{"title":"A Lightweight Region Proposal Network for Task Specific Applications","authors":"Simon O'Keeffe, Rudi C. Villing","doi":"10.1109/ISSC.2019.8904949","DOIUrl":"https://doi.org/10.1109/ISSC.2019.8904949","url":null,"abstract":"Quickly and cheaply finding areas of interest within an image can save computationally intensive image processing in a vision pipeline. Existing region proposal networks are either too general (finding all objects in an image) or too complex (providing fine-tuned bounding boxes for classification). We propose a straightforward region proposal network that simply scores parts of the image based on whether or not they contain an object of interest. This calculation can be carried out quickly and for many applications including autonomous driving only a small fraction of of the image area may contain objects of interest. We trained our network on an autonomous robot soccer dataset with similar characteristics to the popular KITTI autonomous driving dataset and achieved a recall greater than 95% while eliminating on average over 80% of the image area from further processing.","PeriodicalId":312808,"journal":{"name":"2019 30th Irish Signals and Systems Conference (ISSC)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121608181","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":"String Stability Experimentation using a Low-Cost Mobile Robotic Testbed","authors":"Michael Johnson, M. Hayes","doi":"10.1109/ISSC.2019.8904961","DOIUrl":"https://doi.org/10.1109/ISSC.2019.8904961","url":null,"abstract":"This paper presents a practical implementation of string stability research in autonomous convoy formation that is suitable for use in a typical undergraduate project lab. The research presents a benchmark test problem that is challenging without representing a prohibitively expensive undertaking. The testbed development that is presented facilitates convoy formation, the implementation of different control laws and provides a good motivational example for a large range of complementary research themes. A case study that illustrates a loop shaping proportional plus integral control scheme is described. The example exhibits good stability and performance results that allows students to determine hard constraints on limits of convoy performance.","PeriodicalId":312808,"journal":{"name":"2019 30th Irish Signals and Systems Conference (ISSC)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126281295","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}
Kun Tian, Liaoyuan Zeng, S. McGrath, Qian Yin, Wenyi Wang
{"title":"3D Facial Expression Recognition Using Deep Feature Fusion CNN","authors":"Kun Tian, Liaoyuan Zeng, S. McGrath, Qian Yin, Wenyi Wang","doi":"10.1109/ISSC.2019.8904930","DOIUrl":"https://doi.org/10.1109/ISSC.2019.8904930","url":null,"abstract":"As an important way of human communication, facial expression not only reflects our mental activities but also provides useful information for human behavior research. Recently, 3D technology becomes promising method to achieve robust facial expression analysis. 3D face scans are robust to lighting and pose variations. In this paper, a novel deep feature fusion convolution neural network (CNN) is designed for 3D facial expression recognition (FER). Each 3D face scan is firstly represented as 2D facial attribute maps (including depth, normal, and shape index values). Then, we combine different of facial attribute maps to learn facial representations by fine-tuning a pre-trained deep feature fusion CNN subnet trained from a large-scale image dataset for universal visual tasks. Moreover, Global Average Pooling is utilized to reduce the number of parameters to decrease the effect of overfitting. The experiments are conducted on the Bosphorus database and the results demonstrate the effectiveness of the proposed method.","PeriodicalId":312808,"journal":{"name":"2019 30th Irish Signals and Systems Conference (ISSC)","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124596442","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}
George D. O’Mahony, Philip J. Harris, Colin C. Murphy
{"title":"Developing Low-Cost Testbeds for Enhancing Security Techniques in Wireless Sensor Network Protocols","authors":"George D. O’Mahony, Philip J. Harris, Colin C. Murphy","doi":"10.1109/ISSC.2019.8904967","DOIUrl":"https://doi.org/10.1109/ISSC.2019.8904967","url":null,"abstract":"Wireless sensor network (WSN) applications have expanded considerably over the past decade or so and now, solutions exit for various innovative applications. These wireless networks adopt commercial off the shelf devices and standardized protocols, which inherently creates security challenges. These challenges are ever changing as malicious interference and intrusion techniques evolve and dynamic efficient hardware becomes increasingly accessible. This paper presents the development of multiple low-cost hardware and software platforms designed so security enhancements and modifications to WSN protocol architecture and packet structure can be designed and tested. Each testbed has been built satisfying the requirements of being available as unmodified commercial off the shelf (COTS) components and based on open source software. The testbeds provide versatility through operating on various operating systems including Windows and Linux, are reproducible and can be deployed in a way which replicates real world WSNs. Each distinct system provides remote access, real time and off line data analysis, specific control of each network node and the ability to upload data from the WSN. This paper describes in-detail the individual pieces of suitable hardware for WSN protocol and packet structure design and illustrates the system architecture required to form testbeds which can experimentally validate modifications to a WSN protocol. Additionally, a baseline is defined and encapsulates the ZigBee standard. Example results of the distinct testbeds in operation are provided along with the specific open source software being used.","PeriodicalId":312808,"journal":{"name":"2019 30th Irish Signals and Systems Conference (ISSC)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124713275","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":"How to Learn Quickly: An investigation of how to optimally train deep neural networks and its implications for human learning","authors":"Luke Rickard","doi":"10.1109/ISSC.2019.8904953","DOIUrl":"https://doi.org/10.1109/ISSC.2019.8904953","url":null,"abstract":"This paper investigates the speed at which a deep neural network learns to play Tic- Tac- Toe as a function of the player's opponent's level of play. The goal of this work is not to find a faster deep learning algorithm or architecture, but rather to gain insight into the nature of adversarial learning and training. Do we learn faster by playing against an opponent of slightly worse, identical, better, or grandmaster ability?","PeriodicalId":312808,"journal":{"name":"2019 30th Irish Signals and Systems Conference (ISSC)","volume":"409 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132749229","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}
F. McGuinness, S. O’Keeffe, G. Dooly, D. Duraibabu, P. Woulfe, G. Leen
{"title":"Use of an Optical Fibre based Temperature Sensor for Radiotherapy Dosimetry","authors":"F. McGuinness, S. O’Keeffe, G. Dooly, D. Duraibabu, P. Woulfe, G. Leen","doi":"10.1109/ISSC.2019.8904917","DOIUrl":"https://doi.org/10.1109/ISSC.2019.8904917","url":null,"abstract":"This paper presents preliminary results on the evaluation of a novel optical fibre based sensor for the measurement of incident ionising radiation. The sensor is designed to be extremely sensitive to variations in temperature and the hypothesis being explored is that incident ionising radiation will generate some degree of heat in the sensor itself and its surrounding environment, which may in turn be measured with high resolution. Experiments were conducted on a radiotherapy linear accelerator for two clinical doses of 100 MU at 6 MV and 10 MV, in addition to this one non-clinical dose of 10,204 MU at 10 MV was performed. Results indicated that the sensor in its current configuration, while temperature sensitive, was unsuitable for measuring clinical levels of radiotherapy incident ionising radiation and further work is required to achieve the desired outcome.","PeriodicalId":312808,"journal":{"name":"2019 30th Irish Signals and Systems Conference (ISSC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130146003","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}
Amir Heidary, S. Mousavi, K. Rouzbehi, Juan Manuel Escaño
{"title":"Modelling and control of a Concentrating Solar Power Plant prototype","authors":"Amir Heidary, S. Mousavi, K. Rouzbehi, Juan Manuel Escaño","doi":"10.1109/ISSC.2019.8904946","DOIUrl":"https://doi.org/10.1109/ISSC.2019.8904946","url":null,"abstract":"This paper presents a type of solar thermal power plant and also studies the efficiency of the common type of this distributed generation resource. In order to improve the efficiency of the power station, several techniques are studied such as the combined cycle plant, the thermoelectric generator and the intelligent control application. The thermodynamic analysis of the power plant and the performance of the equipment with an intelligent control system are validated by the developed experimental prototype.","PeriodicalId":312808,"journal":{"name":"2019 30th Irish Signals and Systems Conference (ISSC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130256999","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":"Reference Point Estimation Technique for Direct Validation of Subpixel Point Detection Algorithms for Internet of Things","authors":"Mariusz P. Wilk, Brendan Q'Flynn","doi":"10.1109/issc.2019.8904921","DOIUrl":"https://doi.org/10.1109/issc.2019.8904921","url":null,"abstract":"Subpixel point detection algorithms are important in many application spaces, especially those where limitations of the imaging device's resolution need to be overcome. Such algorithms help decrease the overall requirements of the given system. Many factors, such as power consumption and cost, are critical in the context of the Internet of Things. While these algorithms do offer an improvement in the precision of point detection, it is often difficult to directly determine their precision. The main reason for it is the lack of the point of reference that the outputs of subpixel point detection methods can be compared to. In this work, we present a novel method for finding the point of reference for validating the subpixel point detection algorithms directly. Its operation is demonstrated on an experimentally obtained sample dataset.","PeriodicalId":312808,"journal":{"name":"2019 30th Irish Signals and Systems Conference (ISSC)","volume":"04 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131333975","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":"Jitter Buffer Compensation in Voice over IP Quality Estimation","authors":"Tong Mo, Andrew Hines","doi":"10.1109/ISSC.2019.8904962","DOIUrl":"https://doi.org/10.1109/ISSC.2019.8904962","url":null,"abstract":"Voice over Internet Protocol (VoIP) communications has grown in popularity and has been widely adopted as an alternative to traditional telephone technologies. As packet delivery time can vary, congestion and poor connections can result in delays being introduced. In order to maximise the Quality of Experience (QoE) for VoIP users, jitter buffers are deployed to manage the speech output at the receiver by minimising stalls in signal playout. Automated computer models have been created to compare the signal at the origin and destination in order to predict the perceived quality. Although short playout adjustments introduced by jitter buffers are imperceptible to human listeners, they can skew the results from speech quality prediction models. In this paper, the influence of origin and destination signal time alignment is investigated. A new algorithm for delay estimation that can be used for Jitter Buffer Compensation is proposed and evaluated for use within a speech quality prediction model called VISQOL. Two experiments were conducted. The first was used to design a delay estimation algorithm and to tune its parameters. The second validates the algorithm performance by comparing the quality prediction accuracy of the VISQOL speech quality model with the proposed Jitter Buffer Compensation model to the baseline model results. The results show that the proposed algorithm produces significantly fewer signal mis-alignments and better quality prediction.","PeriodicalId":312808,"journal":{"name":"2019 30th Irish Signals and Systems Conference (ISSC)","volume":"2023 9","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114090279","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}
Jiang Liu, Weiyu Cui, Liaoyuan Zeng, Ji Lin, Rumin Zhang, S. McGrath
{"title":"Racewalking Gait Analysis Based on RGB Images","authors":"Jiang Liu, Weiyu Cui, Liaoyuan Zeng, Ji Lin, Rumin Zhang, S. McGrath","doi":"10.1109/ISSC.2019.8904954","DOIUrl":"https://doi.org/10.1109/ISSC.2019.8904954","url":null,"abstract":"In this paper, we propose a novel method for race-walking gait analysis based on RGB images. Our method provides an efficient way to quantitatively evaluate an athlete's racewalking techniques, which enables them to improve through more precise training programs accordingly. Our method includes angle prediction and pace measurement, which in combination can indicates the impact of a racewalker's unique racewalking gait on his/her competition performance in terms of time. 1) In angle prediction, the calculation about the angle of limbs is based on the coordinates of the human skeleton points. 2) In pace measurement, we derive the racewalker's pace by detecting the distance covered by the racewalker in RGB images during a period of time. Finally, the results of a practical experiment on professional racewalking athletes show that our method can efficiently quantify and analyze the racewalking gait with high precision.","PeriodicalId":312808,"journal":{"name":"2019 30th Irish Signals and Systems Conference (ISSC)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131819756","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}