@sru.edu.in
Professor and Head-Department of Civil Engineering
SR University, Telangana, India
is presently serving as Professor and Head of the Department, Civil Engineering of SR University, Telangana, India and also a member of Center for Construction Materials and Methods division. He completed his PhD in the field of Environmental Geotechnology and Disaster Management from Center for Disaster Management and Mitigation, VIT, Vellore, M.E in Environmental Management from College of Engineering, Guindy, Anna University and BE in Civil engineering from Bharathiar University. He had handled several under graduate course in Civil and Environmental engineering including Project management, smart materials and structures, Geosynthetics, Engineering Mechanics etc and also presently handling elective courses related to Disaster Management and Intellectual Property rights in various Universities.
His research interests includes Sustainable materials, Construction Materials, Landslide mitigation and Management, Soil Bioengineering, Engineering Education, Geotechnology, Environmental Geotechnology, Sustainable Development, Sustainable construction technologies, he had handled several projects related to this domains in various levels. He also had executed good number of consultancy projects related to Geotechnical and environmental engineering for various organisations.
B.E- Civil Engineering (2001), Bharathiar University
M.E- Environmental Management (2007), College of Engineering, Guindy, Anna University
PhD ( Environmental Geotechnology), VIT University, Vellore, India
Sustainable materials, Construction Materials, Landslide mitigation and Management, Soil Bioengineering, Engineering Education, Geotechnology, Environmental Geotechnology, Sustainable Development, Sustainable construction technologies, Image processing, Machine Learning applications in Civil Enginee
This project work involves obtaining sustainable construction materials without depleting the natural resources and by using non convetional material development techniques. It involves lot of analysis, simulation based works and the work is initiated under the aegies of Center for Construction Methdos and Materials of SR University
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Lakshmana Rao Kalabarige, Jayaprakash Sridhar, Sivaramakrishnan Subbaram, Palaniappan Prasath, and Ravindran Gobinath
Hindawi Limited
This study aimed to develop accurate models for estimating the compressive strength (CS) of concrete using a combination of experimental testing and different machine learning (ML) approaches: baseline regression models, boosting model, bagging model, tree-based ensemble models, and average voting regression (VR). The research utilized an extensive experimental dataset with 14 input variables, including cement, limestone powder, fly ash, granulated glass blast furnace slag, silica fume, rice husk ash, marble powder, brick powder, coarse aggregate, fine aggregate, recycled coarse aggregate, water, superplasticizer, and voids in mineral aggregate. To evaluate the performance of each ML model, five metrics were used: mean absolute error (MAE), mean squared error (MSE), root mean squared error (RMSE), coefficient of determination (R2-score), and relative root mean squared error (RRMSE). The comparative analysis revealed that the VR model exhibited the highest effectiveness, displaying a strong correlation between actual and estimated outcomes. The boosting, bagging, and VR models achieved impressive R2-scores in the range of 86.69%–92.43%, with MAE ranging from 3.87 to 4.87, MSE from 21.74 to 38.37, RMSE from 4.66 to 4.87, and RRMSE between 8% and 11%. Particularly, the VR model outperformed all other models with the highest R2-score (92.43%) and the lowest error rate. The developed models demonstrated excellent generalization and prediction capabilities, providing valuable tools for practitioners, researchers, and designers to efficiently evaluate the CS of concrete. By mitigating environmental vulnerabilities and associated impacts, this research can significantly contribute to enhancing the quality and sustainability of concrete construction practices.
S. Karthik, S. Anandaraj, M. Senthil Rajan, R. Gobinath, S. Rajasekar, and R. Navinkumar
AIP Publishing
Ashwini Salunke, Pradnya Bidbag, R. Gobinath, S. Bhore, A. Patil, and Y. Mane
AIP Publishing
G. Shyamala, R. Gobinath, and K. Rajesh Kumar
EDP Sciences
This paper analyzes the problem of septage management related to opportunities and solution. in accordance with present treatment technologies. The scenario in India is about 41 % of septage sludge is disposed in local area without treatment Still some of the individual housing is not connected to suitable public sewage system. The current scenario of FSM in Warangal city is 77 % of the households have proper access to toilet and 23% insanitary toilet and open defecation were found. The samples were collected from the Warangal city and were tested for the characteristics. BOD and COD were very high above 9800 mg/l. As per CPHEEO norms TSS should be less than 15000 mg/l, but it is observed in all the samples it is in the range of 24,800 mg/l to 82,460 mg/l. Currently the treatment such as sludge drying beds, lime treatment, anaerobic baffled reactor, stabilization pond, constructed wetland, composting with solid waste, Mechanical dewatering,. Neglected septage waste ash was tried for several trial run in the mix design and found 20 % to be optimum replacement of septage ash. Strength enhancement is achieved by adding glass chopped strands and workability is improved by Super plasticizer Polycarboxlate ether. Utilization of residue in septage treatment plant in cost effective and ecofriendly way by replacing cement in concrete was tried in the pilot scale study near Warangal and proven to be effective.
Rabindra Kumar, Purushottam Kumar Singh, Showmen Saha, Santosh Kr. Mishra, Pankaj Kumar, and Ravindran Gobinath
Elsevier BV
Gokulan Ravindiran, Sivarethinamohan Rajamanickam, Sujatha Sivarethinamohan, Balamurugan Karupaiya Sathaiah, Gobinath Ravindran, Senthil Kumar Muniasamy, and Gasim Hayder
MDPI AG
Most water systems that support ecosystems and feed humans are depleted or stressed. Aquifer characteristics, topography, subsurface activities, climate, and geochemical processes regulate groundwater availability, a reliable source of fresh water. Globally, agriculture, industries, and the domestic sector are the three major sectors that consume vast quantities of freshwater resources. Further anthropogenic activities, such as soil leaching, acid rain, fertilizer, pesticides, mining, and other industrial activities, resulted in the release of organic and inorganic pollutants that affected global water resources. In India, groundwater is used in huge quantities, resulting in groundwater depletion of 1 to 2 m a year. Low-income countries face many issues related to water pollution, and the availability of safe water is minimal. In 2019, deaths due to unsafe sanitation accounted for 2.2% of the total global deaths, amounting to 1.2 million people’s deaths. India recorded 6.6% of deaths due to unsafe sanitation in 2019. India and China accounted for around 90.41% and 60.4% of the groundwater utilization for agricultural purposes, respectively. In 2020, China and India utilized vast quantities of nutrients (nitrate and phosphate) for crop growth to enhance crop yield, resulting in the highest nitrate and phosphate concentrations in groundwater. Remediating contaminants from different sources requires knowledge of their concentration, behavior, cycling, and degradation pathways. According to safety guidelines, limiting and optimizing crop organic and inorganic fertilizer, pesticide waste disposal, and empty container disposal can reduce groundwater contamination. The present study summarized groundwater utilization in various sectors, potential sources of groundwater contamination impacts on human health and the environment, preventive measures, and mitigation methods to overcome groundwater pollution.
Gobinath Ravindran, Alireza Bahrami, Vutukuru Mahesh, Herda Yati Binti Katman, Katakam Srihitha, Alamadri Sushmashree, and Alugoju Nikhil Kumar
MDPI AG
Soil, a naturally occurring resource, is increasingly used as a construction material. Stabilisation strengthens soil, which is weak as an engineering material. Stabilising soil changes its physical qualities, enhancing its strength. Soil stabilisation increases the shear strength and load-bearing capacity. Soil stabilisation refers to any endeavour to change natural soil for engineering purposes using physical, chemical, mechanical, or biological methods, or a mix of these. Strengthening road pavements includes improving the load-bearing capacity, tensile strength, and performance of unstable subsoils, sands, and waste materials. Due to market demands and scientific advances, the number of soil-stabilising additives has increased. These innovative stabilisers include reinforcing fibres, calcium chloride, sodium chloride, and cross-linking water-based styrene acrylic polymers, which are geopolymers that boost the load-bearing capacity and tensile strength of soil. Many materials are being explored for soil stabilisation. In this article, the authors investigated the direction of soil stabilisation research. Scientometric analysis identifies stabilisation challenges and research trends in the field. This study analysed research patterns by countries, authors, institutions, keywords, and journals from 1959 to 2023; in 2021, 150 articles were published, which was the highest number in a year. Citations peaked at 3084 in 2022. With 253 publications and 3084 citations, India was the most productive country. Iran and France published the fewest, 34 and 33, respectively. The Islamic Azad University and the National Institute of Technology had the fewest published articles with 17 articles. This work can help track soil stabilisation research and will serve as an information document for future research.
Ananthakumar Ayyadurai, Balaji Shanmugam, and Gobinath Ravindran
MDPI AG
As the load increases, most composite beams generally experience failure in both shear and flexural behavior. This outcome highlights the critical challenges of achieving sufficient strength and structural integrity in such beams. The proposed study has used the cold-formed behavior of an Enhanced C-channel (EC) shear connectors and Light Weight Concrete (LWC) to examine the new Steel-Lightweight Concrete-Steel sandwich Beams (SLCSB). The ECs have provided significant shear resistance at the faceplate-LWC interfacial interface and the tension separation resistance for faceplates (cold form steel) from the LWC core. Cold Form Steel (CFS) is the most often used substitute because of its high productivity and practicality in the field. Four different composite beams are examined in the proposed research with different ECs spacing. The beams’ top and bottom face plates are covered using CFS (1.6 mm). In addition to that, two different types of shear connectors are used. Two unique longitudinal spacing of 100 mm and 150 mm are also used for one with lipped ECs and without lipped ECs. Importantly, self-tapping screws are used to secure ECs in place between the top and bottom of the face plates. The effectiveness of the composite beams with various shear connector spacing subjected to a two-point load test is assessed through a series of experiments.
Yajish Giri A/L Parama Giri, Bashar S. Mohammed, M. S. Liew, Noor Amila Wan Abdullah Zawawi, Isyaka Abdulkadir, Priyanka Singh, and Gobinath Ravindran
MDPI AG
The construction industry is increasingly focused on sustainability, with a particular emphasis on reducing the environmental impact of cement production. One approach to this problem is to use recycled materials and explore eco-friendly raw materials, such as alumino-silicate by-products like fly ash, which can be used as raw materials for geopolymer concrete. To enhance the ductility, failure mode, and toughness of the geopolymer, researchers have added crumb rubber processed from scrap tires as partial replacement to fine aggregate of the geopolymer. Therefore, this study aims to develop rubberized geopolymer concrete (RGC) by partially replacing the fine aggregate with crumb rubber (CR). To optimize the mechanical properties of RGC, response surface methodology (RSM) has been used to develop 13 mixes with different levels and proportions of CR (10–30% partial replacement of fine aggregate by volume) and sodium hydroxide molarity (10–14 M) as input variables. The results showed that the strength properties increased as the molarity of NaOH increased, while the opposite trend was observed with CR. The maximum values for compressive strength, flexural strength, and uniaxial tensile strength were found to be 25 MPa, 3.1 MPa, and 0.41 MPa, respectively. Response surface models of the mechanical strengths, which were validated using ANOVA with high R2 values of 72–99%, have been developed. It has been found that using 10% CR with 14 M sodium hydroxide resulting in the best mechanical properties for RGC, which was validated with experimental tests. The result of the multi-objective optimization indicated that the optimum addition level for NaOH is 14 M, and the fine aggregate replacement level with CR is 10% in order to achieve a rubberized geopolymer suitable for structural applications.
Pavankumar Korke, R. Gobinath, Manisha Shewale, and Bhagyashree Khartode
EDP Sciences
The construction business currently contributes 13% of the world's Gross Domestic Product (GDP), and it is anticipated that by the year 2030, its value would have increased by 85%, reaching $15.5 billion globally. China, the United States of America, and India are the three countries that are most responsible for the demand in the building business. Keeping subcontractors, contractors, designers, clients, and other parties routinely supplied with vast amounts of information has been one of the most challenging difficulties in the construction industry. The application of Information Technology (IT) has significantly contributed to the integration of disparate pieces of information within the context of widely dispersed construction projects. The construction sector, including the full construction value chain, is presently going through a period of transformation. The amount of money that is being invested into Artificial Intelligence (AI) is rising at a rate that is almost impossible to keep up with. Because of this, there is the potential to enhance the productivity of human work by forty percent and double the annual rates of economic growth by the year 2035. This research presents a discussion of the numerous methodologies that have been researched by the researchers along with a review of the artificial intelligence that is used in the construction industry, specifically Construction Project Management. Additionally, this research offers a review of the artificial intelligence that is utilized in the construction business.
Gobinath Ravindran, Vutukuru Mahesh, Naraindas Bheel, Sampada Chittimalla, Katakam Srihitha, and Alamadri Sushmasree
MDPI AG
Natural-fibre-reinforced composites (NFRCs) are revolutionising the way materials are used for various purposes, and they have enriched applications from aerospace to concrete. In tandem with these works, sustainable materials that are eco-friendly and possess strength and endurance are rapidly replacing conventional materials. Recent decades have shown that many exuberant, curious-minded researchers are working on this particular domain, creating numerous materials for a variety of applications. What exactly is being performed in the laboratory is not being carried out in the field and duly disseminated. The major constraint is knowledge sharing and bottlenecks involved in assessing that research. Scientometrics is a field providing access to the consolidated research landscape report on a particular topic informing research on what work is being performed, how it is performed, who performs it, and what is the future scope. In this work, we analyse the research works, trends, and challenges related to NFRCs for engineering applications. It is found that research works, and the utilisation related to NFRCs, have soared in the last two decades, which proves to be a promising area to work upon. We use the Scopus database for the analysis, and scientometric analysis is carried over with biblioshiny. We find that there is a decreasing trend in publications (−12.74%/year); 272 sources are involved with 1690 documents published containing 5554 authors with 54 single-authored documents. There are 3919 keywords involved with 16.51 average citations received for the documents published. This work can be used to understand the research trend and also to take up newer research.
K. Rajesh Kumar, Thiruchengode Jothimani Vijay, Alireza Bahrami, and Gobinath Ravindran
MDPI AG
In recent decades, corrosion in steel reinforcement has been one of the fundamental risks in steel-reinforced concrete (RC) structures. Geosynthetics can be an alternative approach to solve corrosion problems. The current experimental research work investigates the structural performance of geogrid-reinforced concrete (GRC) elements. Initially, five different geotextiles and biaxial geogrid materials were selected and embedded in the concrete specimens separately to study their mechanical properties. The results of the testing showed that the geogrid embedded specimen behaved more mechanically than the conventional concrete (CC) specimens due to increased bonding characteristics. The limiting moment and load-carrying capacities of the RC and GRC beams were determined with reference to limit state design principles. In order to compare the structural performance of the beams, two RC beams and two GRC beams with the size of 150 mm × 300 mm × 2100 mm were cast. The structural performances in terms of the load-carrying capacity, energy absorption, stiffness degradation, and ductility were examined. The results of the tests indicated that even though the load-carrying capacity of the GRC beams was slightly lower, they demonstrated enhanced performance by 42%, 40%, and 68% higher in the energy absorption, stiffness degradation, and ductility, respectively, than those of the RC beams on average. The augmented inelastic performance and better bonding properties of the GRC beams aid in noticeable structural performance.
Omrane Benjeddou, Gobinath Ravindran, and Mohamed Abuelseoud Abdelzaher
MDPI AG
A large amount of industrial solid waste is generated from industrial activities worldwide. One such waste is marble waste, a waste generated from quarries which is generated in larger amount which needs attention. It is proved that this waste has a significant impact both on the people health and on the environment. Hence, research works are directed towards addressing usage of waste marble power, the aim of this experimental investigation is to study the usability of sand obtained by crushing marble waste (MWS) on the mixing of lightweight concrete based on expanded perlite aggregate (EPA). First, the mechanical, chemical, and physical properties of marble waste sand and expanded perlite aggregate were determined after which different mixtures of concrete are prepared by varying the percentage of EPA (0, 20, 40, 60, 80, and 100%), in order to find the optimum mixture focussing on obtaining best hydraulic properties. Also, in this work, the thermal and acoustic properties (thermal conductivity, thermal diffusivity, specific heat capacity and sound reduction index at different frequencies) of the tested concrete samples were investigated. Results shows that it is possible to obtain thermal and acoustic insulation lightweight concrete by using sand obtained by crushing marble wastes. Also, addition of more than 20% of EPA aggregate in concrete, develops a thermal insulating lightweight concrete which possess capacity to store heat and produce better thermal performance. Concrete blend with a percentage of more than of 20% of EPA aggregate can be placed in the category of acoustic insulation lightweight concrete. In summary, cement based on MWs and EPA provides better workability and energy saving qualities, which are economical and environmentally beneficial and may result in decreased construction budget and improve a long-term raw materials sustainability.
Settiannan Karuppannan Maniarasan, Palanisamy Chandrasekaran, Sridhar Jayaprakash, and Gobinath Ravindran
MDPI AG
In reinforced concrete (RC) constructions, the beam-column junctions are very sensitive to lateral and vertical loads. In the event of unforeseen earthquake and wind loads, this insufficient joint performance can lead to the failure of the entire structure. Cement industries emit a large amount of greenhouse gases during production, thus contributing to global warming. The nature of cement concrete is fragile. Cement output must be reduced in order to ensure environmental sustainability. Geopolymer concrete (GC), which is a green and low-carbon material, can be used in beam-column joints. M30 grade BBGC was developed and employed in the current study. Alkaline liquids are produced when sodium silicate and sodium hydroxide are mixed at room temperature. The alkaline liquid to fly ash ratio was fixed at 0.5, and the concentration of NaOH was fixed at 8 M. The mechanical properties of the Binary Blended Geopolymer concrete (BBGC), containing fly ash and GGBS, at proportions ranging from 0% to 100%, were investigated. This study was further expanded to examine the behavior of two groups of binary blended geopolymer concrete (BBGC) exterior beam-column joints, with cross sections of 230 mm × 120 mm and 170 mm × 120 mm. The column heights and lengths were both 600 mm under reverse cyclic loads in order to simulate earthquake conditions. The failure mechanism, ductility, energy absorption capacity, initial crack load, ultimate load carrying capacity, and structural performance was evaluated. The test findings showed that BBGC with 20% fly ash and 80% GGBS had the highest compressive strength and split tensile strength. When compared with other beam column joints, those containing 20% fly ash and 80% GGBS performed better under cyclic loading. The test findings imply that GGBS essentially enhances the joint performance of BBGC. The microstructural SEM and EDS studies revealed the reasons behind the improvement in strength of the GGBS fly ash-based Geopolymer concrete.
K R N Aswini, S. P. Prakash, Gobinath Ravindran, T Jagadesh, and Ashitha V Naik
IEEE
The Content-Based Image Retrieval (CBIR) method is a challenging task in research areas because of multimedia growth in internet. The search of relevance images on search engines is critical task for research community. In this manuscript, the Extended Canberra Similarity measure Method is proposed for measuring the similarity in image retrieval. The dataset utilized for research of content-based image retrieval is Corel 1K and median filter is utilized in preprocessing phase to remove the noise. The Generalized Search Tree (GIST) and Scale Invariant Feature Transform (SIFT) are utilized for the feature extraction and the extracted features are fused by average and weighted average method. At last, the Extended Canberra Distance (ECD) method is utilized for measuring the similarity among query image and image database. The performance of proposed method is estimated by performance metrics like precision, recall and f1-score. The proposed method attained precision of 94.12, recall of 17.64 and F1-score of 60.58 which is comparatively higher than other existing similarity measure methods such as Euclidean, D1 and Canberra.
Hassan M. Al-Jawahry, V. Thirumurugan, R. Vijayarangan, Gobinath Ravindran, and Ghazi Mohamad Ramadan
IEEE
In the realm of aerial image georeferencing and mapping, the primary challenge is to enhance georeferencing accuracy and segmentation efficiency for precise remote sensing applications. The core obj ective is to refine georeferencing precision, ensuring heightened mapping reliability, while concurrently developing efficient segmentation methods for valuable geospatial data extraction. The incorporation of the Coco dataset validates and enhances the effectiveness of the segmentation technique devised in this paper. This paper introduces an innovative approach centered on refining pixel-level semantic segmentation for both aerial images and georeferencing processes. This proposed method marks substantial advancements in accurately categorizing and delineating objects within aerial imagery, contributing to an elevated precision in geo-referencing. The emphasis on improved pixel-level semantic segmentation underscores the commitment to enhancing the efficacy of georeferencing in the context of aerial images. The proposed approach demonstrates remarkable performance metrics, including an accuracy of 96.71 %, precision scaling to 98.75%, and a commendable recall of 90.62 %. Through comprehensive comparative analysis with established models, such as semantic segmentation, panoptic segmentation, and 3D semantic segmentation, this method emerges as a leader in the field.
Abbas Hameed Abdul Hussein, Gobinath Ravindran, Zamen Latef naser, Muntather Almusawi, and Santhiya K
IEEE
Fingerprint authentication is one of the methods used to prevent the loss of personal data, but the minutiae and angle variance of finger patterns make the process difficult. To overcome the issue, an authentication system for fingerprint orientation using an improved Generative Adversarial Network (GAN) with Support Vector Machine (SVM) is being developed. The process begins with image enhancement using Contrastive Limited Adaptive Histogram Equalization (CLAHE) techniques to increase image contrast. Next, GAN with SVM is employed to generate synthetic data through data augmentation, and decision-making is carried out using SVM. Both real and synthetic samples are binarized using the global thresholding technique, and edge-based thinning methods are applied to enhance the fingerprint patterns. Finally, features such as minutiae points of fingerprints are extracted using the Scale Invariant Feature Transform (SIFT) algorithm, serving as input for the SVM classifier. The implemented GAN-SVM model demonstrates superior performance, achieving a False Acceptance Rate (FAR) of 0.12%, a False Rejection Rate (FRR) of 1.3%, an Equal Error Rate (EER) of 0.29%, and an accuracy of 95.87%. When compared to previous models like Multi-layer Perceptron Neural Network (MLP), Fuzzy Commitment (FC), and Genetic Encryption Algorithm (GEA).
Hassan M. Al-Jawahry, Mohammed Ayad Alkhafaji, Gobinath Ravindran, Pradeep Kumar S, and Abbas Hameed Abdul Hussein
IEEE
Deep learning enhances precision and efficiency in object tracking, enabling applications in autonomous vehicles and surveillance while adapting to dynamic environments. To address issues such as overlapping and anchor box regions of interest for tiny objects, this research introduces a YOLOv3 model with a Bidirectional Feature Pyramid Network (BiFPN) for overcome the start-of-art methods problems. The FLIR dataset is employed for effective object tracking and classification, with preprocessing techniques like Histogram Equalization and Laplacian sharpening to reduce Gaussian noise and enhance object edges in the benchmark dataset. The pre-processed images and video clips are input into the YOLOv3 and BiFPN for detecting both tiny and major objects and constructing anchor boxes. The results demonstrate the outstanding performance of the YOLOv3 with BiFPN model, achieving an impressive mean average precision (mAP) of 90.50%. It also offers rapid detection, with a time of only 6 milliseconds, and maintains a remarkable frames per second (FPS) value of 5, ensuring superior classification compared to other existing methods such as NS EfficientDet and Tiny YOLOv3 network.
Regan D, Gobinath Ravindran, P. Senthil, M. Jamuna Rani, and Subhra Chakraborty
IEEE
The classification of land use and land cover (LULC) using remote sensing data is essential for many environmental models and land-use inventories. A lightweight deep learning classifier is implemented in this research to improve the performance of LULC classification, assisting in the prediction of declining environmental quality, haphazard elements, wildlife habitat, and so on. LULC classification is evaluated using Eurosat dataset and it uses algorithms like the Haralick texture features, histogram of the oriented gradient, and local Gabor binary pattern histogram sequence for feature extraction. The Grey Wolf Optimization (GWO) method is applied to select the best features, offering fast convergence tares and ease of implementation. A Long Short-Term Memory (LSTM) network is then used to categorize the LULC. The research outcomes show that the GWO method with an LSTM classifier efficiently differentiates the classification of LULC in terms of 99.80% accuracy, 98.99% precision, and 99.53% recall when compared to the Deep SHAP, HFEL-CCGSA, Human group-based PSO with LSTM and IMO-mLSTM.
Muntather Almusawi, Subhra Chakraborty, Gobinath Ravindran, S Prabu, and Zainab Abed Almoussawi
IEEE
The stock market is financial market where stocks of openly listed corporations are bought and sold. It is needle of economic health of country, reflects the company performance and entire environment of business. The stock prices are determined through demand and supply. Investing in stock market may be risk, but that offered potential fir important returns over high term. In this research, the Long Short-term Memory (LSTM) with Improved Artificial Rabbits optimization (IARO) algorithm for predicting the stock market price. The IARO algorithm is utilized to optimize hyperparameters of LSTM method to maximize accuracy of stock market price prediction. The dataset used for predicting stock market price is collected dataset. The performance of proposed method is estimated with error rates of Mean Square Error (MSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and Coefficient of Determination (R2). The proposed method less MSE of 0.43, MAE of 0.37, MAPE of 0.21 and R2 of 0.17 which is superior than other existing methods.
V Saravanan, Mohammad Yahya, Abbas Hameed Abdul Hussein, Gobinath Ravindran, and Myasar Mundher Adnan
IEEE
Alzheimer’s disease (AD) is one of dangerous neurodegenerative diseases affecting elderly worldwide. A several Deep Learning (DL) and Machine Learning (ML) approaches are employed, but it attains high complicated patterns from MRI scans for detecting AD. To overcome these limitations, an efficient DL approaches are proposed for predicting Alzheimer disease in 3D brain Magnetic Resonance Imaging (MRI). A proposed DL approach involves two stages namely segmentation as well as classification, these approaches are based on DL. 3D Brain MRI input is converted into 2D slices and Adaptive Histogram Equalization (AHE), skull stripping approaches are utilized in preprocessing. Then preprocessing, integration of Gaussian Mixture Model (GMM) and Recurrent Neural Network (RNN) is applied for segmenting a MRI input. After segmentation, an integration of Deep Neural Network (DNN) and Extreme Gradient Boosting (XGBoost) are utilized for classifying an AD based on segmented tissues. In this proposed approach, datasets such as Alzheimer’s Disease Neuroimaging Initiative (ADNI), Open Access Series of Imaging Studies (OASIS) are utilized and attains better performance of 99.85% and 99.84% of accuracies when compared with existing approaches.
A. H. A. Hussein, Mohammed I. Habelalmateen, Gobinath Ravindran, V Malsoru, and J. Rajalakshmi
IEEE
Sentiment analysis (SA) is a popular method for collecting relevant and arbitrary information from text-based data. To locate, examine, extract reactions, and emotions from the data or states, it applies computational linguistics, biometrics, text analysis, and Natural Language Processing (NLP). A SA model can be developed and improved with the use of the features analysis method. However, it can be difficult to find best classification methods for this type of data. When compared to current feature-based methods, machine learning approaches for analysis of sentiment, are capable of providing precise representation and improved performance. In this paper, the machine learning (ML) method was proposed for improving sentiment classification performance with a sophisticated embedding word method and develop an Emperor Penguin Optimization (EPO) and Multi-class Support Vector Machine (SVM). For the purpose of predicting the sentiment of tweets for classification, a large amount of Amazon data is analysed. This study, concentrate on improving sentiment analysis performance by building a Multi-class SVM network and particularized model of machine learning with novel word embedding techniques. The Multi-class SVM model has achieved 99.89% accuracy sentiment analysis.
Rama Rao Karri, Nabisab Mujawar Mubarak, Suraj Kumar Bhagat, Tiyasha Tiyasha, Lakshmi Prasanna Lingamdinne, Janardhan Reddy Koduru, Gobinath Ravindran, Inderjeet Tyagi, and Mohammad Hadi Dehghani
Elsevier
Namo Jain, Mukund Pratap Singh, Kuldeep Chaurasia, and Gobinath Ravindran
IEEE
Intrusion detection systems, which inspect and analyze network data for signs of hostile activity, are critical to computer network security. These systems are suggested to distinguish and respond to not permitted access, misuse, and other confidence consequences that could concession the concealment, veracity, and accessibility of network resources. In this research, we give an overview of intrusion detection employed in computer networks, including their classification, architecture, and detection methods. The structure intends to detect both recognized-notorious intrusions and attacks with better detection accuracy and lesser untruthful-probability measures. We look at the challenges of setting up and maintaining IDS with their importance in distinguishing various categories of network infringements. This study indicates that intrusion detection systems are an important part of contemporary network protection and are frequently used in many organizations to defend against cyber-attacks. Voting method to identify the intrusion detection systems representing the best performance scores on the dataset. The performance parameter (accuracy, F1_score, precision, and recall) values of the voting model are 0.998015, 0.998015, 0.998016 and 0.998015.
Palaniappan Prasath, Ravindran Gobinath, and Jayaprakash Sridhar
Hindawi Limited
The performance of structural composites during loading has always been a concern for the designers and construction industry since the reinforced concrete structure was discovered. In this study, lateral load–displacement behavior of beam–column joints wrapped with aramid fiber is evaluated using both experimental and numerical analysis subjected to torsional moment (beam-eccentric loading). Three categories of reinforcement concepts are adopted for the preparation of the beam–column joints, where members are wrapped with aramid fiber at the joints, and others are not fortified with aramid fibers. Prior to testing, the structural composites are cured for maximum 28 days into water. The beam–column joints are subjected to lateral load at a point near the column end of the beam–column connection, and the corresponding deflections are measured until the member fails. Based on the test results, ductility and energy absorption capacity are evaluated. The findings of the numerical investigation of beam–column joint show there is not much variation in the experimental and numerical analysis; it is clearly found that aramid fiber wrapping provided large rigidity in the joint, and it is also prolonged the final failure of the joints. This study shows that in addition to the conventional reinforcement, providing the hanger reinforcement and the diagonal reinforcement improves the rigidity of the beam–column joints during severe loadings, as this study described.
A NOVEL METHOD OF ENHANCE FREEZE-THAW RESISTANCE OF SOIL - Patent application no: 202041005809
A NOVEL METHOD TO PREPARE SELF-COMPACTING CONCRETE USING SINGLE ALKALI ACTIVATED ASH BASED CONCRETE - Patent application no: 202041004257
A NOVEL STRENGTH ENHANCEMENT PROCEDURE FOR NATURAL CURED BINDERLESS CONCRETE- Patent application no:201941042302
A NOVEL METHOD OF WATER CONTENT IDENTIFICATION USING IMAGE PROCESSING FOR LAND SLIDE PRE CURSOR - Patent application no:201941042299
SILICA BASED BINDER COMPOSITION FOR SOIL STABILIZATION AND ENHANCING PAVEMENT LOAD BEARING CAPACITY OF ROADS - Patent application no:201941012760
Covenant University, Otta, Nigeria
VIT University, Vellore
Anna University, Chennai
Windsor University, Canada