Pub Date : 2022-03-23DOI: 10.1109/DASA54658.2022.9765309
Indah Wigati, Mia Fithriyah
For the world of education, including students, instructors, and policymakers for adoption of digital literacy has now become a key concern. Teachers must be aware of the importance of mastering digital literacy in the learning experience. After the Covid-19 epidemic, this research intends to examine educator knowledge of the application of digital literacy in the learning process. The study employs a quantitative descriptive technique to carefully review the types of teacher digital literacy awareness, supportive factors in the usage of digital literacy, and the consequences of tutor computer literacy recognition following the Covid 19 epidemic. The research process was conducted in the Islamic Public Senior High School (MAN) in Palembang, Sumatra. The consistent findings indicated that positive' competence of digital literacy was significant in terms of their capacity to use technology about 100%. The most influential supporting factor correctly is the motivation of friends (97.90%). The implication of using digital literacy for teachers is the execution of virtual meeting learning (94%). The logical conclusion of this study is that teachers develop awareness in utilizing technology, and it is more effortless to convey material after the Covid-19 pandemic. Mastery of digital literacy for teachers needs to be carefully reviewed to the stage of performance and application to students.
{"title":"Post Covid-19 Strategy Through Supporting Teacher Digital Literacy as the Sustainable Decision to Enhance Education System: Indonesia Case Study","authors":"Indah Wigati, Mia Fithriyah","doi":"10.1109/DASA54658.2022.9765309","DOIUrl":"https://doi.org/10.1109/DASA54658.2022.9765309","url":null,"abstract":"For the world of education, including students, instructors, and policymakers for adoption of digital literacy has now become a key concern. Teachers must be aware of the importance of mastering digital literacy in the learning experience. After the Covid-19 epidemic, this research intends to examine educator knowledge of the application of digital literacy in the learning process. The study employs a quantitative descriptive technique to carefully review the types of teacher digital literacy awareness, supportive factors in the usage of digital literacy, and the consequences of tutor computer literacy recognition following the Covid 19 epidemic. The research process was conducted in the Islamic Public Senior High School (MAN) in Palembang, Sumatra. The consistent findings indicated that positive' competence of digital literacy was significant in terms of their capacity to use technology about 100%. The most influential supporting factor correctly is the motivation of friends (97.90%). The implication of using digital literacy for teachers is the execution of virtual meeting learning (94%). The logical conclusion of this study is that teachers develop awareness in utilizing technology, and it is more effortless to convey material after the Covid-19 pandemic. Mastery of digital literacy for teachers needs to be carefully reviewed to the stage of performance and application to students.","PeriodicalId":231066,"journal":{"name":"2022 International Conference on Decision Aid Sciences and Applications (DASA)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123913989","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 : 2022-03-23DOI: 10.1109/DASA54658.2022.9765114
S. Rani, Sandeep Kumar, D. Ghai, K. Prasad
Automatic detection of brain tumors from CT and MRI images is always an effortful task because of the complexity and heterogeneous images. Many neural networks architecture (NN) have recently been developed for segmentation and classification tasks and have proved quite successful. Studies that have taken into account the sizes of items have been rare; as a result, the majority of them show poor detection performance for tiny objects. This has the potential to have a significant influence on illness identification. Recently, the 3D neural network became popular because it can work with a large labeled dataset. We proposed a 3D Alex-Net-based architecture that can classify the different types of a brain tumors at an early stage. First, the image contour is identified and given to the classifier for class-wise identification. We tested our proposed approach on RSNA- MICCAI brain tumors and found that the proposed method delivers the highest accuracy, and the results provide a clear advantage for the classification of a brain tumor in medical images.
由于图像的复杂性和异质性，从CT和MRI图像中自动检测脑肿瘤一直是一项艰巨的任务。近年来，许多神经网络架构(NN)被开发用于分割和分类任务，并被证明是相当成功的。考虑到物品大小的研究很少;因此，它们中的大多数对微小物体的检测性能较差。这有可能对疾病鉴定产生重大影响。最近，3D神经网络因其可以处理大型标记数据集而受到欢迎。我们提出了一个基于3D alex - net的架构，可以在早期阶段对不同类型的脑肿瘤进行分类。首先，识别图像轮廓并将其交给分类器进行分类识别。我们在RSNA- MICCAI脑肿瘤上测试了我们提出的方法，发现我们提出的方法提供了最高的准确性，结果为医学图像中脑肿瘤的分类提供了明显的优势。
{"title":"Automatic Detection of Brain Tumor from CT and MRI Images using Wireframe model and 3D Alex-Net","authors":"S. Rani, Sandeep Kumar, D. Ghai, K. Prasad","doi":"10.1109/DASA54658.2022.9765114","DOIUrl":"https://doi.org/10.1109/DASA54658.2022.9765114","url":null,"abstract":"Automatic detection of brain tumors from CT and MRI images is always an effortful task because of the complexity and heterogeneous images. Many neural networks architecture (NN) have recently been developed for segmentation and classification tasks and have proved quite successful. Studies that have taken into account the sizes of items have been rare; as a result, the majority of them show poor detection performance for tiny objects. This has the potential to have a significant influence on illness identification. Recently, the 3D neural network became popular because it can work with a large labeled dataset. We proposed a 3D Alex-Net-based architecture that can classify the different types of a brain tumors at an early stage. First, the image contour is identified and given to the classifier for class-wise identification. We tested our proposed approach on RSNA- MICCAI brain tumors and found that the proposed method delivers the highest accuracy, and the results provide a clear advantage for the classification of a brain tumor in medical images.","PeriodicalId":231066,"journal":{"name":"2022 International Conference on Decision Aid Sciences and Applications (DASA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128499451","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}
The objective research was to study the transformation of the coffee consumption behavior of coffee drinkers and factors affecting the coffee consumption behavior before and during the COVID-19 pandemic. Because coffee is a famous beverage among university student groups. Therefore, we want to know the coffee consumption behavior and aspects of coffee drinkers such as the time most people need to consume coffee, the price, and the amount of coffee consumed each day. Both before and during the pandemic. To benefit those who are interested in studying coffee and as a guide for decision making in the business development of coffee shop operators. The sample used in this study is 407 students at the University of Thailand who consume coffee. The questionnaire was used to collect data for surveys of coffee consumption behavior. The study results revealed that consumer behavior has changed in coffee drinking patterns, health effects, and budgets for coffee purchases have decreased. Including the amount of coffee consumed on average per day by consumers, slightly increased from before the pandemic.
{"title":"COVID-19 pandemic affected on coffee beverage decision and consumers’ behavior","authors":"Akedanai Thubsang, Chanu Thiwongwiang, Chuleeporn Wisetdee, Jutamanee Chompoonuch, Maesaya Anson, Sairin Phalamat, T. Arreeras","doi":"10.1109/DASA54658.2022.9765074","DOIUrl":"https://doi.org/10.1109/DASA54658.2022.9765074","url":null,"abstract":"The objective research was to study the transformation of the coffee consumption behavior of coffee drinkers and factors affecting the coffee consumption behavior before and during the COVID-19 pandemic. Because coffee is a famous beverage among university student groups. Therefore, we want to know the coffee consumption behavior and aspects of coffee drinkers such as the time most people need to consume coffee, the price, and the amount of coffee consumed each day. Both before and during the pandemic. To benefit those who are interested in studying coffee and as a guide for decision making in the business development of coffee shop operators. The sample used in this study is 407 students at the University of Thailand who consume coffee. The questionnaire was used to collect data for surveys of coffee consumption behavior. The study results revealed that consumer behavior has changed in coffee drinking patterns, health effects, and budgets for coffee purchases have decreased. Including the amount of coffee consumed on average per day by consumers, slightly increased from before the pandemic.","PeriodicalId":231066,"journal":{"name":"2022 International Conference on Decision Aid Sciences and Applications (DASA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130559465","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 : 2022-03-23DOI: 10.1109/DASA54658.2022.9765023
C. Ukwuoma, Qin Zhiguang, Md Belal Bin Heyat, Haider Mohammed Khan, F. Akhtar, Mahmoud Masadeh, Olusola Bamisile, Omar Alshorman, G. Nneji
The most common and widely known type of head and neck cancer is the Oral or mouth neoplasm, of which Oral Cavity Squamous Cell Carcinoma (OCSCC) is the most popular. Despite its impact on Mortality, it is always diagnosed at a late stage due to the inefficiency of the screening models at the early detection stage. Early detection of OCSCC has more than 83% survival rate, although the rate of early detection currently is 29%. Partnering with OCSCC early detection, the deep learning model aids in detecting patterns of oral cancer cells. Sequel to that, this paper proposes using ensemble pretrained deep learning models while unifying the ensemble heads with more shared layers for the early detection of OCSCC from microscopic images. Various pre-trained deep learning models are evaluated using transfer learning while using the Augmentor library to establish high-quality microscopic oral cancer image datasets. The proposed approach obtained a 0.1-0.6% improvement compared with transfer learning methods using 100x magnification and 400x magnification, thus illustrating the robustness of the model for low-quality and high-quality images. Noting that the dataset used in this paper is a newly released competition dataset, a comparison was made with only the article that used the same data when writing this paper. The result obtained proves that the proposed methodology is a promising method for detecting and classifying OCSCC.
{"title":"Detection of Oral Cavity Squamous Cell Carcinoma from Normal Epithelium of the Oral Cavity using Microscopic Images","authors":"C. Ukwuoma, Qin Zhiguang, Md Belal Bin Heyat, Haider Mohammed Khan, F. Akhtar, Mahmoud Masadeh, Olusola Bamisile, Omar Alshorman, G. Nneji","doi":"10.1109/DASA54658.2022.9765023","DOIUrl":"https://doi.org/10.1109/DASA54658.2022.9765023","url":null,"abstract":"The most common and widely known type of head and neck cancer is the Oral or mouth neoplasm, of which Oral Cavity Squamous Cell Carcinoma (OCSCC) is the most popular. Despite its impact on Mortality, it is always diagnosed at a late stage due to the inefficiency of the screening models at the early detection stage. Early detection of OCSCC has more than 83% survival rate, although the rate of early detection currently is 29%. Partnering with OCSCC early detection, the deep learning model aids in detecting patterns of oral cancer cells. Sequel to that, this paper proposes using ensemble pretrained deep learning models while unifying the ensemble heads with more shared layers for the early detection of OCSCC from microscopic images. Various pre-trained deep learning models are evaluated using transfer learning while using the Augmentor library to establish high-quality microscopic oral cancer image datasets. The proposed approach obtained a 0.1-0.6% improvement compared with transfer learning methods using 100x magnification and 400x magnification, thus illustrating the robustness of the model for low-quality and high-quality images. Noting that the dataset used in this paper is a newly released competition dataset, a comparison was made with only the article that used the same data when writing this paper. The result obtained proves that the proposed methodology is a promising method for detecting and classifying OCSCC.","PeriodicalId":231066,"journal":{"name":"2022 International Conference on Decision Aid Sciences and Applications (DASA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130840614","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 : 2022-03-23DOI: 10.1109/DASA54658.2022.9765314
Venu Parameswaranpillai, A. Al-khazraji
This paper proposes a framework to incorporate a smart module into a refrigerator capable to collect product data from the items kept inside for refrigeration. This data is collected with the help of smart devices to provide an interface for the users to input product feature rating or innovative requirements to the company involved in making the product. The customer input travel to a QFD interface that uses modern algorithms to act as a dynamic deployment platform to support the decision-makers to initiate the product improvement activities. This framework can be implemented in smart refrigerators to help the customers understand the product underuse, compare the one they are consuming or using with similar other products, recommend product improvement features and get in touch with the company to continuously push the feedback. The companies could make use of this platform to customize their product to suit customers of diverse nature, tackle regional competitions, and always stay flexible to make necessary product improvement that meets the customer needs.
{"title":"An IoT-Based Framework to Support Decision Making Process Using Quality Function Deployment","authors":"Venu Parameswaranpillai, A. Al-khazraji","doi":"10.1109/DASA54658.2022.9765314","DOIUrl":"https://doi.org/10.1109/DASA54658.2022.9765314","url":null,"abstract":"This paper proposes a framework to incorporate a smart module into a refrigerator capable to collect product data from the items kept inside for refrigeration. This data is collected with the help of smart devices to provide an interface for the users to input product feature rating or innovative requirements to the company involved in making the product. The customer input travel to a QFD interface that uses modern algorithms to act as a dynamic deployment platform to support the decision-makers to initiate the product improvement activities. This framework can be implemented in smart refrigerators to help the customers understand the product underuse, compare the one they are consuming or using with similar other products, recommend product improvement features and get in touch with the company to continuously push the feedback. The companies could make use of this platform to customize their product to suit customers of diverse nature, tackle regional competitions, and always stay flexible to make necessary product improvement that meets the customer needs.","PeriodicalId":231066,"journal":{"name":"2022 International Conference on Decision Aid Sciences and Applications (DASA)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122350531","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 : 2022-03-23DOI: 10.1109/DASA54658.2022.9765310
M. Mallek, Mohamed Ali Elleuch, Jalel Euchi, Yacin Jerbi
Renewable energy is certain to play a key role in future electricity generation due to the rapid depletion of conventional energy. Photovoltaic and wind energy are the major renewable energy sources. However, renewable energies are an inexhaustible, expensive, and unpredictable source of energy. An alternative solution is to combine one or more renewable energy with other conventional energy. In recent years, the research interest towards the utilization of hybrid energy systems in desalination plants. This paper aims to optimize several hybrid energy system models consisting of photovoltaic, wind, and the national grid in desalination plant in Tunisia. Optimization is based on the techno-economic analysis of the proposed energy system is performed by using HOMER simulation software. The simulation will be focused on the net present costs, Levelized cost of energy, produced excess electricity, the Renewable Fraction of Energy, and the reduction of CO2emission for the hybrid energy configurations. Results show that the system photovoltaic, wind, and the national grid is the best energy system installed in the desalination plant.
{"title":"Optimal design of a hybrid photovoltaic–wind power system with the national grid using HOMER: A case study in Kerkennah, Tunisia","authors":"M. Mallek, Mohamed Ali Elleuch, Jalel Euchi, Yacin Jerbi","doi":"10.1109/DASA54658.2022.9765310","DOIUrl":"https://doi.org/10.1109/DASA54658.2022.9765310","url":null,"abstract":"Renewable energy is certain to play a key role in future electricity generation due to the rapid depletion of conventional energy. Photovoltaic and wind energy are the major renewable energy sources. However, renewable energies are an inexhaustible, expensive, and unpredictable source of energy. An alternative solution is to combine one or more renewable energy with other conventional energy. In recent years, the research interest towards the utilization of hybrid energy systems in desalination plants. This paper aims to optimize several hybrid energy system models consisting of photovoltaic, wind, and the national grid in desalination plant in Tunisia. Optimization is based on the techno-economic analysis of the proposed energy system is performed by using HOMER simulation software. The simulation will be focused on the net present costs, Levelized cost of energy, produced excess electricity, the Renewable Fraction of Energy, and the reduction of CO2emission for the hybrid energy configurations. Results show that the system photovoltaic, wind, and the national grid is the best energy system installed in the desalination plant.","PeriodicalId":231066,"journal":{"name":"2022 International Conference on Decision Aid Sciences and Applications (DASA)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127069961","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 : 2022-03-23DOI: 10.1109/DASA54658.2022.9765078
Sarutanan Sopanik
This research is considered to be a case - study research which explores the competence levels of three selected community-based tourism (CBT) communities in Chiang Rai, Thailand, for high value meetings incentives conferences (or conventions) and exhibitions (MICE) travelers who are considered to be a potentially untapped tourism segment for local CBT residents in Thailand. The framework of this research is adapted from governmental tourism organizations in Thailand and international organizations with the intention to promote CBT communities. The evaluation criteria focus on CBT community management, cultural presentation skills and natural resources. The unique ability to use local creativities to impress MICE travelers beyond their expectations is the key success which will indicate higher level of competence.
{"title":"The Competence Development of Community Based Tourism Communities in Chiang Rai for MICE Travelers","authors":"Sarutanan Sopanik","doi":"10.1109/DASA54658.2022.9765078","DOIUrl":"https://doi.org/10.1109/DASA54658.2022.9765078","url":null,"abstract":"This research is considered to be a case - study research which explores the competence levels of three selected community-based tourism (CBT) communities in Chiang Rai, Thailand, for high value meetings incentives conferences (or conventions) and exhibitions (MICE) travelers who are considered to be a potentially untapped tourism segment for local CBT residents in Thailand. The framework of this research is adapted from governmental tourism organizations in Thailand and international organizations with the intention to promote CBT communities. The evaluation criteria focus on CBT community management, cultural presentation skills and natural resources. The unique ability to use local creativities to impress MICE travelers beyond their expectations is the key success which will indicate higher level of competence.","PeriodicalId":231066,"journal":{"name":"2022 International Conference on Decision Aid Sciences and Applications (DASA)","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124080744","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 : 2022-03-23DOI: 10.1109/DASA54658.2022.9765195
Jamal Amadid, Zakaria El Ouadi, L. Wakrim, Asma Khabba, A. Zeroual
This work provides a straightforward channel estimator to overcome an unrealistic property provided by Minimum Mean Square Error Estimator (MMSEE) for Multi-Cell (MC) Massive Multiple-Input Multiple-Output (M-MIMO) systems operating under Time-Division Duplex (TDD) protocol. Besides, this work is in purpose to study and analyze the current ideal Least-Squares Estimator (LSE), the current ideal MMSEE, and the Maximum Likelihood Estimator (MLE) under various circumstances and considering under Pilot Contamination (PC) problems. This work compared and evaluate the performance of the studied estimators using the metric Mean Square Error (MSE). The traditional LSE provides the worst performance under a high interference level since it is considerably affected by PC. In spite of the greater accuracy achieved by MMSEE in many studies in the literature. However, the MMSEE is relying on an unrealistic assumption, which can be explained by the complete knowledge of among cell large-scale fading (LSF) coefficients as an unrealistic hypothesis in practical use. The suggested estimator (i.e., the MLE) is introduced to overcome the unusable property on which the MMSEE is based. Besides, the MLE is introduced to provides higher performance than LSE. Furthermore, we investigate a scenario of LSF coefficient (i.e., a LSF depends on the distance at which the user is located from its serving Base Station (BS)), wherewith we assert our analysis. An analytical, simulated, and approximated, results are provided for MLE to affirm our study, whereas analytical and simulated results are given for both LSE and MMSEE to assert the presented theoretical expressions.
{"title":"Pilot Sequence-based Channel Estimation in Massive MIMO wireless communication networks under strong Pilot Contamination","authors":"Jamal Amadid, Zakaria El Ouadi, L. Wakrim, Asma Khabba, A. Zeroual","doi":"10.1109/DASA54658.2022.9765195","DOIUrl":"https://doi.org/10.1109/DASA54658.2022.9765195","url":null,"abstract":"This work provides a straightforward channel estimator to overcome an unrealistic property provided by Minimum Mean Square Error Estimator (MMSEE) for Multi-Cell (MC) Massive Multiple-Input Multiple-Output (M-MIMO) systems operating under Time-Division Duplex (TDD) protocol. Besides, this work is in purpose to study and analyze the current ideal Least-Squares Estimator (LSE), the current ideal MMSEE, and the Maximum Likelihood Estimator (MLE) under various circumstances and considering under Pilot Contamination (PC) problems. This work compared and evaluate the performance of the studied estimators using the metric Mean Square Error (MSE). The traditional LSE provides the worst performance under a high interference level since it is considerably affected by PC. In spite of the greater accuracy achieved by MMSEE in many studies in the literature. However, the MMSEE is relying on an unrealistic assumption, which can be explained by the complete knowledge of among cell large-scale fading (LSF) coefficients as an unrealistic hypothesis in practical use. The suggested estimator (i.e., the MLE) is introduced to overcome the unusable property on which the MMSEE is based. Besides, the MLE is introduced to provides higher performance than LSE. Furthermore, we investigate a scenario of LSF coefficient (i.e., a LSF depends on the distance at which the user is located from its serving Base Station (BS)), wherewith we assert our analysis. An analytical, simulated, and approximated, results are provided for MLE to affirm our study, whereas analytical and simulated results are given for both LSE and MMSEE to assert the presented theoretical expressions.","PeriodicalId":231066,"journal":{"name":"2022 International Conference on Decision Aid Sciences and Applications (DASA)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127726764","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 : 2022-03-23DOI: 10.1109/DASA54658.2022.9765268
M. M. Alam, M. Rahman, M. Hosen, Khairul Anam Mubin, S. Hossen, M. F. Mridha
In the past few years, many works are done in object detection using images and machine translation. Inspired by those works we introduced Bahdanau Attention Based Bengali Image Caption Generation (BABBICG) that generate automatically bangla caption based on images. The Conventional encoder-decoder architectures performance curse will reduce by Bahdanau Attention and achieving momentous improvements over encoder-decoder architectures. In this work, we extract features from images using InceptionV3 neural network and generate caption using RNN decoder. We used Gated Recurrent Unit (GRU) approach as RNN. We evaluate the model using BanglaLekhaImageCaptions dataset from Mendeley Data that can help to generate bangla caption.
{"title":"Bahdanau Attention Based Bengali Image Caption Generation","authors":"M. M. Alam, M. Rahman, M. Hosen, Khairul Anam Mubin, S. Hossen, M. F. Mridha","doi":"10.1109/DASA54658.2022.9765268","DOIUrl":"https://doi.org/10.1109/DASA54658.2022.9765268","url":null,"abstract":"In the past few years, many works are done in object detection using images and machine translation. Inspired by those works we introduced Bahdanau Attention Based Bengali Image Caption Generation (BABBICG) that generate automatically bangla caption based on images. The Conventional encoder-decoder architectures performance curse will reduce by Bahdanau Attention and achieving momentous improvements over encoder-decoder architectures. In this work, we extract features from images using InceptionV3 neural network and generate caption using RNN decoder. We used Gated Recurrent Unit (GRU) approach as RNN. We evaluate the model using BanglaLekhaImageCaptions dataset from Mendeley Data that can help to generate bangla caption.","PeriodicalId":231066,"journal":{"name":"2022 International Conference on Decision Aid Sciences and Applications (DASA)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127775724","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 : 2022-03-23DOI: 10.1109/DASA54658.2022.9765258
Von Cedrick M. Calderon, Jeffrey S. Sarmiento, Christopher Franco Cunanan, Carla May C. Ceribo, Gemma D. Belga
Patients' cells need to be examined, thus healthcare facilities require changes as well as advancements in terms of instruments and technology, notably software that aids in the diagnosis of certain symptoms and diseases by looking at them. This aids in the identification and diagnosis of intracellular parasites in a person's cell, making it easier to identify a person's health condition. These parasites are responsible for a variety of acute and chronic illnesses. The paper aims to provide an enhanced model for cell classification. This will help to increase the accuracy of detection for intercellular parasites within the patient cell and easily diagnose a person’s health condition. In response to that, the system implements a deep learning technique in cell categorization using the YOLOv3 algorithm. Having a model with 90.6% mean Average precision, made a cell classification with 99.06% precision determining whether the subjected single cell is parasitized or normal.
{"title":"Identification of Parasitized Single Cell from Normal Using Deep Learning Approach","authors":"Von Cedrick M. Calderon, Jeffrey S. Sarmiento, Christopher Franco Cunanan, Carla May C. Ceribo, Gemma D. Belga","doi":"10.1109/DASA54658.2022.9765258","DOIUrl":"https://doi.org/10.1109/DASA54658.2022.9765258","url":null,"abstract":"Patients' cells need to be examined, thus healthcare facilities require changes as well as advancements in terms of instruments and technology, notably software that aids in the diagnosis of certain symptoms and diseases by looking at them. This aids in the identification and diagnosis of intracellular parasites in a person's cell, making it easier to identify a person's health condition. These parasites are responsible for a variety of acute and chronic illnesses. The paper aims to provide an enhanced model for cell classification. This will help to increase the accuracy of detection for intercellular parasites within the patient cell and easily diagnose a person’s health condition. In response to that, the system implements a deep learning technique in cell categorization using the YOLOv3 algorithm. Having a model with 90.6% mean Average precision, made a cell classification with 99.06% precision determining whether the subjected single cell is parasitized or normal.","PeriodicalId":231066,"journal":{"name":"2022 International Conference on Decision Aid Sciences and Applications (DASA)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127777608","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：