Table of contents

Proceedings of the Second International Conference on Robotics and Artificial Intelligence

Editors of the Proceedings

Dr.G. Geetha, Advanced Computing Research Society, Chennai, India geetha@advancedcomputingresearchsociety.org

Dr. Vincenzo Piuri, University of Milan, Italy vincenzo.piuri@unimi.it

Dr. Debao Zhou, University of Minnesota Duluth, USA dzhou@d.umn.edu

Preface

We are honoured and glad to welcome you at the Second International Conference on Robotics and Artificial Intelligence 2021 organized by Advanced Computing Research Society on 29^th and 30^th November 2021. Initially, this conference was planned to be held in Chennai. Later on, due to the covid-19 pandemic situation and travel restrictions imposed by various Governments, the options available was to either postpone, cancel or conduct in virtual mode. Postponement was too unsure, since it was not clear when normalcy will be restored, conducive for physical conference. Cancellation of the conference will upset and disappoint people who have contributed to the conference. Hence the committee decided to go for online mode on the same dates as planned earlier. The organizers hosted the conference from Chennai, India.

Keynote Speakers were :

Dr. Jagannathan Sarangapani

Rutledge Emerson Distinguished Professor and NSF I/UCRC Site Director Director, Embedded Control Systems and Networking Laboratory Missouri University Of Science And Technology, USA

Dr. Ashwin Ashok Department of Computer Science Georgia State University Atlanta, Georgia, USA

Dr. Ramamohanarao Kothagiri

Former Professor, Head of the Department and Research Director School of School of Computing and Information Systems,

The University of Melbourne, Australia

This conference and these proceedings are a unique opportunity for sharing ideas and achievements, discoveries and innovation for growing together our knowledge and contribute to expand the knowledge of humanity.

The conference covers topics on robotics, artificial intelligence, computational science, mathematical physics and electronics and devices. We received 48 papers and after peer review 22 papers were accepted and presented in this conference. The papers were evaluated on the basis of completeness, relevance to the conference, originality, sufficiently novel, technical quality, structure and presentation of the paper and adequate references to previous work. Every paper was reviewed by at least 2 reviewers and the review comments were shared with the authors for incorporating the suggestions and comments.

The conference had participation from various countries – India, Hongkong, Australia, Romania, United Arab Emirates, United States of America and Peru. Total number of participants were 48.

On the day of the conference, all the presenters were able to present online and the sessions were held smoothly as per the schedule. 22 papers were presented in 3 sessions. Each presenter was given 15 minutes for presentation, followed by question-and-answer session. A networking session was also arranged, which enabled the participants to interact, learn and network with each other. We used "Google Meet" as conference platform.

We are thankful to the IOP Journal of Physics : Conference Series and its editor for accepting our proposal, for providing valuable guidance and for publishing this conference proceedings. We also thank the Morressier Conference submission and review management for providing software services which enabled timely peer review. We thank all the Committee members for their valuable inputs and time, for making this conference very successful. We thank all the authors and presenters for disseminating their research outcomes through this conference. We appreciate each and everyone who have made this conference meaningful.

List of Committees, Technical Program Committee, Budget and Finance Committee are available in this Pdf.

All papers published in this volume have been reviewed through processes administered by the Editors. Reviews were conducted by expert referees to the professional and scientific standards expected of a proceedings journal published by IOP Publishing.

• Type of peer review: Single Anonymous

• Conference submission management system: Morressier

• Number of submissions received: 47

• Number of submissions sent for review: 47

• Number of submissions accepted: 22

• Acceptance Rate (Submissions Accepted / Submissions Received × 100): 46.8

• Average number of reviews per paper: 2

• Total number of reviewers involved: 17

• Contact person for queries:

Name: Dr Geetha Ganesan

Email: geetha@advancedcomputingresearchsociety.org

Affiliation: Advanced Computing Research Society

Novel interactions between futuristic devices and humans in the ever-expanding digital world is gaining momentum in the current era. In this paper, a system is proposed where electromyography (EMG) signals are used to control the cursor on a PC with the movement of the hand, making effortless interaction between user and the computer. The hand movements are detected using accelerometer and EMG signals acquired using electrodes are used to classify the hand gestures. Time domain features are extracted from the EMG signals and the gestures are classified using K-Nearest Neighbor (KNN) classifier. The operation to be performed on PC is determined from the gesture with help of a suitable interface. This system is implemented to perform the positioning of the cursor and two of the most common actions of a mouse, namely, single click and double click. The system showed an accuracy of 98% in classifying the gestures.

Bikes require their brakes to be tested. There are adequately defined conditions under which these tests need to be performed: the brake pedal has to be pressed by a constant force. This force varies depending on the standardized test, but the value remains constant under each standard. No bike brake is perfect and thus has imperfections like disc thickness variation and disc misalignment. These imperfections cause judder due to which force experienced by the brakes under a specific pedal position varies too. This can create errors in tests and thus needs to be overcome for proper performance testing of brakes. "Robotic arm for brake performance testing" provides an effective solution by constantly measuring the braking force and instantly moving the brake pedal to keep the braking force constant.

The communication between a human and a humanoid robot is a real challenge for the researchers in the field of the robotics. Despite of the progress in the acoustic modelling and in the natural languages the humanoid robots are overtaken by the humans when the humanoid robots are engaged in the real life because the speech and the human emotions are extremely ambiguous due to the noises and the external audio events from the robot's environment. The humans assign a correct interpretation to the perceived ambiguous signal, but the humanoids robots cannot interpret the ambiguous signal. The most common software used in the interpretation of the ambiguous signal is a fuzzy based software. The artificial neuro-fuzzy inference system, shortly known as ANFIS is the emotion recognition system based on the fuzzy sets which acts as the thalamus of the human brain and it is responsible for the sensorial perception of the humanoid robot. Our goal in this work is to create the fuzzy-based sound signals software and the fuzzy-based genetic algorithm with high performance in the communication between the human and the humanoid robots which help the humanoid robots to think, to understand the human speech and the human emotions and all the ambiguous signals from the robot's environment in a way that it is distinguishable for every humanoid robot as the human.

Robotic technology is now applied in a variety of domains, including hazardous and urban situations, security, planetary systems, rescue missions, and military operations. The current mobility designs are difficult due to the amount of wheels or legs used. They are not designed to withstand the harsh environment of Mars in terms of mechanical breakdown. Four-Wheel rovers can navigate tough terrain thanks to an effective high degree of mobility suspension system. The rocker-bogie design's most important mechanical feature is its drive train simplicity, which is achieved by having only two motors for motion. Six wheels are used since there are rarely obstacles on natural terrain that require both front wheels of the rover to climb at the same time.

It would be ideal for the teacher to give individual attention to each student. However, this is infeasible as teachers only have limited time and they will be tired after long periods of consultation. Chatbots can be an effective tool to overcome this problem. A pilot was conducted on 11 Feb 2019 in which 27 students tried a chatbot prototype built by the author. The students compared the chatbot and a quiz website. The academic contents provided by the chatbot are exactly the same as the website. Over 80% of the students agreed that the chatbot is better than the quiz website in many aspects. However, about half of the students also indicated that the chatbot took them more time to complete the quiz than the quiz website. The author proposed using the Unified Theory of Acceptance and Use of Technology (UTAUT) framework to conduct more research into this area. The knowledge would allow more teachers to create chatbots in more disciplines of study so that students are more motivated to achieve the learning outcomes better.

: Based on a neuro evolutionary algorithm, this study proposes a neural network model for efficient crop price prediction. When viewed from the perspective of agricultural business, the market price of corn reflects its current demand. For agricultural management, to improve profits, it is important to track and predict the market price. In this manuscript, a neural network model based on the output prediction of a neuro evolutionary algorithm is used to predict the price of the crop and compared with the existing Naive Bayes algorithm. By recognizing patterns in our training dataset, which serves as one of the inputs to the algorithm, we are able to determine the price of the crop. The parameters (Yield, Rainfall, Minimum Support Price, and Maximum Trade ) are fed to the algorithm by the user. It is compared with existing algorithms to determine the performance of the proposed algorithm. The features considered for the analysis are Climate, historical costs, location, demand indicators, and crop health are the variables used for predicting future corn crop cost. According to the empirical analysis, the proposed model is significantly more accurate in predicting crop prices.

Sign Language recognition is one of the essential and focal areas for researchers in terms of improving the integration of speech and hearing-impaired people into common society. The main idea is to detect the hand gestures of impaired people and convert them to understandable formats, such as text by leveraging advanced approaches. In this paper, we present our contribution to the improvement of Azerbaijani Sign Language (AzSL). We worked on AzSL Alphabet static signs real-time recognition. The method applied in this work is Object Classification and Recognition by leveraging pre-trained lightweight Convolutional Neural Networks models. At first, a dataset containing near to 1000 images has been collected, then interesting objects on images have been labeled with bounding boxing option. To build, train, evaluate and deploy the relevant model, TensorFlow Object Detection API with Python has been employed. MobileNet v2 pre-trained model has been leveraged for this task. In the trial experiment with four sign classes (A, B, C, E) and 5000 step numbers 15.2% training loss and 83% evaluation mean average precision results have been obtained. In the next step of model deployment experiments with all 24 static signs of AzSL, 49700 and 27700 steps (180 and 100 epochs, respectively) 6.4% and 18.2% training losses, 66.5% and 71.6% mAP outcomes gained, respectively.

Handwritten Text Recognition is an important area of research because of growing demand to process and convert a huge data and information available in handwritten form to Digital form. The digital data instead of handwritten form can prove to be highly useful in different fields. Handwritten text recognition plays an important role in applications involved in, postal services, banks for cheque processing, searching of information and organization dealing with such applications. In text recognition application dataset of the specified script is required for training purpose. Datasets of the different languages could be found online but dataset of dogra script characters is still not available. This paper presents a Dogra handwriting character dataset which contains around 38690 character images etc grouped in 73 character classes extracted from 530 one-page handwritings of 265 individuals of having variable age, sex, qualification, location. The dogra character dataset would be freely accessible by scholars and researchers which could also be used for further recognition improvement and updating with more characters and word, Identification of writer, dogra word segmentation. Dogra dataset could also be used for extracting variation of handwriting according to age and gender.

A definitive form of Mobile Ad-hoc Network (MANET) is the Vehicular Ad-hoc Network (VANET), which delivers data communication using wireless transmission with the collection of vehicular nodes in a vehicular environment. The main goal of this VANET is to improve the Quality of Service (QoS) which is road safety, environmental kindliness, and logistics in intelligent transport. Moreover, mobility and routing play an important challenge for information interchange to the process in the VANET environment. In developing countries, smart cities are encountering problematic traffic congestion. Furthermore, in cluster communications, stable cluster formation and maintenance with the guarantying QoS has always remained a great challenge. In order to overcome the above-mentioned issue, this article proposes a congestion-free routing process ensuring QOS parameters. The main objective of the proposed scheme is to analyze the impact of QOS parameters while choosing the best routing path in Vehicular communication. The scheme also introduces the Hybrid-Harris Hawks Black Widow optimization-based VANET (H-HHBW-VANET) algorithm to improve QoS for routing between nodes. This algorithm differs from other algorithms in terms of optimal solution generation, which makes it more efficient. The proposed work is implemented in the working platform of NS2 to analyze the parameters such as Drop, Delay, Energy Consumption, Throughput, and Fairness Index. The simulation results provide better QOS service in terms of low energy consumption with higher throughput and low delay.

Human Face recognition algorithms have made huge progress in the last decade. In this manuscript, we have presented an approach for the implementation of a face recognition system in a successful manner by varying pose, scale, lighting, and age variation. The different empirical analysis was performed with various datasets for face detection and face identification. Face identification system detects efficiently segments and recognizes face in a cluttered sequence under varying pose, lighting and age variations. From this experimental analysis morphological model outperformed k-NNC, NMC based closest mean classifier and informative knowledge distillation with fairly reasonable accuracy. Three proposed methods on the basis of an efficient way of handling the face recognition problems. The morphological method outperformed well when compared with k-NNC, NMC based closest mean classifier a proposed method, and another innovative method named Informative knowledge Distillation. The morphological method is suitable for large datasets where occlusion, pose variation, age variations, and different expression of images.

The paper illustrates with an approach for formulation of generalized field data based model for cylinder head moulding operation. The aim of field data based modeling for cylinder head moulding operation is to evaluate variable responsible for productivity enhancement & with minimum human energy expenditure. The study identifies important ergonomic and other work environment related parameters which affect the productivity. The identified parameters are properties of sand, physical dimensions of tools, energy outflow of workers, workers anthropometric data, working environment. Out of all the variables responses and causes are identified.

After dimensional analysis relationship between the dependent and independent parameters, a mathematical model is established having relationship between output parameters and input. To get the optimized values model is optimized using the optimization technique. Sensitivity analysis is a tool which can be used to find out the effect of input one parameter over the other. The model will be useful for an industrialist to select optimized inputs so as to get targeted responses.

Many Mechanical structures are manufacture by using plates. However Harmonic Analysis of plate is growing research subject in today's era. In the present research paper vibrational response of simply supported square plate with uncertain parameters are studied. In designing any real life mechanical system uncertainty phenomenon plays vital role. Thus it becomes important to study the effect of uncertainty for different frequency domain in mechanical system. In present research work square plate as structural element is selected. On this plate mass, stiffness and both collectively mass and stiffness uncertainty are taken. The plate boundary condition selected is simply supported. For determining the plate dynamic response FEM tool is used. While doing harmonic analysis the behavior of all uncertain parameters plates are compare with bare plate. In the FRF plot of plate with stiffness uncertainty, it is found that it has drastic changes in dynamic response. Thus this shows that uncertain parameters have adverse effects and it changes the dynamic behavior of the structure.

The public lighting poles are part of the public lighting system, so its operation is important and is offered as a welfare mechanism for citizens, it has the disadvantage of the high cost of operation because it is in operation all night for 365 days of the year, in this work a low-cost system is designed to be able to supply power to the public lighting poles, based on a solar panel system and with sensors to be able to measure luminosity, voltages and current, this system sends the information to a base station using the XBEE protocol and viewed using LABVIEW software.

Water is an essential element in the life of the human being for which its conservation and good use is necessary, in this work we make a proposal for the development of a low-cost system for water management in order to save on Its consumption, using infrared technology, the results provide a mechanism that can be replicated and at different scales, by the use of commonly used devices.