@ksriet.ac.in
Professor / Electrical and Electronics Engineering
K S R Institute for Engineering and Technology
IoT, ADAS, SRM
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Kapil Aggarwal, G. Sreenivasula Reddy, Ramesh Makala, T. Srihari, Neetu Sharma, and Charanjeet Singh
Elsevier BV
Prathipa Ravanappan, Maragatharajan M, Rashika Tiwari, Srihari T, and Lavanya K
Anapub Publications
The ever-increasing amount of network traffic generated by various devices and applications has made it crucial to have efficient methods for analyzing and managing network traffic. Traditional approaches, such as statistical modeling, have yet to be proven enough due to network traffic's complex nature and dynamic characteristics. Recent research has shown the effectiveness of complex network analysis techniques for understanding network traffic patterns. This paper proposes multilayer seasonal autoregressive integrated moving average models for analyzing and predicting network traffic. This approach considers the seasonal patterns and interdependencies between different layers of network traffic, allowing for a more accurate and comprehensive representation of the data. The Multilayer Seasonal Autoregressive Integrated Moving Average (MSARIMA) model consists of multiple layers, each representing a different aspect of network traffic, such as time of day, day of week, or type of traffic. Each layer is modeled separately using SARIMA, a popular time series forecasting technique. The models for different layers are combined to capture the overall behavior of network traffic. The proposed approach has several benefits over traditional statistical approaches. It can capture network traffic's complex and dynamic nature, including short-term and long-term seasonal patterns. It also allows for the detection of anomalies and the prediction of future traffic patterns with high accuracy.
Jeyakumar Ponraj, R. Jeyabharath, P. Veena, and Tharumar Srihari
Elsevier BV
M Pavithra, A Murugesan, K Saranya, T Srihari, K Mohanraj, and M Parimala Devi
IEEE
Combining Linear Discriminant Analysis (LDA) and Primary Component Analysis (PCA) feature extraction techniques to improve the efficacy of the face-centered real-time review approach. The measurement functions used to extract PCA and LDA values must be combined to get scores expressing the degree of similarity. When the total of the values generated from both functions is used, the scores are identical. The combination extractor has the capacity to enhance specific qualities in scanned facial photographs. The Euclidean distance between a subset of the test shots and the templates must be computed in order to determine the template image that most closely resembles the test shots. A comparative study of the user’s facial traits in relation to a database-stored reference image can be used to authenticate an individual’s identity. Based on the assessment of the eleven-user image, it appears that the combination extractor outperforms the single extraction feature. On average, the performance of the proposed methodology outperforms that of using a single extractor. If the performance of a system is proven to be insufficient, one alternative course of action is to implement a facial identification instrument. To achieve better results, it is critical to increase the adaptability and applicability of the time allotted for problem-solving activities.
P. Madasamy, Rajesh Verma, C. Bharatiraja, Barnabas Paul Glady J., T. Srihari, Josiah Lange Munda, and Lucian Mihet-Popa
MDPI AG
The pulse width modulation (PWM) inverter is an obvious choice for any industrial and power sector application. Particularly, industrial drives benefit from the higher DC-link utilization, acoustic noise, and vibration industrial standards. Many PWM techniques have been proposed to meet the drives’ demand for higher DC-link utilization and lower harmonics suppression and noise reductions. Still, random PWM (RPWM) is the best candidate for reducing the acoustic noises. Few RPWM (RPWM) methods have been developed and investigated for the AC drive’s PWM inverter. However, due to the lower randomness of the multiple frequency harmonics spectrum, reducing the drive noise is still challenging. These PWMs dealt with the spreading harmonics, thereby decreasing the harmonic effects on the system. However, these techniques are unsuccessful at maintaining the higher DC-link utilizations. Existing RPWM methods have less randomness and need complex digital circuitry. Therefore, this paper mainly deals with a combined RPWM principle in space vector PWM (SVPWM) to generate random PWM generation using an asymmetric frequency multicarrier called multicarrier random space vector PWM (MCRSVPWM). he SVPWM switching vectors with different frequency carrier are chosen with the aid of a random bi-nary bit generator. The proposed MCRSVPWM generates the pulses with a randomized triangular carrier (1 to 4 kHz), while the conventional RPWM method contains a random pulse position with a fixed frequency triangular carrier. The proposed PWM is capable of eradicating the high-frequency unpleasant acoustic noise more effectually than conventional RPWM with a shorter random frequency range. The simulation study is performed through MATLAB/Simulink for a 2 kW asynchronous induction motor drive. Experimental validation of the proposed MCRSVPWM is tested with a 2 kW six-switch (Power MOSFET–SCH2080KE) inverter power module-fed induction motor drive.
W. Devapriya, C. Nelson Kennedy Babu, and T. Srihari
IEEE
Nowadays the number of vehicle users increasing day by day, so the vehicle manufacture trying to develop higher end vehicle that reduce the complexity during driving. Advance Driver Assists Sytsem is one of such type that provide alert, warning and information during driving. In our proposed method Gaussian filtering, median filtering and connected component analysis are used to detect speed bump. This system go well with the roads that are constructed with proper painting. Several existing method need special hardware, sensors, accelerometer and GPS for detecting speed bump.
W. Devapriya, C. Nelson Kennedy Babu, and T. Srihari
IEEE
In Intelligent Transportation System, Advance Driver Assistance Systems (ADAS) plays a vital role. In ADAS, many research works are done in the area of traffic sign recognition, Forward Collision Warning, Automotive navigation system, Lane departure warning system but an another important area to look through is speed bumps detection. The recognition of speed bump is a safety to a human and a vehicle. Early research in speed bump detection is done with the help of sensors, accelerometer and GPS. In this paper, a novel method is presented to achieve speed bump detection and recognition either to alert or to interact directly with the vehicle. Detection of speed bump is recognized with a help of image processing concepts. This methodology is effortless and simple to implement without the investment of special sensors, hardware, Smartphone and GPS. This procedure suits very well for the roads constructed with proper marking, and can be used in self-driving car.