{"title":"Prediction of Neuro Cognitive Disorders using Supervised Comparative Machine Learning Model & Scanpath Representations","authors":"V. Vinayak, Mohan Paliwal, A. J, J. C.","doi":"10.1109/I2CT57861.2023.10126188","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126188","url":null,"abstract":"Dementia has become a pressing public health issue worldwide, with the number of affected individuals steadily increasing. As a syndrome, it is characterized by a decline in cognitive performance that extends beyond normal biological aging, caused by a diverse range of brain disorders and diseases. Alzheimer’s disease is the most prevalent form of dementia, and it constitutes the majority of dementia cases. In addition to its physical and psychological impacts, dementia is also a significant economic burden on families and society at large, given the extensive care required. One potential approach to understanding the cognitive performance of individuals with dementia is the use of scan path representations. A scan path is a visual representation of eye movements and is created by an ordered set of fixations connected by saccades. By analyzing these patterns, researchers aim to better understand the visual behaviors of people with dementia and potentially develop more effective treatment options. To achieve this goal, the proposed supervised comparative machine learning model utilizes scan path representations to provide a more comprehensive understanding of dementia. By exploring the visual behaviors of individuals with the condition, the model aims to provide insights into the use of supervised machine learning algorithms in trail making tests to better classify the dementia patients using their scanpath representations. This research paper aims to contribute to the ongoing efforts to combat the global challenge of dementia and provide a more nuanced understanding of the condition.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122638182","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}
{"title":"Analytical Performance of Traditional Feature Selection Methods on High Dimensionality Data","authors":"D. S., Bharath Mahesh Gera, K. N.","doi":"10.1109/I2CT57861.2023.10126303","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126303","url":null,"abstract":"Dimensionality Reduction is a technique to select features or split contents from a dataset which reduces the dimension. Dimensionality Reduction techniques reduce the computational time to train the Machine Learning Model using the selected features to predict an outcome with higher accuracy. Feature Selection is a part of Dimensionality Reduction which reduces the number of features when developing a model for predictions. Wrapper method is used as Sequential Feature Selection to select the features from the dataset which contributes highly towards the accuracy of the model. Breast Cancer dataset, Vehicle Loan dataset and Loan Defaulter dataset have been used to compare four traditional feature selection algorithms. Once the features are selected from each of the four algorithms, we train the Logistic [15] Regression Model (ML Model) with those features which gives us the computational time and accuracy. Using computational time and accuracy given by the model, of the features selected, of all four algorithms; we put together a comparison.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122934511","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}
Subhash Mondal, Souptik Dutta, Soumadip Ghosh, Sarbartha Gupta, Dhrubajit Kakati, A. Nag
{"title":"Thyroid Disease Prediction Model on Boosting-based Stacking Ensemble Approach","authors":"Subhash Mondal, Souptik Dutta, Soumadip Ghosh, Sarbartha Gupta, Dhrubajit Kakati, A. Nag","doi":"10.1109/I2CT57861.2023.10126389","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126389","url":null,"abstract":"The thyroid gland plays a significant role in the human body's metabolism, growth, and development. Though it is not a life-threatening disease, a person suffering from thyroid faces many complications in their daily life. Recent trends have shown that women suffer more from thyroid-related diseases than men. The many contributing factors that lead to thyroid disease may be controlled upon early diagnosis stages. Machine learning prediction models help healthcare professionals diagnose thyroid diseases at an initial stage and take measures accordingly. This study deployed initial Sixteen ML models, including six boosting algorithms, on a dataset of 9172 instances with related features. The model performances have been judged through various standard performance metrics. The boosting algorithms showed exceptional results, and Cat Boost (CB) model produced the best accuracy of 95.75%. The hyperparameter tuning performed on boosting models by implementing Randomized Search CV increased the accuracy to 96.19% for CB. The stacking ensemble approach was applied on top of the six boosting tuned models with the CB classifier as the meta-learner. At the same time, the other boosting algorithms were kept as a base learner for the final model prediction. The accuracy of the stack model was impressive, with 95.32% compared with default models, the ROC-AUC at 0.95, and the other results were also promising. The model’s standard deviation was significantly less at 0.57, implying the model’s stability and robustness, and the False Negative (FN) rate reached 1.8%.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123849999","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}
{"title":"Weighted Pooling RoBERTa for Effective Text Emotion Detection","authors":"Meenu Mathew, J. Prakash","doi":"10.1109/I2CT57861.2023.10126396","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126396","url":null,"abstract":"Textual emotion detection is a classification problem that assigns different emotions to a given text input. It reveals the writer’s mental state. Its diversity and uncertainty make it a challenging task. The existing methods in machine learning can be used for emotion detection; however, it fails in processing very long passages. In this work, we employ weighted pooling pretrained RoBERTa model for effective textual emotion detection. To perform experiments, we use two data sets, ISEAR and tweets, with 7516 and 21048 records, respectively. Precision, recall, F1-score, and classification accuracy are used to assess the models. Experimental results indicate that the weighted pooling RoBERTa model outperforms the deep learning models on both datasets with significant improvement in accuracy.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123853003","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}
Janani T, Nandhini Jagadeesan, Shivangi Pandey, Divya B
{"title":"Design and Development of A Brain Computer Interface Controlled Wheelchair Prototype","authors":"Janani T, Nandhini Jagadeesan, Shivangi Pandey, Divya B","doi":"10.1109/I2CT57861.2023.10126472","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126472","url":null,"abstract":"Wheelchairs are the most prominently used assistive devices. They are used for different kinds of disabilities which can include entire lower body paralysis, multiple sclerosis, or for elderly people who have degenerated mobility. This work attempts to enhance the life’s quality of people with locomotive disabilities by providing automotive control to the wheelchair using the non-invasive Brain Computer Interface (BCI) module instead of applying manual force. The EEG signals are processed and converted into mental command by the NeuroSky MindWave headset. The system acquires and analyzes the alpha and beta waves produced by the brain to determine the attention and meditation level of the user along with eye blinks being recognized as disruption to the signal. These parameters are used to frame an algorithm and command the movements of the wheelchair which are forward, backward, left, and right.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124111504","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}
{"title":"Implementation of stochastic computing in activation functions using stochastic arithmetic components","authors":"P. Ashok, B. T. Sundari","doi":"10.1109/I2CT57861.2023.10126491","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126491","url":null,"abstract":"A new computing method using stochastic-based numbers is gaining importance as an approximate computing method to save area, energy, and computation time based on the accuracy required. This works uses stochastic computing, which is suitable for enhancing the efficiency of neural network. Herein we focus on developing activation functions that are essential parameters in the design of neural networks. The activation function in stochastic computing is typically a threshold function that maps the input bits to a binary output based on a probability distribution. This paper presents the development of modified activation functions tanh and COS using SC-based arithmetic components. Two different types of stochastic number generators (SNGs) have been used. Error analysis has been done based on the computation using two SNGs. Also, accuracy measurement is performed using error analysis for these complex functions mentioned above.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125163226","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}
{"title":"Deep Convolution Neural Network-Based Classification and Diagnosis of Heart Disease using ElectroCardioGram (ECG) Images","authors":"Thanu Kurian, T. S","doi":"10.1109/I2CT57861.2023.10126473","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126473","url":null,"abstract":"A cardiovascular disease, if identified correctly at an early stage, could reduce the critical consequences in patients , including fatality. One of the best diagnostic tool for detecting heart disease is through an ECG test. Models trained using signal data related to ECG is difficult to be implemented in an actual healthcare scenario. A CNN model is proposed which makes use of 12-lead ECG images to diagnose cardiac conditions such as myocardial infarction, abnormal heart beat, history of myocardial infarction and normal heartbeat. The ECG image can be taken by scanning the image using a smart phone. This would be very helpful in small healthcare centers where there are no experts for diagnosis. The proposed model was efficiently trained with an accuracy of 99% and cardiac condition was diagnosed using ECG images scanned using a mobile with a superior performance. The work also compares the performance of model with pretrained models as ResNet and EfficientNet-B0 for the same ECG image dataset.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125181784","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}
{"title":"PQTBA: Priority Queue based Token Bucket Algorithm for congestion control in IoT network","authors":"A. P, Vimala H S, J Shreyas","doi":"10.1109/I2CT57861.2023.10126166","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126166","url":null,"abstract":"The Internet of Things connects millions of devices in the areas of smart cities, e-health, transportation, and the military to fulfill a variety of human needs. To offer these services, a large amount of data must be transmitted to the IoT network servers. But the node processing power, buffer size, and server capacity limitations on IoT networks have a negative influence on throughput, latency, and energy consumption. Additionally, the IoT network’s performance is decreased by congestion caused by the high network traffic that results from the high volume of data. In order to handle congestion challenges in IoT networks, unique congestion control strategies—such as the queue management strategy—must be created. In this study, a novel Priority Queue-based Token Bucket Algorithm (PQTBA) is suggested as a means of controlling congestion in IoT networks. The PQTBA uses a preemptive/non-preemptive technique with a discretionary rule to categorize network traffic into priority groups in accordance with real-time requirements. Our proposed work performs con-siderably better than the most recent techniques in terms of throughput, packet loss ratio, and energy consumption.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125581063","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}
{"title":"Indoor Localization Advancement Using Wasserstein Generative Adversarial Networks","authors":"Shivam Kumar, Saikat Majumder, S. Chakravarty","doi":"10.1109/I2CT57861.2023.10126229","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126229","url":null,"abstract":"Fingerprint-based indoor localization methods rely on a database of Received Signal Strength (RSS) measurements and corresponding location labels. However, collecting and maintaining such a database can be costly and time consuming. In this work, we proposed Wasserstein Generative Adversarial Networks (WGAN) to generate synthetic data for fingerprinting-based indoor localization. The proposed system consists of a WGAN that is trained on a dataset of real RSS measurements and corresponding location labels. The generator of the WGAN learns to generate synthetic RSS measurements, and the critic learns to differentiate the generated and the real measurements. We validate the proposed system on a dataset of real RSS measurements. The result of the proposed system shows better localization accuracy as compared to using real data, while being more cost-effective and scalable.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125676925","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}
Nilesh P. Sable, R. Bhimanpallewar, Rajhendra H Mehta, Sara Shaikh, Anay Indani, S. Jadhav
{"title":"A Machine Learning approach for Early Detection and Prevention of Obesity and Overweight","authors":"Nilesh P. Sable, R. Bhimanpallewar, Rajhendra H Mehta, Sara Shaikh, Anay Indani, S. Jadhav","doi":"10.1109/I2CT57861.2023.10126346","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126346","url":null,"abstract":"More than 2.1 billion people worldwide are shuddering from overweightness or obesity, which represents approximately 30% of the world’s population. Obesity is a serious global health problem. By 2030, 41% of people will likely be overweight or obese, if the current trend continues. People who show indications of weight increase or obesity run the danger of contracting life-threatening conditions including type 2 diabetes, respiratory issues, heart disease, and stroke. Some intervention strategies, like regular exercise and a balanced diet, might be essential to preserving a healthy lifestyle. Thus, it is crucial to identify obesity as soon as feasible. We have collected data from sources like schools and colleges within our organization to create our dataset. A vast range of ages is considered and the BMI value is examined in order to determine the level of obesity. The dataset of people with normal BMI and those at risk has an inherent imbalance. The outcomes are collected and showcased via a website which also includes various preventive measures and calculators. The outcomes are promising, and clock an accuracy of about 90%.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129799278","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}