016 and 2022. A total of 401 fatal accident descriptions were pre-processed and vectorized using Bag-of-Words, TF-IDF, and Word2Vec techniques, followed by model evaluation across multiple algorithms. A semi-automated classification scheme was developed to balance efficiency with expert oversight, where high-confidence predictions were assigned automatically and uncertain cases were flagged for manual review. Logistic regression combined with TF-IDF unigram features achieved the highest performance, with an F1 score of 0.78 and an accuracy of 0.81. Overall, the developed framework successfully auto-coded 68.75% of cases with 94% accuracy, 0.93 recall, and 0.91 precision. Word cloud visualizations were also employed to capture dominant words associated with different cause categories. The proposed framework offers a practical and operationally feasible solution for assigning fatality causes in the mining sector, contributing to active safety management, surveillance, and policy formulation. © Society for Mining, Metallurgy & Exploration Inc. 2025.
Influence of masonry infill on fundamental natural frequency of 2D RC frames
(2010) Chethan, K.; Ramesh Babu, R.; Venkataramana, K.; Sharma, A.
Reinforced Concrete (RC) framed structures with Un-Reinforced Masonry (URM) infill panels form a major portion of all the RC framed structures worldwide. The URM panels are considered as non-structural members, which is fairly good assumption under gravity loads, however, it is not the same under lateral forces. Under seismic loads, the stiffness additions due to infill panels modify the dynamic behavior of the structure significantly by altering the frequency of the structure. A research project has been taken up at Earthquake Engineering and Vibration Research Centre (EVRC), Central Power Research Institute (CPRI), Bangalore to investigate the influence of masonry infill on fundamental natural frequency of RC frames. 2D RC frames of one bay and two bay having single storey, double storey and three storeys are cast and tested for bare frame and many combinations of URM infill panels. Tri-axial shake table is used for testing. The details of the numerical analysis and experimentation carried out in the research project are brought out in this paper.
Inner Attention Based bi-LSTMs with Indexing for non-Factoid Question Answering
(2019) Sharma, A.; Harithas, C.
In this paper, we focussed on non-factoid question answering problem using a bidirectional LSTM with an inner attention mechanism and indexing for better accuracy. Non factoid QA is an important task and can be significantly applied in constructing useful knowledge bases and extracting valuable information. The advantage of using Deep Learning frameworks in solving these kind of problems is that it does not require any feature engineering and other linguistic tools. The proposed approach is to extend a LSTM (Long Short Term Memory) model in two directions, one with a Convolutional layer and other with an inner attention mechanism, proposed by Bingning Wang, et al., to the LSTMs, to generate answer representations in accordance with the question. On top of this Deep Learning model we used an information retrieval model based on indexing to generate answers and improve the accuracy. The proposed methodology showed an improvement in accuracy over the referred model and respective baselines and also with respect to the answer lengths used. The models are tested with two non factoid QA data sets: TREC-QA and InsuranceQA. � 2018 IEEE.
Inner Attention Based bi-LSTMs with Indexing for non-Factoid Question Answering
(Institute of Electrical and Electronics Engineers Inc., 2018) Sharma, A.; Harithas, C.
In this paper, we focussed on non-factoid question answering problem using a bidirectional LSTM with an inner attention mechanism and indexing for better accuracy. Non factoid QA is an important task and can be significantly applied in constructing useful knowledge bases and extracting valuable information. The advantage of using Deep Learning frameworks in solving these kind of problems is that it does not require any feature engineering and other linguistic tools. The proposed approach is to extend a LSTM (Long Short Term Memory) model in two directions, one with a Convolutional layer and other with an inner attention mechanism, proposed by Bingning Wang, et al., to the LSTMs, to generate answer representations in accordance with the question. On top of this Deep Learning model we used an information retrieval model based on indexing to generate answers and improve the accuracy. The proposed methodology showed an improvement in accuracy over the referred model and respective baselines and also with respect to the answer lengths used. The models are tested with two non factoid QA data sets: TREC-QA and InsuranceQA. Â© 2018 IEEE.
Mechanical and Thermal Behaviour of Epoxy/Hexagonal Boron Nitride/Short Sisal Fiber Hybrid Composites
(Institute of Physics Publishing helen.craven@iop.org, 2020) Agrawal, A.; Chandraker, S.; Sharma, A.
Hybrid composite i.e. surface modified hexagonal boron nitride (hBN) and short sisal fiber reinforced in epoxy matrix is fabricated using hand lay-up method. The effect of surface modified hBN filler and sisal fiber content on mechanical and thermal properties of epoxy based hybrid composites were investigated in this paper. The main aim of the investigation is to develop a material which can found its application in microelectronic components. As per the requirement of microelectronic industry, the material should possess high thermal conductivity. Hence, thermal conductivity of epoxy increases with increase in hexagonal boron nitride content. Inspite of insulative nature of sisal fiber, the study shows that its inclusion in combination with hBN enhances the thermal conductivity if the content of both the fillers were properly selected. Other thermal property like coefficient of thermal expansion and glass transition temperature appreciably improves when combination of fillers were added in epoxy matrix. Mechanical properties under study i.e. tensile strength and compressive strength also enhances when combination of sisal fiber and hBN were incorporated as compared to when single filler hBN were used. Hence, usage of hybrid filler as reinforcement in epoxy improve overall mechanical and thermal property of the developed material. Â© 2020 Published under licence by IOP Publishing Ltd.
Mechanical and Thermal Properties of Sisal Fiber-Based Composites
(wiley, 2021) Mishra, V.; Agrawal, A.; Chandraker, S.; Sharma, A.
Natural fibers have attracted the scientific community toward their usage as reinforcement in polymeric composites mainly because of multiple benefits such as low cost, huge/easy availability, easy processing, and growing concern toward environmental awareness as they are biodegradable. Reinforcing natural fibers is an efficient approach toward reducing the consumption of nonbiodegradable plastic material. Also, natural fibers are promising reinforcing materials that can replace different synthetic fibers. Among the various natural fibers available, sisal fiber as reinforcement in a polymeric matrix is a strong competitor. Sisal fiber has several advantages like they are the widely used natural fiber and has the second-largest consumption across the world after cotton. It has high strength with good durability. It also has a good percentage of elongation before the break and does not deteriorate quickly in salty water. These fibers are smooth and straight with a high degree of inflexibility. Sisal represents around 2% of the total cultivation among plant fibers. In this regard, the present chapter focuses on sisal fiber as reinforcement with different polymeric matrices. The main emphasis is on the mechanical and thermal behavior of composite understudy and applications of this category of composites in various fields. A review of selected work on the research of sisal fiber with polymer matrix is the content of this chapter. © 2022 WILEY-VCH GmbH, Boschstr. 12, 69469 Weinheim, Germany.
Modified null space strategy to solve consensus problem
(University of Kuwait, 2016) Sharma, A.; Kurapati, N.G.; Jagannath, R.P.K.; Wira, P.; Lal, S.; Narasimhadhan, A.V.
In the domain of multi robot systems, several applications necessitate agreement of all the individual robots at consensus/rendezvous point. Such an agreement can only be achieved by means of a control strategy. However, presence of obstacles in the navigation-environment makes the achievement of control objective floundering. This paper accentuates the failure of extant null space based control strategy to circumvent rectangular obstacles by means of mathematical proofs and extensive simulation studies. To over-come these short-comings, a modified null space based control strategy is proposed to solve the consensus problem. Proposed control strategy is tested in a complex environment consisting of rectangular and concave obstacles by means of computer simulations. Finally, a qualitative comparative analysis is presented to contrast the differences between conventional null space based strategy and the proposed modified null space strategy. © 2016, University of Kuwait. All rights reserved.
Physical and mechanical properties of epoxy reinforced with pistachio shell particulates
(American Institute of Physics Inc., 2021) Chandraker, S.; Agrawal, A.; Prakash, P.; Khan, I.A.; Sharma, A.
Recently, natural fillers have gain huge interest among the academic researchers and scientists to be used as potential reinforcement material in polymeric matrix composites. The various reasons which attract the scientific community toward it usage in polymer composites are its low cost, ample availability, easy processing and the most important is the growing concern towards environmental awareness as they are bio-degradable. Reinforcing natural fillers is also an efficient approach towards waste management as most of the promising natural fillers were dumped if not used. Following the similar trend, an attempt has been made to utilize pistachio shells as a filler material in polymeric resin for developing a composite body. Pistachio shell with particle size 75 micron is used with epoxy matrix in present investigation. Six sets of epoxy based composites are fabricated using hand lay-up method by varying the filler content upto 30 wt. %. Density of the composites is evaluated using Archimedes principle. Micrographs are taken to visualize the compatibility between filler and matrix body. Tensile strength, compressive strength, flexural strength and hardness are the various mechanical properties evaluated of the developed materials. From the experimental analysis, it has been found that, all the mechanical properties of the composite under consideration increases with filler content. Though increase in density is also observed with filler loading but the increment is marginal. On the basis of experimental findings, it can be concluded that the developed material can be gainfully found its application in light duty structures. Â© 2021 Author(s).
Physical, mechanical and sliding wear behavior of solid glass microsphere filled epoxy composites
(Elsevier Ltd, 2018) Agrawal, A.; Chandraker, S.; Sharma, A.
Performance of epoxy based composites filled with micro-size solid glass microsphere (SGM) is reported in this work. The main emphasis of the present work is on the common trends detected in properties of epoxy/SGM composites. For physical property, densities of all the fabricated samples were presented.Glass micro-sphere filled epoxy composites haveless porosity. They also exhibit improvedmicro-hardness, flexural and impact strength, though tensile strength is compromised marginally. Further, sliding wear performance of the fabricated composites with respect to filler content, sliding velocity and applied force were studied.With improved physical, mechanical and sliding wear, the presently fabricated composites found its potential application where wear predominated. Â© 2018 Elsevier Ltd. All rights reserved.
Quality Dimensions of Augmented Reality-based Mobile Apps for Smart-Tourism and its Impact on Customer Satisfaction & Reuse Intention
(Routledge, 2023) Anand, K.; Arya, V.; Sheena, S.; Sharma, A.
The COVID-19 pandemic has severely affected the tourism industry, with national lockdowns aimed at curbing the spread of the virus mandating travel restrictions and prohibiting events and gatherings. The shift to online video conferencing tools, which offer limited interactivity, has spurred the need to integrate augmented reality (AR) in various contexts, such as meetings, exhibitions, museums, and travel. This quantitative study examines visitors’ perspectives on AR-based apps in tourism. It investigates the influence of three kinds of quality determinants, such as information quality, system quality, and service quality, on visitors’ perspectives on AR apps. Their impact on visitor satisfaction ultimately triggers visitors to reuse AR-based mobile apps. The research makes a theoretical contribution to the literature on AR and the quality dimensions of mobile apps. We expect demand for AR-based apps to rapidly increase, as people continue to follow preventive measures even after COVID-19. © 2022 Informa UK Limited, trading as Taylor & Francis Group.
Reconstruction of Edges from Fan-Beam Projections
(2019) Narasimhadhan, A.V.; Sharma, A.; Koolagudi, S.G.; Naganjaneyulu, G.V.S.S.K.R.; Avinash, S.; Peddireddy, V.; Kishan, N.B.; Rajan, J.
The goal of computerised tomography is to reconstruct cross sectional image of the object under consideration from it's projections whereas edge detection is an image analysis problem of utmost importance in medical imaging to outline the boundaries of tumours, bones etc. In this paper, a technique to reconstruct the edges directly from fan-beam projections, using the Marr-Hildreth operator, is presented. To obtain the edge map of object under consideration, the divergent beam transform of Marr-Hildreth operator is convolved with ramp filter to yield an edge reconstruction filter which is finally convolved with the acquired fan-beam projections and back-projected, resulting in a convolution back-projection, to reconstruct the edges. The paper also discusses about the utilisation of state-of-the-art Noo's algorithm to reconstruct the edges directly from equi-angular fan beam projections. Finally, the proposed technique is simulated to make relevant conclusions and inferences. � 2018 IEEE.
Reconstruction of Edges from Fan-Beam Projections
(Institute of Electrical and Electronics Engineers Inc., 2018) Narasimhadhan, A.V.; Sharma, A.; Koolagudi, S.G.; Naganjaneyulu, G.V.S.S.K.R.; Avinash, S.; Peddireddy, V.; Kishan, N.B.; Rajan, J.
The goal of computerised tomography is to reconstruct cross sectional image of the object under consideration from it's projections whereas edge detection is an image analysis problem of utmost importance in medical imaging to outline the boundaries of tumours, bones etc. In this paper, a technique to reconstruct the edges directly from fan-beam projections, using the Marr-Hildreth operator, is presented. To obtain the edge map of object under consideration, the divergent beam transform of Marr-Hildreth operator is convolved with ramp filter to yield an edge reconstruction filter which is finally convolved with the acquired fan-beam projections and back-projected, resulting in a convolution back-projection, to reconstruct the edges. The paper also discusses about the utilisation of state-of-the-art Noo's algorithm to reconstruct the edges directly from equi-angular fan beam projections. Finally, the proposed technique is simulated to make relevant conclusions and inferences. Â© 2018 IEEE.
Significance of modeling techniques in pushover analysis of RC buildings
(2010) Thapa, M.; BabuNarayan, K.S.; Halemane, K.P.; Venkataramana, K.; Yaragal, S.C.; Ramesh Babu, R.; Sharma, A.; Reddy, G.R.
The study presented here focuses on the effectiveness of the models adopted for the nonlinear static pushover (NSP) analysis and providing the best model that can predict the nonlinear response of RC buildings with sufficient accuracy with respect to the experimentally obtained results. NSP analysis considers material nonlinearity and is an effective tool to evaluate the performance of the structure under lateral seismic loads. However, the actual test data in order to verify the results of NSP analysis are very rare for RC structures, which are analytically sensitive to the models and procedure adopted by the analyzer. Under the present work three cases of geometric models; a) Frame with beamcolumn elements, b) Frame with beam-column elements and slabs modelled as a rigid diaphragm and c) Frame with beam-column elements and slabs modelled as shell element considering concrete as confined and unconfined were analyzed. Comparision of analytical curve with the experimental pushover curve, clearly suggests that frame modelled as confined beam-column elements and slabs modelled as a rigid diaphragm gives closer results. © 2010 CAFET-INNOVA TECHNICAL SOCIETY. All rights reserved.
Strength retention characteristics of concrete cubes subjected to elevated temperatures
(2010) Yaragal, S.C.; Clarke, K.S.; Mahesh Babu, K.; Ashokumar, S.; Venkataramana, K.; Babu Narayan, K.S.; Chinnagiri Gowda, H.C.; Reddy, G.R.; Sharma, A.
Concrete in structures is likely to be exposed to high temperatures during fire. The relative properties of concrete after such an exposure are of great importance in terms of the serviceability of buildings. The probability of its exposure to elevated temperatures is high due to natural hazards, accidents and sabotages. Therefore, the performance of concrete during and after exposure to elevated temperature is a subject of great interest to the designer. Physical changes like cracking, colour change, spalling and chemical changes like decomposition of Ca(OH)2 and the C-S-H gel take place when subjected to elevated temperatures. This work reports the characteristics of concrete at elevated temperatures. Popular normal strength grades (M20, M25, M30, M35, M40 and M45) produced by Ready Mix Concrete (RMC) India, Mangalore have been used in production of test specimens (150 mm cubes) to obtain more meaningful and realistic data. In the preliminary phase 150 mm cubes were cast, cured and tested by destructive method for gathering data on strength characteristics. Later these test samples were subjected to elevated temperatures ranging from 100°C to 800°C, in steps of 100°C with a retention period of 2 hours. After exposure, weight losses were determined and then again destructive tests were conducted to estimate the residual compressive strength. Test results indicated that weight and strength significantly reduces with an increase in temperature. © 2010 CAFET-INNOVA TECHNICAL SOCIETY.
Studies on concrete cylinders subjected to elevated temperatures
(2010) Babu Narayan, K.S.; Anil Kumar, G.; Chandrakala, C.; Shashikumar, H.M.; Venkataramana, K.; Yaragal, S.C.; Chinnagiri Gowda, H.C.; Reddy, G.R.; Sharma, A.
Concrete is a poor conductor of heat, but can suffer considerable damage when exposed to fire. Concrete in structures is likely to be exposed to high temperatures during fire. The relative properties of concrete after such an exposure are of great importance in terms of the serviceability of buildings. Unraveling the heating history of concrete is important to forensic research or to determine whether a fire exposed concrete structures and its components are still structurally sound or not. Assessment of fire damage concrete structures usually starts with visual observation of color change, cracking and spalling. On heating, a change in color from normal to pink is often observed and this is useful since it coincides with the onset of significant loss of concrete strength. This work reports the characteristics of concrete at elevated temperatures. Popular normal strength grades (M20, M25, M30, M35, M40 and M45) produced by Ready Mix Concrete (RMC) India, Mangalore have been used in production of test specimens (150 mm diameter and 300mm height cylinders) to obtain more meaningful and realistic data. In the preliminary phase 150 mm diameter and 300mm height cylinders were cast, cured and tested by destructive method for gathering data on strength characteristics. Later these test samples were subjected to elevated temperatures ranging from 100°C to 800°C, in steps of 100°C with a retention period of 2 hours. After exposure, weight losses were determined and then again destructive tests were conducted to estimate the residual split tensile strength. Test results indicated that weight and strength significantly reduces with an increase in temperature. © 2010 CAFET-INNOVA TECHNICAL SOCIETY. All rights reserved.