Dr Loganathan R
@svcengg.edu.in
Professor and Computer Science and Engineering
Sri Venkateshwara College of Engineering
RESEARCH INTERESTS
Medical Image Compression, Data Mining, Machine Learning, Wireless Sensor Networks
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Scopus Publications
Suhas G K, Ashwini Singh S, Trupthi V, Keerthishree P V, Deepak N R, and Loganathan R
IEEE
The car business is changing as a result of recent developments in lithium-ion (Li-ion) storage technology. Fully electric cars (EVs) have the greatest range of autonomy and can operate in a variety of driving and environmental conditions. Stated differently, the same State of Charge (SOC) on two similar model EVs does not always equate to the same distance traveled because other factors affect how well the EVs perform, including the driver's style of behavior, the route, and even the State of Health (SOH) of the battery. The ratio of the battery's rated capacity to its current maximum capacity is known as the state of health, or SOH. It is an essential metric for characterizing the level of deterioration in a battery for a fully electric car. It also acts as a critical reference point for assessing the condition of a retired battery and computing its driving range. Support vector regression is used to estimate the state of health (SOH) of lithium-ion batteries, which is essential for their safe and lifetime-optimized operation.
H. L. Chandrakala and R. Loganathan
Computers, Materials and Continua (Tech Science Press)
Mrs. Ismath Unnisa and Dr. Loganathan R.
ENGG Journals Publications
In this work, a hybrid approach which carries the Radial Basis Function Neural Network and Multilayer Perceptron Neural Network have been applied in a cascaded manner to recognize the face and associated emotions. The variability of individual classifier performances has been reduced by providing the ensemble approach. The formation of ensemble has been developed using the intelligent manner with the help of particle swarm optimization. The applied ensemble approach provided the weighted importance of individual entities according to their performances. The proposed ensemble approach has been proven to be useful over the development of ensemble classifier for XOR classification problem. Each face has been carried with a different form of emotion which has been tested and performance was compared against the individual classifier module.
Smitha Kurian and Loganathan Ramasamy
Springer Science and Business Media LLC
Smitha Kurian and Loganathan Ramasamy
EverScience Publications
Mobile Ad Hoc networks (MANET) are resource constrained and operate on the basis of mutual cooperation. As a result, service discovery is one of the essential services of MANET. Service discovery was integrated onto Ad Hoc on Demand Distance Vector (AODV) Routing protocol, since service discovery was best performed at the network layer with minimal control messages. But this integration echoes the security threats of AODV protocol onto the service discovery process. The security of AODV protocol has drawn ample attention and various studies and methodologies are proposed. But most of the proposed techniques either address the flooding attack or the black hole attack but addressing both these issues simultaneously has been a challenge. Since the nodes in the network are resource constrained achieving the security objective with minimal overhead is also a target that needs to be achieved. We propose a trust based methodology at the level of individual node, that avoids the denial of service attack by controlling both the packet dropping attack and the flooding attack of the service discovery extended AODV protocol. This scheme assists in the selection of a safe path between the consumer and the server by ensuring that a cooperative node with high trust is selected at every hop. The trust value of the non-cooperative or flooding nodes is decreased and is thus avoided from safe paths. With simulated experiments it is demonstrated that the proposed system has 4% lesser control message overhead, the service discovery ratio improved by 13% and the service discovery latency was also considerably reduced. Index Terms – Service Discovery, AODV, Flooding Attack, Packet Dropping Attack, Denial of Service, Sleep Deprivation.
Zabiha Khan and R. Loganathan
Springer Singapore
Zabiha Khan and R Loganathan
IEEE
Gastrointestinal (GI) cancer consists of a group of ten cancers that affect the various accessory organs of the digestive system and liver cancer is one of them. In India, it is ranked twelfth in terms of new cases, eight in terms of deaths and increasing as per the Global cancer Observatory data of last year. Like other cancers, it can be cured if detected early. But the diagnostic performance of Computerized Tomography (CT) images for Liver cancer is interpreter-dependent and prone to human errors. Medical image segmentation and analysis of tumor can help in Computer-aided diagnosis (CAD). Automatic Segmenting of liver and tumor is a complex task as it depends on the shape, location, texture and intensity. Therefore, to develop a general-purpose algorithm that fits all is not possible. Both these tasks can be performed either manually or in a semi-automated manner. In this paper we present AutoLiv, automated liver-tumor detection in CT images. In the first stage, threshold-based slope difference differentiation (SDD) technique is used for segmentation of liver and using this in the second stage we carry out tumor detection by alternative fuzzy c-means (AFCM) clustering algorithm. MATLAB based results and manual segmentation results are compared. A close correlation is observed between both the manual and automated approach with very high degree of spatial overlap seen in the regions-of-interest (ROIs) isolated by both methods.
Mrs. Ismath Unnisa, , Dr. Loganathan R, and
Blue Eyes Intelligence Engineering and Sciences Engineering and Sciences Publication - BEIESP
The human face is very sensitive towards inner feelings particularly with different state of mind under various conditions. The facial expression has used in computer vision to understand the human response against stimuli. But the facial expression is also having the nature of variability and controllability hence its complete generalization from a computer vision point of view is very difficult and challenging, though acceptable performances can be achieved. In this paper, a two stage based facial expression recognition model which carry the Principal component analysis as a feature extractor in the first stage and self-adaptive based activation function in feedforward neural network as a classifier in the second stage have applied. Use of principal component analysis reduces the dimension of features while the adaptive slope of transfer function provides another parameter along with weights to change in making learning faster and accurate. Six most dominant state of facial emotion like angry, surprise, sadness, normal, happy and fear have considered in this paper and performances have been tested over variable expressions. The benefit of the proposed model of self-adaptive activation function has verified through the benchmark XOR problem classification.
Chandrakala H L, , Dr. Loganathan R, and
Blue Eyes Intelligence Engineering and Sciences Engineering and Sciences Publication - BEIESP
Cloud computing is that on-demand service in which the computing resources and the information technology like the storage, operating systems, databases, networks, hardware and databases for the whole software of applications have been delivered. Problem Statement: In case of data clouds, there are different algorithms of application which is needed for the various replication algorithms that have been seeking attention recently. This particular distinguishing feature of the algorithm that is simplicity and efficiency of search has been present in case of Harmony Search. Method: The main idea of a replication will be to be able to provide the data replication in several other locations. The Data access will be enhanced using the Data Replication Strategy (DRS). And the decision of where and what the replicate will be NP complete. The work further involves the problem of data replication which has been addressed in cloud using the Harmony search. Result: The harmonized replication performed better in terms of produce bandwidth and saving by about 12.5%. Conclusion: The storage effectiveness has been improved by means of data deduplication and for the experiments, the static, the adaptive and the methods of harmonized replication have been used.
Loganathan
Science Publications
Problem statement: With increasing bandwidth, digital medical image s torage and transmission is a boon to patients and health profe ssionals alike. Medical images are available instan tly and avoid the need to carry the data physically. Po pular imaging techniques extensively used in medicine include X-Ray, Magnetic Resonance Imaging (MRI), Ultrasound and Computed Tomography (CT). The images produced from the above techniques can be segregated into spatial regions with some regions more important for diagnosis compared to other regions. The region of interest for diagnosis is usually a small area comp ared to the whole image captured. Compression techniques play a very important role for fast and efficient transfer of medical images. Lossless comp ression techniques ensure no data loss but have the limitat ions of low compression rate. Lossy compression techniques on the other hand provide better compres sion ratios but the cost of wrong diagnosis is very high. In this study it is proposed to explore multiple co mpression techniques based on Region OF Interest (ROI). Approach: In this study a novel active contour method is pro posed which is adaptive and marks the outer region of interest without edges. Based on the ROI, the active area of interest is compressed using lo ssless compression and the other areas compressed with lossy wavelet compression techniques. Results and Conclusion: Our proposed procedure was applied to different MRI images obtaining overall compression ratios of 70-80% without losing the originality in the ROI.
R Loganathan and Y.S. Kumaraswamy
IEEE
Digital medical images like X-Ray, Magnetic Resonance Imaging (MRI), Ultrasound, Computed Tomography (CT) are extensively used in diagnosis. The ease of storing and transmission of digital medical images is a boon to patients and medical professionals. Due to the large volume of images, image compression is required to accomplish fast and efficient transmission and reduction in storage space of medical images. Compression techniques used are very important while compressing digital medical images as the region of interest for diagnosis is generally small when compared to the whole image captured. Lossless compression techniques compress with no data loss but have low compression rate and lossy compression techniques can compress at high compression ratio but with a slight loss of data. Using lossless techniques in medical image does not give enough advantage in transmission and storage and lossy techniques may lose crucial data required for diagnosis. To maximize compression, in this paper it is proposed to investigate multiple compression techniques based on Region of Interest (ROI). In this paper a novel active contour method is proposed which is adaptive and marks the ROI without edges. The marked area of ROI is compressed using lossless compression and the other areas of the image are compressed using lossy wavelet compression techniques. The proposed procedure when applied on diverse MRI images, achieved an overall compression ratio of 69–81% without loss in the originality of ROI.