Manikandaprabu Nallasivam

Manikandaprabu Nallasivam

Auto-generated profile, based on publicly available information

Manikandaprabu Nallasivam

Nandha Engineering College

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 September 2024 in Cellulose Chemistry and Technology
Verified
Journal Article
Closed access
SKShettahalli Mantaiah Vinu Kumar
Shettahalli Mantaiah Vinu Kumar
RJRengaraj Jeyakumar
Rengaraj Jeyakumar
NMNallasivam Manikandaprabu
Nallasivam Manikandaprabu
CSChandrasekaran Sasikumar
Chandrasekaran Sasikumar
Flax reinforced epoxy (F-Ep) composites were prepared by the compression moulding technique, varying the fiber content (0, 25, 35 and 45 wt%). The free vibration test was performed on the neat epoxy and F-Ep composites to understand their dynamic characteristics, and results showed that natural frequency and damping factor of the F-Ep composites increased with an increase in the fiber content. The F-Ep composite (45F-Ep) that exhibited better damping was selected for performing the drilling operation. Factors such as spindle speed (rpm), feed rate (mm/min) and drill point angle (degree) were chosen as input parameters and the tabulated set of experiments were in accordance with Taguchi’s design of experiment. The response measured was thrust force and the obtained values were found in the range of 19.66 to 50.75 N. The minimum value of thrust force was achieved when the F-Ep composite was drilled at high spindle speed (3000 rpm), with a feed rate of 75 mm/min using the drill point angle of 118°. ANOVA analysis showed that the developed regression model was significant and thrust force was mainly influenced by the spindle speed. Mathematical models were developed for drilling F-Ep composite using response surface methodology (RSM) and adaptive neuro fuzzy inference system (ANFIS) and compared for their efficacy.

24 April 2022 in ECS Transactions
Verified
Journal Article
Closed access
MNManikandaprabu Nallasivam
Manikandaprabu Nallasivam
SRSaravanavasan R.
Saravanavasan R.
VAVignesh A.
Vignesh A.
NSNandhu S.
Nandhu S.
Electricity is one of the essential needs of human. It's commonly used for domestic, industrial, and agricultural purposes in day-to-day life. Most folks know the role of the energy meter within the electricity grid. It’s a fundamental component of the distribution grid. The energy meter helps the utility (electricity distribution company) to account for the utilization of electricity by the buyer on a KW per hour basis. To know this we want to seek out the drawbacks of the present energy meter, and therefore the biggest problem in electricity metering. The most important problem in electricity distribution is collecting meter reading data. Straight away meter reading is collected manually, which provides scope for corruption and human error in reading. It is the wastage of manpower and utility of resources. Our existing electricity meter isn't tamper-proof. There is to several temper cases are detected. In the existing meter, there is no under voltage and over voltage protection, as well as there is no over power use alert system. Because of these problems, the utility is unable to gather a fine for max demand cross. Power theft is the biggest problem in recent days, which causes a lot of loss to electricity boards. To overcome these drawbacks, the IoT-based Smart Energy Meter (SEM) is developed.

1 January 2014
Verified
Conference Paper
Closed access
GLG. Lalli
G. Lalli
NMN. Manikandaprabu
N. Manikandaprabu
DKD. Kalamani
D. Kalamani
MARIMUTHU C NMARIMUTHU C N
MARIMUTHU C N
Thermography is considered as the most effective method for the detection of breast cancers. However, it is difficult for radiologists to predict Photomicrograph of Microcalcification clusters. Therefore, we have developed a computerized scheme for predicting early-stage microcalcification clusters in thermogram images. The gray and color channels of a thermogram image are enhanced by Contrast Limited Adaptive Histogram Equalization (CLAHE).Optimal set of features selected by Genetic algorithm are fed as input to Adaptive Neuro-Fuzzy Inference System (ANFIS) for classification of images into normal, suspect and abnormal categories. The method has been evaluated on real time images comprising normal and abnormal images. The performance of the proposed technique is analyzed in terms convergence time. Experimental results shows that the features used are clinically significant for the accurate detection of breast cancer related tumor.

28 November 2022 in U.Porto Journal of Engineering
Verified
Journal Article
Open access
PDF file
MNManikandaprabu Nallasivam
Manikandaprabu Nallasivam
VSVijayachitra Sivakumar
Vijayachitra Sivakumar
Detecting and discriminating humans in video frames for surveillance applications is a demanding task. Identifying and highlighting humans by eliminating shadows from the video frames is vital for prudence motive. In this paper, a three-step procedure is proposed, which includes motion detection by background subtraction in live video frames, morphological gradient-based shadow removal, and human detection by Hybrid Feature Set (HFS), which comprises Histogram Oriented Gradient (HOG) and Local Binary Pattern (LBP) with adaptive Neuro-Fuzzy inference system. The first step incorporates static background subtraction and dynamic background subtraction. The second step is to remove shadows by using a morphological gradient with the horizontal directional mask. The third step includes near-field, mid-field, and far-field human detection by using an adaptive Neuro-Fuzzy inference system. The results obtained from the various performed experimental analysis demonstrates diverse parametrical measures, which outperforms comparatively when benchmark databases and real-time surveillance video frames were used.

24 April 2022 in ECS Transactions
Verified
Journal Article
Closed access
MNManikandaprabu Nallasivam
Manikandaprabu Nallasivam
FDFemi D
Femi D
RJRaja Paulsingh J
Raja Paulsingh J
A novel prediction-based Reversible Steganographic scheme based on image inpainting can be optimized by choosing the reference pixels using optimization technique. Partial differential equations based on image inpainting are introduced to generate a prediction image, from the reference image that has similar structural and geometric information as the cover image. Then the histogram of the prediction error is shifted to embed the secret bits reversibly using two selected sets of peak points and zero points. From the stego image, the cover image can be restored losslessly after extracting the embedded bits correctly. Since the same reference pixels can be exploited in the extraction procedure, the embedded secret bits can be extracted. Through optimization of reference pixels selection and the inpainting predictor, the prediction accuracy is high, and more embeddable pixels are acquired with greater embedding rate and better visual quality, and reduced time required for the stego00 image generation.

10 May 2026 in Cellulose Chemistry and Technology
Verified
Journal Article
Closed access
MNManikandaprabu Nallasivam
Manikandaprabu Nallasivam
SKShettahalli Mantaiah Vinu Kumar
Shettahalli Mantaiah Vinu Kumar
CSChandrasekaran Sasikumar
Chandrasekaran Sasikumar
DPDr Rishi J P
Dr Rishi J P
In this study, flax fiber reinforced epoxy (FFRE) composites were fabricated using the hand layup method. The effects of spindle speed (900, 1800, 2700 rpm), feed rate (70, 90, 110 mm/min), and end mill cutters (6, 8, 10 mm) on milling behavior were analyzed. Milling tests were conducted on a vertical CNC machine for a 2 mm constant depth of cut. Experimental details followed Taguchi’s L27 orthogonal array, where cutting force and surface roughness (Ra) were evaluated as output responses. The investigation revealed that cutting force increased with the increase in the feed rate, but decreased as spindle speed was increased. Better surface quality of the milled surface in terms lower cutting force and surface roughness value was achieved at the optimal input conditions. Artificial neural network (ANN) models with different architectures were implemented to predict the cutting force and surface roughness. The analysis showed that predicted values were in close agreement with the experimental results and exhibited a maximum error deviation of ±5%, particularly when 3-5-4-1, and 3-5-4-2 ANN models (Purelin-Purelin-Purelin Transfer function) were employed for single and dual output respectively. The accuracy of the aforesaid models was measured in terms of highest R2 value and lowest mean absolute percentage error (MAPE). Field emission scanning electron microscopy (FESEM) images of the machined surface exposed matrix damage, cavity formation, fiber pull-out, and micro-tear.