2022 IEEE World Conference on Applied Intelligence and Computing (AIC)最新文献_第9页

Solving Speed Reducer Design Problem by Memorized Differential Evolution 用记忆差分进化法求解减速器设计问题

2022 IEEE World Conference on Applied Intelligence and Computing (AIC) Pub Date : 2022-06-17 DOI: 10.1109/AIC55036.2022.9848936

Raghav Prasad Parouha

引用次数: 2

Comparative Analysis of Fruit Fly-Inspired Multi-Robot Cooperative Algorithm for Target Search and Rescue 果蝇启发的多机器人目标搜救协同算法比较分析

2022 IEEE World Conference on Applied Intelligence and Computing (AIC) Pub Date : 2022-06-17 DOI: 10.1109/AIC55036.2022.9848813

Vikram Garg, R. Tiwari, A. Shukla

{"title":"Comparative Analysis of Fruit Fly-Inspired Multi-Robot Cooperative Algorithm for Target Search and Rescue","authors":"Vikram Garg, R. Tiwari, A. Shukla","doi":"10.1109/AIC55036.2022.9848813","DOIUrl":"https://doi.org/10.1109/AIC55036.2022.9848813","url":null,"abstract":"In an unforeseen or human-made disaster, any search and rescue agency’s primary concern are to locate the survivor immediately. For the victim’s survival, even minutes may play a critical part. To strengthen the performance of the SAR community, the research community could introduce some creative technologies. With faster victim searches, initial assessment and visualization of the environment, and real-time assessment and management of search and rescue operations, multi-robot programs can significantly increase the productivity of search and rescue operations. This article proposes an intelligent algorithm based on the fruit fly optimization algorithm’s food search pattern. To update the fruit flies’ position and speed, it uses particle swarm optimization. Repeated research simulations have confirmed the feasibility of the proposed process in a forest-like environment. The simulation results under different scenarios and performance comparison with existing techniques show the proposed algorithm’s accuracy and robustness to be quite efficient in terms of detection rate and search and rescue time. The detection rate improves 10-25% and search and rescue time by 5 to 15%.","PeriodicalId":433590,"journal":{"name":"2022 IEEE World Conference on Applied Intelligence and Computing (AIC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129230235","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}

引用次数: 0

Heart Rate Prediction from Human Speech using Regression Models 基于回归模型的人类语音心率预测

2022 IEEE World Conference on Applied Intelligence and Computing (AIC) Pub Date : 2022-06-17 DOI: 10.1109/AIC55036.2022.9848913

S. Redekar, Aditi Sawant, Rajkumar Kolanji, Nirmit Sawant

{"title":"Heart Rate Prediction from Human Speech using Regression Models","authors":"S. Redekar, Aditi Sawant, Rajkumar Kolanji, Nirmit Sawant","doi":"10.1109/AIC55036.2022.9848913","DOIUrl":"https://doi.org/10.1109/AIC55036.2022.9848913","url":null,"abstract":"The heart and the mind are intimately connected. Negative states of mind, including depression, anxiety, loneliness, anger, and chronic stress, may increase the risk for heart disease over time or worsen heart issues that already exist. Heart Rate (HR) monitor is a term used to describe a device that monitors and records the HR in real time. Electrode leads linked to the chest were utilized in the early types of HR monitors. We thought of whether and if possible, the way we speak can be used to predict HR. As we know, speech is affected by the emotional environment so we can not only rely on the basic classification of speech so, we need to consider other factors to analyze and predict. This is where the spectral features come into the picture, one of them being MFCC. So, we move away from a conventional model to prove that your voice does depict and give what your HR is. Voice-based detection of HR is attractive because it does not require any additional sensors. In contrast to previous studies, we use real-time speech data as input. Regression is used when we can have the output over a range of values of the class label. In our case, it is the heart rate that can vary over a range of 60 to 130 in ideal conditions. We decided to compare various algorithms under regression and find the one with the best accuracy Results using random forest show modest but significant effects on HR predictions.","PeriodicalId":433590,"journal":{"name":"2022 IEEE World Conference on Applied Intelligence and Computing (AIC)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115197646","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}

引用次数: 0

Welcome from IEEE AIC 2022 General Chair 欢迎来自IEEE AIC 2022的总主席

2022 IEEE World Conference on Applied Intelligence and Computing (AIC) Pub Date : 2022-06-17 DOI: 10.1109/aic55036.2022.9848849

引用次数: 0

Developing a Multi-Module Machine Learning System to Identify Clinically Important Traumatic Brain Injuries in Children 开发多模块机器学习系统以识别临床重要的儿童创伤性脑损伤

2022 IEEE World Conference on Applied Intelligence and Computing (AIC) Pub Date : 2022-06-17 DOI: 10.1109/AIC55036.2022.9848900

Melody Yin

{"title":"Developing a Multi-Module Machine Learning System to Identify Clinically Important Traumatic Brain Injuries in Children","authors":"Melody Yin","doi":"10.1109/AIC55036.2022.9848900","DOIUrl":"https://doi.org/10.1109/AIC55036.2022.9848900","url":null,"abstract":"Clinically important traumatic brain injuries (ciTBI) are a major health concern, yet early recognition is challenging. This research developed a multi-module machine learning system for efficient pre-screening and diagnosis with improved specificity. The study achieved a lower false positive rate and reduced unnecessary computed tomography (CT) scans, which pose risks especially for children. This system consists of three independent modules intended to assist ciTBI diagnosis. Module 1 prescreens patients using clinical metrics to determine if a CT scan is necessary, reaching specificities of 98.85% and 98.73% and positive predictive values 32.43% and 33.33% for ages under and over 2, respectively, better than previous reports. Module 2, a hybrid model, integrates clinical metrics and CT scans to predict ciTBI. Accuracy reached 99.08% and 99.28%, specificity 99.21% and 99.48%, and NPV 99.86% and 99.78% for the respective age groups, further improving previous results. Module 3 used CNNs to detect CT image abnormalities, achieving an accuracy of 86.56% and AUC ROC of 83.79%. The proposed system demonstrated the ability to improve current ED procedural efficiency by detecting higher risk cases with low false negative rate for early recognition and management.","PeriodicalId":433590,"journal":{"name":"2022 IEEE World Conference on Applied Intelligence and Computing (AIC)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124732236","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}

引用次数: 0

Comparative Study of Feature Engineering for Automated Short Answer Grading 特征工程在自动简答评分中的比较研究

2022 IEEE World Conference on Applied Intelligence and Computing (AIC) Pub Date : 2022-06-17 DOI: 10.1109/AIC55036.2022.9848851

Patil Shweta, K. Adhiya

{"title":"Comparative Study of Feature Engineering for Automated Short Answer Grading","authors":"Patil Shweta, K. Adhiya","doi":"10.1109/AIC55036.2022.9848851","DOIUrl":"https://doi.org/10.1109/AIC55036.2022.9848851","url":null,"abstract":"Recent advancement in the field of Natural Language Processing (NLP) has shown promising results in numerous NLP applications. Automated Short Answer Grading (ASAG) is one of the challenging applications of NLP. Understanding the underlying context and semantics in text will help to evaluate short answer responses and predict the scores more similar to human evaluator. Training machine to understand the domain knowledge of courses and utilize the same for evaluation has demanded for more robust method to generate word vectors which are capable of understanding the meaning of words based on context. In this paper we have studied and experimented with already existing word vector generation techniques TF-IDF, word2vec and BERT. Along with the pre-trained word2vec we have computed domain specific word vectors too. Finally, by the utilization of XGBoost we have computed the category of student answer. The comparison of similarity between human evaluated category and category generated by all studied embedding technique along with XGBoost algorithm is computed with the help of Quadratic Weighted Kappa. The results have shown that domain specific embedding will help to predict correct category of student answer.","PeriodicalId":433590,"journal":{"name":"2022 IEEE World Conference on Applied Intelligence and Computing (AIC)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128768042","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}

引用次数: 2

Data Security in IoT Networks using Software-Defined Networking: A Review 使用软件定义网络的物联网网络中的数据安全:综述

2022 IEEE World Conference on Applied Intelligence and Computing (AIC) Pub Date : 2022-06-17 DOI: 10.1109/AIC55036.2022.9848896

S. Shah, Raghav Sharma, N. Shukla

引用次数: 0

Comparative Analysis on Ensemble Learning Techniques for Groundwater Quality Assessment of Chhattisgarh Region 恰蒂斯加尔邦地下水水质评价的集合学习技术比较分析

2022 IEEE World Conference on Applied Intelligence and Computing (AIC) Pub Date : 2022-06-17 DOI: 10.1109/AIC55036.2022.9848863

Anushree Shrivastava, Mridu Sahu, D. Jhariya

引用次数: 1

Semantic Image Segmentation using CNN (Convolutional Neural Network) based Technique 基于卷积神经网络的语义图像分割技术

2022 IEEE World Conference on Applied Intelligence and Computing (AIC) Pub Date : 2022-06-17 DOI: 10.1109/AIC55036.2022.9848977

B. Mahmud, G. Hong

{"title":"Semantic Image Segmentation using CNN (Convolutional Neural Network) based Technique","authors":"B. Mahmud, G. Hong","doi":"10.1109/AIC55036.2022.9848977","DOIUrl":"https://doi.org/10.1109/AIC55036.2022.9848977","url":null,"abstract":"Segmenting images makes computer vision applications more manageable. By breaking an image into smaller groups called “image segments,” an image segmentation approach simplifies the complexity of an image for later processing or analysis. Individual pixels are labeled as part of the process known as segmentation. Many computational research, modeling, and forecasts require a sufficient microstructure sample. An alternate method is to extrapolate a 2D image into a virtual 3D sample, which saves time and money compared to collecting 3D microstructural images. A CNN Architecture-based U-NET technique was used to find extrapolation-based reconstructions for alloys, porous media, and sandstones. Using a deep convolutional neural network, VGG16, the objective function in this optimization is built using microstructural properties. We use a permutation operator to create multiclass feature maps from these stacks. Sandstone datasets, which contain a number of unique materials, are used to demonstrate the actual application of our technique. Pre-annotated data was used to guide our analysis. Image reconstruction is a commonly used approach in various fields for deciphering the many objects in a picture. Using U-NET, we first segment the photographs and then reassemble the image slices to be shown. The overall IoU and accuracy rates for this suggested design were both high, at 85% and 96%, respectively.","PeriodicalId":433590,"journal":{"name":"2022 IEEE World Conference on Applied Intelligence and Computing (AIC)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114505944","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}

引用次数: 1

A review on Secutity in Internet of Things 物联网安全研究综述

2022 IEEE World Conference on Applied Intelligence and Computing (AIC) Pub Date : 2022-06-17 DOI: 10.1109/AIC55036.2022.9848853

Eisha Akanksha, A. Javali, Jyoti

引用次数: 1