Papers by Dr.Senthil Singh
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.
ECS transactions, Apr 24, 2022
Computer Systems Science and Engineering
Brain tumors are potentially fatal presence of cancer cells over a human brain, and they need to ... more Brain tumors are potentially fatal presence of cancer cells over a human brain, and they need to be segmented for accurate and reliable planning of diagnosis. Segmentation process must be carried out in different regions based on which the stages of cancer can be accurately derived. Glioma patients exhibit a different level of challenge in terms of cancer or tumors detection as the Magnetic Resonance Imaging (MRI) images possess varying sizes, shapes, positions, and modalities. The scanner used for sensing the location of tumors cells will be subjected to additional protocols and measures for accuracy, in turn, increasing the time and affecting the performance of the entire model. In this view, Convolutional Neural Networks deliver suitable models for efficient segmentation and thus delivered promising results. The previous strategies and models failed to adhere to diversity of sizes and shapes, proving to be a well-established solution for detecting tumors of bigger size. Tumors tend to be smaller in size and shape during their premature stages and they can easily evade the algorithms of Convolutional Neural Network (CNN). This proposal intends to furnish a detailed model for sensing early stages of cancer and hence perform segmentation irrespective of the current size and shape of tumors. The size of networks and layers will lead to a significant weightage when multiple kernel sizes are involved, especially in multiresolution environments. On the other hand, the proposed model is designed with a novel approach including a dilated convolution and level-based learning strategy. When the convolution process is dilated, the process of feature extraction deals with multiscale objective and level-based learning eliminates the shortcoming of previous models, thereby enhancing the quality of smaller tumors cells and shapes. The level-based learning approach also encapsulates the feature reconstruction processes which highlights the sensing of small-scale tumors growth. Inclusively, segmenting the images is performed with better accuracy and hence detection becomes better when compared to that of hierarchical approaches.
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...
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.
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.
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...
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.
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...
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.
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.
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. ...
International Journal of Research in Engineering and Technology, 2014
Image processing is an active research area in which medical image processing is a highly challen... more Image processing is an active research area in which medical image processing is a highly challenging field. Medical imaging techniques are used to image the inner portions of the human body for medical diagnosis. Brain tumor is a serious life altering disease condition. Image segmentation plays a significant role in image processing as it helps in the extraction of suspicious regions from the medical images. In this paper we have proposed segmentation of brain MRI image using K-means clustering algorithm followed by morphological filtering which avoids the misclustered regions that can inevitably be formed after segmentation of the brain MRI image for detection of tumor location.
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...
International Journal of Research in Engineering and Technology, 2014
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 cascaded integrator comb compensation filter is used to compensate the losses of CIC filter by filtering the input signal. The multiplier is used for multiplying the upsampled signal from CIC filter with the carrier signal generated from DDS and gives the DUC output. In this DUC, the input signal is upsampled at the rate of eight. Here, two digital up converters are used and connected with an adder in order to obtain a low noise output signal. The coding of this work is done in VHDL. The simulation and functional verification is carried out using Xilinx ISE and FPGA implementation is carried out using Virtex 5.
International Journal of Research in Engineering and Technology, 2014
Real time object detection and tracking is an important task in various computer vision applicati... more Real time object detection and tracking is an important task in various computer vision applications. For robust object tracking the factors like object shape variation, partial and full occlusion, scene illumination variation will create significant problems. We introduce object detection and tracking approach that combines Prewitt edge detection and kalman filter. The target object's representation and the location prediction are the two major aspects for object tracking this can be achieved by using these algorithms. Here real time object tracking is developed through webcam. Experiments show that our tracking algorithm can track moving object efficiently under object deformation, occlusion and can track multiple objects.
American Journal of Applied Sciences, 2014
The face recognition is an application which is for identifying a person from a digital image. Th... more The face recognition is an application which is for identifying a person from a digital image. The common problem that often occurs while identifying the face from image is due to the low resolution in images especially when it is captured from a long distance. In automated face recognition system, this has always been a challeging problem. To overcome this problem, an approach is proposed to learn the high resolution face and the VLR image face for face. In this new approach the face recognition applications under the VLR problem is designed for good visuality. To create the Very Low Resolution (VLR) image corresponding to each of these High Resolution (HR) images, the HR images are resized to 64×48 pixels. The Very Low Resolution (VLR) of the face image is lower than 16×12 pixels. The proposed system is implemented in MATLAB. The performance of the proposed system is tested. The proposed system is highly accurate and extremely fast in processing the image data. Experimental results show that proposed method outperforms existing methods. The new data constraint that measures the error in the HR image space was developed and RLSR was proposed.
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...
Uploads
Papers by Dr.Senthil Singh