Vidyalankar Institute of Technology

About: Vidyalankar Institute of Technology is a based out in . It is known for research contribution in the topics: The Internet & Deep learning. The organization has 479 authors who have published 293 publications receiving 868 citations.

CAVE: An Emerging Immersive Technology -- A Review

Abstract: Currently, the CAVE (Cave Automatic Virtual Environment) systems are one of the best virtual reality (VR) immersive devices available for portraying the virtual environment. The CAVE gives the illusion of being surrounded by a fictional world, providing a fully interactive, scientific visualization. The CAVE systems can provide a completely new dimension to scientific experimentation as well as entertainment. At the same time, the CAVE systems are a work-in-progress, with CAVE2 having improvements to reduce the complexity, high costs, and cumbersome hardware required by the original CAVE systems. In this paper, we give a system overview of the CAVE systems, its applications and enhancements.

Cucumber disease detection using artificial neural network

Abstract: India is an agricultural country; wherein most of the population depends on agricultural products. Disease on any plants leads to the considerable reduction in both the quality and quantity of agricultural products. Thus detection and diagnosis of disease at the right time is essential to the farmer. Accurate detection and identification of crop diseases plays an important role in effectively controlling and preventing diseases for sustainable agriculture and food security. For detecting crop disease early and accurately, a system is developed using image processing techniques and artificial neural network. The system mainly includes various concepts related to image processing such as image acquisition, image pre-processing, feature extraction, creating database and classification by using artificial neural network. In the proposed work, database is a collection of various texture features of cucumber leaves.

Objects Talk - Object Detection and Pattern Tracking Using TensorFlow

Abstract: Objects in household that are frequently in use often follow certain patterns with respect to time and geographical movement. Analysing these patterns can help us keep better track of our objects and maximise efficiency by minimizing time wasted in forgetting or searching for them. In our project, we used TensorFlow, a relatively new library from Google, to model our neural network. The TensorFlow Object Detection API is used to detect multiple objects in real-time video streams. We then introduce an algorithm to detect patterns and alert the user if an anomaly is found. We consider the research presented by Laube et al., Finding REMO-detecting relative motion patterns in geospatial lifelines, 201–214, (2004)[1].

Health Monitoring System Using Internet of Things

Abstract: Healthcare has become one of the principal issue with the rise in human population and medical expenditure. For a healthy life, it is essential to follow human body's vital signals. Continuous Monitoring of patient's vital signals cannot be provided outside hospital. As it is hard to monitor the patient's condition for 24 hours, it was proposed in this paper to observe continuously the condition of patient despite the patient being busy with his routine and to screen the health status to the doctors through Internet of Things. This paper proposes health monitoring system using non-intrusive biomedical sensors that measure five parameters like ECG, heartbeat, respiration, temperature and blood pressure. Proposed method makes use of Arduino Mega Controller to which non-invasive biomedical sensors are connected. The output is displayed on any digital monitoring system using Arduino Mega. The data obtained from the sensors is uploaded to the ThingSpeak cloud to store and to access patient's information by their doctors or by the concerned for necessary follow-ups in real-time. IoT is a powerful domain where sensors can connect and data is viewed over the Internet.

Automorphism group of the complete transposition graph

Abstract: The complete transposition graph is defined to be the graph whose vertices are the elements of the symmetric group $$S_n$$Sn, and two vertices $$\alpha $$? and $$\beta $$β are adjacent in this graph iff there is some transposition (i, j) such that $$\alpha =(i,j) \beta $$?=(i,j)β. Thus, the complete transposition graph is the Cayley graph $$\mathop {\mathrm {Cay}} olimits (S_n,S)$$Cay(Sn,S) of the symmetric group generated by the set S of all transpositions. An open problem in the literature is to determine which Cayley graphs are normal. It was shown recently that the Cayley graph generated by four cyclically adjacent transpositions is non-normal. In the present paper, it is proved that the complete transposition graph is not a normal Cayley graph, for all $$n \ge 3$$n?3. Furthermore, the automorphism group of the complete transposition graph is shown to equal $$\begin{aligned} \mathop {\mathrm {Aut}} olimits (\mathop {\mathrm {Cay}} olimits (S_n,S)) = (R(S_n) \rtimes \mathop {\mathrm {Inn}} olimits (S_n)) \rtimes \mathbb {Z}_2, \end{aligned}$$Aut(Cay(Sn,S))=(R(Sn)?Inn(Sn))?Z2,where $$R(S_n)$$R(Sn) is the right regular representation of $$S_n$$Sn, $$\mathop {\mathrm {Inn}} olimits (S_n)$$Inn(Sn) is the group of inner automorphisms of $$S_n$$Sn, and $$\mathbb {Z}_2 = \langle h \rangle $$Z2=?h?, where h is the map $$\alpha \mapsto \alpha ^{-1}$$???-1.