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.

Energy monitoring by energy audit and supply side management

Abstract: Educational Institutions are often overlooked as a contributor to energy intensive operations in India within the commercial buildings sector. Energy cost is one of the major costs in the institute's budget. Electricity consumption can be reduced with targeted efforts. Resultant energy savings provides a venue for reinvestment within the educational institute itself. Energy audit aims at loss reduction, improvement in energy efficiency and integrated resource planning. The paper gives analysis of energy audit at College of Engineering, Pune-5 (COEP) hostel campus. An attempt is made to simulate Hostel Single Line Diagram with various distributed sources and their combination. A generic program to calculate effective tariff using the different sources has been developed.

Handwritten MODI Character Recognition Using Transfer Learning with Discriminant Feature Analysis

Abstract: “MODI lipi” is one of the ancient scripts of Western India. Considerable work has been reported for various other ancient Indian languages except for MODI lipi. Its structural characteristics and n...

Speech modification for prosody conversion in expressive Marathi text-to-speech synthesis

Abstract: During Expressive speech, the voice conveys intended message as well as basic emotions of the speaker. This work focuses on the development of expressive Text-to-Speech synthesis techniques for a Marathi (spoken in Maharashtra, India) language. The Pitch contour is one of the important properties of speech that is affected by emotional speech. This work presents analysis of Emotional and Neutral Marathi speech from pitch contour. Pitch features derived from emotional speech samples with punctuation marks. Presently, question mark and exclamation mark in text are studied to find prosodic information. First, pitch features derived from emotional speech samples are compared with the features derived from neutral speech. Speaker usually tends to put more emphasis on one particular syllable within a prosodic word. We identify such syllable as the core syllable that can be derived with the punctuation marks. The experimental results showed that the proposed prosody conversion, based on pitch modification and prosodic word detection with punctuation mark, can improve speech quality.

Hydraulic Conductivity Prediction of Saturated Sand-Bentonite Mixtures

Abstract: In this paper, models have been developed to predict the hydraulic conductivity of the saturated bentonite and saturated sand-bentonite mixtures. For these models, free swell void ratio of the bentonite is required which can be obtained using a simple test. It was observed that hydraulic conductivity of the saturated bentonite and saturated sand-bentonite mixtures could be predicted within 5 or 1/5 times of the measured values for most of the cases.

Wind Power Forecasting Using Support Vector Machine Model in RStudio

Abstract: Wind energy has gained a lot of importance in few decades, as it is the cleanest form of renewable energy and available at free of cost. Wind power generation is increasing rapidly due to concerns about global warming and financial incentives from government. With the increased percentage of wind power in power grid, wind power forecasting has become essential to system operator for electric power scheduling and power reserve allocation. Wind power producers can get benefit of wind power prediction while bidding in the electricity market. This paper presents the wind power forecasting model using Support Vector Machine technique. In this model, wind speed, wind direction, air temperature, air pressure and air density are taken as input parameters to build accurate and efficient model. New statistical computing software called RStudio is used to develop prediction model. The model is trained and tested by using data of Dutch Hill Wind Farm available on website of National Renewable Energy Laboratory (NREL). According to results, the model performs significantly better than linear SVM and other regression models of SVM. The model is used to implement one hour ahead wind power forecasting and the results are validated with dataset.