Dr.Senthil Singh | Anna University (original) (raw)

Papers by Dr.Senthil Singh

Research paper thumbnail of A novel design and implementation algorithm for recognition face from very low resolution images

Research paper thumbnail of Detection and Classification of Brain Tumor from MR Images Using an Improvised Image Analysis Algorithm

ECS transactions, Apr 24, 2022

Early detection of brain tumour and its classification are predominantly achieved by conventional... more Early detection of brain tumour and its classification are predominantly achieved by conventional methods of image processing and machine learning. Brain tumour, known for its rapid development in terms of size and effects over human health, has to be detected immediately from the onset for an effective diagnosis. Unless a treatment plan is defined to mitigate further growth, there are high chances of fatality. Detecting and classifying processes are an exigent task even for experienced radiologists. Segmentation and feature extraction are traditional image processing techniques used for the purpose. Nowadays, a computer-aided diagnosis system is merged with machine learning and deep learning strategies for distinguishing tumour cells. The proposed system is an investigation of classifying brain tumour in its early stages using enriched feature sets support vector machine classifiers for increasing the precision of accuracy. Dice coefficient was introduced, along with the said methods, to ensure classification accuracy. Enrichment of the features was achieved by area-based analysis with prospective growth metrics on a four quadrants designated on two-dimensional plane. Genetic algorithm with soft computing techniques improvised the classification accuracy. Two standard and open source data sets deployed the proposed model, which resulted in an accuracy of 98%, sensitivity of 92%, and the specificity of 98.1% as an average. The proposed model also consumed lesser time than the conventional standards with respect to detection and classification of brain tumours.

Research paper thumbnail of Extaction of Maximum Power from PV and Wind Energy Sources Using Predictive Control System in Microgrids

ECS transactions, Apr 24, 2022

Research paper thumbnail of Brain Tumor Segmentation through Level Based Learning Model

Computer Systems Science and Engineering

Research paper thumbnail of Detection and Classification of Brain Tumor from MR Images Using an Improvised Image Analysis Algorithm

ECS Transactions

Early detection of brain tumour and its classification are predominantly achieved by conventional... more Early detection of brain tumour and its classification are predominantly achieved by conventional methods of image processing and machine learning. Brain tumour, known for its rapid development in terms of size and effects over human health, has to be detected immediately from the onset for an effective diagnosis. Unless a treatment plan is defined to mitigate further growth, there are high chances of fatality. Detecting and classifying processes are an exigent task even for experienced radiologists. Segmentation and feature extraction are traditional image processing techniques used for the purpose. Nowadays, a computer-aided diagnosis system is merged with machine learning and deep learning strategies for distinguishing tumour cells. The proposed system is an investigation of classifying brain tumour in its early stages using enriched feature sets support vector machine classifiers for increasing the precision of accuracy. Dice coefficient was introduced, along with the said metho...

Research paper thumbnail of Iterative Dense Network using Laplacian Pyramid Model for Blind Super Resolution

2021 IEEE 18th India Council International Conference (INDICON), 2021

The Deep learning-based approach for solving the ill-posed problem of single image super-resoluti... more The Deep learning-based approach for solving the ill-posed problem of single image super-resolution reconstruction (SRR) has achieved tremendous success in recent times. However, not much work is carried out in the direction of blind image super-resolution, where the degradation kernel is said to be unknown. This paper addresses the said problem of blind single image super-resolution reconstruction using an alternative learning approach by training two convolutional neural networks. Most of the available model for blind super-resolution considers a fixed degradation kernel for reconstruction, which leads to drop in performance. Therefore a learnable kernel estimation approach is adopted by using a kernel-estimator network. Further, this estimated kernel is used to generate a super-resolution image using a Generator network. To successfully model the reconstruction of vital features like edges and texture and to learn the inter-pixel dependencies between multi-level feature maps, we employ a densely residual Laplacian attention block (DLA-Block). The proposed method is extensively tested on real image and synthetic image datasets. The experimental results have shown out-performance compared to the state-of-the-art in terms of high reconstruction accuracy as well as PSNR and SSIM.

Research paper thumbnail of International Journal of Intellectual Advancements and Research in Engineering Computations A REVIEW ON PRIVACY PRESERVING DATA PUBLISHING IN DATA MINING

The data mining process of collecting, extracting and storing valuable information is actively do... more The data mining process of collecting, extracting and storing valuable information is actively done by many enterprises now-a-days. Among lots of developments, data mining face hot issues on security, privacy and data integrity. People become embarrassed when adversary tries to know the sensitive information about an individual. Data mining use one of the latest technique called privacy preserving data publishing (PPDP) in the field of data security, which enforces security for the digital information provided by governments, corporations, multinational companies and individuals. This information act as a source of decision making in business. PPDP provides required tools and techniques to secure exchanging and publishing data. PPDP gathers more involvement of research communities because of securing sensitive information belongs to an individual. This survey will be a key of collecting various methods used for preserving and publishing useful data.

Research paper thumbnail of The Catalytic Converter

In our world, communication systems play an important role in day to day life. In wireless and wi... more In our world, communication systems play an important role in day to day life. In wireless and wired communication systems, signals are to be upsampled at the transmitter. Digital up converter (DUC) is a sample rate conversion technique which is widely used to increase the sampling rate of an input signal. The digital up converter converts low sampled digital baseband signal to a pass band signal. In this paper, we are going to design and implement a low noise digital up converter on a FPGA (Field Programmable Gate Array). In digital up converter, the input signal is filtered and converted to higher sampling rate and then it is modulated with the carrier signal generated from the direct digital synthesizer (DDS). This system consists of a cascaded integrator comb (CIC) interpolation filter, cascaded integrator comb compensation filter, multiplier and a direct digital synthesizer. The cascaded integrator comb interpolation filter performs upsampling of the input signal and the cascad...

Research paper thumbnail of International Journal of Intellectual Advancements and Research in Engineering Computations Data acqusition system for testing of vertical axis wind turbine

Wind tunnel test bench is one of the important methods to research the characteristics of vertica... more Wind tunnel test bench is one of the important methods to research the characteristics of vertical axis wind turbine (VAWT). To improve the test performance, intelligent test equipment for VAWTs is developed. The whole equipment is divided into three sub system. support and adjustment, intelligent data-acquisition and analysis and loading system, each of them is analyzed and designed. An intelligent test bench is established, with which, the performance of a rotor is tested and analyzed. The results show that the test equipment is simple structured, convenient to manufactured, reliable to operate, and able to intelligently acquire the important data such as wind speed, rotor torque and power etc., which provides an effective way to study the performance of the wind turbines.

Research paper thumbnail of Design and Implementation of Face Detection Using Adaboost Algorithm

Face recognition system is an application for identifying someone from image or videos. Face reco... more Face recognition system is an application for identifying someone from image or videos. Face recognition is classified into three stages ie)Face detection,Feature Extraction ,Face Recognition. Face detection method is a difficult task in image analysis. Face detection is an application for detecting object, analyzing the face, understanding the localization of the face and face recognition.It is used in many application for new communication interface, security etc.Face Detection is employed for detecting faces from image or from videos. The main goal of face detection is to detect human faces from different images or videos.The face detection algorithm converts the input images from a camera to binary pattern and therefore the face location candidates using the AdaBoost Algorithm. The proposed system explains regarding the face detection based system on AdaBoost Algorithm. AdaBoost Algorithm selects the best set of Haar features and implement in cascade to decrease the detection ti...

Research paper thumbnail of Secure Data Aggregation Algorithm in Heterogeneous Wireless Sensor Network

Wireless Sensor Networks (WSN) is comprised of a number of nodes distributed or arranged in a net... more Wireless Sensor Networks (WSN) is comprised of a number of nodes distributed or arranged in a network for a specific function. Sensor node will sense the information and transmitting to a sink node. Due to this a replication of data may store. The data aggregation techniques will aggregate the data and store only a single copy. This paper presents how a new algorithm is proposed to aggregate the data from various sensor nodes with less memory, less communication overhead, less energy, high security. Simulations are conducted to verify the validity of the proposed schemes.

Research paper thumbnail of Control Approach of shunt active power filter for Current compensation

Power system can employ many attractive applications of power electronics technologies for curren... more Power system can employ many attractive applications of power electronics technologies for current compensation. A control approach of shunt active filter is proposed for power quality improvement in three phase distribution system. The shunt active filter is utilized to overcome all current related problems, such as current harmonics, reactive current and current unbalance. The steady state and dynamic operation of control circuit in different load current and utility voltages conditions is studied through simulation results. This method has acceptable dynamic response with a very simple conFigureuration of control circuit.

Research paper thumbnail of A novel design and implementation algorithm for recognition face from very low resolution images

Research paper thumbnail of Intelligent battery management system for fuel Vehicles

Advances in Automobile Engineering, 2020

Sometimes the vehicles wouldn’t start this is due to the battery of the vehicle, more especially ... more Sometimes the vehicles wouldn’t start this is due to the battery of the vehicle, more especially either it’ state of charge (SOC) or its state of health (SOH). The challenge is to devise a user friendly application based battery management tool through which the user can get critical information about the state of charge (SOC) as well as the state of health (SOH) along with the set of actions required to ensure a reliability of the starting is maintained. This application also helps in monitoring the temperature of the car battery. Keywords- state of charge, state of health, battery management system, MQTT protocol. Car Battery is one of the most crucial and essential part of the car elements. The Car battery can majorly hamper your fuel economy drastically. If the car is flat then we have to spend hours to start the car. This will not only waste your time but also exert the engine and decrease the life expectancy. So it is important to monitor and manage the health of the battery. ...

Research paper thumbnail of Brain Tumor Mri Image Segmentation and Detection in Image Processing

International Journal of Research in Engineering and Technology, 2014

Research paper thumbnail of A Study on Parallel and Pipelining Simulation Techniques for Edge Detection and Their Performance Analysis

Journal of Computational and Theoretical Nanoscience, 2019

Real processing components along with component simulators are combined together to construct a n... more Real processing components along with component simulators are combined together to construct a new virtual prototyping system. The increase in component simulators result in degraded performance of the simulation in distributed systems. The speed of simulation can be increased by doing parallel simulation techniques. Prime number test and Image edge detection are chosen to implement the parallel simulation techniques and achieved the expected results while implementing in real time applications. The prime number test calculates the number of processors in a system and the image edge detection can be done in two stages by Canny Edge detection and Sobel Edge detection. The Canny Edge detection is used to detect the edges in the images by using a multi-stage algorithm. The smaller, separable and integer valued filter in images are combined in horizontal and vertical directions by using the Sobel edge detection resulting in reduction of implementation cost. The tool named OpenMP is use...

Research paper thumbnail of Novel Fpga Design and Implementation of Digital Up Converter

International Journal of Research in Engineering and Technology, 2014

Research paper thumbnail of Real Time Implementation of Object Tracking Through Webcam

International Journal of Research in Engineering and Technology, 2014

Research paper thumbnail of Face Recognition Using Relationship Learning Based Super Resolution Algorithm

American Journal of Applied Sciences, 2014

Research paper thumbnail of Detection of Esophageal Cancer with Regions of Interest Analysis of Deep Learning Approaches

Computer vision and automated methods of detection are available in the domain of computer scienc... more Computer vision and automated methods of detection are available in the domain of computer science. The same approaches are implemented in the medical industry for clearer, accurate and immediate results with the same expertise of experienced doctors. Esophageal cancer is the reason for nearly six percent of total fatality. Medically the cancer is termed to be esophageal adenocarcinoma and the regions affected are identified from high dimension endoscopy images captured under white light. Deep learning approaches are proven to produce better accuracy in terms of detection and analysis of esophageal cancer. Conventional neural networks are implemented to perform object detection techniques from the input images. VCG architecture is defined as the backbone of entire model, over which feature extraction techniques are implied to identify the abnormal regions with esophageal cancer. The predominant techniques available in feature detection are single shot multi box detectors, Fast CNN a...

Research paper thumbnail of A novel design and implementation algorithm for recognition face from very low resolution images

Research paper thumbnail of Detection and Classification of Brain Tumor from MR Images Using an Improvised Image Analysis Algorithm

ECS transactions, Apr 24, 2022

Early detection of brain tumour and its classification are predominantly achieved by conventional... more Early detection of brain tumour and its classification are predominantly achieved by conventional methods of image processing and machine learning. Brain tumour, known for its rapid development in terms of size and effects over human health, has to be detected immediately from the onset for an effective diagnosis. Unless a treatment plan is defined to mitigate further growth, there are high chances of fatality. Detecting and classifying processes are an exigent task even for experienced radiologists. Segmentation and feature extraction are traditional image processing techniques used for the purpose. Nowadays, a computer-aided diagnosis system is merged with machine learning and deep learning strategies for distinguishing tumour cells. The proposed system is an investigation of classifying brain tumour in its early stages using enriched feature sets support vector machine classifiers for increasing the precision of accuracy. Dice coefficient was introduced, along with the said methods, to ensure classification accuracy. Enrichment of the features was achieved by area-based analysis with prospective growth metrics on a four quadrants designated on two-dimensional plane. Genetic algorithm with soft computing techniques improvised the classification accuracy. Two standard and open source data sets deployed the proposed model, which resulted in an accuracy of 98%, sensitivity of 92%, and the specificity of 98.1% as an average. The proposed model also consumed lesser time than the conventional standards with respect to detection and classification of brain tumours.

Research paper thumbnail of Extaction of Maximum Power from PV and Wind Energy Sources Using Predictive Control System in Microgrids

ECS transactions, Apr 24, 2022

Research paper thumbnail of Brain Tumor Segmentation through Level Based Learning Model

Computer Systems Science and Engineering

Research paper thumbnail of Detection and Classification of Brain Tumor from MR Images Using an Improvised Image Analysis Algorithm

ECS Transactions

Early detection of brain tumour and its classification are predominantly achieved by conventional... more Early detection of brain tumour and its classification are predominantly achieved by conventional methods of image processing and machine learning. Brain tumour, known for its rapid development in terms of size and effects over human health, has to be detected immediately from the onset for an effective diagnosis. Unless a treatment plan is defined to mitigate further growth, there are high chances of fatality. Detecting and classifying processes are an exigent task even for experienced radiologists. Segmentation and feature extraction are traditional image processing techniques used for the purpose. Nowadays, a computer-aided diagnosis system is merged with machine learning and deep learning strategies for distinguishing tumour cells. The proposed system is an investigation of classifying brain tumour in its early stages using enriched feature sets support vector machine classifiers for increasing the precision of accuracy. Dice coefficient was introduced, along with the said metho...

Research paper thumbnail of Iterative Dense Network using Laplacian Pyramid Model for Blind Super Resolution

2021 IEEE 18th India Council International Conference (INDICON), 2021

The Deep learning-based approach for solving the ill-posed problem of single image super-resoluti... more The Deep learning-based approach for solving the ill-posed problem of single image super-resolution reconstruction (SRR) has achieved tremendous success in recent times. However, not much work is carried out in the direction of blind image super-resolution, where the degradation kernel is said to be unknown. This paper addresses the said problem of blind single image super-resolution reconstruction using an alternative learning approach by training two convolutional neural networks. Most of the available model for blind super-resolution considers a fixed degradation kernel for reconstruction, which leads to drop in performance. Therefore a learnable kernel estimation approach is adopted by using a kernel-estimator network. Further, this estimated kernel is used to generate a super-resolution image using a Generator network. To successfully model the reconstruction of vital features like edges and texture and to learn the inter-pixel dependencies between multi-level feature maps, we employ a densely residual Laplacian attention block (DLA-Block). The proposed method is extensively tested on real image and synthetic image datasets. The experimental results have shown out-performance compared to the state-of-the-art in terms of high reconstruction accuracy as well as PSNR and SSIM.

Research paper thumbnail of International Journal of Intellectual Advancements and Research in Engineering Computations A REVIEW ON PRIVACY PRESERVING DATA PUBLISHING IN DATA MINING

The data mining process of collecting, extracting and storing valuable information is actively do... more The data mining process of collecting, extracting and storing valuable information is actively done by many enterprises now-a-days. Among lots of developments, data mining face hot issues on security, privacy and data integrity. People become embarrassed when adversary tries to know the sensitive information about an individual. Data mining use one of the latest technique called privacy preserving data publishing (PPDP) in the field of data security, which enforces security for the digital information provided by governments, corporations, multinational companies and individuals. This information act as a source of decision making in business. PPDP provides required tools and techniques to secure exchanging and publishing data. PPDP gathers more involvement of research communities because of securing sensitive information belongs to an individual. This survey will be a key of collecting various methods used for preserving and publishing useful data.

Research paper thumbnail of The Catalytic Converter

In our world, communication systems play an important role in day to day life. In wireless and wi... more In our world, communication systems play an important role in day to day life. In wireless and wired communication systems, signals are to be upsampled at the transmitter. Digital up converter (DUC) is a sample rate conversion technique which is widely used to increase the sampling rate of an input signal. The digital up converter converts low sampled digital baseband signal to a pass band signal. In this paper, we are going to design and implement a low noise digital up converter on a FPGA (Field Programmable Gate Array). In digital up converter, the input signal is filtered and converted to higher sampling rate and then it is modulated with the carrier signal generated from the direct digital synthesizer (DDS). This system consists of a cascaded integrator comb (CIC) interpolation filter, cascaded integrator comb compensation filter, multiplier and a direct digital synthesizer. The cascaded integrator comb interpolation filter performs upsampling of the input signal and the cascad...

Research paper thumbnail of International Journal of Intellectual Advancements and Research in Engineering Computations Data acqusition system for testing of vertical axis wind turbine

Wind tunnel test bench is one of the important methods to research the characteristics of vertica... more Wind tunnel test bench is one of the important methods to research the characteristics of vertical axis wind turbine (VAWT). To improve the test performance, intelligent test equipment for VAWTs is developed. The whole equipment is divided into three sub system. support and adjustment, intelligent data-acquisition and analysis and loading system, each of them is analyzed and designed. An intelligent test bench is established, with which, the performance of a rotor is tested and analyzed. The results show that the test equipment is simple structured, convenient to manufactured, reliable to operate, and able to intelligently acquire the important data such as wind speed, rotor torque and power etc., which provides an effective way to study the performance of the wind turbines.

Research paper thumbnail of Design and Implementation of Face Detection Using Adaboost Algorithm

Face recognition system is an application for identifying someone from image or videos. Face reco... more Face recognition system is an application for identifying someone from image or videos. Face recognition is classified into three stages ie)Face detection,Feature Extraction ,Face Recognition. Face detection method is a difficult task in image analysis. Face detection is an application for detecting object, analyzing the face, understanding the localization of the face and face recognition.It is used in many application for new communication interface, security etc.Face Detection is employed for detecting faces from image or from videos. The main goal of face detection is to detect human faces from different images or videos.The face detection algorithm converts the input images from a camera to binary pattern and therefore the face location candidates using the AdaBoost Algorithm. The proposed system explains regarding the face detection based system on AdaBoost Algorithm. AdaBoost Algorithm selects the best set of Haar features and implement in cascade to decrease the detection ti...

Research paper thumbnail of Secure Data Aggregation Algorithm in Heterogeneous Wireless Sensor Network

Wireless Sensor Networks (WSN) is comprised of a number of nodes distributed or arranged in a net... more Wireless Sensor Networks (WSN) is comprised of a number of nodes distributed or arranged in a network for a specific function. Sensor node will sense the information and transmitting to a sink node. Due to this a replication of data may store. The data aggregation techniques will aggregate the data and store only a single copy. This paper presents how a new algorithm is proposed to aggregate the data from various sensor nodes with less memory, less communication overhead, less energy, high security. Simulations are conducted to verify the validity of the proposed schemes.

Research paper thumbnail of Control Approach of shunt active power filter for Current compensation

Power system can employ many attractive applications of power electronics technologies for curren... more Power system can employ many attractive applications of power electronics technologies for current compensation. A control approach of shunt active filter is proposed for power quality improvement in three phase distribution system. The shunt active filter is utilized to overcome all current related problems, such as current harmonics, reactive current and current unbalance. The steady state and dynamic operation of control circuit in different load current and utility voltages conditions is studied through simulation results. This method has acceptable dynamic response with a very simple conFigureuration of control circuit.

Research paper thumbnail of A novel design and implementation algorithm for recognition face from very low resolution images

Research paper thumbnail of Intelligent battery management system for fuel Vehicles

Advances in Automobile Engineering, 2020

Sometimes the vehicles wouldn’t start this is due to the battery of the vehicle, more especially ... more Sometimes the vehicles wouldn’t start this is due to the battery of the vehicle, more especially either it’ state of charge (SOC) or its state of health (SOH). The challenge is to devise a user friendly application based battery management tool through which the user can get critical information about the state of charge (SOC) as well as the state of health (SOH) along with the set of actions required to ensure a reliability of the starting is maintained. This application also helps in monitoring the temperature of the car battery. Keywords- state of charge, state of health, battery management system, MQTT protocol. Car Battery is one of the most crucial and essential part of the car elements. The Car battery can majorly hamper your fuel economy drastically. If the car is flat then we have to spend hours to start the car. This will not only waste your time but also exert the engine and decrease the life expectancy. So it is important to monitor and manage the health of the battery. ...

Research paper thumbnail of Brain Tumor Mri Image Segmentation and Detection in Image Processing

International Journal of Research in Engineering and Technology, 2014

Research paper thumbnail of A Study on Parallel and Pipelining Simulation Techniques for Edge Detection and Their Performance Analysis

Journal of Computational and Theoretical Nanoscience, 2019

Real processing components along with component simulators are combined together to construct a n... more Real processing components along with component simulators are combined together to construct a new virtual prototyping system. The increase in component simulators result in degraded performance of the simulation in distributed systems. The speed of simulation can be increased by doing parallel simulation techniques. Prime number test and Image edge detection are chosen to implement the parallel simulation techniques and achieved the expected results while implementing in real time applications. The prime number test calculates the number of processors in a system and the image edge detection can be done in two stages by Canny Edge detection and Sobel Edge detection. The Canny Edge detection is used to detect the edges in the images by using a multi-stage algorithm. The smaller, separable and integer valued filter in images are combined in horizontal and vertical directions by using the Sobel edge detection resulting in reduction of implementation cost. The tool named OpenMP is use...

Research paper thumbnail of Novel Fpga Design and Implementation of Digital Up Converter

International Journal of Research in Engineering and Technology, 2014

Research paper thumbnail of Real Time Implementation of Object Tracking Through Webcam

International Journal of Research in Engineering and Technology, 2014

Research paper thumbnail of Face Recognition Using Relationship Learning Based Super Resolution Algorithm

American Journal of Applied Sciences, 2014

Research paper thumbnail of Detection of Esophageal Cancer with Regions of Interest Analysis of Deep Learning Approaches

Computer vision and automated methods of detection are available in the domain of computer scienc... more Computer vision and automated methods of detection are available in the domain of computer science. The same approaches are implemented in the medical industry for clearer, accurate and immediate results with the same expertise of experienced doctors. Esophageal cancer is the reason for nearly six percent of total fatality. Medically the cancer is termed to be esophageal adenocarcinoma and the regions affected are identified from high dimension endoscopy images captured under white light. Deep learning approaches are proven to produce better accuracy in terms of detection and analysis of esophageal cancer. Conventional neural networks are implemented to perform object detection techniques from the input images. VCG architecture is defined as the backbone of entire model, over which feature extraction techniques are implied to identify the abnormal regions with esophageal cancer. The predominant techniques available in feature detection are single shot multi box detectors, Fast CNN a...