{"title":"High Level Optimization Methodology for High Performance DSP Systems using Retiming Techniques","authors":"Harpreet Mehra, M. S. Bhat","doi":"10.1109/DISCOVER.2018.8674128","DOIUrl":"https://doi.org/10.1109/DISCOVER.2018.8674128","url":null,"abstract":"Due to increasing complexity of VLSI systems, design optimization at higher levels of abstraction is all the more important to derive maximum performance mileage. Retiming is a powerful sequential optimization technique used to move registers across the combinational logic or to optimize the number of registers to improve performance via power-delay trade-off, without changing the input-output behavior of the circuit. This paper presents a high-level technique to retime a given sequential circuit to achieve lower clock period and a lower register count and their trade-off. The techniques used in this paper include cutset retiming, retiming for clock period minimization and retiming for register minimization. An environment is created using MATLAB, which takes a non-retimed circuit in the form of a netlist and a retimed netlist is generated with reduced critical path and/or with reduced number of flip-flops, thereby improving the overall performance.","PeriodicalId":109938,"journal":{"name":"2018 IEEE Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124306703","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
S. Charitha, Nagaratna B. Chittaragi, S. Koolagudi
{"title":"Extractive Document Summarization Using a Supervised Learning Approach","authors":"S. Charitha, Nagaratna B. Chittaragi, S. Koolagudi","doi":"10.1109/DISCOVER.2018.8674133","DOIUrl":"https://doi.org/10.1109/DISCOVER.2018.8674133","url":null,"abstract":"In this paper, we present a model for extractive multi-document text summarization using a supervised learning approach. The model uses a convolutional neural networks (CNN) which is capable of learning sentence features on its own for sentence ranking. This approach has been used in order to avoid the overhead of extracting features from sentences manually. Integer linear programming (ILP) approach has been adopted for selecting sentences to generate the summary based on sentence ranks. This ILP model minimizes the redundancy in the generated summary. We have evaluated our proposed approach on the DUC 2007 dataset and its performance is found to be competitive or better in comparison with state-of-the-art systems.","PeriodicalId":109938,"journal":{"name":"2018 IEEE Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134091725","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
G. S. Sai Venkatramana Prasada, G. Seshikala, Niranjana Sampathila
{"title":"Performance Analysis of 64×64 bit Multiplier Designed Using Urdhva Tiryakbyham and Nikhilam Navatashcaramam Dashatah Sutras","authors":"G. S. Sai Venkatramana Prasada, G. Seshikala, Niranjana Sampathila","doi":"10.1109/DISCOVER.2018.8674125","DOIUrl":"https://doi.org/10.1109/DISCOVER.2018.8674125","url":null,"abstract":"In VLSI systems like microprocessors and application specific DSP architectures, the arithmetic operation which is extensively used is ‘Multiplication’. The overall performance of most of the systems is determined by the multipliers. The power efficient, faster and low area multiplier design decides the performance of the system. This paper focuses on the comparison of the 64×64 bit multipliers based on the Urdhva Tiryakbyham and Nikhilam Navatashcaramam Dashatah sutras of Vedic mathematics. The proposed designs were implemented using Verilog code and simulated using Xilinx10.1 for parameters such as slices, number of 4 input LUT’s and delay. Simulation was also done using Cadence simvision with 45nm technology. 64×64 bit multiplier designed using Urdhva Tiryakbyham sutra exhibits less combinational delay and power utilization. But device utilization in Nikhilam multiplication is less compared to Urdhva multiplication.","PeriodicalId":109938,"journal":{"name":"2018 IEEE Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123915881","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A fault-tolerant control strategy for non-linear system: An application to the two tank canonical noninteracting level control system","authors":"H. Patel, V. Shah","doi":"10.1109/DISCOVER.2018.8674119","DOIUrl":"https://doi.org/10.1109/DISCOVER.2018.8674119","url":null,"abstract":"Two tank canonical system is highly used in process industries because of its mechanical structure which contributes fast release for liquid, slurries, viscous, and solid mixture. Two tank canonic system is highly nonlinear system due to its shape and varying cross-sectional area, hence the level control of this system is extremely difficult due to nonlinear behavior of the system. As a matter of facts, when abnormal activity occur such as system component, actuator and sensor faults occur in the system and hence system performances degrade drastically and a hazardous situation occurs. Fault-tolerant control is an advanced control strategy, which maintains control performance and system stability even though fault occurred in the system. The paper attributes to design a passive FTC strategy for a Two-Tank Canonical Non-Interacting Level Control System (TTCNILCS) with the constraint of a system, actuator faults, and process disturbances. FTC will increasing system performance in the presence of the faults. The simulation results demonstrate the proposed strategy has definite fault tolerant ability against the system and actuator faults also it has disturbance rejection capability. To verify the efficacy of the proposed passive FTC strategy Mean Square Error (MSE) indices is used.","PeriodicalId":109938,"journal":{"name":"2018 IEEE Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123606604","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
S. R. Rimitha, Vedasamhitha Abburu, Annem Kiranmai, K. Chandrasekaran
{"title":"Ontologies to Model User Profiles in Personalized Job Recommendation","authors":"S. R. Rimitha, Vedasamhitha Abburu, Annem Kiranmai, K. Chandrasekaran","doi":"10.1109/DISCOVER.2018.8674084","DOIUrl":"https://doi.org/10.1109/DISCOVER.2018.8674084","url":null,"abstract":"Personalized recommendation aims to provide results that are likely to be of interest to a particular user. Personalized recommendation is useful in the domain of job search in order to provide individuals more personalized recommendations of job listings based on their preferences. User profiles a re thus constructed based on the individual users preferences. On the other hand, user profiles a re helpful in improving the recommendations. In general, user profiles are structured based on the individual’s preferences. User profiles can be represented in various ways, one such way is ontology which is the systematic categorization and representation of relationships between various entities within a domain. Ontologies has been widely used in the domain of e-commerce and medicine. In this paper, we use ontologies in the domain of personalized job recommendation, to model user profiles. The major objective of this paper is to provide an ontology based user profile for the domain of job recommendation. In particular, we identified suitable classes, attributes and relations that are specific to job recommendation system. In addition, we presented OWL representation of the proposed ontological model such that it can be reused by domain experts.","PeriodicalId":109938,"journal":{"name":"2018 IEEE Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)","volume":"158 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125778216","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Distributed Computing and Image Processing for Autonomous Driving Systems","authors":"Tejaswa Gavankar, Aditi Joshi, Shantanu Sharma","doi":"10.1109/DISCOVER.2018.8673972","DOIUrl":"https://doi.org/10.1109/DISCOVER.2018.8673972","url":null,"abstract":"in an autonomous driving system, the field of view spans multiple cameras placed around a car driven through numerous driving scenarios. Sensor data is received by the analyzing unit at a high velocity, also the camera provides over millions of images for a small drive of about half a mile. Also not all the images captured by the cameras are capable of being analyzed as some of them might have to be discarded on accounts of high noise levels or lack of lighting. A simple example of this is when pictures clicked on burst mode often have more throwaways than the ones which can be utilized. So, it is important for the analyzing unit to make a series of decisions before even starting the feature extraction process. Efficient processing of a high volume of images is therefore a challenge which autonomous systems such as the driving system face. Given the multiple cameras present on autonomous cars, providing high resolution pictures through varying driving scenarios, the objective is to process and analyze this huge dataset efficiently. This paper shall demonstrate the power of distributed computing in image processing algorithms and analysis of incredibly large datasets using a distributed approach. This paper gives a statistical proof of concept of how implementing a distributed parallel programming paradigm can improve autonomous systems such as the driving system which deal with high volumes of images.","PeriodicalId":109938,"journal":{"name":"2018 IEEE Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128731000","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Development of Smart Drip Irrigation System Using IoT","authors":"Anushree Math, L. Ali, U. Pruthviraj","doi":"10.1109/DISCOVER.2018.8674080","DOIUrl":"https://doi.org/10.1109/DISCOVER.2018.8674080","url":null,"abstract":"India is a country with agriculture having paramount significance. Hence it is important to irrigate the plants in an astute way to get good production by maximizing the yield per unit space. Irrigation is the supply of an appropriate amount of water to the plants at a precise time. The objective of this endeavour is to irrigate the plants using the smart drip irrigation system within National Institute of Technology Karnataka campus. To achieve this, open source platform is used as a central controller of the system. Various sensors have been employed which continuously provide the existing parameters of factors governing healthiness of plants. Based on the information obtained from the RTC module water is supplied to the plants at regular interval of time by controlling a solenoid valve. The entire irrigation system can be monitored and managed by the webpage. This web page has a facility for controlling the irrigation of plants, both in manual and automatic fashion. The health of the plants is monitored by a raspberry pi camera which gives live streaming to the webpage. Water flow sensor accords information about water flow to the controller by the means of wireless communication. This information is analyzed by the controller to find out leakages in the pipe. Further, weather prediction is carried out, so as to regulate the quantity of water being administered thus making it more reliable and efficient.","PeriodicalId":109938,"journal":{"name":"2018 IEEE Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)","volume":"248 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121428782","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Review on Network Intrusion Detection Techniques using Machine Learning","authors":"K. Shashank, Mamatha Balachandra","doi":"10.1109/DISCOVER.2018.8673974","DOIUrl":"https://doi.org/10.1109/DISCOVER.2018.8673974","url":null,"abstract":"The security given to a network from unapproved access and dangers is broadly called as network security. It is the obligation of network managers to embrace preventive measures to shield their networks from potential security dangers. Computer networks that are associated with consistent data transactions inside the administration or business require security. The exponential development in the information that streams inside network, the quantity of individuals active on network, makes it essential to have a productive system that disallows outsiders to attack and access secret information. Consistently developing digital attacks should be checked to defend classified information. Machine learning methods which have a critical part in distinguishing the attacks are for the most part utilized as a part of the advancement of Intrusion Detection Systems. Because of colossal increment in network activity and diverse sorts of attacks, checking every single parcel in the system movement is tedious and computationally expensive.","PeriodicalId":109938,"journal":{"name":"2018 IEEE Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116184222","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}