Feature selection: A review
Feature selection is an important process in machine learning, whose goal is to find a small number of features by removing irrelevant and/or redundant features. The main idea of feature selection is to choose a subset of input variables by eliminating features with or no predictive information. Feature selection removes dimensionality reduction problem. It is best for high dimensional data. Feature selection methods can be divided into three classes. One of is filter methods and another one is wrapper method and the third one is embedded method. This is one of two ways of avoiding the curse of dimensionality. This work reviews several fundamental feature selection algorithms found in the literature.
Published by: Dipti Chaudhari, Sarika Kadam, Shital Sungare
Author: Dipti Chaudhari
Paper ID: V4I3-1824
Paper Status: published
Published: June 15, 2018
Automated street lighting system using IoT
In this modern era where energy is a major concern worldwide, it is our prior responsibility & liability to save energy effectively. With the development of technology, where automation system plays a vital role in daily life experience and it is being preferred over the traditional manual system today. Here we propose an IOT based street light monitoring and controlling system to ensure, low power consumption, instant faulty light detection and light dimming as per external lighting conditions. Our proposed system consists of smart street lights that have external light sensing that automatically turns on at the desired intensity based on an amount of lighting needed.
Published by: Prashanth Keni, Shaik Mohammed Wajid, Syed Zuber Ahmad, Rahimunnisa, Shruthi K
Author: Prashanth Keni
Paper ID: V4I3-1830
Paper Status: published
Published: June 15, 2018
Comparison between seismic variation of conventional RC slab and flat slab with drop for G+15 storey building in different zones using etabs software
Every year thousands of buildings are damaged and collapsed and thousands of people become homeless due to the natural calamity Earthquake, which occurs with intensities not less than 3 on the seismic scale. In the present era, the low rise to high rise buildings is constructed due to limited space. Once, this earthquake occurs, its effects these structures most. Huge property loss and human loss occur. In order, to control this some precautions and codes for seismic-resistant building construction are assigned by various countries. In India, IS 1893-2002 provides the rules and precautions for various types of building construction that is seismic resistant. Buildings such as Conventional RC Frame structures are common in practice .but due to highly advanced technologies, beamless slab called Flat slab is in use these days. T Hough flat slab possess many advantages over conventional buildings when dealing with seismicity, the flat slab is far less potentially strong to resist for seismic conditions. In the present work the comparison of Conventional building and Flat slab with Drop in different zones, using ETABS software. Therefore, the characteristics of a seismic behavior of Flat slab and Conventional RC frame building measures for guiding the concept and design of these structures and for improving the performance of buildings during seismic loading. In Present work, a good amount of information regarding parameters such as Storey Displacement, Storey Shear, Overturning Moment, and Storey Drift for Flat Slab and Conventional Slab is provided and its variation of these parameters in different zones is also detailed.
Published by: Thummala Spoorthy, S. Ramesh Reddy
Author: Thummala Spoorthy
Paper ID: V4I3-1840
Paper Status: published
Published: June 15, 2018
Profiling outcomes in clients with bimodal hearing
The current study aims to profile the outcome measures of bimodal hearing in terms of speech perception in noise, pitch pattern differentiation ability and also the range of hearing disabilities across several domains using the Speech, Spatial and Qualities of Hearing Scale (SSQ). A total of 15 subjects with age range of 6 – 20 years have participated in the study. Primarily aided responses were obtained for frequencies ranging from 250Hz to 8 KHz under three conditions. Loudness scaling procedure was attempted to obtain the most comfortable level. At the level of MCL, Pitch pattern test scores and also speech perception in noise scores by using variable SNR procedure were obtained under three conditions along with SSQ questionnaire administration. The results of the speech perception in noise test reveal that subjects with bimodal stimulation have shown a mean of +4 dB SNR improvement in signal to noise ratio when compared with CI alone condition. The temporal organization capacity is also better with bimodal condition with a mean percentage of 58.4% when compared with the unimodal condition. The perceptual rating of the bimodal condition also seems to be better than the unimodal condition for each question in SSQ questionnaire. To conclude with the Outcome measures of all test procedures, the subjects with bimodal stimulation perform significantly better than Unimodal stimulation condition. Binaural hearing improves better speech perception in noise with the help of squelch effect, better localization skills with the help of ITD and ILD cues, ease of listening through binaural summation. Bimodal stimulation provides the above mentioned binaural advantages to the hearing-impaired population. This bimodal stimulation is also helpful in restricting the auditory deprivation in the non-implanted side of the individual with bilateral Severe to Profound hearing loss, which in turn will give good prognosis if the CI is done on the other ear later
Published by: P. Anita Phoebe Ivvah, Narendra Kumar M., Ranjith R.
Author: P. Anita Phoebe Ivvah
Paper ID: V4I3-1896
Paper Status: published
Published: June 15, 2018
A shrewd and pervasive controlled condition farming framework
With new technological advancement in controlled-environment agriculture systems, the level of productivity has significantly increased. Agriculture systems are now more capable, reliable, and provide enhanced productivity. An agriculture environment can range from a single plant in a house, a backyard garden, a small farm, to a large farming facility. These agricultural automated systems will help in managing and maintain safe environment especially the agricultural areas. In this paper, we propose a smart Agriculture System (AgriSys) that can analyze an agriculture environment and intervene to maintain its adequacy. The system deals with general agriculture challenges, such as temperature, humidity, pH, and nutrient support. In addition, the system deals with desert-specific challenges, such as dust, infertile sandy soil, constant wind, very low humidity, and the extreme variations in diurnal and seasonal temperatures. The system interventions are mainly intended to maintain the adequacy of the agriculture environment. For a reduced controller complexity, the adoption of fuzzy control is considered. The system implementation relies on state-of-art computer interfacing tools from National Instruments as programmed under LabVIEW
Published by: G. Prudhvi Sai Krishna, Dr. J. Mohana
Author: G. Prudhvi Sai Krishna
Paper ID: V4I3-1704
Paper Status: published
Published: June 15, 2018
Ripening and quality detection of mango using Arduino
Ripening is the methodology of maturing fruit to become more palatable. The ripening procedure of mango contains different stages in which a mango develops. There is a specific example in which the way toward maturing of mango is satisfied. In this paper, we are developing a technique for identifying the different ripening stages of Climacteric fruit like mango by utilizing an Arduino framework which will predict the quality of mango and show the total ripening procedure as per the color changing stages with the help of MATLAB. The HSV color space is used to read the color changes of mango and the information about the ripening is send to the user via GSM module using Arduino.
Published by: Akshay Ramesh Amrutkar, Hemant Balu Jaisingpure, Pavan Ashokrao Bhujade
Author: Akshay Ramesh Amrutkar
Paper ID: V4I3-1876
Paper Status: published
Published: June 15, 2018
