National Institute of Technology, Silchar

About: National Institute of Technology, Silchar is a education organization based out in Silchar, Assam, India. It is known for research contribution in the topics: Computer science & Control theory. The organization has 1934 authors who have published 4219 publications receiving 41149 citations. The organization is also known as: NIT Silchar.

The simplest 4-D chaotic system with line of equilibria, chaotic 2-torus and 3-torus behaviour

Abstract: The paper reports the simplest 4-D dissipative autonomous chaotic system with line of equilibria and many unique properties. The dynamics of the new system contains a total of eight terms with one nonlinear term. It has one bifurcation parameter. Therefore, the proposed chaotic system is the simplest compared with the other similar 4-D systems. The Jacobian matrix of the new system has rank less than four. However, the proposed system exhibits four distinct Lyapunov exponents with $$(+, 0, -, -)$$ sign for some values of parameter and thus confirms the presence of chaos. Further, the system shows chaotic 2-torus $$(+,0,0,-)$$ , quasi-periodic $$[(0,0,-,-), (0,0,0,-)]$$ and multistability behaviour. Bifurcation diagram, Lyapunov spectrum, phase portrait, instantaneous phase plot, Poincare map, frequency spectrum, recurrence analysis, 0–1 test, sensitivity to initial conditions and circuit simulation are used to analyse and describe the complex and rich dynamic behaviour of the proposed system. The hardware circuit realisation of the new system validates the MATLAB simulation results. The new system is developed from the well-known Rossler type-IV 3-D chaotic system.

CNN based feature extraction and classification for sign language

Abstract: Hand gesture is one of the most prominent ways of communication since the beginning of the human era. Hand gesture recognition extends human-computer interaction (HCI) more convenient and flexible. Therefore, it is important to identify each character correctly for calm and error-free HCI. Literature survey reveals that most of the existing hand gesture recognition (HGR) systems have considered only a few simple discriminating gestures for recognition performance. This paper applies deep learning-based convolutional neural networks (CNNs) for robust modeling of static signs in the context of sign language recognition. In this work, CNN is employed for HGR where both alphabets and numerals of ASL are considered simultaneously. The pros and cons of CNNs used for HGR are also highlighted. The CNN architecture is based on modified AlexNet and modified VGG16 models for classification. Modified pre-trained AlexNet and modified pre-trained VGG16 based architectures are used for feature extraction followed by a multiclass support vector machine (SVM) classifier. The results are evaluated based on different layer features for best recognition performance. To examine the accuracy of the HGR schemes, both the leave-one-subject-out and a random 70–30 form of cross-validation approach were adopted. This work also highlights the recognition accuracy of each character, and their similarities with identical gestures. The experiments are performed in a simple CPU system instead of high-end GPU systems to demonstrate the cost-effectiveness of this work. The proposed system has achieved a recognition accuracy of 99.82%, which is better than some of the state-of-art methods.

Prediction and optimization of process parameters of green composites in AWJM process using response surface methodology

Abstract: The objective of this paper is to develop a response surface methodology (RSM)-based optimization design for process parameter optimization of abrasive water jet machining (AWJM) process on machining of green composites. The experiments are performed based on the Box-Behnken design, and most optimal parameters are selected using multi-response optimization through desirability. The machining parameters are pressure within the pumping system (PwPS), stand-off distance (SoD), and nozzle speed (NS). The corresponding response parameters that have been identified are surface roughness (Ra) and process time (PT). Additionally, the significance of the developed optimization design has been identified using analysis of variance (ANOVA). Finally, the validity and adequacy of the developed model are done through confirmation tests. The numerical result shows that the optimum process parameters obtained are PwPS (150 MPa), SoD (3.5 mm), and NS (125 mm/min), and also the percentage error in prediction of response parameters is reasonable and comparable with the experimental results. The proposed design can be used as a systematic framework for parameter optimization in environmentally conscious manufacturing processes.

Design and Deployment of UAV-Aided Post-Disaster Emergency Network

Abstract: Designing a reliable, resilient, and quickly deployable emergency communication network is a key challenge for post-disaster management. In this paper, a UAV-assisted emergency Wi-Fi network is proposed to expedite the rescue operations by guiding the survivors to the nearest rescue camp location. Here, the Raspberry PI (RPI) development board, mounted on UAV is considered to form a Wi-Fi chain network over the disaster region. During network set-up, the proposed solutions for the design challenges like UAV synchronization, avoid communication disruption and surveillance data management are the key contributions of this paper. The designed UAV network is capable of doing on-site surveillance and transmitting the data to the relief center for better rescue planning. One major challenge is to alert a survivor about the emergency network, which is addressed by designing a captive portal. Furthermore, to extend the Wi-Fi network, an Android-based application is developed by which each smartphone acts as a relay for its neighbor. Three types of field experiment are carried out to evaluate the performance of the designed prototype. It is found from the field results; the Wi-Fi access point mode and user datagram protocol are more suitable for network design as compared to Ad-Hoc mode and transmission control protocol, respectively. It is also observed from the experiment that the maximum hop distance for the prototype is 280 meters and 290 meters for a Wi-Fi configuration following IEEE 802.11n and IEEE 802.11ac protocol, respectively.