Pub Date : 2020-11-16DOI: 10.1109/TENCON50793.2020.9293764
Pallavi Madhukar, Rachana Chetan, Supriya Prasad, Mohamed Shayan, B. N. Krupa
This study presents a technique to generate face age progression by adopting a conditional generative adversarial network based approach. The best model resulting from a five-fold cross validation has an accuracy of 91.93%, False Omission Rate of 0.45% and Negative Prediction Value of 99.55%. Building on prior work, this paper has three contributions. First, the use of uneven age clusters is presented to account for more rapid and drastic ageing in babies and toddlers than older individuals. Second, perceptual losses rather than per-pixel losses are considered to enable identity preservation. Third, a facial recognition system is applied to verify the identity of individuals upon ageing. Identity preservation was achieved and confirmed, with a facial recognition accuracy of 92.4%. Visual fidelity was also confirmed, with 95.2% subjects identifying ageing in the conducted survey.
{"title":"Age Progression using Generative Adversarial Networks","authors":"Pallavi Madhukar, Rachana Chetan, Supriya Prasad, Mohamed Shayan, B. N. Krupa","doi":"10.1109/TENCON50793.2020.9293764","DOIUrl":"https://doi.org/10.1109/TENCON50793.2020.9293764","url":null,"abstract":"This study presents a technique to generate face age progression by adopting a conditional generative adversarial network based approach. The best model resulting from a five-fold cross validation has an accuracy of 91.93%, False Omission Rate of 0.45% and Negative Prediction Value of 99.55%. Building on prior work, this paper has three contributions. First, the use of uneven age clusters is presented to account for more rapid and drastic ageing in babies and toddlers than older individuals. Second, perceptual losses rather than per-pixel losses are considered to enable identity preservation. Third, a facial recognition system is applied to verify the identity of individuals upon ageing. Identity preservation was achieved and confirmed, with a facial recognition accuracy of 92.4%. Visual fidelity was also confirmed, with 95.2% subjects identifying ageing in the conducted survey.","PeriodicalId":283131,"journal":{"name":"2020 IEEE REGION 10 CONFERENCE (TENCON)","volume":"35 11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116652809","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 : 2020-11-16DOI: 10.1109/TENCON50793.2020.9293851
Erwin B. Daculan
This paper emerged during the process of continuous quality improvement of an introductory course on occupational safety and health. Did the students correctly associate an assessment activity to the right course outcome? The paper compared the evaluation of the students and the facilitator on the different activities used to assess the demonstration of abilities/outcomes attributed with the course. There were two activities per quarter of the semester. Each activity had been scheduled to demonstrate specific outcome indicators by the facilitator and is described in detail. An evaluation questionnaire was provided at the end of the semester to ascertain whether the students assessed the same outcome indicator as what course the set for each activity. The contention was to harmonize what outcomes the students believed they are exhibiting and what outcomes the course had intended for such activity. The gathered data from the evaluation questionnaire were tabulated and then compared with the original intended outcomes by the facilitator. Interpretation of the data was also forwarded and the path for continuous quality improvement was drawn.
{"title":"Comparative Evaluation of Assessment Activities in an Introductory Occupational Safety and Health Course","authors":"Erwin B. Daculan","doi":"10.1109/TENCON50793.2020.9293851","DOIUrl":"https://doi.org/10.1109/TENCON50793.2020.9293851","url":null,"abstract":"This paper emerged during the process of continuous quality improvement of an introductory course on occupational safety and health. Did the students correctly associate an assessment activity to the right course outcome? The paper compared the evaluation of the students and the facilitator on the different activities used to assess the demonstration of abilities/outcomes attributed with the course. There were two activities per quarter of the semester. Each activity had been scheduled to demonstrate specific outcome indicators by the facilitator and is described in detail. An evaluation questionnaire was provided at the end of the semester to ascertain whether the students assessed the same outcome indicator as what course the set for each activity. The contention was to harmonize what outcomes the students believed they are exhibiting and what outcomes the course had intended for such activity. The gathered data from the evaluation questionnaire were tabulated and then compared with the original intended outcomes by the facilitator. Interpretation of the data was also forwarded and the path for continuous quality improvement was drawn.","PeriodicalId":283131,"journal":{"name":"2020 IEEE REGION 10 CONFERENCE (TENCON)","volume":"224 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127188294","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 : 2020-11-16DOI: 10.1109/TENCON50793.2020.9293784
Jayanth Shreekumar, Ganesh K Shet, Vijay P N, Preethi S J, Niranjana Krupa
The proliferation of convolutional neural networks (CNN) has resulted in increased interest in the field of visual speech recognition (VSR). However, while VSR for word-level and sentence-level classification has received much of this attention, recognition of visemes has remained relatively unexplored. This paper focuses on the visemic approach for VSR as it can be used to build language-independent models. Our method employs generative adversarial networks (GANs) to create synthetic images that are used for data augmentation. VGG16 is used for classification both before and after augmentation. The results obtained prove that data augmentation using GANs is a viable technique for improving the performance of VSR models. Augmenting the dataset with images generated using the Progressive Growing Generative Adversarial Network (PGGAN) model led to an average increase in test accuracy of 3.695% across speakers. An average increase in test accuracy of 2.59% was achieved by augmenting the dataset using images generated by the conditional Deep Convolutional Generative Adversarial Network (DCGAN) model.
{"title":"Improved Viseme Recognition using Generative Adversarial Networks","authors":"Jayanth Shreekumar, Ganesh K Shet, Vijay P N, Preethi S J, Niranjana Krupa","doi":"10.1109/TENCON50793.2020.9293784","DOIUrl":"https://doi.org/10.1109/TENCON50793.2020.9293784","url":null,"abstract":"The proliferation of convolutional neural networks (CNN) has resulted in increased interest in the field of visual speech recognition (VSR). However, while VSR for word-level and sentence-level classification has received much of this attention, recognition of visemes has remained relatively unexplored. This paper focuses on the visemic approach for VSR as it can be used to build language-independent models. Our method employs generative adversarial networks (GANs) to create synthetic images that are used for data augmentation. VGG16 is used for classification both before and after augmentation. The results obtained prove that data augmentation using GANs is a viable technique for improving the performance of VSR models. Augmenting the dataset with images generated using the Progressive Growing Generative Adversarial Network (PGGAN) model led to an average increase in test accuracy of 3.695% across speakers. An average increase in test accuracy of 2.59% was achieved by augmenting the dataset using images generated by the conditional Deep Convolutional Generative Adversarial Network (DCGAN) model.","PeriodicalId":283131,"journal":{"name":"2020 IEEE REGION 10 CONFERENCE (TENCON)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124864631","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 : 2020-11-16DOI: 10.1109/TENCON50793.2020.9293833
Jiao Wu, B. Shim
Employing intelligent reflecting surfaces (IRSs) is emerging as a green alternative to improve the signal quality and suppress interference for massive antenna systems. Specifically, IRS is a planar surface consisting of a large number of low-cost and passive elements each being able to reflect the incident signal independently with an adjustable phase shift. In this paper, we study the power control problem at the user for an IRS-aided uplink system under the quality of service (QoS) constraints. Our goal is to minimize the total transmit power at the user by jointly optimizing the phase shifts of passive elements at the IRS and the receiving beamforming at the BS, subject to the signal-to-noise ratio (SNR) constraint at the user. To solve the resulting non-convex optimization problem, we develop an efficient algorithm, called the manifold-based alternating optimization (M-AO). Simulation results show that the proposed algorithm significantly saved the transmit power.
{"title":"Transmit Power Minimization in Intelligent Reflecting Surfaces-Aided Uplink Communications","authors":"Jiao Wu, B. Shim","doi":"10.1109/TENCON50793.2020.9293833","DOIUrl":"https://doi.org/10.1109/TENCON50793.2020.9293833","url":null,"abstract":"Employing intelligent reflecting surfaces (IRSs) is emerging as a green alternative to improve the signal quality and suppress interference for massive antenna systems. Specifically, IRS is a planar surface consisting of a large number of low-cost and passive elements each being able to reflect the incident signal independently with an adjustable phase shift. In this paper, we study the power control problem at the user for an IRS-aided uplink system under the quality of service (QoS) constraints. Our goal is to minimize the total transmit power at the user by jointly optimizing the phase shifts of passive elements at the IRS and the receiving beamforming at the BS, subject to the signal-to-noise ratio (SNR) constraint at the user. To solve the resulting non-convex optimization problem, we develop an efficient algorithm, called the manifold-based alternating optimization (M-AO). Simulation results show that the proposed algorithm significantly saved the transmit power.","PeriodicalId":283131,"journal":{"name":"2020 IEEE REGION 10 CONFERENCE (TENCON)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125866463","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 : 2020-11-16DOI: 10.1109/TENCON50793.2020.9293790
N. JagadishD., Lakshman Mahto, Arun Chauhan
Multiple object detection using deep neural networks can lead to transportation vehicles estimate, a necessary requirement for prediction and management of road traffic and parking lot. Highly overlapped objects that look similar and objects that are there at far distances have lesser probability of detection by state-of-art techniques. We propose techniques to estimate the traffic at regions of poor detection probability in the image based on (i) density based clustering and (ii) exclusive object detection in the regions of poor detection. The proposed techniques lead to better estimation in comparison to state-of-art by approximately 12 %. We have utilized RetinaNet and YOLOv3 networks for object detection.
{"title":"Density Based Clustering Methods for Road Traffic Estimation","authors":"N. JagadishD., Lakshman Mahto, Arun Chauhan","doi":"10.1109/TENCON50793.2020.9293790","DOIUrl":"https://doi.org/10.1109/TENCON50793.2020.9293790","url":null,"abstract":"Multiple object detection using deep neural networks can lead to transportation vehicles estimate, a necessary requirement for prediction and management of road traffic and parking lot. Highly overlapped objects that look similar and objects that are there at far distances have lesser probability of detection by state-of-art techniques. We propose techniques to estimate the traffic at regions of poor detection probability in the image based on (i) density based clustering and (ii) exclusive object detection in the regions of poor detection. The proposed techniques lead to better estimation in comparison to state-of-art by approximately 12 %. We have utilized RetinaNet and YOLOv3 networks for object detection.","PeriodicalId":283131,"journal":{"name":"2020 IEEE REGION 10 CONFERENCE (TENCON)","volume":"88 1-2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123433087","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}
When the human population is experiencing a decline but the turnover rate of pharmacists in general hospitals is gradually increasing, department of pharmacy starts to import more modern technologies including automation and artificial intelligence to aid in the workflow. One of the lengthy and routine work is to count the number of remaining medications of each ward, which requires many pharmacists and technicians depends on the size of hospital. This study thereby introduces a design of a medication assist device with an integration of the machine vision and multiple object recognition algorithm. The work can be divided into hardware design, data collection, training and validation, respectively. The recognition algorithm is based on deep learning Faster RCNN, which can successfully identify 7 classes of the anesthetics often used with an accuracy of 99.03%. This pilot study presents the capability of medication recognition, and the potential to expand numbers of medication.
{"title":"A Development of Medication Assist Device Based on Multi-Object Recognition","authors":"Yu-Sheng Lin, Chia-Ching Tsai, Kai-Ming Chang, Pao-Chin Shih, Ching-Lan Cheng","doi":"10.1109/TENCON50793.2020.9293874","DOIUrl":"https://doi.org/10.1109/TENCON50793.2020.9293874","url":null,"abstract":"When the human population is experiencing a decline but the turnover rate of pharmacists in general hospitals is gradually increasing, department of pharmacy starts to import more modern technologies including automation and artificial intelligence to aid in the workflow. One of the lengthy and routine work is to count the number of remaining medications of each ward, which requires many pharmacists and technicians depends on the size of hospital. This study thereby introduces a design of a medication assist device with an integration of the machine vision and multiple object recognition algorithm. The work can be divided into hardware design, data collection, training and validation, respectively. The recognition algorithm is based on deep learning Faster RCNN, which can successfully identify 7 classes of the anesthetics often used with an accuracy of 99.03%. This pilot study presents the capability of medication recognition, and the potential to expand numbers of medication.","PeriodicalId":283131,"journal":{"name":"2020 IEEE REGION 10 CONFERENCE (TENCON)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126639318","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 : 2020-11-16DOI: 10.1109/TENCON50793.2020.9293894
Gennylyn Canacan, John Thimotee Llanto, Eala Eireen Moredo, Adonis S. Santos, Francis A. Malabanan, J. Tabing, Sherryl M. Gevana
Efficiency is a requirement when it comes to utilizing a wireless sensor network (WSN) where hydrokinetic energy harvesting through turbine is involved. Thus, not only WSN needs an efficient supply but also the sensors and the storage unit which are powered up by an energy harvesting module, a turbine DC generator. Turbine DC generator produces a low voltage and low voltage means low power. To produce high efficiency output despite the low power it produces, a DC-DC converter is one of the preliminaries. DC-DC converter regulates its input coming from the turbine DC generator and produces a more stable power supply. However, blocks that the DC-DC converter supplies have different voltage requirement. Therefore, the researchers will develop two DC-DC converter topology which are the Buck Converter and the Boost Converter. On the contrary, turbine DC generator produces varying DC supply to the boost converter inducing noises and reducing the efficiency needed. Therefore, to achieve a highly efficient output the device needs to be low noise. To prevent noise from affecting the efficiency of the device, the researchers will use a technique called Hysteretic Control (HC) of DC-DC converter. This research intended to design a high efficiency Direct Current-to-Direct Current Converter for hydroelectric energy harvester in wireless sensor network. Using an Electronic Design Automation (EDA) tool, Synopsys, and ensuing the full custom analog design is practiced, the researchers develop a DC-DC converter that will provide an efficiency of 80% - 95% by reducing the noise by using a switching DC-DC converter.
{"title":"Development of a High Efficiency DC-DC Converter Using Hysteretic Control for Hydroelectric Energy Harvester in a Wireless Sensor Network","authors":"Gennylyn Canacan, John Thimotee Llanto, Eala Eireen Moredo, Adonis S. Santos, Francis A. Malabanan, J. Tabing, Sherryl M. Gevana","doi":"10.1109/TENCON50793.2020.9293894","DOIUrl":"https://doi.org/10.1109/TENCON50793.2020.9293894","url":null,"abstract":"Efficiency is a requirement when it comes to utilizing a wireless sensor network (WSN) where hydrokinetic energy harvesting through turbine is involved. Thus, not only WSN needs an efficient supply but also the sensors and the storage unit which are powered up by an energy harvesting module, a turbine DC generator. Turbine DC generator produces a low voltage and low voltage means low power. To produce high efficiency output despite the low power it produces, a DC-DC converter is one of the preliminaries. DC-DC converter regulates its input coming from the turbine DC generator and produces a more stable power supply. However, blocks that the DC-DC converter supplies have different voltage requirement. Therefore, the researchers will develop two DC-DC converter topology which are the Buck Converter and the Boost Converter. On the contrary, turbine DC generator produces varying DC supply to the boost converter inducing noises and reducing the efficiency needed. Therefore, to achieve a highly efficient output the device needs to be low noise. To prevent noise from affecting the efficiency of the device, the researchers will use a technique called Hysteretic Control (HC) of DC-DC converter. This research intended to design a high efficiency Direct Current-to-Direct Current Converter for hydroelectric energy harvester in wireless sensor network. Using an Electronic Design Automation (EDA) tool, Synopsys, and ensuing the full custom analog design is practiced, the researchers develop a DC-DC converter that will provide an efficiency of 80% - 95% by reducing the noise by using a switching DC-DC converter.","PeriodicalId":283131,"journal":{"name":"2020 IEEE REGION 10 CONFERENCE (TENCON)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116226244","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 : 2020-11-16DOI: 10.1109/TENCON50793.2020.9293787
K. Jayasena, K. M. P. Bandaranayake, B. Kumara
Cloud computing is a computing platform that allows users to access various kinds of computing services over the internet. Cloud provides on-demand, scalable and highly available resources on pay-per-usage subscriptions. Cloud is an optimum solution for executing a large number of different size tasks as for the computing capability it offers. Task scheduling is one of the major open challenges that need to be addressed. The Task scheduling problem in the cloud is known to be an NP- complete problem. Hence heuristics can be used to get an optimal solution. There have been many heuristics proposed for the task scheduling problem in the cloud. None of them has considered the total execution time of the virtual machine as a factor for finding a better schedule. In this paper, we proposed a new task scheduling algorithm named Total Resource Execution Time Aware Algorithm (TRETA) which takes into account the total execution time of computing resources in obtaining an optimal schedule. The algorithm is compared with Min-Min, Min-Max, FCFS, and MCT heuristics for Makespan, Degree of Imbalance and System Throughput. The proposed algorithm shows a significant amount of improvement in Makespan compared to other heuristics. The algorithm also outperforms other heuristics with respect to System Throughput and Degree of Imbalance which results in better workload distribution among the cloud resources.
云计算是一个允许用户通过互联网访问各种计算服务的计算平台。云提供按需、可扩展和高可用性的按使用付费订阅资源。云是执行大量不同规模任务的最佳解决方案，因为它提供了计算能力。任务调度是需要解决的主要开放挑战之一。云中的任务调度问题是一个NP完全问题。因此，可以使用启发式方法来获得最优解。针对云中的任务调度问题，已经提出了许多启发式算法。它们都没有将虚拟机的总执行时间作为寻找更好调度的一个因素。本文提出了一种新的任务调度算法——总资源执行时间感知算法(Total Resource Execution Time Aware algorithm, TRETA)，该算法考虑计算资源的总执行时间来获得最优调度。将该算法与Min-Min、Min-Max、FCFS和MCT启发式算法在Makespan、不平衡度和系统吞吐量方面进行了比较。与其他启发式算法相比，所提出的算法在Makespan方面显示出显著的改进。该算法在系统吞吐量和不平衡程度方面也优于其他启发式算法，从而在云资源之间更好地分配工作负载。
{"title":"TRETA - A Novel Heuristic Based Efficient Task Scheduling Algorithm in Cloud Environment","authors":"K. Jayasena, K. M. P. Bandaranayake, B. Kumara","doi":"10.1109/TENCON50793.2020.9293787","DOIUrl":"https://doi.org/10.1109/TENCON50793.2020.9293787","url":null,"abstract":"Cloud computing is a computing platform that allows users to access various kinds of computing services over the internet. Cloud provides on-demand, scalable and highly available resources on pay-per-usage subscriptions. Cloud is an optimum solution for executing a large number of different size tasks as for the computing capability it offers. Task scheduling is one of the major open challenges that need to be addressed. The Task scheduling problem in the cloud is known to be an NP- complete problem. Hence heuristics can be used to get an optimal solution. There have been many heuristics proposed for the task scheduling problem in the cloud. None of them has considered the total execution time of the virtual machine as a factor for finding a better schedule. In this paper, we proposed a new task scheduling algorithm named Total Resource Execution Time Aware Algorithm (TRETA) which takes into account the total execution time of computing resources in obtaining an optimal schedule. The algorithm is compared with Min-Min, Min-Max, FCFS, and MCT heuristics for Makespan, Degree of Imbalance and System Throughput. The proposed algorithm shows a significant amount of improvement in Makespan compared to other heuristics. The algorithm also outperforms other heuristics with respect to System Throughput and Degree of Imbalance which results in better workload distribution among the cloud resources.","PeriodicalId":283131,"journal":{"name":"2020 IEEE REGION 10 CONFERENCE (TENCON)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121897787","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 : 2020-11-16DOI: 10.1109/TENCON50793.2020.9293865
Punyanuch Borwarnginn, J. Haga, Worapan Kusakunniran
Natural disasters are a global problem that causes widespread losses and damage. A system to provide timely information is required in order to help reduce losses. Flooding is one of the major natural disasters that requires a monitoring and detection system. The traditional flood detection systems use remote sensors such as river water levels and rainfall to provide information to both disaster management professionals and the general public. There is an attempt to use visual information such as CCTV cameras to detect extreme flooding events; however, it requires human experts and consistent attention to monitor any changes. In this paper, we introduce an approach to the automatic river water level detection using deep learning to determine the water level from surveillance cameras. The model achieves 93% accuracy using a single camera location and 83% accuracy using multiple camera locations.
{"title":"Water Level Detection from CCTV Cameras using a Deep Learning Approach","authors":"Punyanuch Borwarnginn, J. Haga, Worapan Kusakunniran","doi":"10.1109/TENCON50793.2020.9293865","DOIUrl":"https://doi.org/10.1109/TENCON50793.2020.9293865","url":null,"abstract":"Natural disasters are a global problem that causes widespread losses and damage. A system to provide timely information is required in order to help reduce losses. Flooding is one of the major natural disasters that requires a monitoring and detection system. The traditional flood detection systems use remote sensors such as river water levels and rainfall to provide information to both disaster management professionals and the general public. There is an attempt to use visual information such as CCTV cameras to detect extreme flooding events; however, it requires human experts and consistent attention to monitor any changes. In this paper, we introduce an approach to the automatic river water level detection using deep learning to determine the water level from surveillance cameras. The model achieves 93% accuracy using a single camera location and 83% accuracy using multiple camera locations.","PeriodicalId":283131,"journal":{"name":"2020 IEEE REGION 10 CONFERENCE (TENCON)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129852451","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 : 2020-11-16DOI: 10.1109/TENCON50793.2020.9293726
Mohammad F. Jamaluddin, M. F. A. Fauzi, F. S. Abas, Jenny T. H. Lee, S. Y. Khor, K. Teoh, L. Looi
In this paper, we present our recent work on cells detection and segmentation in estrogen receptor immunohistochemistry (ER-IHC)-stained breast carcinoma images. The proposed cell detection and segmentation is very useful in the predictive scoring of hormone receptor status in ER-IHC stained whole-slide images, which helps pathologists to decide whether a patient should be offered hormonal therapy or other treatments. The proposed method is based on deep convolutional neural network, followed by watershed-based post-processing. The cell detection results are compared and evaluated objectively against the ground truth provided by our collaborating pathologists. The cell segmentation results, on the other hand, are evaluated visually by overlaying the computer segmented boundaries on the ER-IHC images for comparison. The automated cell detection algorithm recorded precision and recall rates of 95% and 91% respectively. The very promising performances for both the detection and segmentation paves the way for an automated system for hormone receptor scoring in ER-IHC stained whole-slide breast carcinoma images.
{"title":"Cells Detection and Segmentation in ER-IHC Stained Breast Histopathology Images","authors":"Mohammad F. Jamaluddin, M. F. A. Fauzi, F. S. Abas, Jenny T. H. Lee, S. Y. Khor, K. Teoh, L. Looi","doi":"10.1109/TENCON50793.2020.9293726","DOIUrl":"https://doi.org/10.1109/TENCON50793.2020.9293726","url":null,"abstract":"In this paper, we present our recent work on cells detection and segmentation in estrogen receptor immunohistochemistry (ER-IHC)-stained breast carcinoma images. The proposed cell detection and segmentation is very useful in the predictive scoring of hormone receptor status in ER-IHC stained whole-slide images, which helps pathologists to decide whether a patient should be offered hormonal therapy or other treatments. The proposed method is based on deep convolutional neural network, followed by watershed-based post-processing. The cell detection results are compared and evaluated objectively against the ground truth provided by our collaborating pathologists. The cell segmentation results, on the other hand, are evaluated visually by overlaying the computer segmented boundaries on the ER-IHC images for comparison. The automated cell detection algorithm recorded precision and recall rates of 95% and 91% respectively. The very promising performances for both the detection and segmentation paves the way for an automated system for hormone receptor scoring in ER-IHC stained whole-slide breast carcinoma images.","PeriodicalId":283131,"journal":{"name":"2020 IEEE REGION 10 CONFERENCE (TENCON)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128744609","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：