Md. Mohsin Kabir, Tanvir Ahamed Anik, Md. Shahnewaz Abid, M. Mridha, Md. Abdul Hamid
{"title":"Facial Expression Recognition Using CNN-LSTM Approach","authors":"Md. Mohsin Kabir, Tanvir Ahamed Anik, Md. Shahnewaz Abid, M. Mridha, Md. Abdul Hamid","doi":"10.1109/icsct53883.2021.9642571","DOIUrl":"https://doi.org/10.1109/icsct53883.2021.9642571","url":null,"abstract":"Automated Facial Expression Recognition (FER) has remained a promising and challenging domain for Computer Vision with the appearance of Deep Learning approaches. The FER has turned up very encouraging because it mirrors our mental conditions and gives valuable facts on human behaviors. Most of this area’s research has been conducted with the posed image dataset, but posed images do not describe the human face’s genuine emotions. The non-posed images carry non-verbal knowledge among individuals in face-to-face communications. Hence, to get the human’s accurate mental state, a Posed and Non-posed Facial Expression (PNFE) dataset is built to evaluate the best performance. This paper proposed a new architecture based on Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM) that classifies six fundamental expressions: happiness, anger, disgust, fear, sadness, and surprise with neutral. This combined approach is split into two phases. First, visual features are extracted by CNN by learning on the PNFE dataset, and then LSTM is applied to bound the relationship between image sequences and emotions. Besides, the result of this architecture is evaluated by confusion matrices and compared with relevant architectures and renowned FER datasets.","PeriodicalId":320103,"journal":{"name":"2021 International Conference on Science & Contemporary Technologies (ICSCT)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128332038","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}
Dewan Mahnaaz Mahmud, Farhan Tasnim, Fardeen Mahbub, Md. Zilan Uddin Saif, Siam Hasan Khan
{"title":"Tentative Prospects and Overview of General Awareness Towards Sustainable Energy in Bangladesh","authors":"Dewan Mahnaaz Mahmud, Farhan Tasnim, Fardeen Mahbub, Md. Zilan Uddin Saif, Siam Hasan Khan","doi":"10.1109/icsct53883.2021.9642609","DOIUrl":"https://doi.org/10.1109/icsct53883.2021.9642609","url":null,"abstract":"Global energy consumption has grown dramatically with emerging nations accounting for the largest chunk of this increase. Bangladesh now contributes just 3% of total energy to renewable energy, although it has preestablished a plan in the renewable energy sector. The installed capacity of the power production has quickly grown to a healthy proportion with captive generation capacity and inadequate to meet the electricity demand of the nation. In this paper, a survey had been carried out for determining the kind of mindset the people of Bangladesh have regarding the paramountcy of sustainable energy sources in recent times. Also, the future undertook projects of the Government of Bangladesh along with a survey consists of a standardized questionnaire regarding the evolving demand for sustainable energy sources. More than 200 individuals of different Bangladesh genres participated in the survey to share their valuable opinions about sustainable resources. However, from the survey, we have perceived that a healthy percentage of people possess a rigid intention to shift their fossil fuel usage with clean energy resources for the planet’s progress. Therefore, after a detailed review of the survey, it can be deduced that Bangladesh’s people are ready to change using renewable resources replacing fossil fuels.","PeriodicalId":320103,"journal":{"name":"2021 International Conference on Science & Contemporary Technologies (ICSCT)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127921294","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}
Homeyra Akter, H. Howlader, A. Saber, A. Hemeida, Hiroshi Takahashi, T. Senjyu
{"title":"Optimal Sizing and Operation of Microgrid in a Small Island Considering Advanced Direct Load Control and Low Carbon Emission","authors":"Homeyra Akter, H. Howlader, A. Saber, A. Hemeida, Hiroshi Takahashi, T. Senjyu","doi":"10.1109/ICSCT53883.2021.9642669","DOIUrl":"https://doi.org/10.1109/ICSCT53883.2021.9642669","url":null,"abstract":"Hybrid energy optimization is a challenge in energy sector when it consists of renewable and non-renewable energy. The output power fluctuation of renewables and environmental pollution from non-renewable sources is the reason behind it. Optimal design is needed for reducing the total cost of the system. For minimizing the Life Cycle Cost (LCC) and carbon emission of hybrid power system in the presence of Advanced Direct Load Control (ADLC), a multi-objective optimization problem is proposed in this paper. The first objective is to reduce the LCC of this hybrid power systems, and the second one is to reduce the total CO2 emissions, which is the opposite of the first one. The multi-objective optimization function is changed to the single objective function by the $epsilon$ constraints method, and Mixed Integer Linear Programming (MILP) is applied to solve the problem. The results from MATLAB program validates the usefulness of the proposed system.","PeriodicalId":320103,"journal":{"name":"2021 International Conference on Science & Contemporary Technologies (ICSCT)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125442750","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":"Donation: A Social Engineering Model for Extreme Poverty Eradication","authors":"Md. Abdul Hamid","doi":"10.1109/icsct53883.2021.9642614","DOIUrl":"https://doi.org/10.1109/icsct53883.2021.9642614","url":null,"abstract":"This paper pens a possibility about how donation may be a good approach to eradicate extreme poverty for a particular community. First, we discuss how introducing an innovative product may empower the community and make them able to generate income, and gradually help develop other basic needs. Then, we engineer a mathematical model, based on donation and population using differential equations, delivering an exceptional policy that may help short, medium and long term plan to eradicate extreme poverty. We strongly believe that our idea may root out the systemic underpinnings of an acuity that perpetuates cycles of poverty.","PeriodicalId":320103,"journal":{"name":"2021 International Conference on Science & Contemporary Technologies (ICSCT)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121337806","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}
Md. Shahidul Islam, Fariha Mamud, Rakib Ul Haque, A. Saber, A. Saha
{"title":"Automatic formulation and optimization of linear problems from a structured paragraph","authors":"Md. Shahidul Islam, Fariha Mamud, Rakib Ul Haque, A. Saber, A. Saha","doi":"10.1109/icsct53883.2021.9642516","DOIUrl":"https://doi.org/10.1109/icsct53883.2021.9642516","url":null,"abstract":"Though plenty of research work has been done on natural language processing and linear problem optimization, none of them focused on automatic linear problem formulation from passages and optimizing them at a time. In this research, we developed a problem formulation method using NLTK and developed a completely new linear optimization solver using C# GUI and Python pulp library. We classify the problem with Support Vector Machine(SVM) to identify that the problem is a linear or a non-linear problem. Support Vector Machine(SVM) has an accuracy of 70% due to the small dataset. We extract all the cardinal digits using NLTK Pos_Tagger from the passage. Using the proposed algorithm, we generate all the equations for objective functions and constraints. We also developed software for the solution of the formulated problems. We got an accuracy of 100% for equation generation with our software. Moreover, the proposed system shows an impressive result in problem formulation from our designed structured passage.","PeriodicalId":320103,"journal":{"name":"2021 International Conference on Science & Contemporary Technologies (ICSCT)","volume":"132 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121364909","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}
M. Ashrafuzzaman, Suman Saha, Neser Uddin, Pranto Saha, Sojib Hossen, Prof. Dr. Kamruddin Nur
{"title":"Design and Development of a Low-cost Smart Stick for Visually Impaired People","authors":"M. Ashrafuzzaman, Suman Saha, Neser Uddin, Pranto Saha, Sojib Hossen, Prof. Dr. Kamruddin Nur","doi":"10.1109/icsct53883.2021.9642500","DOIUrl":"https://doi.org/10.1109/icsct53883.2021.9642500","url":null,"abstract":"One of the biggest problem faced by visually impaired people is to navigate from one place to another. They always need human support for moving either indoors or outdoors. The unfavourable conditions of the environment make it more complicated for visually impaired people. A blind person always needs to be alert to get off the situations like crashing with obstacles, holes, staircases, slipping down wet territory. Also, in case of any emergency, they might want to send an alert message to their families or friends nearly their location. Considering the above, in this paper, we have addressed all these issues and provides a solution to assist visually impaired people so that they can live without the much help of others. The Ultrasonic sensor of this system helps blind people to detect obstacles, hole, and staircase alongside water sensor is used to detect the water. The buzzer is placed at the smart stick which provides a sound when any obstacle is identified. The GPS and GSM module of this device assists peoples to obtain the specific location of the smart stick. In the system, Arduino UNO is used as a controller of the device. The proposed smart stick is a low-cost device with faster response, user-friendly, and low energy consumption.","PeriodicalId":320103,"journal":{"name":"2021 International Conference on Science & Contemporary Technologies (ICSCT)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125644149","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}
Musfiquer Rhman, Farjana Rahman, Md. Mintu Hossain, Umma Habiba Emu, Khadija Akter, M. F. Mridha
{"title":"Predicting Alzheimer’s Disease at Low Cost Using Machine Learning","authors":"Musfiquer Rhman, Farjana Rahman, Md. Mintu Hossain, Umma Habiba Emu, Khadija Akter, M. F. Mridha","doi":"10.1109/icsct53883.2021.9642536","DOIUrl":"https://doi.org/10.1109/icsct53883.2021.9642536","url":null,"abstract":"Modeling and predicting Alzheimer's disease (AD) is a noteworthy field of study for many years. However, diagnosing and treating AD for poor people in many developing and underdeveloped countries is a luxury. Many countries lack the proper tools. Many people do not have the capability of bearing the cost of MRI tests. In this paper, we analyzed a way of identifying AD as cheaply as possible. We investigated the difference in efficiency between the Machine learning models using Magnetic Resonance Imaging (MRI) data versus models without MRI data. We had around a 3% difference between the best models of these tests. We used the OASIS dataset. We used patients' longitudinal lifestyle data like age, gender, education, income, MMSC score, and other features for Non-MRI models. For MRI models, we also analyzed MRI data along with the lifestyle data. We trained different Machine learning models like Random Forest Classifier, GaussianNB, LinearSVC, Logistic Regression, KNeighbors Classifier, Adaboost Classifier, and several other models. After that, we combined our best models and created a hybrid model. Our best result was 96.07% accuracy with MRI data and 93.37% accuracy without MRI data. The non-MRI result may not be as efficient as the models with the MRI dataset and not crucially inefficient. Our result can be summarized as the Non-MRI data can be used for starting the diagnosis for those poor people.","PeriodicalId":320103,"journal":{"name":"2021 International Conference on Science & Contemporary Technologies (ICSCT)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131826746","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}
A. Asaduzzaman, P. Kamalakannan, M. Altaf-Ul-Amin, S. Kanaya
{"title":"Improving Quality of Service in Computer Networks Applying the Eight Classes of Service","authors":"A. Asaduzzaman, P. Kamalakannan, M. Altaf-Ul-Amin, S. Kanaya","doi":"10.1109/ICSCT53883.2021.9642613","DOIUrl":"https://doi.org/10.1109/ICSCT53883.2021.9642613","url":null,"abstract":"Class of Service (CoS) is implemented in communication networks to simplify the management of traffic data and ensure Quality of Service (QoS) requirements. Because of the substantial growth in network data generation, the present-day Five CoS (5CoS) model is not acceptable to ensure the required QoS. This paper presents a new CoS model, the Eight CoS (8CoS) model, to improve the QoS. The 8CoS consists of eight traffic classes and is designed considering the intention of accommodating as many classes of traffic as possible along with the migration strategy of converging networks. The functions such as classifier, shaper, and scheduler are used for the class-based queueing experiments. In the experiments, differentiated services are used so that the network’s QoS will clearly depend on the services of the classes and by the associated per-hop behavior. r8CoS model is almost double the throughput of a 5CoS model. Also, the 8CoS model offers a 39.25% shorter delay time, a 33.70% lower jitter, and a 25.42% smaller packet loss when compared to the 5CoS model. This paves a way for the new 8CoS model to substitute the current 5CoS model.","PeriodicalId":320103,"journal":{"name":"2021 International Conference on Science & Contemporary Technologies (ICSCT)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114721022","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}
Maodudul Hasan, E. Nishiyama, Takayuki Tanaka, I. Toyoda
{"title":"Proposal of Pattern-Reconfigurable Self-Oscillating Active Array Antenna Integrating Slot-Line Gunn Oscillator and Hybrid Coupler","authors":"Maodudul Hasan, E. Nishiyama, Takayuki Tanaka, I. Toyoda","doi":"10.1109/icsct53883.2021.9642411","DOIUrl":"https://doi.org/10.1109/icsct53883.2021.9642411","url":null,"abstract":"This study proposes a self-oscillating active integrated array antenna (AIAA) with pattern-reconfigurable functionality for X-band applications. The AIA has a dual-patch array antenna and a hybrid coupler, and it can switch its main beam with the aid of three PIN diodes among three states; state $1 (theta=-20^{circ})$, state $2 (theta=+20^{circ})$, and state $3 (theta =0^{circ})$. By embedding a slot-line Gunn oscillator, which shows an excellent output power of +7.71 dBm at 10.2GHz, the proposed antenna has the self-oscillating capability as well. Simulated radiation patterns in all three states validate the concept with an excellent impedance matching.","PeriodicalId":320103,"journal":{"name":"2021 International Conference on Science & Contemporary Technologies (ICSCT)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115016485","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}