{"title":"Retinal Vessel Segmentation from Fundus Images Using DeepLabv3+","authors":"M. Tang, S. S. Teoh, H. Ibrahim","doi":"10.1109/CSPA55076.2022.9781891","DOIUrl":"https://doi.org/10.1109/CSPA55076.2022.9781891","url":null,"abstract":"Blood vessel segmentation from retinal images is crucial for identifying a range of eye diseases, including diabetic retinopathy and glaucoma. Therefore, research on automatic retinal blood vessels segmentation has sparked much attention. Numerous image processing techniques have been developed for segmenting retinal vessels from fundus images. In this paper, we propose a method that is based on deep learning. A semantic segmentation convolutional neural network (CNN) based on DeepLabv3+ was implemented. To allow for blood vessel segmentation, the network was modified to accept single-channel images and perform two-class pixelbased classification (vessel and non-vessel). Following segmentation, the output images are refined using morphological closing operation. The suggested technique was validated using images from the DRIVE dataset. The results show that it can achieve accuracy, sensitivity, specificity, precision, Jaccard, and Dice values of 0.9263, 0.8006, 0.9385, 0.5579, 0.4874, and 0.6551, respectively. We demonstrated that the proposed method could produce better results than those produced by other proposed methods.","PeriodicalId":174315,"journal":{"name":"2022 IEEE 18th International Colloquium on Signal Processing & Applications (CSPA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130178017","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}
K. H. Yusof, Fadhilah Aman, A. Ahmad, M. Abdulrazaq, M. N. Mohammed, Mohamad Syahrul Zahwan Mohd Zabidi, A. Asyraf
{"title":"Design and Development of Real Time Indoor and Outdoor Air Quality Monitoring System Based on IoT Technology","authors":"K. H. Yusof, Fadhilah Aman, A. Ahmad, M. Abdulrazaq, M. N. Mohammed, Mohamad Syahrul Zahwan Mohd Zabidi, A. Asyraf","doi":"10.1109/CSPA55076.2022.9781937","DOIUrl":"https://doi.org/10.1109/CSPA55076.2022.9781937","url":null,"abstract":"While the countries grow to be developed and industrial, the pollution level is increased significantly, and this becomes a critical downfall for the people’s health. This paper presents a system of smart air quality monitoring for urban city area by using IoT Technology. The main purpose of this research is to minimize, improvise, and use low-cost configuration, yet with equal ability to perform as industrial sensor capability, as required by the IEEE 1451 Sensor Standard. This enables the usage of this system in range of 20 meters for the WIFI module. This module consists of two sensors that function to detect concentrate elements in nearby environment. The first sensor is an air quality sensor that functions to detect the value of carbon dioxide in the environment. The second sensor detects and indicates the temperature and humidity. Both sensors will show the values detected through wireless monitor, either by smartphone or any device that can access web-based or application platforms. This is to ensure that the value is detected, hence ability to observe. Any malfunction can be reset remotely, and the user can determine the next decisions. The proposed system, by combination of esp32, IoT Platform and the Wi-Fi modules, is also able to give immediate data reading, while being remotely observed by notice from the system output.","PeriodicalId":174315,"journal":{"name":"2022 IEEE 18th International Colloquium on Signal Processing & Applications (CSPA)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129369778","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":"Deep Learning Based Single Pixel Imaging Using Coarse-to-fine Sampling","authors":"Bing Hong Woo, Mau-Luen Tham, S. Chua","doi":"10.1109/CSPA55076.2022.9781926","DOIUrl":"https://doi.org/10.1109/CSPA55076.2022.9781926","url":null,"abstract":"Image quality and time efficiency are the primary concerns in single pixel imaging (SPI) system. In general, one can increase the number of measurements to improve the image quality, but this will overloads the acquisition and reconstruction process on the other hand. The improvement should not only address the image quality issue, but also needs to consider the efficiency. Therefore, this paper proposes a deep learning based SPI using coarse-to-fine sampling scheme. Benefits from the efficiency of deep learning reconstruction, the proposed method progressively samples and reconstructs a better image until a specific criterion is fulfilled. The results show that coarse-to-fine sampling consistently outperforms the uniform sampling in terms of image quality. At the same time, efficient image computation is achieved by the deep learning GAN based reconstruction. In conclusion, the proposed method is proven as a feasible solution to optimise the trade-off between image quality and computational load.","PeriodicalId":174315,"journal":{"name":"2022 IEEE 18th International Colloquium on Signal Processing & Applications (CSPA)","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122562901","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":"Fault Diagnosis System of Hall Sensor in Brushless DC Motor based on Neural Networks Approach","authors":"KennySauKang Chu, K. Chew, YoongChoon Chang","doi":"10.1109/CSPA55076.2022.9781875","DOIUrl":"https://doi.org/10.1109/CSPA55076.2022.9781875","url":null,"abstract":"Hall sensors are commonly used or built in a motor system. The functionality of the hall sensor is to detect the speed and position of the motor. The normal operation of motors is affected by hall sensor’s fault. A fault diagnosis system is implemented in the motor system is commonly used to detect faults. In the industry, traditional methods such as the state-sensitive method or edge-sensitive method are widely implemented. Traditional methods have limitations such as complexity for implementation in other models and less robust. This paper proposed a fault diagnosis system based on the neural network approach. The characteristics of different types of neural networks were studied. Different types of neural networks were implemented, not every neural network variant was able to achieve a decent performance for the fault diagnosis system. The results were shown that the fault diagnosis system based on both CNN and DNN effectively determine faults and achieve accuracy above 95%.","PeriodicalId":174315,"journal":{"name":"2022 IEEE 18th International Colloquium on Signal Processing & Applications (CSPA)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117112737","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}
Raihah Aminuddin, Farizul Azlan Maskan, Ummu Mardhiah Abdul Jalil, Siti Feirusz Ahmad Fesol, Shafaf Ibrahim
{"title":"Support Vector Machine-based approach for Recognizing Bonsai Species using Leaf Image","authors":"Raihah Aminuddin, Farizul Azlan Maskan, Ummu Mardhiah Abdul Jalil, Siti Feirusz Ahmad Fesol, Shafaf Ibrahim","doi":"10.1109/CSPA55076.2022.9781913","DOIUrl":"https://doi.org/10.1109/CSPA55076.2022.9781913","url":null,"abstract":"Recognition of Bonsai plant is one of the most challenging task. This is because most of the people have less knowledge about Bonsai especially for a beginner. For those who new to this field, it might be hard for them to recognize and identify the species of Bonsai because of its similarity in terms of shape, colour and etc. The incorrect identification of species, may resulting in damaging the Bonsai plant. Furthermore, different species of Bonsai may have different ways to take care of it. Therefore, the information about the Bonsai need to be accessible with the recognition of the species. As a solution, the aims of this project is to develop a system for recognising three species of Bonsai: 1) Adenium, 2) Red Japanese Maple and 3) Natal Plum by using its leaf. The project implemented a Rapid Application Development (RAD) Model as the methodology. There are four phases in RAD: 1) Planning, 2) Design, 3) Implementation and 4) Finalization. In pre-processed phase, feature extraction of the leaf is using colour moment and Gray-Level Co- occurrence Matrix (GLCM) were used for extracting the colour of the leaf. The species of Bonsai has been classified using Support Vector Machine-based approach and the system has been successfully recognize the species of Bonsai with accuracy of 98.2%.","PeriodicalId":174315,"journal":{"name":"2022 IEEE 18th International Colloquium on Signal Processing & Applications (CSPA)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121496617","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}
Chrizel O. Andrada, Geraldine Joy M. Tolentino, J. D. dela Cruz
{"title":"Application of LoRa Technology in ET based Irrigation of Village Parks","authors":"Chrizel O. Andrada, Geraldine Joy M. Tolentino, J. D. dela Cruz","doi":"10.1109/CSPA55076.2022.9781881","DOIUrl":"https://doi.org/10.1109/CSPA55076.2022.9781881","url":null,"abstract":"The communication coverage of Long Range (LoRa) in a dense urban environment has not been much focused specifically in the Philippines. Long Range (LoRa) communication opened various possibilities for LPWAN communications, including Smart Irrigation solutions. A smart irrigation system involves water conservation in which controlled irrigation is practiced because it has medium water consumption. This paper presents the application of LoRa (abbreviation of Long Range) of an evapotranspiration based-irrigation (ET-based) system to meet the required volume of water of a turf. The system harnessed two sources of environmental data; (1) sensor nodes that collect temperature, soil moisture, water flow sensor, and (2) public weather forecast. These data will be stored in the raspberry pi data logger. The system is configured to calculate the reference evapotranspiration using the Penman-Monteith equation and the crop water requirement. Users can schedule the irrigation in the system; through LoRa communication, it can send a trigger signal along with the calculated water requirement to start the irrigation. The data is also sent to the ThingSpeak cloud for monitoring. This paper also presents the localization of the LoRa device in the remote stations to find the best position to set up the LoRa devices. Finally, the researchers presented how much water is saved through ET-based irrigation compared to manual irrigation.","PeriodicalId":174315,"journal":{"name":"2022 IEEE 18th International Colloquium on Signal Processing & Applications (CSPA)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130473757","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}
K. H. Yusof, Fadhilah Aman, A. Ahmad, M. Abdulrazaq, M. N. Mohammed, Mohamad Syahrul Zahwan Mohd Zabidi, Mohammad Yusuf Harith Sauzi
{"title":"Determination of Soil Texture Using Image Processing Technique","authors":"K. H. Yusof, Fadhilah Aman, A. Ahmad, M. Abdulrazaq, M. N. Mohammed, Mohamad Syahrul Zahwan Mohd Zabidi, Mohammad Yusuf Harith Sauzi","doi":"10.1109/CSPA55076.2022.9781996","DOIUrl":"https://doi.org/10.1109/CSPA55076.2022.9781996","url":null,"abstract":"Agriculture is the backbone of world’s economy and it is one of the largest employment sectors. Nowadays, the population is growing fast and simultaneously, the total cultivable land is lessening drastically. Soil texture has a significant impact on the agriculture affecting crop selection and crop growth. This paper presents the development of soil texture detection and pH value determination of the soil using the image processing technique. In this paper, two methods have been applied to identify the soil texture using two color-space methods in the MATLAB toolbox, which are the Hue Saturation Value (HSV) and Red Green Blue (RGB) color method. Furthermore, to determine the pH value of the soil, an image processing algorithm was applied to obtain the desired output. Moreover, these two proposed methods were applied in the Graphical User Interface (GUI) in MATLAB software. The proposed system is expected to contribute to the community by saving human effort, increases efficiency and generates more accurate results in shorter time.","PeriodicalId":174315,"journal":{"name":"2022 IEEE 18th International Colloquium on Signal Processing & Applications (CSPA)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122952357","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":"Performance Analysis of OTFS Signal with Different Pulse Shapes for JCR Systems","authors":"Olivia Zacharia, V. M","doi":"10.1109/CSPA55076.2022.9781902","DOIUrl":"https://doi.org/10.1109/CSPA55076.2022.9781902","url":null,"abstract":"The integration of radars and communication systems has become inevitable due to the need for sharing the radar spectrum with communication systems as the communication spectrum is being congested due to the increased number of connected devices. The recently evolved orthogonal time frequency space (OTFS) modulation scheme was found to be very efficient in designing a joint communication and radar (JCR) waveform. We propose a circular-prolate pulse shape (CPPS) for the OTFS modulation scheme and perform a comparative analysis of various existing pulse shapes for OTFS in terms of bit error rate (BER) and out-of-band (OoB) power radiation. We then investigate the application of the proposed pulse shape in an OTFS based JCR system by providing simulation results for a linear minimum mean square error (LMMSE) communication data receiver and both generalized likelihood ratio test detector (GLRT) and matched filter detector for target parameter estimation. Results show that the proposed CPPS OTFS has the least OoB compared to the other pulse shapes while being able to provide a BER performance similar to that of the existing pulse shapes like the discrete prolate spheroidal pulse shape (DPSPS) and the circular Dirichlet pulse shape (CDPS).","PeriodicalId":174315,"journal":{"name":"2022 IEEE 18th International Colloquium on Signal Processing & Applications (CSPA)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123562357","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}
Muhammad Amir Hakim Ismail, Muhammad Luqman Yasruddin, Z. Husin, W. Tan
{"title":"Automated Trading System for Forecasting the Foreign Exchange Market Using Technical Analysis Indicators and Artificial Neural Network","authors":"Muhammad Amir Hakim Ismail, Muhammad Luqman Yasruddin, Z. Husin, W. Tan","doi":"10.1109/CSPA55076.2022.9781856","DOIUrl":"https://doi.org/10.1109/CSPA55076.2022.9781856","url":null,"abstract":"The article discusses an automated trading system for forecasting foreign exchange markets that utilise Technical Analysis (TA) indicators and Artificial Neural Networks (ANN). Manual traders are usually swayed by their emotions, resulting in a catastrophic loss. As a result, this research will focus on developing an automated trading system that operates independently of human emotions. We provide a strategy for forecasting the movement of the foreign exchange market that incorporates TA indicators and the ANN system. The article examines TA indicators and the ANN system in automated trading systems to achieve accurate foreign exchange price forecasts. The experimental results on the Pound-Dollar (GBP/USD) exchange rate demonstrate that the combination of the TA indicators and the ANN system effectively provides information for forecasting the GBP/USD exchange rate. The performance of the suggested method is examined, revealing that it is capable of forecasting foreign exchange market movement utilising TA indicators and an ANN system.","PeriodicalId":174315,"journal":{"name":"2022 IEEE 18th International Colloquium on Signal Processing & Applications (CSPA)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114671329","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":"Lyapunov Stability Analysis of Covid-19 SIRV Model","authors":"D. Mahayana","doi":"10.1109/CSPA55076.2022.9781865","DOIUrl":"https://doi.org/10.1109/CSPA55076.2022.9781865","url":null,"abstract":"Until now, it is not known when the COVID-19 pandemic in Indonesia will end. As COVID-19 cases continue to increase, predicting the number of cases infected with COVID-19 is very important to design a control strategy to reduce the disease spread. Towards the end of 2020, several manufacturers announced high efficacy rates of COVID-19 vaccine candidates. Vaccines have been believed to be an important tool for improving the health of the population so that the disease spread can be controlled without hindering economic growth. A Mathematical model of infectious diseases is an important tool that has been focused on predicting the dynamics of the disease spread. It can be used to predict the future situation of a potential outbreak and evaluate the best strategy to reduce the spread of the outbreak. There are many types of mathematical models to predict the behavior of an infectious disease that is transmitted from human to human. One of the commonly used is called the compartment model. In this paper, we use a modified SIR model with vaccination to predict the behavior of the disease spread after vaccination. Theoretically, a successful vaccination program should slow down the rate of the virus spread. The modified SIR model with vaccination is adopted to predict the spread of coronavirus. Here, we proof that the model has a unique equilibrium point that is globally asymptotically stable by using Lyapunov function if the vaccination rate is greater than zero. Otherwise, if there is no vaccination is done, the equilibrium points only stable if reproduction number of infection is less than one. Further, the model will be implemented to Indonesia data to predict the behavior of the spread of the disease after the vaccination program.","PeriodicalId":174315,"journal":{"name":"2022 IEEE 18th International Colloquium on Signal Processing & Applications (CSPA)","volume":"2015 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114726566","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}