scispace - formally typeset
Search or ask a question
Institution

College of Engineering, Pune

About: College of Engineering, Pune is a based out in . It is known for research contribution in the topics: Sliding mode control & Control theory. The organization has 4264 authors who have published 3492 publications receiving 19371 citations. The organization is also known as: COEP.


Papers
More filters
Journal ArticleDOI
01 Apr 2016
TL;DR: The designed robust fault tolerant controller with periodic output feedback with multi model approach provides satisfactory stabilization to AUV depth system.
Abstract: Active thruster control is an important problem in AUV. One of the way to tackle this problem is to make the dynamic system like AUV as adaptive and self-controlling. This article discusses the fault tolerant controller design with periodic output feedback for Autonomous Underwater Vehicle using multi model approach. The entire system is modelled in state space. Assuring high degree of reliability and persisting autonomy under thruster failure the controller has to be designed such that the thrust distribution is effectively controlled if any one of the signals and corresponding thrusters fails. The AUV is modelled in six degrees of freedom having six inputs and six outputs. Four thrusters are used for vertical and horizontal movements in AUV. Fault tolerant controller is designed for depth control of AUV, with periodic output feedback gains with multi model approach. To each thruster failure the multi model is presented with the gain matrix having all off diagonal terms zero. The designed robust fault tolerant controller with periodic output feedback with multi model approach provides satisfactory stabilization to AUV depth system.

7 citations

Proceedings ArticleDOI
13 May 2013
TL;DR: This paper reviews and compares some of the available methods to give an insight into the area of query log processing for information retrieval and classifies web query intent based on knowledge extraction from query log analysis.
Abstract: Query log is the pouch of valuable information that records user's search queries and related actions on the internet. By mining the recorded information, it is possible to exploit the user's underlying goals, preferences, interests, search behaviors and implicit feedback. The wealth of mined information can be used in many applications such as query log analysis, query recommendation, query reformulation, query intent identification and many more to improve performance of search engine by providing more relevant results. Over the past decade, there has been tremendous work done for improving search engine results to flourish the users for searching. This paper reviews and compares some of the available methods to give an insight into the area of query log processing for information retrieval. Our approach classifies web query intent based on knowledge extraction from query log analysis.

7 citations

Proceedings ArticleDOI
01 Dec 2017
TL;DR: This paper has studied different papers on Tsunami detection and alert system for the survey and has recommended different techniques, algorithms, protocols proposed by authors using IoT for solving these problems.
Abstract: Internet of Things (IoT) is the connectivity between the numbers of devices in the network. In which different types of devices, sensors, software, embedded devices are connected to each other for information sharing and exchange. In different applications, IoT technology is used for communication and data exchange between the two or more stations or devices. IoT technology is used in various application and fields like Transport, business, home automation and education. Tsunami detection is also one of the major problems, which is solved by using IoT. Tsunami alert and detection are important for avoiding the human death. So to solve these problems different techniques, algorithms, protocols are proposed by authors using IoT. In this paper, we have studied different papers on Tsunami detection and alert system for the survey. This paper is very helpful for new researchers and IoT learners.

7 citations

Journal ArticleDOI
TL;DR: The experiment reveals that hand radiographs contain biometric information that can be used to identify humans in disaster victim identification and indicates that the proposed approach is significantly effective than conventional methods for the person authentication using hand radiograph based human authentication.
Abstract: Biometric radiographs have gained importance in recent times owing to the rise in crime and disaster incidents. In recent times, authentication and identification of a person has become an essential part of most of the computer vision automation systems. Conventional fingerprint, iris, face, palm prints fail to recognize the human when the external biometric parts have been damaged due to rashes, wounds, and severe burning. Security, robustness, privacy, and non-forgery are the critical aspects of any person authentication system. In such situations, identification based on radiographs of the skull, hand, and teeth are effective replacement methods. In this paper, a novel forensic hand radiograph based human authentication is proposed using a deep neural network. Three-layered convolutional deep neural network architecture is used for the feature extraction of hand radiographs and for recognition; KNN and SVM classifiers are used. As a part of the experimentation, a total of 750 hand radiographs acquired from 150 subjects of different age groups, professions, and gender are considered. The performance of the algorithm is evaluated based on cross-validation accuracy by varying striding pixels, polling window size, kernel size, and the number of filters. Our experiment reveals that hand radiographs contain biometric information that can be used to identify humans in disaster victim identification. The experimental study also indicates that the proposed approach is significantly effective than conventional methods for the person authentication using hand radiographs.

7 citations

Proceedings ArticleDOI
01 Aug 2018
TL;DR: A dynamic traffic system that takes in present traffic footage and calculates the percentage congestion and based on this, allocates the timer to each signal and consists of a prediction mechanism based on clustering, capable of predicting the congestion based on previous observable patterns.
Abstract: Traffic around the world has become a major problem and with a sharp increase in the number of vehicles, there is a dire need for systems that can adapt towards the changes in traffic. The inability of current systems to deal with this increased traffic leads to inefficient traffic management. The current static traffic systems do not account for the present congestion and current scenario of traffic. The paper proposes a dynamic traffic system that takes in present traffic footage and calculates the percentage congestion and based on this, allocates the timer to each signal. The system makes use of the Image Processing techniques like background subtraction, edge detection in order to process the video. The system also consists of a prediction mechanism based on clustering, which is capable of predicting the congestion based on previous observable patterns. The image processing algorithm along with the prediction mechanism, process each frame into a value, the congestion percentage. The system is implemented on Raspberry Pi 0 W's and makes use of the OpenCV library for image processing.

7 citations


Authors

Showing all 4264 results

Network Information
Related Institutions (5)
Amrita Vishwa Vidyapeetham
11K papers, 76.1K citations

89% related

National Institute of Technology, Karnataka
7K papers, 70.3K citations

86% related

National Institute of Technology, Rourkela
10.7K papers, 150.1K citations

86% related

National Institute of Technology, Tiruchirappalli
8K papers, 111.9K citations

86% related

Performance
Metrics
No. of papers from the Institution in previous years
YearPapers
202227
2021491
2020323
2019325
2018373
2017334