{"title":"IOT Based Smart Vending Machine for Bangladesh","authors":"Wahidul Alam, Fahima Sultana, Jubaida Bahar Saba, Ayikutu Courage Kofi","doi":"10.1109/RAAICON48939.2019.36","DOIUrl":"https://doi.org/10.1109/RAAICON48939.2019.36","url":null,"abstract":"This paper proposes the concept of “Vending Machine” in the prospect of Bangladesh. In this approach we put forward the design a IoT enabled service of a vending machine which will be operated through a mobile application and bKash (digital payment system of Bangladesh) with the incorporation of cloud computing which aims to be cost effective and less time consuming and yet user friendly. The ultimate goal is to introduce a cost effective vending machine solution for Bangladesh enhancing the customer purchasing experience, driving up the demand for mass adoption of the IoT based smart vending machines.","PeriodicalId":102214,"journal":{"name":"2019 IEEE International Conference on Robotics, Automation, Artificial-intelligence and Internet-of-Things (RAAICON)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115026592","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}
Dipankar Gupta, Emam Hossain, Mohammad Shahadat Hossain, Karl Andersson, S. Hossain
{"title":"A Digital Personal Assistant using Bangla Voice Command Recognition and Face Detection","authors":"Dipankar Gupta, Emam Hossain, Mohammad Shahadat Hossain, Karl Andersson, S. Hossain","doi":"10.1109/RAAICON48939.2019.47","DOIUrl":"https://doi.org/10.1109/RAAICON48939.2019.47","url":null,"abstract":"Though speech recognition has been a common interest of researchers over the last couple of decades, but very few works have been done on Bangla voice recognition. In this research, we developed a digital personal assistant for handicapped people which recognizes continuous Bangla voice commands. We employed the cross-correlation technique which compares the energy of Bangla voice commands with prerecorded reference signals. After recognizing a Bangla command, it executes a task specified by that command. Mouse cursor can also be controlled using the facial movement of a user. We validated our model in three different environments (noisy, moderate and noiseless) so that the model can act naturally. We also compared our proposed model with a combined model of MFCC & DTW, and another model which combines crosscorrelation with LPC. Results indicate that the proposed model achieves a huge accuracy and smaller response time comparing to the other two techniques.","PeriodicalId":102214,"journal":{"name":"2019 IEEE International Conference on Robotics, Automation, Artificial-intelligence and Internet-of-Things (RAAICON)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132974027","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. Raseduzzaman Ruman, A. Barua, Md. Rafiur Rahman Recent, Waladur Rahman, MS Islam, Rakib Hasan Shuvo
{"title":"Implementation of an Advanced Irrigation System with Logical Output","authors":"Md. Raseduzzaman Ruman, A. Barua, Md. Rafiur Rahman Recent, Waladur Rahman, MS Islam, Rakib Hasan Shuvo","doi":"10.1109/RAAICON48939.2019.71","DOIUrl":"https://doi.org/10.1109/RAAICON48939.2019.71","url":null,"abstract":"In this paper an illustration of an automated system of farm irrigation and soil moisture control by Arduino is proposed. This automated system for irrigation identifies the moisture content present in soil and automatically toggles the switching of pump when the power is supplied. An appropriate usage of irrigation system is substantial and it is essential to maintain suitable water content and avoid shortage of water due to lack of rain and spontaneous use of water, to avoid wastage of water. Due to this reason, this automatic plant watering and soil moisture monitoring system can be used which is very useful in all climatic conditions. In our country the livelihood of most of the people, especially the farmers, are completely dependent on the agricultural harvesting. Agriculture is a source of employment which contributes critically on the economy of the Bangladesh. In dry areas or in case of lacking rainfall, irrigation becomes difficult. Moreover, during summer, the temperature of Bangladesh goes high which effects the water of the different water bodies across the countryside which makes the situation more difficult. This project aims at reducing excessive and uncontrolled water usage as well as maintaining moisture content of the soil to get healthy irrigation. Automatic irrigation system can be used for saving time using low power consuming monitoring device thus minimizing human effort. Overall, the project achieved its primary goal to avoid the wastage of water while maintaining the moisture content of the soil with very less power consumption and less delay in the processing time.","PeriodicalId":102214,"journal":{"name":"2019 IEEE International Conference on Robotics, Automation, Artificial-intelligence and Internet-of-Things (RAAICON)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133737956","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}
P. P. Sarkar, Md. Asaduzzaman Tohin, M. Khaled, Md.Robiul Islam
{"title":"Design Process of an Affordable Smart Robotic Crutch for Paralyzed Patients","authors":"P. P. Sarkar, Md. Asaduzzaman Tohin, M. Khaled, Md.Robiul Islam","doi":"10.1109/RAAICON48939.2019.6260845","DOIUrl":"https://doi.org/10.1109/RAAICON48939.2019.6260845","url":null,"abstract":"The research work is to suggest a smart multifunctional Robotic Crutch which is designed for Cripple or Physically disabled people for instant object detection purposes. It is a robotic crutch designed for the movement of cripple or physically disabled persons. Crutches help to transfer weight from the legs to the upper body. The crutch can be attached to the both sides of the user and help the user to move. The proposed model enables the user to control the crutch with the manual switching device. This crutch can detect the object around the user while moving. After detecting the object, the high torque gear motor will be automatically stopped. Moreover, typically people who have disabilities or injuries, or older adults who are at increased risk of falling, to reduce user fall and instant object detection purposes for physically disabled people, there was no Robotics Crutch introduced in the past. The lighting feature of this crutch will help the user to move during the night. A GPS tracking device has added as an extra feature to detect the exact position of disabled people by the family members. The proposed outcome of the project is to give the proper and efficient support to the physically disabled people by helping them to move and detect the user's exact position.","PeriodicalId":102214,"journal":{"name":"2019 IEEE International Conference on Robotics, Automation, Artificial-intelligence and Internet-of-Things (RAAICON)","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115173791","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}
Iffat Arefa, M. Alam, Ipshita Siddiquee, N. Siddique
{"title":"Performance Analysis of Machine Learning Algorithms for Hypertension Decision Support System","authors":"Iffat Arefa, M. Alam, Ipshita Siddiquee, N. Siddique","doi":"10.1109/RAAICON48939.2019.8","DOIUrl":"https://doi.org/10.1109/RAAICON48939.2019.8","url":null,"abstract":"Machine learning algorithms are helpful to build a model-based decision support system using data to predict risk of hypertension disease which is deadly in Bangladesh as in other parts of the world. It is necessary to figure out which machine learning algorithm is suitable for implementing a decision support system practically. Therefore, in this work, 21 types of supervised machine learning algorithms have been employed training the prediction system for hypertension risk. Various types of Decision Trees, Logistic Regression, Support Vector Machines, Nearest Neighbors Classifiers and Ensemble Classifiers are used for training the model. 5 fold cross validation has been used in this case. 16 inputs are chosen based on expert knowledge and 2 outputs are selected as response. In this paper, performance is evaluated in terms of confusion matrix and ROC curve. 129 patients' data have been collected from local hospital to conduct this work.","PeriodicalId":102214,"journal":{"name":"2019 IEEE International Conference on Robotics, Automation, Artificial-intelligence and Internet-of-Things (RAAICON)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121946216","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}
Shayekh Mohiuddin Ahmed Navid, Shamima Haque Priya, Nabiul Hoque Khandakar, Zannatul Ferdous, A. B. Haque
{"title":"Signature Verification Using Convolutional Neural Network","authors":"Shayekh Mohiuddin Ahmed Navid, Shamima Haque Priya, Nabiul Hoque Khandakar, Zannatul Ferdous, A. B. Haque","doi":"10.1109/RAAICON48939.2019.19","DOIUrl":"https://doi.org/10.1109/RAAICON48939.2019.19","url":null,"abstract":"Signatures are widely used to validate the authentication of an individual. A robust method is still awaited that can correctly certify the authenticity of a signature. The proposed solution provided in this paper is going to help individuals to distinguish signatures for determining whether a signature is forged or genuine. In our system, we aimed to automate the process of signature verification using Convolutional Neural Networks. Our model is constructed on top of a pre-trained Convolutional Neural Network called the VGG-19. We evaluated our model on widely accredited signature datasets with a multitude of genuine signature samples sourced from ICDAR[3], CEDAR[1] and Kaggle[2]; achieving accuracies of 100%, 88%, and 94.44% respectively. Our analysis shows that our proposed model can classify the signature if they do not closely resemble the genuine signature.","PeriodicalId":102214,"journal":{"name":"2019 IEEE International Conference on Robotics, Automation, Artificial-intelligence and Internet-of-Things (RAAICON)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127154239","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":"A Low-Cost Urban Search and Rescue Robot for Developing Countries","authors":"S. Sharmin, Saiful Islam Salim, K. R. I. Sanim","doi":"10.1109/RAAICON48939.2019.27","DOIUrl":"https://doi.org/10.1109/RAAICON48939.2019.27","url":null,"abstract":"Since urban search and rescue is a difficult domain for autonomous mobile robots to operate in, the environment can be expected to be highly unstructured, with many obstacles and hazards for a robot to deal with. Besides, if human rescue teams are going to accept robotic assistance, they need to be assured that the robots are going to be helpful, not a hindrance. With these factors in mind, we work toward the development of a swarm of small, inexpensive search and rescue robots. The platform has been developed to be low in cost and easy to construct from commonly available parts so that they are suitable for developing countries like Bangladesh. The robot can provide useful information to human rescuers without requiring specialized knowledge in operating robots. It can be controlled remotely from a station. It sends continuous thermal and video feed, environmental sensory data of the disaster site to the associated web application through the control station. It can run through rough terrain in a completely dark environment with the help of a powerful remote-controlled flashlight. It can detect living humans inside the rubble and can establish communication between them and the rescuers.","PeriodicalId":102214,"journal":{"name":"2019 IEEE International Conference on Robotics, Automation, Artificial-intelligence and Internet-of-Things (RAAICON)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130118369","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":"Robust Pose-Based Human Fall Detection Using Recurrent Neural Network","authors":"M. Hasan, Md Shamimul Islam, Sohaib Abdullah","doi":"10.1109/RAAICON48939.2019.23","DOIUrl":"https://doi.org/10.1109/RAAICON48939.2019.23","url":null,"abstract":"Detecting falling event from the video for providing timely assistance to the fallen person is a challenging problem in computer vision due to the absence of large-scale fall dataset and the presence of many covariate factors like varying view angle, illumination, and clothing. In this paper, to address this problem, an effective approach for fall detection has been proposed. We have developed a recurrent neural network (RNN) with LSTM architecture that models the temporal dynamics of the 2D pose information of a fallen person. Human 2D pose information, which has proven effective in analyzing fall pattern as it ignores people's body appearance and environmental information while capturing the true motion information makes the proposed model simpler and faster. Experimental results have verified that our proposed method has achieved 99.0% sensitivity on both of the benchmark datasets of fall detection FDD and URFD.","PeriodicalId":102214,"journal":{"name":"2019 IEEE International Conference on Robotics, Automation, Artificial-intelligence and Internet-of-Things (RAAICON)","volume":"232 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114257668","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":"Design of An Intelligent Autonomous Accident Prevention, Detection And Vehicle Monitoring System","authors":"Md Habib Ullah Khan, M. K. Howlader","doi":"10.1109/RAAICON48939.2019.6263505","DOIUrl":"https://doi.org/10.1109/RAAICON48939.2019.6263505","url":null,"abstract":"In modern days, vehicles are one of the most indispensable transportation medium. With the increase of vehicles in the roads, incidents of accidents are also increasing for various reasons. Although in last few decades, driver assistance and safety system has been upgraded significantly, still the possibility of accident cannot be discarded. Real time detection including tracing down of accident spot is vital for swift rescue operation. Therefore, in this work a low priced Arduino uno and nano based automatic accident prevention, post accidental rescue and a black-box system has been developed. This system will allow the drivers to avoid accident. In worst case scenario, if the accident is inevitable, it will help the rescue team through providing accurate location of the accident spot.","PeriodicalId":102214,"journal":{"name":"2019 IEEE International Conference on Robotics, Automation, Artificial-intelligence and Internet-of-Things (RAAICON)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126896787","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":"Know Your Enemy: Analysing Cyber-threats Against Industrial Control Systems Using Honeypot","authors":"S. M. Z. Ur Rashid, M. J. Uddin, Md. Ariful Islam","doi":"10.1109/RAAICON48939.2019.69","DOIUrl":"https://doi.org/10.1109/RAAICON48939.2019.69","url":null,"abstract":"Industrial Control System (ICS) devices are being increasingly targeted by cyber attackers due to the lack of internet-ready security controls. IDS, firewall, IPS, and other protection measures are often used to prevent attacks on these systems but their efficiency depends on the prior knowledge of the attack patterns. In case of sophisticated and new attacks, they can't detect and take proper security measures. In this study, we deploy three low-interactive multi-platform honeypot in three different locations to lure cybercriminals to attack the networks. We perform large-scale analysis to observe current attack trends toward Industrial Control System (ICS), capture adversaries malicious activities and techniques for adaptive threat defense in the future.","PeriodicalId":102214,"journal":{"name":"2019 IEEE International Conference on Robotics, Automation, Artificial-intelligence and Internet-of-Things (RAAICON)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123958529","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}