Pub Date : 2022-12-17DOI: 10.1109/ICCIT57492.2022.10055134
Satirtha Paul Shyam, C. M. A. Rahman, H. Rashid
Compared to edge-based models, region-based active contour models (ACM) have demonstrated superior performance in a number of areas, including noise tolerance, back- ground complexity and inhomogeneity correction, initialization resilience, and speed of curve evolution. However, combining both of their credentials with suitable and relevant parameters exhibits promising potential in enhancing segmentation performance. Therefore, this work reports an effective fusion of optimized Difference of Gaussian (DoG) edge estimation, with the region scalable fitting ( RSF) m odel t o c apitalize o n t heir a ttributes. A locally computed edge entropy image is also used as a weight to the energy functional to infuse local edge information in the energy functional. With the integration of relevant edge and region based feature descriptors, the proposed model thereby, outperforms the established ACMs in terms of iteration time, noise tolerance, initial contour convergence, inhomogeneity suppression and segmentation accuracy.
{"title":"A Faithful DoG is All you Need","authors":"Satirtha Paul Shyam, C. M. A. Rahman, H. Rashid","doi":"10.1109/ICCIT57492.2022.10055134","DOIUrl":"https://doi.org/10.1109/ICCIT57492.2022.10055134","url":null,"abstract":"Compared to edge-based models, region-based active contour models (ACM) have demonstrated superior performance in a number of areas, including noise tolerance, back- ground complexity and inhomogeneity correction, initialization resilience, and speed of curve evolution. However, combining both of their credentials with suitable and relevant parameters exhibits promising potential in enhancing segmentation performance. Therefore, this work reports an effective fusion of optimized Difference of Gaussian (DoG) edge estimation, with the region scalable fitting ( RSF) m odel t o c apitalize o n t heir a ttributes. A locally computed edge entropy image is also used as a weight to the energy functional to infuse local edge information in the energy functional. With the integration of relevant edge and region based feature descriptors, the proposed model thereby, outperforms the established ACMs in terms of iteration time, noise tolerance, initial contour convergence, inhomogeneity suppression and segmentation accuracy.","PeriodicalId":255498,"journal":{"name":"2022 25th International Conference on Computer and Information Technology (ICCIT)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131160724","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}
Pub Date : 2022-12-17DOI: 10.1109/ICCIT57492.2022.10054644
Nusratul Jannat, Avishek Das, Omar Sharif, M. M. Hoque
Advances in social media platforms led to the widespread adoption of memes, making them a powerful communication tool on the internet. Memes’ visual aspect gives them a remarkable ability to influence users’ opinions. However, individuals misemploy this popularity to foment animosity. The spread of these hostile memes can have a detrimental effect on people, causing depression and suicidal thoughts. Therefore, stopping inappropriate memes from spreading on the internet is crucial. However, identifying memes is di cult due to their multimodal nature. This paper proposes a deep-learning-based framework to classify sentiment (into ‘positive’ or ‘negative’) from multimodal memes in Bengali. Due to the unavailability of standard corpora, a Bengali meme corpus consisting of 1671 memes is developed to perform the memes’ sentiment classification task. Five popular deep learning models (CNN, BiLSTM) and pre-trained models (VGG16, VGG19, InceptionV3) are investigated for textual and visual features. The framework is developed by combining visual and textual models. The comparative analysis confirms that the proposed model (BiLSTM + VGG19) achieved the highest f1-score (0.68) compared to other multimodal methods.
{"title":"An Empirical Framework for Identifying Sentiment from Multimodal Memes using Fusion Approach","authors":"Nusratul Jannat, Avishek Das, Omar Sharif, M. M. Hoque","doi":"10.1109/ICCIT57492.2022.10054644","DOIUrl":"https://doi.org/10.1109/ICCIT57492.2022.10054644","url":null,"abstract":"Advances in social media platforms led to the widespread adoption of memes, making them a powerful communication tool on the internet. Memes’ visual aspect gives them a remarkable ability to influence users’ opinions. However, individuals misemploy this popularity to foment animosity. The spread of these hostile memes can have a detrimental effect on people, causing depression and suicidal thoughts. Therefore, stopping inappropriate memes from spreading on the internet is crucial. However, identifying memes is di cult due to their multimodal nature. This paper proposes a deep-learning-based framework to classify sentiment (into ‘positive’ or ‘negative’) from multimodal memes in Bengali. Due to the unavailability of standard corpora, a Bengali meme corpus consisting of 1671 memes is developed to perform the memes’ sentiment classification task. Five popular deep learning models (CNN, BiLSTM) and pre-trained models (VGG16, VGG19, InceptionV3) are investigated for textual and visual features. The framework is developed by combining visual and textual models. The comparative analysis confirms that the proposed model (BiLSTM + VGG19) achieved the highest f1-score (0.68) compared to other multimodal methods.","PeriodicalId":255498,"journal":{"name":"2022 25th International Conference on Computer and Information Technology (ICCIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129736171","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}
Pub Date : 2022-12-17DOI: 10.1109/ICCIT57492.2022.10056025
Syed Muaz Ali, Md. Ashraful Alam
In medical application, deep learning-based biomedical semantic segmentation has provided state-of-the-art results and proven to be more efficient than manual segmentation by human interaction in various cases. One of the most popular architectures for biomedical segmentation is U-Net. In this paper, a convolutional neural architecture based on 3D U-Net but with fewer parameters and lower computational cost is used for the segmentation of brain tumors. The proposed model is able to maintain a very efficient performance and provides better results in some cases compared to conventional U-Net, while reducing memory usage, training time and inference time. The model is trained on the BraTS 2021 dataset and is able to achieve Dice scores of 0.9105, 0.884 and 0.8254 on Whole Tumor, Tumor Core and Enhancing-Tumor on the testing dataset.
{"title":"An Efficient Deep Learning Approach for Brain Tumor Segmentation using 3D Convolutional Neural Network","authors":"Syed Muaz Ali, Md. Ashraful Alam","doi":"10.1109/ICCIT57492.2022.10056025","DOIUrl":"https://doi.org/10.1109/ICCIT57492.2022.10056025","url":null,"abstract":"In medical application, deep learning-based biomedical semantic segmentation has provided state-of-the-art results and proven to be more efficient than manual segmentation by human interaction in various cases. One of the most popular architectures for biomedical segmentation is U-Net. In this paper, a convolutional neural architecture based on 3D U-Net but with fewer parameters and lower computational cost is used for the segmentation of brain tumors. The proposed model is able to maintain a very efficient performance and provides better results in some cases compared to conventional U-Net, while reducing memory usage, training time and inference time. The model is trained on the BraTS 2021 dataset and is able to achieve Dice scores of 0.9105, 0.884 and 0.8254 on Whole Tumor, Tumor Core and Enhancing-Tumor on the testing dataset.","PeriodicalId":255498,"journal":{"name":"2022 25th International Conference on Computer and Information Technology (ICCIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129025471","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}
Thyroid illness is a medical disorder in which the thyroid gland fails to produce enough hormones. Males, females, babies, teenagers, and the elderly are all susceptible to thyroid illness. It could be present from birth (hypothyroidism), or it could develop as you become older (often after menopause in women). People with thyroid diseases suffer from various problems like gaining weight, forgetfulness, anxiety, losing weight, fatigue, sleeping disorder, etc. So, diagnosing thyroid diseases is a vital issue as the diseases can be cured through proper and timely diagnosis. Recently machine learning techniques are used for diagnosing thyroid diseases. The feature selection approach was used to eliminate certain irrelevant characteristics from the thyroid dataset (from the UCI machine learning repository) and to select optimal features. The dataset has three target classes named normal, hypothyroid, and hyperthyroid. The subjects were classified through seven different machine-learning algorithms. Random Forest classifier achieves the highest accuracy 99.58% which is better than the existing state-of-the-art methods.
{"title":"Thyroid Disease Prediction based on Feature Selection and Machine Learning","authors":"Zahrul Jannat Peya, Md. Shymon Islam, Mst. Kamrun Naher Chumki","doi":"10.1109/ICCIT57492.2022.10054746","DOIUrl":"https://doi.org/10.1109/ICCIT57492.2022.10054746","url":null,"abstract":"Thyroid illness is a medical disorder in which the thyroid gland fails to produce enough hormones. Males, females, babies, teenagers, and the elderly are all susceptible to thyroid illness. It could be present from birth (hypothyroidism), or it could develop as you become older (often after menopause in women). People with thyroid diseases suffer from various problems like gaining weight, forgetfulness, anxiety, losing weight, fatigue, sleeping disorder, etc. So, diagnosing thyroid diseases is a vital issue as the diseases can be cured through proper and timely diagnosis. Recently machine learning techniques are used for diagnosing thyroid diseases. The feature selection approach was used to eliminate certain irrelevant characteristics from the thyroid dataset (from the UCI machine learning repository) and to select optimal features. The dataset has three target classes named normal, hypothyroid, and hyperthyroid. The subjects were classified through seven different machine-learning algorithms. Random Forest classifier achieves the highest accuracy 99.58% which is better than the existing state-of-the-art methods.","PeriodicalId":255498,"journal":{"name":"2022 25th International Conference on Computer and Information Technology (ICCIT)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126328702","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}
Pub Date : 2022-12-17DOI: 10.1109/ICCIT57492.2022.10055636
M. Rahman, Faisal Bin Ashraf, Md Rayhan Kabir
People connect with a plethora of information from many online portals due to the availability and ease of access to the internet and electronic communication devices. However, news portals sometimes abuse press freedom by manipulating facts. Most of the time, people are unable to discriminate between true and false news. It is difficult to avoid the detrimental impact of Bangla fake news from spreading quickly through online channels and influencing people’s judgment. In this work, we investigated many real and false news pieces in Bangla to discover a common pattern for determining if an article is disseminating incorrect information or not. We developed a deep learning model that was trained and validated on our selected dataset. For learning, the dataset contains 48,678 legitimate news and 1,299 fraudulent news. To deal with the imbalanced data, we used random undersampling and then ensemble to achieve the combined output. In terms of Bangla text processing, our proposed model achieved an accuracy of 98.29% and a recall of 99%.
{"title":"An Efficient Deep Learning Technique for Bangla Fake News Detection","authors":"M. Rahman, Faisal Bin Ashraf, Md Rayhan Kabir","doi":"10.1109/ICCIT57492.2022.10055636","DOIUrl":"https://doi.org/10.1109/ICCIT57492.2022.10055636","url":null,"abstract":"People connect with a plethora of information from many online portals due to the availability and ease of access to the internet and electronic communication devices. However, news portals sometimes abuse press freedom by manipulating facts. Most of the time, people are unable to discriminate between true and false news. It is difficult to avoid the detrimental impact of Bangla fake news from spreading quickly through online channels and influencing people’s judgment. In this work, we investigated many real and false news pieces in Bangla to discover a common pattern for determining if an article is disseminating incorrect information or not. We developed a deep learning model that was trained and validated on our selected dataset. For learning, the dataset contains 48,678 legitimate news and 1,299 fraudulent news. To deal with the imbalanced data, we used random undersampling and then ensemble to achieve the combined output. In terms of Bangla text processing, our proposed model achieved an accuracy of 98.29% and a recall of 99%.","PeriodicalId":255498,"journal":{"name":"2022 25th International Conference on Computer and Information Technology (ICCIT)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122547055","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}
Pub Date : 2022-12-17DOI: 10.1109/ICCIT57492.2022.10055860
Nasehatul Mustakim, Avishek Das, Omar Sharif, M. M. Hoque
People usually express their emotions, views, or sentiment in textual form. The textual sentiment analysis (TSA) identifies or classifies opinions or feelings from texts in a predefined class. The TSA is complicated or infeasible manually due to its voluminous nature and unstructured or messy conditions. Therefore, the automatic sentiment analysis method quickly paves the way to identify the hidden sentiment polarity from the textual content. Although a few studies on sentiment analysis were conducted on a single or specific domain, developing the TSA method concerning multi-domains is unexplored in Bengali. This paper presents a deep learning-based framework called DeepSen to detect textual sentiment from Bengali texts into three polarities: positive, negative and neutral. Four benchmark corpora from available domains, Book, Restaurant, Drama and Cricket, have been used to analyze sentiment from multi-domain heterogeneous data. This work investigates six popular machine learning (LR, DT, MNB, SVM, RF, AdaBoost) and five deep learning (CNN, LSTM, GRU, BiGRU, BiLSTM) techniques using four benchmark Bengali corpora to perform TSA tasks. The evaluation result reveals that the BiLSTM method obtained the highest weighted f1-score (0.85) among all models.
{"title":"DeepSen: A Deep Learning-based Framework for Sentiment Analysis from Multi-Domain Heterogeneous Data","authors":"Nasehatul Mustakim, Avishek Das, Omar Sharif, M. M. Hoque","doi":"10.1109/ICCIT57492.2022.10055860","DOIUrl":"https://doi.org/10.1109/ICCIT57492.2022.10055860","url":null,"abstract":"People usually express their emotions, views, or sentiment in textual form. The textual sentiment analysis (TSA) identifies or classifies opinions or feelings from texts in a predefined class. The TSA is complicated or infeasible manually due to its voluminous nature and unstructured or messy conditions. Therefore, the automatic sentiment analysis method quickly paves the way to identify the hidden sentiment polarity from the textual content. Although a few studies on sentiment analysis were conducted on a single or specific domain, developing the TSA method concerning multi-domains is unexplored in Bengali. This paper presents a deep learning-based framework called DeepSen to detect textual sentiment from Bengali texts into three polarities: positive, negative and neutral. Four benchmark corpora from available domains, Book, Restaurant, Drama and Cricket, have been used to analyze sentiment from multi-domain heterogeneous data. This work investigates six popular machine learning (LR, DT, MNB, SVM, RF, AdaBoost) and five deep learning (CNN, LSTM, GRU, BiGRU, BiLSTM) techniques using four benchmark Bengali corpora to perform TSA tasks. The evaluation result reveals that the BiLSTM method obtained the highest weighted f1-score (0.85) among all models.","PeriodicalId":255498,"journal":{"name":"2022 25th International Conference on Computer and Information Technology (ICCIT)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131357812","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}
Pub Date : 2022-12-17DOI: 10.1109/ICCIT57492.2022.10055777
S. Saha, R. Parvin, P. Ng, M. Khoo, Xinying Chew
The assessment of variables that influence the estimation, control, and regulation of the quality of analytical testing processes is increasingly being done using computer simulation. The quality management of manufacturing firms is introduced as a data mining application. For quality control and production management, quality factor analysis is crucial. Numerous studies have investigated the variable sampling interval (VSI) chart for the process average. Despite being significantly more widely used than the median chart, when faced with extremes or unforeseen data sets that cast doubt on the normality assumption, the mean ($bar X$ ) chart is less resistant. The median chart, however, is more effective than the process average chart when outliers or extreme values are present in the process data being monitored. Since practitioners may believe that process shifts could have happened in the dataset because of the extreme values, incorrect inferences may be drawn. To solve this challenge, the variable sampling interval (VSI) median chart is proposed in this study. The VSI feature is used to enhance the performance of the median chart. The average time to signal (ATS) and expected average time to signal (EATS) criteria are used to evaluate the performance of the proposed charts. Based on the ATS and EATS criteria, the results show that the proposed VSI median chart outperforms the Shewhart (SH) median chart in detecting all sizes of shifts.
{"title":"A proposed variable sampling interval median chart for identifying out-of-control signals in process control","authors":"S. Saha, R. Parvin, P. Ng, M. Khoo, Xinying Chew","doi":"10.1109/ICCIT57492.2022.10055777","DOIUrl":"https://doi.org/10.1109/ICCIT57492.2022.10055777","url":null,"abstract":"The assessment of variables that influence the estimation, control, and regulation of the quality of analytical testing processes is increasingly being done using computer simulation. The quality management of manufacturing firms is introduced as a data mining application. For quality control and production management, quality factor analysis is crucial. Numerous studies have investigated the variable sampling interval (VSI) chart for the process average. Despite being significantly more widely used than the median chart, when faced with extremes or unforeseen data sets that cast doubt on the normality assumption, the mean ($bar X$ ) chart is less resistant. The median chart, however, is more effective than the process average chart when outliers or extreme values are present in the process data being monitored. Since practitioners may believe that process shifts could have happened in the dataset because of the extreme values, incorrect inferences may be drawn. To solve this challenge, the variable sampling interval (VSI) median chart is proposed in this study. The VSI feature is used to enhance the performance of the median chart. The average time to signal (ATS) and expected average time to signal (EATS) criteria are used to evaluate the performance of the proposed charts. Based on the ATS and EATS criteria, the results show that the proposed VSI median chart outperforms the Shewhart (SH) median chart in detecting all sizes of shifts.","PeriodicalId":255498,"journal":{"name":"2022 25th International Conference on Computer and Information Technology (ICCIT)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122959771","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}
Pub Date : 2022-12-17DOI: 10.1109/ICCIT57492.2022.10056111
Saifuddin Mahmud, M. Ferdous, R. Sourave, Mohammad Insanur Rahman Shuvo, Jong-Hoon Kim
Routine inspections and emergency response are unavoidable needs for power plants, oil refineries, iron works, and industrial units, as they directly influence output and safety. By utilizing autonomous robots, they can be improved. With the exception of facilities located in hazardous areas, such as off-shore factories, where dispatching people might be impossible, accidents caused by human mistakes can be prevented by autonomous inspections and diagnosis of facilities (pumps, tanks, boilers, and so on). Furthermore, if any disaster or accident happens in the plant victims should get immediate assistance. Autonomous robots can enable quick emergency assistance for victims once they are detected. The primary obstacles in robot-assisted inspection operations and victim detection are identifying various types of gauges and reading them, detecting the actual victims in any lighting condition, and taking appropriate actions. This study describes a unique robot vision system for plant inspection and victim detection system that may be used to enhance the frequency of routine checks, hence minimizing equipment faults and accidents (explosions or fires caused by gas leaks) caused by human mistakes or degradation and detecting victims to provide an immediate response. This suggested system can conduct facility inspections by detecting and reading a variety of gauges and finding victims, and it issues reports if any anomalies are discovered. Furthermore, this system can respond to unforeseen anomalous events that are potentially harmful to people and execute specific activities such as valve control if necessary.
{"title":"An Essential Robot Vision System for Robot Assisted Plant Disaster Prevention and Response Missions","authors":"Saifuddin Mahmud, M. Ferdous, R. Sourave, Mohammad Insanur Rahman Shuvo, Jong-Hoon Kim","doi":"10.1109/ICCIT57492.2022.10056111","DOIUrl":"https://doi.org/10.1109/ICCIT57492.2022.10056111","url":null,"abstract":"Routine inspections and emergency response are unavoidable needs for power plants, oil refineries, iron works, and industrial units, as they directly influence output and safety. By utilizing autonomous robots, they can be improved. With the exception of facilities located in hazardous areas, such as off-shore factories, where dispatching people might be impossible, accidents caused by human mistakes can be prevented by autonomous inspections and diagnosis of facilities (pumps, tanks, boilers, and so on). Furthermore, if any disaster or accident happens in the plant victims should get immediate assistance. Autonomous robots can enable quick emergency assistance for victims once they are detected. The primary obstacles in robot-assisted inspection operations and victim detection are identifying various types of gauges and reading them, detecting the actual victims in any lighting condition, and taking appropriate actions. This study describes a unique robot vision system for plant inspection and victim detection system that may be used to enhance the frequency of routine checks, hence minimizing equipment faults and accidents (explosions or fires caused by gas leaks) caused by human mistakes or degradation and detecting victims to provide an immediate response. This suggested system can conduct facility inspections by detecting and reading a variety of gauges and finding victims, and it issues reports if any anomalies are discovered. Furthermore, this system can respond to unforeseen anomalous events that are potentially harmful to people and execute specific activities such as valve control if necessary.","PeriodicalId":255498,"journal":{"name":"2022 25th International Conference on Computer and Information Technology (ICCIT)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128462267","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}
Pub Date : 2022-12-17DOI: 10.1109/ICCIT57492.2022.10055067
Md. Tauhiduzzaman Khan, Shabnam Ghaffarzadegan, Z. Feng, T. Hasan
Dietary habits play a significant role in public health and well-being. Monitoring dietary activities is thus essential for maintaining a healthy lifestyle and preventing many widespread diseases, such as diabetes, obesity, and hypertension. In this work, we present a low-cost wearable neckband for automatic diet activity monitoring. The $5 fabric-based device, comprising an electret microphone, a Bluetooth radio module, and a rechargeable Lithium-ion battery, can wirelessly transmit audio to a smart device in real-time. The classification algorithm processes the audio stream in 3s segments and extracts short-time spectral, waveform, and energy-based acoustic features. We compute various statistical functions from the acoustic features to obtain segmental feature vectors, which are subsequently used for machine learning. We perform an experimental evaluation using an in-house dataset collected using the neckband. We compare the performance of different classifiers in distinguishing between drinking, chewing solid foods, and other non-dietary activities. An averaged class-wise F-measure of 81.25% is achieved using the proposed wearable device and a Random Forest (RF) based classifier.
{"title":"A Fabric-based Inexpensive Wearable Neckband for Accurate and Reliable Dietary Activity Monitoring","authors":"Md. Tauhiduzzaman Khan, Shabnam Ghaffarzadegan, Z. Feng, T. Hasan","doi":"10.1109/ICCIT57492.2022.10055067","DOIUrl":"https://doi.org/10.1109/ICCIT57492.2022.10055067","url":null,"abstract":"Dietary habits play a significant role in public health and well-being. Monitoring dietary activities is thus essential for maintaining a healthy lifestyle and preventing many widespread diseases, such as diabetes, obesity, and hypertension. In this work, we present a low-cost wearable neckband for automatic diet activity monitoring. The $5 fabric-based device, comprising an electret microphone, a Bluetooth radio module, and a rechargeable Lithium-ion battery, can wirelessly transmit audio to a smart device in real-time. The classification algorithm processes the audio stream in 3s segments and extracts short-time spectral, waveform, and energy-based acoustic features. We compute various statistical functions from the acoustic features to obtain segmental feature vectors, which are subsequently used for machine learning. We perform an experimental evaluation using an in-house dataset collected using the neckband. We compare the performance of different classifiers in distinguishing between drinking, chewing solid foods, and other non-dietary activities. An averaged class-wise F-measure of 81.25% is achieved using the proposed wearable device and a Random Forest (RF) based classifier.","PeriodicalId":255498,"journal":{"name":"2022 25th International Conference on Computer and Information Technology (ICCIT)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128588139","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}
Pub Date : 2022-12-17DOI: 10.1109/ICCIT57492.2022.10055308
Ruhul Amin, Mohammad Shamsul Islam, Redwanul Islam Arif, Ashraful Islam, Md. Monir Hossain
Over time, how we used to keep track of our academic and work certificates has led to problems in terms of security and authenticity. The academic and experience certificate that a person gets over the course of their life are kept by centralized administrations with little to no connection with others. It becomes challenging to gather all these certificates from multiple institutions, arrange them together, and apply for a job. Because certificate forgery is so common, companies have a hard time getting official certifications, hurting the relationship between academia and business. The job market and educational institutions must be more efficient and open. Therefore, we made a blockchain-based integrated education-industry cooperative employment system where educational institutions and businesses can upload information and permit recruiters to use it. The recruiter can post job openings, and applicants looking for a job can apply by generating their CV. In our proposed method, we chose Hyperledger Fabric because of its ability to manage document permissions, transaction speed, scalability, no transaction fees, and other properties.
{"title":"Blockchain-based Integrated Application for Forged Elimination of Hiring System using Hyperledger Fabric 2.x","authors":"Ruhul Amin, Mohammad Shamsul Islam, Redwanul Islam Arif, Ashraful Islam, Md. Monir Hossain","doi":"10.1109/ICCIT57492.2022.10055308","DOIUrl":"https://doi.org/10.1109/ICCIT57492.2022.10055308","url":null,"abstract":"Over time, how we used to keep track of our academic and work certificates has led to problems in terms of security and authenticity. The academic and experience certificate that a person gets over the course of their life are kept by centralized administrations with little to no connection with others. It becomes challenging to gather all these certificates from multiple institutions, arrange them together, and apply for a job. Because certificate forgery is so common, companies have a hard time getting official certifications, hurting the relationship between academia and business. The job market and educational institutions must be more efficient and open. Therefore, we made a blockchain-based integrated education-industry cooperative employment system where educational institutions and businesses can upload information and permit recruiters to use it. The recruiter can post job openings, and applicants looking for a job can apply by generating their CV. In our proposed method, we chose Hyperledger Fabric because of its ability to manage document permissions, transaction speed, scalability, no transaction fees, and other properties.","PeriodicalId":255498,"journal":{"name":"2022 25th International Conference on Computer and Information Technology (ICCIT)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116346911","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：