Vasan Arunachalam | Birla Institute of Technology and Sciences (BITS-Pilani), Hyderabad Campus (original) (raw)

Conference Presentations by Vasan Arunachalam

Proceedings of the 13th International Conference on Agents and Artificial Intelligence, 2021

Facial Expressions are a key part of human behavior, and a way to express oneself and communicat... more Facial Expressions are a key part of human behavior, and a way to express oneself and communicate with others. Multiple groups of muscles, belonging to different parts of the face, work together to form an expression. It is quite possible that the emotions being expressed by the region around the eyes and that around the mouth, don’t seem to agree with each other, but may agree with the overall expression when the entire face is considered. In such a case, it would be inconsiderate to focus on a particular region of the face only. This study evaluates expressions in three regions of the face (eyes, mouth, and the entire face) and records the expression reported by the majority. The data consists of images labelled with intensities of Action Units in three regions – eyes, mouth, and the entire face – for eight expressions. Six classifiers are used to determine the expression in the images. Each classifier is trained on all three regions separately, and then tested to determine an emoti on label separately for each of the three regions of a test image. The image is finally labelled with the emotion present in at least two (or majority) of the three regions. Average performance over five stratified train-test splits it taken. In this regard, the Gradient Boost Classifier performs the best with an average accuracy of 94%, followed closely by Random Forest Classifier at 92%. The results and findings of this study will prove helpful in current situations where faces are partially visible and/or certain parts of the face are not captured clearly.

Papers by Vasan Arunachalam

2023 IEEE 4th Annual Flagship India Council International Subsections Conference (INDISCON)

2023 IEEE IAS Global Conference on Emerging Technologies (GlobConET)

ISH Journal of Hydraulic Engineering

World Environmental and Water Resources Congress 2009, 2009

ABSTRACT The present paper discusses the applicability of Multiobjective Differential Evolution (... more ABSTRACT The present paper discusses the applicability of Multiobjective Differential Evolution (MODE) and single objective Differential Evolution (DE) to a case study of Mahi Bajaj Sagar Project, Rajasthan, India. Three objectives, namely, net benefits, agricultural production and labour employment are analyzed in the multiobjective framework using MODE. Four variations (strategies) of Differential Evolution, namely, DE/rand/1/bin, DE/rand/1/exp, DE/best/1/bin and DE/best/1/exp are explored. Population size, crossover ...

ISH Journal of Hydraulic Engineering, 2012

In the present study, applicability of Multi-objective Differential Evolution (MODE) in irrigatio... more In the present study, applicability of Multi-objective Differential Evolution (MODE) in irrigation planning perspective is demonstrated through a case study of Mahi Bajaj Sagar Project, Rajasthan, India. Three objectives, namely, net benefits, agricultural production and labour employment are analysed in the multi-objective environment. Non-dominated alternatives generated by MODE are reduced to a manageable subset with the help of K-means cluster analysis for effective decision making. Optimal number of groups is determined based on ...

Journal of Water Resources Planning and Management, 2010

ABSTRACT The paper describes the development of a DENET computer model that involves the applicat... more ABSTRACT The paper describes the development of a DENET computer model that involves the application of an evolutionary optimi-zation technique, differential evolution, linked to the hydraulic simulation solver, EPANET, for optimal design of water distribution networks. A model is formulated with the objective of minimizing cost and this formulation is applied to two benchmark water distribution system optimization problems—New York water supply system and Hanoi water distribution network. The study yielded promising results as compared with earlier studies in the literature and encouraged to reformulate the model for a new objective of maximizing network resilience. The results of the analysis demonstrate that DENET can be considered as a potential alternative tool for economical and reliable water distribution network planning and management.

Proceedings of the 13th International Conference on Agents and Artificial Intelligence, 2021

Facial Expressions are a key part of human behavior, and a way to express oneself and communicate... more Facial Expressions are a key part of human behavior, and a way to express oneself and communicate with others. Multiple groups of muscles, belonging to different parts of the face, work together to form an expression. It is quite possible that the emotions being expressed by the region around the eyes and that around the mouth, don't seem to agree with each other, but may agree with the overall expression when the entire face is considered. In such a case, it would be inconsiderate to focus on a particular region of the face only. This study evaluates expressions in three regions of the face (eyes, mouth, and the entire face) and records the expression reported by the majority. The data consists of images labelled with intensities of Action Units in three regions-eyes, mouth, and the entire face-for eight expressions. Six classifiers are used to determine the expression in the images. Each classifier is trained on all three regions separately, and then tested to determine an emotion label separately for each of the three regions of a test image. The image is finally labelled with the emotion present in at least two (or majority) of the three regions. Average performance over five stratified train-test splits it taken. In this regard, the Gradient Boost Classifier performs the best with an average accuracy of 94%, followed closely by Random Forest Classifier at 92%. The results and findings of this study will prove helpful in current situations where faces are partially visible and/or certain parts of the face are not captured clearly.

International Journal of Speech Technology

Speech emotion recognition is one of the fastest growing areas of interest in the field of affect... more Speech emotion recognition is one of the fastest growing areas of interest in the field of affective computing. Emotion detection aids human-computer interaction and finds application in a wide gamut of sectors, ranging from healthcare to retail to education. The present work strives to provide a speech emotion recognition framework that is both reliable and efficient enough to work in real-time environments. Speech emotion recognition can be performed using linguistic as well as paralinguistic aspects of speech; this work focusses on the latter, using non-lexical or paralinguistic attributes of speech like pitch, intensity and mel-frequency cepstral coefficients to train supervised machine learning models for emotion recognition. A combination of prosodic and spectral features is used for experimental analysis and classification is performed using algorithms like Gaussian Naïve Bayes, Random Forest, k-Nearest Neighbours, Support Vector Machine and Multilayer Perceptron. The choice of these ML models was based on the swiftness with which they could be trained, making them more suitable for real-time applications. Comparative analysis of the models reveals SVM and MLP to be the best performers with 77.86% and 79.62% accuracies respectively. The performance of these classifiers is compared with benchmark results in literature, and a significant improvement over state-of-the-art models is presented. The observations and findings of this work can be applied to design real-time emotion recognition frameworks that can be used to design and develop applications and technologies for various domains.

i The book explains in detail the working of Differential Evolution optimization algorithm. It al... more i The book explains in detail the working of Differential Evolution optimization algorithm. It also provides documentation for the use of Differential Evolution computer program to solve user-defined optimization problems. The computer program is written in C language for Windows environment. The book also demonstrates how to modify the program using an example optimization problem. This source code is distributed for academic purposes only. It has no warranty implied or

Maximizing Compressive strength and Minimizing the cost has always been the objectives for select... more Maximizing Compressive strength and Minimizing the cost has always been the objectives for selection of mix design, but with the increase in recent interests in producing eco-friendly materials, another objective has been added to the above two, making it a complex multi-objective problem. This paper presents a way to solve this multi-objective optimizing problem in a more statistical way, optimizing concrete mix designs to obtain a high-strength, low carbon emission and economical mix design using recently developed nature-inspired algorithm namely Cuckoo Search (CS) algorithm. The algorithm was written in MATLAB and the results obtained consist of mix designs having strengths varying from 20 MPa to 90 MPa and their corresponding carbon emissions from 360 to 500 kg of CO2 Emissions for 1 m−3 of concrete. These results were compared with the results obtained with NSGAII and was concluded that MOCS performed better than NSGAII for this application producing wide spread pareto front.

The book explains in detail the working of Differential Evolution optimization algorithm. It also... more The book explains in detail the working of Differential Evolution optimization algorithm. It also provides documentation for the use of Differential Evolution computer program to solve user-defined optimization problems. The computer program is written in C language for Windows environment. The book also demonstrates how to modify the program using an example optimization problem. This source code is distributed for academic purposes only. It has no warranty implied or given, and the author assumes no liability for damage resulting from its use or misuse.

Non-dominated Sorting Genetic Algorithm (NSGA-II) is employed to facilitate multi-objective optim... more Non-dominated Sorting Genetic Algorithm (NSGA-II) is employed to facilitate multi-objective optimization in Water Distribution Network(s) (WDN) framework for a benchmark problem of Hanoi Network and a real-world problem, Pamapur Network, Telangana, India. Maximization of resilience, minimization of cost and minimization of leakages are considered in a multiobjective context which result in generation of Non-dominated WDN Strategies (NWDNS). In order to simplify the decision making process of engineers, Fuzzy Cluster Analysis (FCA) is employed to categorize NWDNS into groups. Thereafter, Dunn’s Cluster Validity Index (DCVI) is used for identification of optimal cluster size. Representative NWDNS i.e. RNWDNS for each sub-cluster is based on the maximum membership of NWDNS in the respective sub-cluster. Ranking of RNWDNS is performed with three decision making algorithms, namely, Preference Ranking Organization METHod for Enrichment of Evaluations-2 (PROMETHEE-2), Multicriterion Q-anal...

2013 IEEE Second International Conference on Image Information Processing (ICIIP-2013)

ABSTRACT Solving complex problems with higher dimensions involving many constraints is often a ve... more ABSTRACT Solving complex problems with higher dimensions involving many constraints is often a very challenging task. While solving multidimensional problems with particle swarm optimization involving several constraint factors, the penalty function approach is widely used. This paper provides a comprehensive survey of some of the frequently used constraint handling techniques currently used with particle swarm optimization. In this paper some of the penalty functional approaches for solving evolutionary algorithms are discussed and a comparative study is being performed with respect to various benchmark problems to assess their performance.

Advances in Structural Engineering, 2014

ABSTRACT The construction sector is booming all over the world with an increase in the demand for... more ABSTRACT The construction sector is booming all over the world with an increase in the demand for the production of cement. Cement produced by India by the end of the financial year 2012–2013 was about 8 % of the global production. Cement production accounts for 7 % of total CO2 emission into the atmosphere. It’s high time for a sustainable replacement for cement in order to prevent greenhouse effect and global warming and other environmental impacts. In the present study, laboratory tests were conducted to investigate the effect of sodium hydroxide concentration on the fresh properties and compressive and flexural strength of self-compacting geopolymer concrete (SCGC) incorporating ground granulated blast slag (GGBS). The experiments were conducted for five different molarities of NaOH varying between 3 and 11 M with an increment of 2 M. In order to investigate the fresh concrete properties of SCGC, slump flow, V-Funnel, and T50 tests were carried out. The workability of GGBS based self-compacting geopolymer concrete showed an evident decrease with the increase in sodium hydroxide concentration. Standard cubes and beams were casted and cured in the open atmosphere. Its 28 days compressive strength and flexural strength were found to be decreasing with the increase in sodium hydroxide concentration. Using ABAQUS numerical modeling for compressive strength and flexural strength was determined and the results obtained were found to be similar to that of the experimental results.

Self-compacting concrete has an enhanced ability to flow which results in an increased segregatio... more Self-compacting concrete has an enhanced ability to flow which results in an increased segregation and bleeding potential. These requirements make the use of mineral and chemical admixtures essential for self-compacting concrete. High flowing ability is achieved using superplasticizers, while stability against segregation is achieved either by using a large quantity of fine materials, or by using appropriate viscosity modifying agents. Superplasticizers and other additives are used in production of SCC; they have an impact on high fluidity and prevent segregation, the additions of fillers reduce the quantity of superplasticizers used in SCC mixes, compared to normal concrete. The superplasticizer and mineral admixture hold the aggregates in suspension, and the combination of powder materials is also used to control the hardened properties, such as strength. This paper reviews on the work done in the recent past with the usage of different superplasticizers and their influence on str...

The construction industry consumes huge amounts of energy and produces substantial pollution. The... more The construction industry consumes huge amounts of energy and produces substantial pollution. The operation of a building accounts for a large portion of its total CO2 emissions. Most efforts are focused on improving the energy efficiency related to the operation of a building. The relative importance of the energy and CO2 emissions from the construction materials increases with the increasing number of low-energy buildings. To minimize the life-cycle energy use of a building, the energy consumed from both materials in the construction phase as well as the energy consumed from the operation of the building must be reduced. In this study, an optimal design method for reinforced concrete building using a cuckoo search algorithm is proposed to reduce CO2 emissions from the structural materials in the construction phase, while satisfying the structural design criteria and constructability conditions. The optimal method is applied to a single storey portal RC frame, and the effective use...

Proceedings of the 13th International Conference on Agents and Artificial Intelligence, 2021

2023 IEEE 4th Annual Flagship India Council International Subsections Conference (INDISCON)

2023 IEEE IAS Global Conference on Emerging Technologies (GlobConET)

ISH Journal of Hydraulic Engineering

World Environmental and Water Resources Congress 2009, 2009

ISH Journal of Hydraulic Engineering, 2012

Journal of Water Resources Planning and Management, 2010

Proceedings of the 13th International Conference on Agents and Artificial Intelligence, 2021

International Journal of Speech Technology

2013 IEEE Second International Conference on Image Information Processing (ICIIP-2013)

Advances in Structural Engineering, 2014

DESCRIPTION This paper discuss the impact of Irrigation and look how optimal water and land alloc... more DESCRIPTION This paper discuss the impact of Irrigation and look how optimal water and land allocations can ensure maximization of crop productivity.