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.

Design and Development of Wireless Sensor Network (WSN) for Water Quality Monitoring Using Zigbee

Abstract: This paper presents the implementation of Wireless Sensor Network for water quality tracking using Zigbee. For continuous monitoring a number of sensor nodes with networking ability can be installed using wireless sensor network for water quality monitoring. In water quality monitoring the parameters involved are pH, and turbidity. These parameters are measured in real time by the sensors that send the data to monitoring room/control station (Base station). Such monitoring system can be setup on the aspect of low cost, low power consumption, easy handling, installation and maintenance. The system consists of sensor nodes (pH Sensor, Turbidity Sensor), a microcontroller, a Zigbee radio, and a base station (Zigbee radio and microcontroller). For comparing routing results of different topologies OPNET simulator is used.

Detecting and Overcoming Blackhole Attack in AODV Protocol

Abstract: A mobile ad-hoc network (MANET) is a self-configuring infrastructure less network of mobile devices. Each must forward traffic unrelated to its own use, and therefore be a router. AODV (Ad-hoc On-demand Distance Vector) is a loop-free routing protocol for ad-hoc networks. It is designed to be self-starting in an environment of mobile nodes, withstanding a variety of network behaviours such as node mobility, link failures etc. Black hole attack is a type of denial-of-service attack in which a router that is supposed to relay packets instead drops them. In this paper, the effect of black hole attack in AODV based network is studied. The network parameters like Throughput, Packet Delivery Ratio and Average End to End Delay are calculated for normal network (without black hole) and a network with one black hole. After detecting the black hole attack in order to resume data transmission, the black hole node is bypassed and the route to the genuine destination is resumed again. The performance of network parameters are compared in all the three scenarios.

Unsupervised topic detection model and its application in text categorization

Abstract: In most of the research, topic detection is defined as the task of finding out different themes from the collection of documents. Our topic detection approach is about finding a topic for every document in the corpus. Any word or group of words which tells what the document is about is defined as the topic of the document. In this paper, we propose a novel topic detection approach using an unsupervised model. It is a simple yet effective approach for topic detection and finding keywords from the corpus. The keywords are extracted by identifying the relationship between the words in a set of unstructured data automatically, without any set of training data. The keyword extraction is based on an hypothesis for word decomposition which says that the words in bigram or trigram word vectors would have words that can be potential distribution of words from the unigram word vector. After keyword extraction, topics are determined for each document using our proposed algorithm of topic detection. The proposed algorithm finds the most suitable topic for each document. The topics detected in the entire corpus and the keywords related with each topic are stored and analyzed. We use the standard term frequency (TF) measure for finding the keywords. The effectiveness and accuracy of keywords is judged by using these keywords as features for classification and comparing the results against the standard bag-of- words approach. The topics detected by our algorithm are found to be relevant to the document. The experimental results using keywords show that the dimensionality of the corpus is drastically reduced while maintaining and in most of the cases, improving F-measure of categorization. Thus, it shows that our approach of feature selection for text categorization not only improves the classification accuracy but also reduces considerably the time required for classification.

Fuzzy logic based decision support system

Abstract: Anaesthesia practice might involve instances proving to be life threatening. Hence one has to be cautious and at the same time be able to avert any danger if any of such situation prevails But humans can make some errors based on their decision which may lead to loss of life. Hence there is a need to introduce an decision support system (DSS), which would take correct decisions based on the inputs. This paper presents the design and implementation of fuzzy logic based decision support system. Fuzzy logic mimics the human decisions as per the inputs. So the chances of propofol being infused wrongly are minimized. Also various parameters like heart rate, oxygen saturation, blood pressure is continuously monitored. Based upon these inputs to the fuzzy decision support system and Lab-view Graphical user interface (GUI) will give appropriate decision as the depth of anesthesia. Hence the risk to life is attenuated to great extent. This type of decision support system can be used in hospitals and health-care facilities and will prove useful not only to professionals but also to the newcomers in the field of anesthesia. Another advantage of this system is cost effective and viable for human society. Experts based decision support system is designed and implemented using Lab-view. Developed GUI is validated from experts for 270 different conditions. Out of 270 experts 3 decisions accepting given by DSS.

Experiments on detection of Denial of Service attacks using ensemble of classifiers

Abstract: Malicious users of the internet can launch Denial of Service (DoS) and Distributed Denial of Service (DDoS) attacks with the intent of making the throughput of a network next to none. As the types and number of users of the internet increases, the requirement of an effective Intrusion Detection System(IDS) to detect these attacks also increases. Different techniques such as data mining and pattern recognition are being used to design IDS. One of the major challenges faced while designing IDSs is maximizing the accuracy of detection. To address this issue, this paper has used Ensemble of classifiers approach where each class uses different learning paradigm. The classifiers used for experimentation are Naive Bayesian(NB), Bayesian Network(BN), Sequential Minimal Optimization(SMO), J48(C4.5) and Reduced Error Pruning Tree(REPTree). Experimental results show improvements in detection accuracy for Denial of Service attacks.