Dr.G.P.Ramesh
@spiher.ac.in
Professor & Head -Electronics and Communication Engineering
St.Peters Institute of Higher Education and Research
began his teaching career at Engineering College in Year 1998 and is now Professor and Head of Electronics and Communication Engineering in Institute of Higher Education and Research. He has been teaching both at the Undergraduate and post graduate levels and subject he excels in are Electronics, VLSI and Antennas. It is with Pride that his made known that he commenced research activities at SPIHER in 2012 and since then has been guiding students leading to their Ph.D Degree. Till date he has successfully guided 18 Ph.D Scholars and significant number of post graduate scholars. There are more students awaiting the opportunity to pursue research under him.
Ramesh is a versatile dynamic personality who has spread his wings across academics, administration, research and development. A fascinating man of action – he has very good communication skills, constructive teamwork and a good believer of consistent policies
EDUCATION
is a passionate educator with teaching research nexus skill set. With 24 years of experience in education, his contributions are holistic which covers Teaching, Research and Administration. He has has completed his undergraduate degree in Electrical and Electronics Engineering from S.V.University, Tirupati in the year 1996 followed by his post graduation in Applied Electronics from Coimbatore Institute of Technology, Coimbatore in the year 1998.He went on to complete his Ph.D. in Electronics and Communication from Anna University, Chennai for his work of Development of Miniature microstrip antenna as sensor for pitting edema and diabetic measurement
RESEARCH INTERESTS
Antenna Design, RF & Microwave, VLSI Design, Applied Electronics
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Scopus Publications
M Vinod Kumar, G.P. Ramesh, Piyush Kumar Pareek, H A Deepak, and J. Ananda Babu
IEEE
Facial recognition is one example of the ways in which computer vision is being applied in modern, people-oriented utility apps. Facial recognition technology has improved in recent years, but it still lags behind other biometric authentication methods such as fingerprint and iris scanning or Radio Frequency Identification (RFID) cards in terms of accuracy. However, it is still frequently utilised due to the fact that the recognition procedure does not involve touching the device in any way. This research takes advantage of advances in facial recognition technology to offer an embedded device integrated AI and IoT-based automated attendance solution for use in smart classrooms. This study uses the ResNet architecture to explore a deep learning classification method for identifying student attendance. In this research, we used facial photos from students to train ResNet-18 and ResNet-50. Models educated to differentiate regular from irregular student attendance. Our photos were evaluated on 20%, 25%, and 40% of simulated and real-world datasets, respectively. Results from three types of testing data show that ResNet-50 outperforms ResNet-18 in rapports of accuracy, F1-measure, and mean accuracy value. This study makes use of the FER2013 dataset for labelling faces, as well as real-time student faces. This study uses a deep learning approach to show how dependable and repeatable student image analysis
Senthilkumar Andi and Ramesh G. P.
Wiley
SummaryA miniaturized frequency‐selective surface (FSS) for radio frequency (RF) filtering applications is reported in this paper. The proposed FSS is designed to operate with band stop property at 1.57 GHz. The FSS element is developed using highly convoluted lines running on either side of the substrate interconnected using via lines. This specific arrangement increases the electrical length of the resonator without increasing the physical size. Furthermore, the stability towards polarization variation and independence to different angles of incidence are other major concerns in the design of FSS. The FSS unit cell has rotational symmetry thereby providing polarization‐independent operation. The angular independence is tested for various incidence angles, and the results are presented. The performance of the FSS is validated in real time, and the results are presented. The maximum realized transmission loss is 27 dB at 1.57 GHz, and the attenuation bandwidth with reference 10 dB shielding level is estimated to be 400 MHz centered around 1.57 GHz. The convolution technique along with shorting vias has offered this extreme miniaturization ranging from 7% to 95.7% with reference to most of the FSS reported for L‐band services such as radio, telecommunications, military, and aircraft surveillance.
P. Manikandan, G. Ramesh, Shashank Naidu K, U. Kartheek, R.V. Sai Prem, and Y. Siva Sai Reddy
IEEE
In India and many developing countries, electrical power usage has been calculated manually by observing the number of units in electrical power meter. Electrical power consumption bill amount is calculated manually and updated to the user as well as Electric board data base. The users need to pay the bill against the calculated amount, and it can be paid by direct cash or digital transaction. This conventional system involved more human resources. It has more chance for wrong calculations. Thus, the cost is too expensive, and the process takes too long. We proposed a system to allow consumers and service providers measure power usage, calculate bills for minimizing unnecessary power usage, and make remote bill payments in order to avoid falling into this trap. This study introduces the idea of an IoT (Internet of Things) enabled digital EB (Electricity bill) meter. The proposed system is developed using Arduino because it consumes less power, is faster and has two UARTs (universal asynchronous receiver-transmitter). Power transformers are used to calculate voltage and current level. Arduino control converts data into power unit using some simple calculations. Users can monitor the power usage, recharge, and pay the bill using android app or web page. The energy consumption is calculated continuously and if the user's electricity account balance reaches a low-level; warning will be given to the user. The electricity will be terminated when the available balance is less than the unit charge.
Inakollu Aswani, Naresh Kumar Kar, Tanaya Ganguly, G.P. Ramesh, and Tejaswini N P
IEEE
The sounds and vibrations that are given off by a rotating machine can provide insight into a wide variety of distinct problem situations. By conducting statistical analysis on the recorded sound and vibration signals and subjecting them to a variety of fault conditions, it is possible to generate statistical parameters. In order to obtain information regarding the numerous flaws, the signals in the temporal domain are analyzed using these characteristics. In order to locate flaws in the system, we make use of these values, also known as “statistical features.” In this work, dimensionality reduction was achieved through the utilisation of a decision tree, principal component analysis (PCA), and independent component analysis (ICA). In order to classify the various fault states, the various classifiers were given these streamlined features to work on. During this inquiry, different kinds of classifiers were utilized, such as decision trees, support vector machines, clonal selection classification algorithms, and proximal support vector machines. This paper presents the findings of two sets of research involving statistical features extracted from sound and vibration signals and used in conjunction with the aforementioned feature reduction techniques and classifiers to detect twelve different fault conditions involving shaft, rotor, and bearing failures. The research was conducted by using sound and vibration signals as the primary source of data. According to this Proposed Approach, the Mean Classification Efficiency% of Vibration Signals for 24 Classes is 94.27%, while the Mean Classification Efficiency”% of Sound Signals for 24 Classes is 95.41%.
G. Hemanth Kumar and Ramesh G.P.
Elsevier BV
Syed Suraya, Shaik Mohammad Irshad, G. P. Ramesh, and P. Sujatha
Springer Science and Business Media LLC
P. Manikandan, G. Ramesh, P. Syam Mohan Reddy, J. Suman, M. Dhanush Vasavai Kumar, and K. Chandra Siddhardha Reddy
IEEE
This paper presents the assistance system for visibly injured community. There are nearly 37 heap family across the globe the one is blind in accordance with the World Fitness Arrangement. Nation with optic restrictions is often helpless on outside help which may be supported by humans, prepared dogs, or distinctive photoelectric devices as support plans for conclusion making. Thus, we were stimulated to overcome these restraints. We consummate this aim by adding fast sensors at particular positions. That determined news about the atmosphere to the user by stimulating the voice playback module. In the proposed plan, we have secondhand quick sensor to avoid barriers utilizing Arduino. In this manner, bureaucracy detects some obstacle shipping specific demand to the blind person through voice alert through voice playback module.
P. Manikandan, G. Ramesh, V. Muneeswaran, S. Sunil Kumar, P. Vara Siddartha, and A K. Koushik
IEEE
In the area of customer service, technology plays a critical role in ensuring customer satisfaction. Although the public transportation system is commonly used by the public, service providers are working to improve the quality of their services in a variety of ways. However, manual collection is still used by fare collection, so this paper focuses on the introduction of efficient methods to extend the ticketing system. Smart Card technology is implemented to get the ticket by drawing money from passengers account instead of transaction of direct money, with this method it eradicates the issues due to scarcityof coin change. Smart Card technology is used to obtain a ticket by withdrawing funds from a passenger’s account rather than making a direct money transaction; thisapproach eliminates problems caused by a lack of coin change. The conductor swipes the smart card with the smart card reader, and the Electronic Ticketing Machine (ETM) generates the tickets after entering the passenger’s travel information, and money is directly transferred to the TC account through General Packet Radio Service (GPRS).
G. Ramesh, P. Manikandan, J. JolinDorrothi, R. Nithya Shree, and S.K. Prabhavathy
IEEE
To prevent excessive potentially harmful obstruction, electrical lines often used to deliver the energy are generally located below the ground in metropolitan areas. As a result, diagnosing the exact site of any problems that emerge becomes incredibly challenging. A malfunction may sometimes occur for a number of driving factors such as excavation, natural disasters, and building and so on. Because of the line's uncertain location, the repair mechanism is complex. This developed framework is intended to identify failures in subterranean networks here Ohm's law is being used to precisely localize a base station to km using an Arduino microcontroller equipment. The resistive networks are used as current sensor and voltage sensor to identify the cable faults such as open or short. Resistive network is connected to Arduino microcontroller of this system. and the Liquid Crystal Display (LCD) is with the microcontroller that shows fault location; if an error occurs, the error occurred distance is calculated, and the fault location can be identified by using GPS device and display the precise position of the fault region on the LCD. It uses GSM to send a message to the registered contact details notifying them of the cable's location.
G. Ramesh, P. Manikandan, Umesh Reddy Venkatathathagari, Govardhan Bandi, Ashwith Garlapti, and Mujayiddin Attar
IEEE
In recent years, due to the rise in the number of novel coronaviruses across the globe nations step forward to stop the crisis. With guidelines of the WHO many methodologies came into existence to prevent the spreading of coronavirus. My SD: A Smart Social distance and Monitoring System takes advantage of the features of the smartphone’s hardware which usually has Bluetooth transmitter-receiver, like GPS to determine the safe distance and required level of compliance. Through artificial intelligence, this new smart device helps maintain uniform social distance and detect COVID 19 patients. In these COVID 19 environments, everyone knows how safe they are. In this paper, we have automated the process whereby the layman can control himself without any priming which makes the system more user-friendly for the public. The user himself or herself can monitor body temperature, social distancing and get an alert in abnormal selfisolation conditions using contactless thermometer, ultrasonic sensors, and GSM modules.
G. Ramesh, P. Manikandan, P. Naveen, M. Saravanan, S. R. Ashok Kumar, and C. Swedheetha
IEEE
Integrated circuit has been widely used in different applications. The design and development of CMOS transistor provides various advantages such as low power dissipation, cost efficient solutions, enhanced processor performance and size reduction. The main aim of the proposed research work is to increase the performance of the processor and reduce the area by increasing the performance of the adder circuits. The adder circuits enable its availability in many processors. In the processor, ALU is considered as the main functional block for performing any arithmetic operations. A novel high performance adders circuits were designed with the 0.18μm technology in TSMC Spice Simulator. Pass transistor logic has been used to reduce the transistors count in the circuit and hence the performance has increased by 10% when compared with the existing CMOS structure.
G. Ramesh, P. Manikandan, Mssd. Amruth, B. Pavan Ramanendra Swamy, B. Revanth Kumar, and Ch. Manish Venkata Satyanarayana
IEEE
This paper presents the vehicle tire scrutinizing and alignment checking system. This method can measure the pressure inside the wheels of the car. The prototype of the designed system consists of a pressure sensor, a switch, a microcontroller, NRF transmitter and LCD display. Wheel alignment, forcing and wheel disengagement were also shown. As the developed prototype is a simple architecture, there is no need to modify the bike in any way. In the same way, the running of the model is not affected by the maintenance of the bike. When the pressure inside the wheel increases or decreases by a certain range and if the wheel adjustment is not within the angle range, it generates a warning. The disadvantages of existing systems are that they are either wired or the hardware of these systems is not properly implemented. By eliminating these shortcomings, this system is now designed to be used even when the vehicle is in motion and is wireless. With the use of this system, most of the accidents will be reduced and driving conditions will become safer.
G Gurumita Naidu and G.P Ramesh
IEEE
Mango Plant Diseases wreak havoc on fruit production and cause growers to lose money. This dilemma prompted the development of a new technology for detecting and diagnosing mango plant illnesses. In agriculture, keeping an eye on the health and illness of crops is critical for the booming output of crops in the cultivation industry. A multilayer convolutional neural network (MCNN) is constructed for the classification of Mango leaves disease, which is a classic and cost-effective solution to the above problem. Canonical correlation analysis (CCA)-based fusion is used to extract and fuse the features. The use of an ultrasonic sensor to detect bacterial canker and phomba blight disease is proposed in this research. The ultrasonic sensor that produces a pulse reflected signal from mango leaves uses the echo pin. Microsoft Excel is used to record the pulse data. A threshold frequency for disease detection is calculated using these values. The proposed approach has a 90% accuracy rate.
Naga Raju Jangam, Likhitha Guthikinda, and G. P. Ramesh
Springer Nature Singapore
G. P. Ramesh and Neha
Springer Nature Singapore
G. P. Ramesh, Pallavi, Hanifa Abdullah, and B. D. Parameshachari
Springer Nature Singapore
P. Subramanian, G. P. Ramesh, and B. D. Parameshachari
Springer Nature Singapore
Naga Raju Jangam, G. P. Ramesh, and P. Rachana
Springer Nature Singapore
K. Ramesh, S. Parasuraman, G. P. Ramesh, and P. Rachana
Springer Nature Singapore
P. Manikandan, G. Ramesh, P. Sivakumar, J.Jyothish Kumar, R.Leela Krishna, and G. Dinesh
IEEE
Indian agrology system is highly based upon the production of food crops. Quality of crops depends upon the nutrients level of the soil. Our nation consists of majorly productive lands in different type of soils. Macro nutrients and micro nutrients are the kind of soil nutrients. Weather the quality of the crop will be improved by addition of fertilizers. This fertilizer can make the crop to rich yield as well as poor yield. The amount of fertilizer is a major factor for the richness of the yield. This proposed IoT based android system is used to test the soil nutrients level and also helps to evaluate the value of fertilizers need to be fed. It evaluates the fertilizer level in an efficient manner and known to the famers. Highly previsioned sensors are used to improve soil nutrients level. This effective proposed system makes the farmer into more educate with the handling of the fertilizer
P. Manikandan, G. Ramesh, P. Lokesh, P.Narasimha Raju, M.Durga Prasad, and P. Madhu
IEEE
This paper unveils the method for Farm protection from Animals and Humans theft using ESP32 camera module. The places with high population and humans' movement, wild animals' invasion is harmful for both humans and animals. It's very difficult to track the animal's movement and keep an eye. In many cases wild animals enter the farm and destroy them, to prevent this farm owner need to place a person for monitoring the field, but it's not sure that the person placed can do the work effectively. As a solution to this problem, this paper presents a system that identifies the animals and humans' movement in the farm and notifies the farm owner through an IOT application. Prototype of this project is prepared by using Arduino IDE for writing code, ESP 32 camera module is used as a microcontroller and Blynk application is used for transmission of messages and images of the intruder. By using this system humans and animals' intrusion into the farm can be controlled and our system is cost effective.
Subramanian P. and Ramesh G. P.
Hindawi Limited
In keratoconus, the cornea assumes a conical shape due to its thinning and protrusion. Early detection of keratoconus is vital in preventing vision loss or costly repairs. In corneal topography maps, curvature and steepness can be distinguished by the colour scales, with warm colours representing curved steep areas and cold colours representing flat areas. With the advent of machine learning algorithms like convolutional neural networks (CNN), the identification and classification of keratoconus from these topography maps have been made faster and more accurate. The classification and grading of keratoconus depend on the colour scales used. Artefacts and minimal variations in the corneal shape, in mild or developing keratoconus, are not represented clearly in the image gradients. Segmentation of the maps needs to be carried out for identifying the severity of the keratoconus as well as for identifying the changes in the severity. In this paper, we are considering the use of particle swarm optimisation and its modifications for segmenting the topography image. Pretrained CNN models are then trained with the dataset and tested. Results show that the performance of the system in terms of accuracy is 95.9% compared to 93%, 95.3%, and 84% available in the literature for a 3-class classification that involved mild keratoconus or forme fruste keratoconus.
Rudra Bhanu Satpathy and G. P. Ramesh
Springer Nature Singapore
P. Britto Corthis and G. P. Ramesh
Springer Nature Singapore
P Subramanian and GP Ramesh
College of Graduate Studies, Walailak University
Keratoconus, by its name, is the condition of the eye wherein the cornea assumes a conical shape due to the thinning and protrusion of the cornea. Keratoconus, though bilateral, can be asymmetric in that it can progress differently in the eyes of the patient. Keratoconus can start from early adulthood and progress till the age of 40. Early detection of keratoconus is vital in preventing vision loss or costly repairs. The diagnostic tools available range from keratoscope to videokeratoscope but involves human efforts and thereby human errors. Automatic detection of keratoconus is required for large screening camps. With the advances in artificial intelligence techniques for medical diagnosis, new algorithms and techniques have been developed for the early and rapid screening of keratoconus, which aids clinicians in fast diagnosis. Artificial Neural Networks, Support Vector Machines, Radial Basis Function Neural Networks, Decision Trees, Computational Neural Networks, and various optimisation techniques have been used in different studies. The progression of keratoconus is identified by analyzing the shape of the cornea with Local Binary Pattern (LBP), Local Directional Pattern (LDP), Local Optimal Oriented Pattern (LOOP), and Cat Swarm Optimization (CSO) to detect the changes in cornea edges. The image processing with the CSO algorithm optimizes the result for the changes in the cornea and keratoconus detection. A new automated solution for detecting keratoconus is presented that employs texture analysis techniques such as LBP, LDP, LOOP, and CSO. The CSO extracts morphological and granular features from images of the cornea. The proposed method can be used to detect keratoconus by identifying the cornea shape change and improving clinical decisions. Further research can be in the way of grading the level of keratoconus. HIGHLIGHTS Extraction of corneal features for Diagnosis of Keratoconus from corneal topography images Feature vector extraction from corneal images using Local Binary Pattern, Local Direction Pattern and Local Optimal Oriented Pattern Optimisation using Cat Swarm Optimisation GRAPHICAL ABSTRACT
RECENT SCHOLAR PUBLICATIONS
MOST CITED SCHOLAR PUBLICATIONS
RESEARCH OUTPUTS (PATENTS, SOFTWARE, PUBLICATIONS, PRODUCTS)
1)Published a Patent Registration no- 201641024238-Novel emergency notification system for elderly protection using MEMs sensor: S-Waistband in the
academic year 2021-22
2) Published a Patent Registration no- 201841026631-RZF antenna for ECG monitoring using IoT in the academic year 2021-22
3) Published a Patent Registration no- 201841026640-Multiband reconfigurable antenna in Wi-max frequency for soil quality sensing applications in the academic year 2021-22
4) Published a Patent Registration no- 202041033291-Mosquito larve level growth identification using optical sensor on the sewage passage to prevent dengue in the academic year 2021-22
5) Published a Patent Registration no- 202041033296-Design and development of a wearable in EAR EEG device to diagnose Schizoprenia in the academic year 2021-22