Convolutional Neural Networks
The human brain is trained in such a way that it can automatically and instantly recognize multiple faces. But when it comes to the computer, it becomes very difficult to do all the challenging tasks on the level of the human brain. The face recognition is an integral part of biometrics. In biometrics, basic traits of human are matched to the existing data and facial features are extracted and implemented through algorithms. Numerous algorithms and techniques have been developed for improving the performance of face recognition. Deep learning is making crucial advances in solving problems that have restricted the best attempts of the artificial intelligence community for many years. Among one of the deep learning, approaches are Convolutional Neural networks (CNN).CNN is a kind of artificial neural networks that employ convolution methodology to extract the features from the input data to increase the number of features. The general structure of the face recognition process is of three stages. It starts with a pre-processing stage: color space conversion and resizing of images, continues with the extraction of facial features, and afterward extracted feature set is classified. In our system, Softmax Classifier is to realize the final stage that is classification on the basis of the facial features extracted from CNN
Published by: Mrunmayee Vaidya, Jigyasa Solanki, Sravani Wayangankar
Author: Mrunmayee Vaidya
Paper ID: V5I3-1675
Paper Status: published
Published: May 30, 2019
Brain tumor segmentation in MRI images
Among cerebrum tumors, gliomas territory unit the preeminent normal and forceful, bringing about a dreadfully short life in their most noteworthy evaluation. In this manner, treatment structuring might be a key stage to upgrade the nature of life of oncologic patients. Attractive Resonance Imaging (MRI) might be a widely utilized imaging procedure to evaluate these tumors. Anyway, the enormous amount of learning made by attractive reverberation imaging anticipates manual division in an entirely reasonable time, constraining the utilization of exact quantitative estimations inside the clinical apply. Along these lines, programmed and dependable division ways territory unit required; be that as it may, the enormous spatial and basic changeability among cerebrum tumors make programmed division a troublesome downside. In this paper, we will, in general, propose a programmed division technique dependent on Statistical Region Merging. To ensure the tumor segmentation based on the merging predicate of the neighborhood pixels to accurately determine the tumor. So effective results are achieved when compared to manual segmentation where the segmentation lacks accuracy.
Published by: Chand Basha, V. Punna Rao
Author: Chand Basha
Paper ID: V5I3-1689
Paper Status: published
Published: May 30, 2019
Ergonomic analysis of bed for bedridden patient- An interdisciplinary overview
This review paper mainly focuses on ergonomics problem which is mainly related to bedridden patients and caretaker of those patients. A bed plays a key role in the patients' life, if ergonomically bed is not suitable for patients then he can't recover fast & also the person who takes care of the patient they go through some injuries or accident. Designing a healthcare facility without giving sufficient consideration to the users who will perform their activities in it may lead to dysfunctional workplace. Like assisted living facilities, nursing homes, outpatient clinics, as well as in home health care services, the design of hospital bed depends largely on users’ anthropometric characteristics to ensure comfort, safety, and productivity of health care service. In attempting to meet the patients’ needs, a survey paper was studied for many cases (patients and caregivers point of view) which aimed at proposing a new prototype to provide their needs.
Published by: Pawan Prakash Khebudkar, S. S. Shinde, Sandesh B. Sangale
Author: Pawan Prakash Khebudkar
Paper ID: V5I3-1649
Paper Status: published
Published: May 29, 2019
Experiment on soil properties made with geocell-shredded tyres reinforced sand
Soil reinforcement is one of the most popular ground improvement techniques. Availability of different material and techniques for reinforcement is one of the major reasons for the continuous increase in the application of the soil reinforcement. Rapid industrialization is full filling the need of the present time and it is also producing a huge amount of waste Under the present investigation, a detailed parametric study through a series of triaxial experiments has been carried out to develop an understanding of the behavior of geocell-shredded tyres reinforced sand under triaxial loading. The influence of various parameters pertaining to geocell- shredded tyres reinforced soil such as relative densities (i.e., 30%, 50%, 70%), confining pressures (i.e., 50kPa, 100kPa, 200kPa), types of geocells (i.e., M=4.79, 3.23), and shredded tyres content (i.e., 10%, 20%, 30%, 40%) have been studied extensively in a systematic manner. The results of the triaxial tests show that the stiffness and the load carrying capacity of the soil improve substantially with the provision of shredded tyres reinforcement in content 10% and 20% respectively while results of tyre content 30% and 40% show less stiffness and the load carrying capacity of the soil. The stiffness and load carrying capacity of the soil also improves with the provision of reinforcement of soil using geocells and also improves with the provision of reinforcement of soil using geocell-shredded tyres. When geocells are used with shredded tyres for reinforcement of soil then improved results have been seen in 10%, 20%, and 30% tyre content as compare to geocell reinforcement of soil without shredded tyres. While 40% of tyre content shows less load carrying capacity as compare to lesser contents of shredded tyres.
Published by: Avinash Shastri, Rajesh Misra, Chandra Mohan Shakya
Author: Avinash Shastri
Paper ID: V5I3-1677
Paper Status: published
Published: May 29, 2019
Leach based routing protocol in wireless sensor networks
The main purpose of wireless sensor networks to manage conventional systems is to adjust the vitality of systems and extend the entire life of the system. The wireless sensor networks have limited energy to micro sensor nodes. When such nodes lose their force absolutely, verbal altercation stops. Wireless sensor networks have the least effort and mandatory sensor hubs with a large degree of control. A sensor hub detects information in numerous applications on wireless sensor networks and transmits it to the sink through solitary or multi-jump routes. A hierarchal-based routing protocol is mainly used in the field of energy consumption. LEACH is also clustering based routing protocol. The main aim of this research is to create a number of rules to offer better and reliable network services for wireless sensors through stable networks with nodes with long service life. Reliable is a durable and better performance platform. In this paper, we are implementing a new algorithm based on soft and hard thresholding for 2-tier cluster head formation. First, the energy efficient routing protocol is studied and analyzed. Then we use new thresholding technology algorithms. It will help in improving the network life time. And also works on alive nodes, throughput etc.
Published by: Geeta Sharma, Bharti, Manit Kapoor, Naveen Dhillon
Author: Geeta Sharma
Paper ID: V5I3-1662
Paper Status: published
Published: May 29, 2019
Designing and implementing result reporting tool using OLAP technology
A large amount of data is generated in educational institutes. The produced data does not provide a clear picture due to which the important details might not be visible. This data can be used in different ways if it is analyzed properly. Analysis of data plays an important role in the understanding of information. The main objective of this paper is to develop a web-based software which evaluates the performance of students, faculty, departments and predict the placement of students which will eventually help in evaluating students potential strengths and weaknesses for the growth of the institutes. As data sets have grown in size and has become more complex, therefore this has made efficiency of data mining algorithms to decrease. So OLAP technology is used in this paper to analyze database information from multiple databases at one time and its data is stored in the multidimensional database.
Published by: Bhavya Agnihotri, Rucha Bendale, Ankita Waghmare, Nisha Sharma
Author: Bhavya Agnihotri
Paper ID: V5I3-1656
Paper Status: published
Published: May 29, 2019
