Early-Stage Dementia Detection by Optimize Feature Weights with Ensemble Learning
Dementia has developed into a significant health problem for many over the age of 50. Numerous kinds of dementia develop gradually and incrementally. Previous researchers have received reports from persons of various ages who have had memory loss and subsequent recall from long-term memory loss as a result of this neurodegenerative illness. Memory loss that is both gradual and irreversible characterises the disorder known as dementia. Although it is more common in the elderly, an increase in cases among the younger population has raised experts' eyes and encouraged them to explore the neuro-disorder, which causes memory loss and a barrier in recalling information from memory. Dementia can slow down to some extent if diagnosed early enough. Optimize learning and an additional tree classifier are used to extract information from brain MRI images and classify dementia at an early stage. In order to discover various patterns of dementia risk, hyper-parameters resulting from XGboost were obtained and assessed. Gradient boosting is commonly used to do variable extractions from independent to dependent variables, and the resulting derived variables are the result of this process
Published by: Tanvi Mahajan, Dr. Jyoti Srivastava
Author: Tanvi Mahajan
Paper ID: V8I3-1338
Paper Status: retracted
Submitted: May 23, 2022
Power Loss and Voltage Profile in Distribution System by Neural Network
The objective of power system operation is to meet the demand at all the locations within the power network as economically and reliably as possible. The traditional electric power generation systems utilize the conventional energy resources, such as fossil fuels, hydro, nuclear etc. for electricity generation. The operation of such traditional generation systems is based on centralized control utility generators, delivering power through an extensive transmission and distribution system, to meet the given demands of widely dispersed users. Nowadays, the justification for the large central-station plants is weakening due to depleting conventional resources, increased transmission and distribution costs, deregulation trends, heightened environmental concerns, and technological advancements. location and size of the DGs before and after radial network reconfiguration are determined using a multi-objective particle swarm optimization technique. In an active distribution network, an ideal network layout with DG coordination eliminates power losses, elevates voltage profiles, and enhances system stability, reliability, and efficiency.
Published by: Sandeep Kaur, Tejpal Singh
Author: Sandeep Kaur
Paper ID: V8I3-1337
Paper Status: published
Published: May 23, 2022
Accident detection system
In this project, we detect the accident between two vehicles. For the purpose of detection, we use certain algorithms such as YOLO and CNN (Convolutional Neural Networks). This project is mainly built upon the combination of Object Detection and Tracking System (which is also abbreviated as ODTS) and RCNN algorithms which are mainly used for detecting purposes. In this project, a video is given as input where the coded algorithm completely separates the video into frames and analyzes the-each frame and detects the crash in the frames, and gives those frames as an output. In addition to accident detection, YOLO also detects the surroundings such as persons, cars, trucks, etc. The main point of using YOLO is to detect the surroundings and the crash (with the help of CNN).
Published by: Manideep Pallerla, Anusha Nallamalla
Author: Manideep Pallerla
Paper ID: V8I3-1335
Paper Status: published
Published: May 23, 2022
Annotations on files
Real-time collaborative editing allows multiple users to edit a shared document at once. It has received a lot of attention from both industry and education and gained popularity due to the wide availability of free services like Google Docs. Although these shared editing programs were originally used in situations that included only a small set of users such as writing a research article, these days we are seeing a change in scale from fewer users to user communities. [2] Annotation can be an important function when trying to understand new information. The methodology can be used to create a ‘summary’ version of real information for later review and to add additional information to an existing document. The growth in web-based learning materials and information sources has created a requirement for systems that allow annotations to be attached to these new sources and, potentially, shared with other learners.[3]
Published by: Vipul Shinde, Siddhant Rathi, Mansi Parmar, Darshana Kumbhakarna, Deepa Sapkal
Author: Vipul Shinde
Paper ID: V8I3-1314
Paper Status: published
Published: May 20, 2022
Caption generator for random images using CNN & LSTM
With the rapid growth of artificial intelligence in recent years, picture caption has steadily grabbed the attention of many artificial intelligence researchers and has become an important study topic. alluring and arduous task. Image captioning and spontaneously generating natural human language captions according to the content observed in the above-captured image is an important part of scene understanding, which requires the knowledge of computer vision and natural language processing. The operation of the image caption generator is far-reaching and eloquent, for instance, the realization of human-computer interactions. This paper encapsulates methods and focuses on the attention mechanism, which plays a vital role in computer vision and is recently used in image caption generation tasks.
Published by: Ranga Prasad, B.Satyanarayana, Shaik Shahid
Author: Ranga Prasad
Paper ID: V8I3-1313
Paper Status: published
Published: May 20, 2022
Comparative Study of Conventional Frame and diagonally intersecting metal with Geometric Irregularities
High-rise buildings are more vulnerable tocollapseduetohighwindandearthquakepressure.Insuchabuildingriskoffailurecanbeminimizedbyadoptinglateralloadresistingsystem.Inthisstudy,wecomparedthreelateralloadresistingframei.e.diagrid frame and chevron braced frame with conventional frame system. The seismic analysis is done on these three frames. Thestructures are analyzed by linear static method. The building is considered to be irregular in plan. For irregular plan, C-shape plan,T-shape plan considered. The results are obtained after analysis are compared by various parameters like storey drift, absolutedisplacement, base shear, moment and axial forces. The First Comparison is between diagridsystem, chevron braced system andconventional frame system for C-Type and T-Plan separately and after that second overall comparison is between C-Plan and T-plan.The analysis is done on by using STAAD Software. The result of work showed that diagrid system resist lateral moreefficiently than chevron braced system and conventional frame system as it yields the least value for absolute displacement, storeydrift,topstoreyshear andbaseshear.
Published by: Priya Uikey, Girish Sawai
Author: Priya Uikey
Paper ID: V8I3-1316
Paper Status: published
Published: May 20, 2022