V. Muneeswaran

Bio: V. Muneeswaran is an academic researcher from Kalasalingam University. The author has contributed to research in topics: Computer science & Image compression. The author has an hindex of 11, co-authored 23 publications receiving 216 citations.

Programmed Multi-Classification of Brain Tumor Images Using Deep Neural Network

Abstract: Identification of brain tumors attends a critical role in evaluating tumors and making decisions about care as per their grades Several imaging methods are employed to identify brain tumors Though, leading to its excellent image quality and the reality that it depends on no cosmic radiation, MRI is widely utilized Deep learning (DL) is a computer vision field of study and has shown remarkable output currently, notably in classification and segmentation issues This article proposes, DL design based on a Convolution Neural Network (CNN) to identify various types of brain tumors leveraging two publicly accessible resources or databases The previous identify tumors into (Meningioma, Glioma, and Pituitary tumors) Another one distinguishes between all three categories (Grade II, Grade III, and Grade IV)

Competent Ultra Data Compression By Enhanced Features Excerption Using Deep Learning Techniques

Abstract: The objective of data compression is to extract the main features of the data and to restore the decompressed data from latent space ie, compressed data without any quality or noise In this paper, a Convolutional LSTM model is proposed to reduce the redundancy data and unnecessary information in the data set The proposed methodology normalizes the picture to reduce blur and noises, with a compression ratio of 50% The Convolutional LSTM model is compared with other models such as autoencoder, denoising autoencoder, convolutional neural network and our present work shows better RMSE compared to the other models Datasets like MNIST and other datasets are used for testing and training the images

VLSI Implementation of Image Compression using TSA Optimized Discrete Wavelet Transform Techniques

Abstract: The Discrete Wavelet transform is one of the best tools for signal and data analysis, It requires efficient hardware implementation in the real-time applications. The submissions established in the field of imaging necessitates compacted architecture. In DWT discrete sampling is accomplished for the wavelets. In this paper, the VLSI implementation of HAAR wavelet-based image compression is proposed and designed. HAAR wavelet transform is one of the easiest methods for image compression because it has coefficients as either 1 or −1. In this work software alone is used for the compression together with optimizing it with a continuous optimization algorithm and provides a hardware-free architecture with low cost. The VHDL work is carried out in Xilinx Platform and provides a truncated power architecture for a concrete application. The same VHDL architecture can also be instigated in FPGA which will harvest hardware effectual compromising outcomes.

A Framework for Data Analytics-Based Healthcare Systems

Abstract: In this modern techno-world, the term data is unavoidable and certainly, nothing is possible without its usage. The trends about how to analyse the data are the need of the hour. Data analytics is becoming a future escalating tool of all industries including medicine, robotics, etc. This article briefly explains how data analytics is used in healthcare systems. Health care is the process of maintaining and improving the health of an individual by preventing, diagnosing and treating the diseases, illness and other physical and mental imbalances in people. Data analytics is classified into four types and they are descriptive, diagnostic, predictive and prescriptive analysis. Health care makes use of prescriptive analysis to arrive at the best results and make better decisions. Big data plays a major role in data analytics. It helps the data analysts to collect data from the patients and store them efficiently. After the completion of this whole article, the reader will be able to get the collective idea about health care analytics.

Analysis of Cyberattacks and its Detection Mechanisms

Abstract: With the help of Internet, there are tremendous innovations and developments in technologies. Most of the business organizations are forced to use the flexible and modern network technologies for business processing. This opens the door for cyber criminals to initiate cyberattacks to disrupt the business process. There are lot of reasons behind these cyberattacks like stealing login credentials, financial information and confidential information, disrupting the services available to legitimate users and to gain unauthorized access. To defend against cyberattacks, several mechanisms were proposed by researchers. In this paper, we analyzed about different types of cyberattacks and detection mechanisms to defend against those attacks. We also analyzed about different datasets and evaluation metrics used to evaluate the performance of every detection mechanism.

Programmed Multi-Classification of Brain Tumor Images Using Deep Neural Network

Abstract: Identification of brain tumors attends a critical role in evaluating tumors and making decisions about care as per their grades Several imaging methods are employed to identify brain tumors Though, leading to its excellent image quality and the reality that it depends on no cosmic radiation, MRI is widely utilized Deep learning (DL) is a computer vision field of study and has shown remarkable output currently, notably in classification and segmentation issues This article proposes, DL design based on a Convolution Neural Network (CNN) to identify various types of brain tumors leveraging two publicly accessible resources or databases The previous identify tumors into (Meningioma, Glioma, and Pituitary tumors) Another one distinguishes between all three categories (Grade II, Grade III, and Grade IV)

Brain-Controlled Adaptive Lower Limb Exoskeleton for Rehabilitation of Post-Stroke Paralyzed

Abstract: Stroke is a standout amongst the most imperative reasons of incapacity on the planet. Due to partial or full paralysis, the majority of patients are compelled to rely upon parental figures and caregivers in residual life. With post-stroke rehabilitation, different types of assistive technologies have been proposed to offer developments to the influenced body parts of the incapacitated. In a large portion of these devices, the clients neither have control over the tasks nor can get feedback concerning the status of the exoskeleton. Additionally, there is no arrangement to detect user movements or accidental fall. The proposed framework tackles these issues utilizing a brain-controlled lower limb exoskeleton (BCLLE) in which the exoskeleton movements are controlled based on user intentions. An adaptive mechanism based on sensory feedback is integrated to reduce the system false rate. The BCLLE uses a flexible design which can be customized according to the degree of disability. The exoskeleton is modeled according to the human body anatomy, which makes it a perfect fit for the affected body part. The BCLLE system also automatically identifies the status of the paralyzed person and transmits information securely using Novel-T Symmetric Encryption Algorithm (NTSA) to caregivers in case of emergencies. The exoskeleton is fitted with motors which are controlled by the brain waves of the user with an electroencephalogram (EEG) headset. The EEG headset captures the human intentions based on the signals acquired from the brain. The brain-computer interface converts these signals into digital data and is interfaced with the motors via a microcontroller. The microcontroller controls the high torque motors connected to the exoskeleton's joints based on user intentions. Classification accuracy of more than 80% is obtained with our proposed method which is much higher compared with all existing solutions.

Indigenous Health Tracking Analyzer Using IoT

Abstract: Nowadays, Health care is considered as an important aspect of our everyday lives. To address the emerging health-related challenges, this research wprk has utilised the advanced digital technologies to develop a health tracking analyzer. Recently, the use of mobile phones and other gadgets has increased unprecedentedly by creating a significant impact on the mobile health care. Mobile Health applications serve a large number of consumers. The main aim of this research work is to create a health tracking analyzer so that any patient or anybody who is concerned about their health may be readily tracked by their doctors or health care providers. This loT -based device aids in critical situations by avoiding illness transmission and providing health diagnoses even when the doctor is at a considerable distance away from the patient. Many people are receiving therapy for a variety of issues, including heart disease. The proposed model plays a vital role in checking and storing the healthcare-related data in server by using a Wi-Fi Module. Furthermore, the proposed device tracks the heartbeat and temperature by using the detectors and also a microcontroller is attached to the sensor. To frequently update the condition of patient's, the microcontroller is linked with LCD display and Wi-Fi to transfer the information to the database. By employing an inter connection, the pulse rate and temperature can also be analyzed. The gadget will exchange the readings from the sensor to the cloud and the information gathered will also remain accessible. The proposed database analyzes the received information and alerts the patient through buzzer.

Competent Ultra Data Compression By Enhanced Features Excerption Using Deep Learning Techniques

Abstract: The objective of data compression is to extract the main features of the data and to restore the decompressed data from latent space ie, compressed data without any quality or noise In this paper, a Convolutional LSTM model is proposed to reduce the redundancy data and unnecessary information in the data set The proposed methodology normalizes the picture to reduce blur and noises, with a compression ratio of 50% The Convolutional LSTM model is compared with other models such as autoencoder, denoising autoencoder, convolutional neural network and our present work shows better RMSE compared to the other models Datasets like MNIST and other datasets are used for testing and training the images