作者：
T R ArunkumarH S JayannaResearch Scholar
Department of Computer Science & Engineering Siddaganga Institute of Technology Tumkur India. Professor
Department of Information Science Siddaganga Institute of Technology Tumkur India.
Psoriasis is a skin disorder which affects the people physically, mentally and emotionally. It is characterized as rough elevated scaly skin which is evident from surrounding skin area. There are various types of psor...
Psoriasis is a skin disorder which affects the people physically, mentally and emotionally. It is characterized as rough elevated scaly skin which is evident from surrounding skin area. There are various types of psoriasis which include plaque psoriasis, nail psoriasis, guttate psoriasis, inverse psoriasis, pustular psoriasis, erythrodermic psoriasis and psoriatic arthritis. The common trend observed is that the people tend to face difficulties in differentiating and tracking the disorder which will worsen the situation of the affected skin. It is essential to keep track of the affected skin for the prognosis of the disorder. In this work, an attempt is made to identify the psoriasis affected area automatically using MobileNet machine learning model which will become an objective tool in accurate identification of the disorder which in turn helps in effective treatment of the disorder.
Image segmentation is a critical process in computer vision. It involves dividing a visible input into segments to simplify image analysis. Segments represent objects or parts of objects and comprise sets of super-pix...
Image segmentation is a critical process in computer vision. It involves dividing a visible input into segments to simplify image analysis. Segments represent objects or parts of objects and comprise sets of super-pixels. Image segmentation sorts pixels into larger components, eliminating the need to believe individual pixels as units of observation. Brain tumour segmentation is a crucial task in medical image segmentation. Early diagnosis of brain tumours plays a crucial role in improving treatment possibilities and increases the survival rate of the patients. Manual segmentation of the brain tumours for cancer diagnosis, from great deal of MRI images generated in clinical routine, may be a difficult and time-consuming task. There is a requirement for automatic brain tumour image segmentation. The method is proposed to segment normal tissues like substantial alba, grey matter, spinal fluid, and abnormal tissue like tumour part from a resonance Imaging (MRI) automatically. The system also uses to segment the tumour cells along the morphological filtering are going to be wont to remove background noises for smoothening of region. The project results will be presented as segmented tissues and classification using, Convolutional Neural Network (CNN) classifier.
With the current trend in lieu of the ongoing pandemic, online learning and technology-based pedagogy receive worldwide attention. There are several pedagogical practices one can use to evaluate students mindful and t...
With the current trend in lieu of the ongoing pandemic, online learning and technology-based pedagogy receive worldwide attention. There are several pedagogical practices one can use to evaluate students mindful and the method will vary based on the learning objective. In this paper, our goal is to dive deeper into identifying the best keyword extraction technique which can be closely mapped with human evaluation. We report the results of three popular keyword extraction techniques specifically RAKE, TF-IDF, and Semantic Fingerprinting on the dataset generated from the discussion board post of a Learning Management System. The results illustrate that the TF-IDF algorithm shows the highest correlation with a human evaluation with 0.76 correlations, RAKE with 0.36, and Semantic Fingerprinting with 0.58. It was also identified Semantic Fingerprinting had a lowest mean square error of 18.26.
Time-series data is widely studied in various scenarios, like weather forecast, stock market, customer behavior analysis. To comprehensively learn about the dynamic environments, it is necessary to comprehend features...
详细信息
ISBN:
(数字)9781728180090
ISBN:
(纸本)9781728180106
Time-series data is widely studied in various scenarios, like weather forecast, stock market, customer behavior analysis. To comprehensively learn about the dynamic environments, it is necessary to comprehend features from multiple data sources. This paper proposes a novel visual analysis approach for detecting and analyzing concept drifts from multi-sourced time-series. We propose a visual detection scheme for discovering concept drifts from multiple sourced time-series based on prediction models. We design a drift level index to depict the dynamics, and a consistency judgment model to justify whether the concept drifts from various sources are consistent. Our integrated visual interface, ConceptExplorer, facilitates visual exploration, extraction, understanding, and comparison of concepts and concept drifts from multi-source time-series data. We conduct three case studies and expert interviews to verify the effectiveness of our approach.
作者：
K RahejaA GoelM MahajanScholar
Department of Computer Science and Engineering SGT University Gurugram India Professor
School of Computing Science and Engineering Galgotias university India Professor
Faculty of Engineering and Technology SGT University Gurugram India
Pneumonia is one of the most prominent basis of premature death globally, according to some of the major health institutions like WHO more than 1 billion people around the world get infected and more than 4 million pe...
Pneumonia is one of the most prominent basis of premature death globally, according to some of the major health institutions like WHO more than 1 billion people around the world get infected and more than 4 million people die prematurely due to pneumonia lung infection. Detection of pneumonia infection requires a lot of medical tests, which can be expensive and time consuming. Deep Learning, the technology which gives computer systems the ability to learn and adapt through unstructured data in order to complex solve real world problems has the potential to make the detection of pneumonia easier, cost effective and less time consuming. The motivation behind this paper is to grasp the criticalness and utilizations of deep computational learning and Convolutional Neural Network (CNN) by executing it so as to recognize Pneumonia by examining a patient's chest x-beam pictures.
E-learning is globalized in a short period of time due to the physical distancing requirement for curbing the spread of COVID-19. There are two major challenges imposed by the migration from face-To-face learning to E...
详细信息
作者：
K RahejaM MahajanA GoelScholar
Department of Computer Science and Engineering SGT University Gurugram India Professor
School of Computing Science and Engineering Galgotias university India Professor
Faculty of Engineering and Technology SGT University Gurugram India
In Vehicular Ad hoc Networks (VANET), topology varies very frequently because vehicles move in high speed. VANET is deployed on road. In GPSR Protocol, as the data packets are forwarded depending upon on the beacon in...
In Vehicular Ad hoc Networks (VANET), topology varies very frequently because vehicles move in high speed. VANET is deployed on road. In GPSR Protocol, as the data packets are forwarded depending upon on the beacon information sent by neighboring nodes, which contain the location of neighbors. Hence nodes move in mobile nature as they change their positions. Mobile pattern of node is reflected by Mobility Models, as they characterize the movement of users who are mobile on the road, with respect to their direction, velocity and location over a period of time. Mobility models are practiced in implementation of protocols and the pattern by which the mobility models reflect real world practices of vehicles on the roads. Using simple pattern randomly, graph constrained mobility models are common practices while doing research. These models donot describe mobility of vehicles in realistic manner. For instance while accelerating and decelerating in the presence of nearby vehicles, these situations greatly affect the Network performance. Selecting the mobility model which is realistic one is the main focus of this paper. To address the challenges such as high mobility of vehicle nodes on the road and random topology, VANET needs a suitable mobility model to obtain improved Packet Delivery Ratio, Throughput, End to End Delay etc. This paper first implements the GPSR Protocol and then GPSR is analyzed by applying different mobility models such as Random Way Point, Gauss Markov, Manhattan Grid, Reference Point Group and Random direction. Results are analyzed by taking the following parameters: Routing overhead, Throughput, PDR and End to End Delivery. The implementation is carried out using NS—2.35 and Bonmotion is used to create mobility models.
In today's day of modern era when the data handling objectives are getting bigger and bigger with respect to volume, learning and inferring knowledge from complex data becomes the utmost problem. The research in K...
In today's day of modern era when the data handling objectives are getting bigger and bigger with respect to volume, learning and inferring knowledge from complex data becomes the utmost problem. The research in Knowledge Discovery in Databases has been primarily directed to attribute-value learning in which one is described through a fixed set tuple given with their values. Database or dataset is seen in the form of table relation in which every row corresponds to an instance and column represents an attribute respectively. In this paper a New framework is introduced a much more sophisticated and deserving approach i.e., Hybrid Multi-Relational Decision Tree Learning Algorithm which overcomes with Exiting technology drawbacks and other anomalies. Result show that Hybrid Multi- Relational Decision Tree Learning Algorithm provides certain methods which reduces its execution time. Experimental results on different datasets provide a clear indication that Hybrid Multi-Relational Decision Tree Learning Algorithm is comprehensively a better approach.
Attendance monitoring is one of the vital administrative processes in all educational institutions and organizations. A well-structured system will enable the institutions to have an increasing growth. It helps the st...
Attendance monitoring is one of the vital administrative processes in all educational institutions and organizations. A well-structured system will enable the institutions to have an increasing growth. It helps the students and teachers in all ways to have a good progress in the attendance, thereby reducing the teachers' time and effort. In physical classrooms, traditional method of calling the students names and marking their presence/absence is the routine process followed regularly. Attendance monitoring system is proposed using artificial intelligence. Firstly, a database containing the facial images of the students in a particular class is constructed. Knowledge gained using Convolutional Neural Network (CNN) is reused in a perfect manner using transfer learning. This system is designed to improve the students' engagement time inside the classroom, to communicate to the parents frequently, to avoid proxy attendance and to generate detailed reports for future reference.
作者：
P V SrimukhS ShrideviStudent
School of Computer Science and Engineering Vellore Institute of Technology University Chennai India Professor
Research Division of Advanced Data Science Vellore Institute of Technology University Chennai India
This paper is an extended version of the research paper 'Ontology based crime investigation process' which deals with the working principle and the construction of an ontology based extensively on organized cr...
This paper is an extended version of the research paper 'Ontology based crime investigation process' which deals with the working principle and the construction of an ontology based extensively on organized crime. Ontologies on various domains are created in which their assistance has been widely recognized. They are being developed for providing basis for allocation of knowledge in a domain and imparting reasonable information. In this paper we describe the structure of the ontology we created and also by validating the ontology via an online ontology evaluating tool.
暂无评论