Noelle Marie D. Espiritu, S. Chen, Tiffany Ann C. Blasa, Francisco Emmanuel T. Munsayac, Rebecca P. Arenos, R. Baldovino, N. Bugtai, Homer S. Co
{"title":"BCI-controlled Smart Wheelchair for Amyotrophic Lateral Sclerosis Patients","authors":"Noelle Marie D. Espiritu, S. Chen, Tiffany Ann C. Blasa, Francisco Emmanuel T. Munsayac, Rebecca P. Arenos, R. Baldovino, N. Bugtai, Homer S. Co","doi":"10.1109/RITAPP.2019.8932748","DOIUrl":"https://doi.org/10.1109/RITAPP.2019.8932748","url":null,"abstract":"This paper presents the retrofitting and conversion of a standard manually-operated wheelchair to a smart device. This includes the use of an electroencephalography (EEG) based computer interface (BCI) control and integration of an easy-to-assemble mount for the portable power unit that does not require any special tools. An EMOTIV Insight headset was used as the main EEG device. The EEG device is connected to a PC that will be used to send signals to the microcontroller via Bluetooth. Then, these signals will be used to control the speed and direction of the friction-drive power units composed of two-wheel hub type motors each held by a fabricated holder and two 12-VDC batteries in their own fabricated holders. Also, an emergency stop was added for safety usage and operation.","PeriodicalId":234023,"journal":{"name":"2019 7th International Conference on Robot Intelligence Technology and Applications (RiTA)","volume":"35 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":"128964301","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}
Jeong-won Jo, Junwon Park, Jinyoung Han, Minsun Lee, Anthony H. Smith
{"title":"Dynamic Bird Detection Using Image Processing and Neural Network","authors":"Jeong-won Jo, Junwon Park, Jinyoung Han, Minsun Lee, Anthony H. Smith","doi":"10.1109/RITAPP.2019.8932891","DOIUrl":"https://doi.org/10.1109/RITAPP.2019.8932891","url":null,"abstract":"Collisions of aircraft and birds cause serious flight accidents, and various studies are underway to find a solution to the problem. In recent image recognition studies, state-of-the-art deep learning technologies have been actively applied. This paper proposes image preprocessing and bird detection methods in all dynamic environments using Convolutional Neural Network (CNN) technology. Image preprocessing separates moving creatures from the dynamic background and removes the background. When image preprocessing is complete, the image of the moving object remaining in the frame is used as input data for the learning model to determine whether the bird is in the frame. We used the Inception -v3 neural network model to improve the accuracy of small object classifications.","PeriodicalId":234023,"journal":{"name":"2019 7th International Conference on Robot Intelligence Technology and Applications (RiTA)","volume":"45 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114098112","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}
Syeda Zuriat-e-Zehra Ali, Rida Ashfaq, Rameesa Afzal, Mehr-un-Nisa, Babar Sultan, Abdul Jalil
{"title":"Smart Pillow:Sleep Apnea Monitoring & Minimization Device","authors":"Syeda Zuriat-e-Zehra Ali, Rida Ashfaq, Rameesa Afzal, Mehr-un-Nisa, Babar Sultan, Abdul Jalil","doi":"10.1109/RITAPP.2019.8932822","DOIUrl":"https://doi.org/10.1109/RITAPP.2019.8932822","url":null,"abstract":"Sleep Apnea is a mutual disorder of sleep caused by obstructing airflow due to collapse of the soft tissue surrounding the upper airway of mouth or throat, and normal breathing would start again with a loud snort or choking sound. A traditional identification process of Sleep Apnea is polysomnography, which can only be accompanied in sleep centre with specific announcements, thus it is costly and problematic. In addition, it is utilized for understanding the conditions, without treatment work. Supplementary detecting techniques are Electrocardiogram (ECG), Pulse Oximeter, microphone or taking a video. A few strategies or gadgets have been created to lighten Sleep Apnea, such as; Continuous Positive Airway Pressure(CPAP), APAP (Automatic Positive Airway Pressure), BiPAP(Bilevel Positive Airway Pressure), intraoral mandibular advancement device and surgery. There are some parameters which help lower the chance of Sleep Apnea are; Surgery(uvulopalatopharyngoplasty), Intra-oral mandibular advancement, use of anti-snore pillows, weight control, sleeping in sideways position (Night Balance) and positional Therapy. In this paper, we propose and implement IoT based real time auto adjustable smart pillow system, we targeted only obstructive Sleep Apnea, initially it detects the attack and adjust the pillow accordingly if patient does not recover due to high Apnea attack it produces an alarm, so that the person lying beside the patient would awake to cater the situation and doctor would also be notified through IoT. Likened with current analysis or usage devices, the pillow is comfortable, non-invasive, inexpensive and portable, which can be used at home or during travelling.","PeriodicalId":234023,"journal":{"name":"2019 7th International Conference on Robot Intelligence Technology and Applications (RiTA)","volume":"87 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":"124168622","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":"ECGDeepNET: A Deep Learning approach for classifying ECG beats","authors":"Tanvir Mahmud, Abdul Rakib Hossain, S. Fattah","doi":"10.1109/RITAPP.2019.8932850","DOIUrl":"https://doi.org/10.1109/RITAPP.2019.8932850","url":null,"abstract":"The Electrocardiogram(ECG) is a wide spread used tool to monitor the health of a human heart. Detecting any abnormalities of heart signal is the primary objective. Researchers have given a great attention to make this detection error- less and to detect the heart beats abnormality as quick as possible. In this paper, we proposed a method to detect heart beats abnormality efficiently. Our proposed structure is quite lightweight requiring less computational power and memory. Furthermore, to reduce class imbalance while increasing accuracy, we preprocessed our data and augmented the lower numbered classes with 6 different operations. For arrhythmia classification, we achieved average accuracy of 97.3%, 98.9% with F1 score of 97.21%, 99.2% & specificity of 99.3%, 98.95% for MIT BIH Arrhythmia database and PTB Diagnostic ECG database respectively, which is higher enough for a lightweight architecture like proposed one.","PeriodicalId":234023,"journal":{"name":"2019 7th International Conference on Robot Intelligence Technology and Applications (RiTA)","volume":"73 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":"133411007","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":"Attention Neural Networks for Pan-Tilt-Zoom Control with Active Hand-Off","authors":"Tyler Highlander, J. Gallagher","doi":"10.1109/RITAPP.2019.8932760","DOIUrl":"https://doi.org/10.1109/RITAPP.2019.8932760","url":null,"abstract":"Communities of cooperating robots would be highly advantaged by the ability to focus the attention of better placed robots upon activities tagged as important by other robots. Neural network and deep learning methods are increasingly applied to attention based steering of cameras and other sensor arrays resident on robots. a hand-off of focus of attention requires that one robot communicate to other robots system state information. The specific state information that needs to be communicated can be difficult to determine in many empirically tuned neural deep learning systems. In this paper, we will propose a method for cleanly transferring focus of attention across physically disjoint deep network based motion trackers. The method has been constructed to have explicit and understandable hand-off capabilities to support tracking of an object of interest across an array of sensors each resident on a disjoint robot or other autonomous agent acting as a community. We will additionally provide an experimental analysis of system efficacy and a discussion of possible future work and the long-term implications of the observed results.","PeriodicalId":234023,"journal":{"name":"2019 7th International Conference on Robot Intelligence Technology and Applications (RiTA)","volume":"41 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":"132203914","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}
Jie Pang, Mengqian Tian, Xingsong Wang, Jiadong Lv, Donghua Shen
{"title":"A Novel Flexible Bidirectional Bending Actuator with Large Angle","authors":"Jie Pang, Mengqian Tian, Xingsong Wang, Jiadong Lv, Donghua Shen","doi":"10.1109/RITAPP.2019.8932744","DOIUrl":"https://doi.org/10.1109/RITAPP.2019.8932744","url":null,"abstract":"Rigid manipulators are widely used in different industrial applications, while the rigid actuators are not suitable for grasping fragile and vulnerable objects. Thus, with the increasing demand for soft actuators in many special areas, soft actuators have also made leap-forward development. Flexible actuators, as the end-effecter of manipulator, has been studied globally. It has the advantages of light weight, high safety and flexible operation. However, flexible actuators are mainly made of silica gel and rubber, which are supplemented by fabric and nylon thread to limit displacement. It takes a lot of time to make silica gel flexible actuators. This paper presents a novel flexible bi-directional bending actuators with large angle made by Aluminized Polyester materials (AP) and Polyethylene terephthalate (PET) using CO2 laser. In this paper, different reinforced structures are designed to limit the radial expansion of actuators. This paper aims to determine the relationship between gas pressure and bending angle under different chamber’s width. The actuators have simple process and excellent performance, which brings new research ideas for the design and manufacture of light and thin soft actuators. A novel soft manipulator was made by this actuator which can lift some objects.","PeriodicalId":234023,"journal":{"name":"2019 7th International Conference on Robot Intelligence Technology and Applications (RiTA)","volume":"39 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":"125896348","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}
Hyeon Cho, Hyungho Kim, Dae-Kwan Ko, Soo-Chul Lim, Wonjun Hwang
{"title":"Which LSTM Type is Better for Interaction Force Estimation?","authors":"Hyeon Cho, Hyungho Kim, Dae-Kwan Ko, Soo-Chul Lim, Wonjun Hwang","doi":"10.1109/RITAPP.2019.8932854","DOIUrl":"https://doi.org/10.1109/RITAPP.2019.8932854","url":null,"abstract":"Tactile, one of the five senses classified into the main senses of human, is the first sensation developed when human beings are formed. The tactile includes various information such as pressure, temperature, and texture of objects, it also helps the person to interact with the surrounding environment. One of the tactile information, the pressure is used in various fields such as medical, beauty, mobile devices and so on. However, humans can perceive the real world with multi-modal senses such as sound, vision. In this paper, we study interaction force estimation using haptic sensor and video. Interact ion force estimation through video analysis is one of a cross-modal approach that is applicable such as a software haptic feedback method that can give haptic feedback to remote control of robot arm by predicting interaction force even in absence of haptic sensor. we compare and analyze three types of a deep neural network to predict the interaction force. In particular, the best model for the stacking structure of CNN and LSTM is selected through a detailed analysis of how the structure change of LSTM affects the video regression problem. The average error of the best suit model is MSE 0.1306, RMSE 0.2740, MAE 0.1878.","PeriodicalId":234023,"journal":{"name":"2019 7th International Conference on Robot Intelligence Technology and Applications (RiTA)","volume":"22 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":"129480773","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. A. Felipe, Tanya V. Olegario, N. Bugtai, R. Baldovino
{"title":"Vision-based Liquid Level Detection in Amber Glass Bottles using OpenCV","authors":"M. A. Felipe, Tanya V. Olegario, N. Bugtai, R. Baldovino","doi":"10.1109/RITAPP.2019.8932807","DOIUrl":"https://doi.org/10.1109/RITAPP.2019.8932807","url":null,"abstract":"All manufacturing processes, from raw material processing to electronics fabrication, require quality control to ensure consistency across all products of same specifications. It helps establish the reputation of a certain brand, gain customer loyalty, and maximize profit. In the bottle filling industry, it is important to ensure that the amount of product in each bottle is consistent with the packaging label. Less than that, the company may lose customers and face legal consequences; more and the company loses profit by giving more than what was marketed. This study makes use of a vision-based technique in detecting the liquid level in amber glass bottles. The proposed system has applied Python and OpenCV for the pre-processing and image processing. Moreover, the study was successful in detecting and classifying filled bottles into three categories: under-fill, within target and over-fill.","PeriodicalId":234023,"journal":{"name":"2019 7th International Conference on Robot Intelligence Technology and Applications (RiTA)","volume":"84 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":"127253834","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":"RiTA 2019 Final Program","authors":"","doi":"10.1109/ritapp.2019.8932808","DOIUrl":"https://doi.org/10.1109/ritapp.2019.8932808","url":null,"abstract":"","PeriodicalId":234023,"journal":{"name":"2019 7th International Conference on Robot Intelligence Technology and Applications (RiTA)","volume":"38 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":"127893562","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}
R. R. Dajay, Jason L. Española, A. Bandala, R. Bedruz, R. R. Vicerra, E. Dadios
{"title":"Longitudinal Wheel Slip Regulation using Nonlinear Autoregressive-Moving Average (NARMA-L2) Neural Controller*","authors":"R. R. Dajay, Jason L. Española, A. Bandala, R. Bedruz, R. R. Vicerra, E. Dadios","doi":"10.1109/RITAPP.2019.8932939","DOIUrl":"https://doi.org/10.1109/RITAPP.2019.8932939","url":null,"abstract":"In this study, the implementation of a nonlinear autoregressive-moving average model ( NARMA-L2) neural network controller to maximize the tra ction of tires during braking scenarios was explored. The proposed controller and system dynamics was done in Simulink. All in all, the neural network controller shows good stability and good response in following the reference trajectory or desired slip ratio. It has experienced the peak worst error of around 2%, its best performance was reached after 89 epochs and it can reach around 99.5% of the reference trajectory or desired slip ratio. Further research should focus on hardware implementation, integration with slip estimation techniques , and, better sets of training data to make the controller more adaptive to different environment and road surface characteristics.","PeriodicalId":234023,"journal":{"name":"2019 7th International Conference on Robot Intelligence Technology and Applications (RiTA)","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":"125430621","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}