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
Proceedings ArticleDOI
01 Dec 2018
TL;DR: To improve the inconsistency present in the series-parallel connected lithium ion (Li-Ion) cells, a cell balancing scheme based on switch-matrix and forward converter with active clamp driver topology is presented.
Abstract: Battery is the heart of electric vehicle and a way of improving the battery life is to equalize the energy of its cells. This can be done by either dissipating excess energy in the form of heat (passive cell balancing) or charging the low voltage cells through high voltage cells (active cell balancing). This paper presents a practical approach of active cell balancing along with a brief comparative study of passive and active cell balancing techniques. To improve the inconsistency present in the series-parallel connected lithium ion (Li-Ion) cells, a cell balancing scheme based on switch-matrix and forward converter with active clamp driver topology is presented. This cell balancing scheme is based on transferring the energy from the over-charged cell to auxiliary battery and from auxiliary battery to less charged cell. The balancing takes place for one cell at a time and the balancing current can be continuously monitored. The energy transfer efficiency of 90% for charging and 72% for discharging is achieved. The proposed battery management system can be used for communicating the faults generated in the battery pack to the master controller and corrective actions can be taken to avoid the damage to the battery.

9 citations

Journal ArticleDOI
TL;DR: The current state of art of Smart Wheelchairs is reviewed, the future research in this field is discussed and the recent development in the field of Artificial Intelligence, Sensor technologies and Robotics help the growth of wheelchairs with new features.
Abstract: In today’s world there are many disabled persons who find it difficult to perform movements or perform daily activities. This types of persons are mainly dependent on others for their assistance. But they can become self-independent and perform some daily activities on their own with the help of assistive devices. The most widely used assistive devices are Wheelchairs. Wheelchairs is basically a chair fitted with wheels, which can help people move around who cannot walk because of illness, disability or injury. But there are many disabled people with weak limbs and joints who cannot move the wheelchair. Thus, Smart Wheelchair can benefit a lot to them and everyone in society. Smart Wheelchairs are electric powered wheelchairs with many extra components such as a computer and sensors which help the user or guardian accompanying wheelchair to handle it easily and efficiently. The recent development in the field of Artificial Intelligence, Sensor technologies and Robotics help the growth of wheelchairs with new features. This paper is to review the current state of art of Smart Wheelchairs and discuss the future research in this field.

9 citations

Proceedings ArticleDOI
15 Jun 2017
TL;DR: The aim is to design a system which captures the image of the number plate of a vehicle using a camera and the details are being retrieved using the character segmentation which is done by a feature extraction optical character recognition algorithm (OCR).
Abstract: The police forces around the world use vehicle number plate for legal vehicle authorization purposes, to check if a vehicle is registered or licensed. Most of us keep the vehicle papers in the vehicle itself, which is not at all safe in case of theft. In today's world, it is not secure to carry our vehicle papers and wherever we go. Hence, a system must be designed in which it is not necessary to carry our important documents to each and every place for verification. The aim is to design a system which captures the image of the number plate of a vehicle using a camera and the details are being retrieved using the character segmentation which is done by a feature extraction optical character recognition algorithm (OCR). Then the details retrieved from the number plate in text format is used to extract all the important information of the vehicle like, the name of the owner, address of the owner, date of registration of the vehicle etc. from the database. The police can verify whether the documents are fake or not. For us, it is useful as we do not have to carry our documents to every place with the fear of losing them.

9 citations

Proceedings ArticleDOI
16 Oct 2014
TL;DR: This paper proposes a more flexible vision based approach of American sign language recognition where the person is free from additional equipment and a novel technique based on combination of these is derived and proposed here.
Abstract: Sign language is a widely used and accepted standard for communication by people with hearing and speaking impairments. A sign language is a language which uses visually transmitted sign patterns, instead of acoustically conveyed sound patterns, to deliver the meaning. Several ways to generalize the American sign language recognition have been proposed in the past [14] [15]. In this paper, novel method of American sign language recognition with Shape and Texture features has been proposed. Many of the existing systems require the person gesticulating to use special data acquisition devices like data gloves which are expensive and difficult to handle. We proposes a more flexible vision based approach where the person is free from additional equipment. The Shape features and Texture feature are more unique, so a novel technique based on combination of these is derived and proposed here. For extracting shape features standard gradient operator such as Robert, Prewitt, Sobel, Canny, Freichein, Kirsh and Laplace are used and for texture feature vector quantization techniques are used. The gradient mask images of the character images are obtained and then LBG vector quantization algorithm is applied on these gradient images to get the codebooks of various sizes. These obtained LBG codebooks are considered as shape texture feature vectors for American sign language recognition. The database includes 26 for American sign language alphabets taken by 12 different people. The images are saved in a jpeg file format and stored in separate folder. Thus there are total 312 images were use for our project and 8 code book sizes (from 4 to 512). The nearest neighbour (KNN) algorithm is considered as performance comparison criteria for proposed character recognition techniques. The best performance is observed in LBG for codebook size 8 of Canny operator and the next best is seen for codebook sizes 4 of freichein gradient mask for feature extraction. The LBG VQ [11] design algorithm is an iterative algorithm which requires an initial codebook C. This initial codebook is obtained by the splitting method. In this method, an initial code vector is set as the average of the entire training sequence. This code vector is then split into two. The iterative algorithm is run with these two vectors as the initial codebook. The final two code vectors are splitted into four and the process is repeated until the desired number of code vectors is obtained.

9 citations

Journal ArticleDOI
TL;DR: In this article, a dimensional analysis method for predicting the 28-day compressive strength of 53-grade cements is presented, which incorporates the modified Buckingham-pi theorem to formulate a general equation by using only two experimental results.
Abstract: Compressive strength is considered to be the paramount property of cement. However, according to the standard test procedure, the results of a compressive strength test on cement can be known only after 7 or 28 days. To overcome this difficulty, a dimensional analysis method for predicting the 28-day compressive strength of 53-grade cements is presented in this paper. This method incorporates the modified Buckingham-pi theorem to formulate a general equation by using only two experimental results. A unique trial-and-error procedure is presented that generates the universal dimensional analysis formulation, wherein one of the experimental data sets, called the control point, generates the dimensional analysis equation, whereas the other data set, the check point, is used to validate the already formed dimensional analysis equation. The results of dimensional analysis are then compared with the available experimental results. The comparison shows the validity of the method.

9 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