College of Engineering, Pune

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

A review of techniques for extraction of cardiac artifacts in surface EMG signals and results for simulation of ECG-EMG mixture signal

Abstract: The electromyography (EMG) is a technique used for recording and analysis of the signals generated due to electrical activity of skeletal muscles. These signals are also called as myoelectric signals. EMG is used as an evaluation tool in the fields such as applied research, physiotherapy, sports training etc. The surface electromyography (sEMG) allows information regarding overall muscle function and conduction. For this, the electrodes are placed on the surface of the skin to obtain the myoelectric signal. When EMG is performed on specific muscles such as shoulder muscles and upper trunk or it is recorded in monopolar configuration, most of the times it is contaminated by electrocardiogram (ECG) signal. This cardiac artifact is difficult to avoid. Therefore, to extract appropriate and qualitative information of the EMG signal, it is essential to extract cardiac artifacts from it and obtain pure EMG signal. A review of techniques used for this are discussed. Also, the simulation results for ECG-EMG mixture are included.

Effect of EGR on the Exhaust Gas Temperature and Exhaust Opacity in Compression Ignition Engines Using Jatropha Oil as Fuel

Abstract: Diesel engines are widely used as power sources for medium and heavy-duty applications because of their lower fuel consumption and lower emissions of carbon monoxide (CO) and unburned hydrocarbons (HC) compared with gasoline engines Efficient use of natural resources is one of the fundamental requirements for any country to become self-sustainable Both in organized and unorganized sectors internal combustion engine has become an indispensable prime mover With the increasing demand on the use of fossil fuels, a stronger threat to clean environment is being posed as the burning of fossil fuels is associated with emissions like CO2, CO, SOx, NOx and particulate matter, which are currently the dominant global source of emissions In diesel engines, NOx formation is a highly temperature-dependent phenomenon Therefore, in order to reduce NOx emissions in the exhaust, it is necessary to keep peak combustion temperatures under control Exhaust gas recirculation is the most important technique for reducing NOx emissions Re-circulating part of the exhaust gas helps in reducing NOx, but appreciable particulate emissions are observed at high loads, hence there is a trade-off between NOx and smoke emission To get maximum benefit from this trade-off, a particulate trap may be used to reduce the amount of unburnt particulates in EGR, which in turn reduce the particulate emission also An experimental investigation was conducted to observe the effect of exhaust gas re-circulation on the exhaust gas temperatures and exhaust opacity The experimental setup for the proposed experiments was developed on a single-cylinder, direct injection, air-cooled, compression ignition engine A matrix of experiments was conducted for observing the effect of different quantities of EGR on exhaust gas temperatures and opacity

E-Waste plastic powder modified bitumen: rheological properties and performance study of bituminous concrete

Abstract: Bitumen being a viscoelastic material sometimes needs modification for stability under adverse environmental conditions. Several researchers have carried out the modification of bitumen with unconv...

Causal Association Mining for Detection of Adverse Drug Reactions

Abstract: Adverse drug reactions (ADRs) are the harmful reactions of the drugs caused to humans due to allergies, overdose, chemical reactions between two chemicals in the medicines, etc. To reduce these reactions is a very important task so as to save lives of the patients as ADRs are a serious topic nowadays [4]. Detecting such harmful effects as early as possible is a very important to prevent harmful consequences. Therefore, mining causal relationships between the drug related events is essential. A method for detecting the potential relationship between drug and ICD is done using causal association rules suitable for the frequent events[1]. Sometimes an infrequent nature of the drugs can cause tremendous harm especially in case of Type-2 diabetes. A new interestingness measure called as exclusive causal leverage can be used based on fuzzy Recognition Primed Decision model (RPD) [3]. On the basis of this measure the relationship between the drug and associated drug reactions can be mined.

A Survey on Human Group Activity Recognition by Analysing Person Action from Video Sequences Using Machine Learning Techniques

Abstract: There has been a tremendous advance in machine learning techniques especially for automatic group activity recognition (GAR) over the past few decades. This review article surveys the modern advancement made towards video-based group activity recognition technique. Various applications, including video surveillance systems, sports analytics and human behaviour for robotics characterization, require a group activity recognition system. Comprehensive reviews of machine learning (ML) techniques like hidden Markov models (HMMs), graphical method and support vector machines employed in GAR are being discussed. A comprehensive review on the latest progress in deep learning model has delivered important developments in GAR performance; those are also presented. The main purpose of this survey is to broadly categorize and analyse GAR according to handcrafted features based on machine learning model and learned features based on deep model. Various GAR models illustrated by considering activities of individual person, person-to-person interaction, person-to-group interaction and group interaction using temporal sequence information from video frames for recognition of group activity are discussed. The review facilitates in diverse applications, and the models described in different applications present specifically in surveillance, sport analytics, video summary, etc.