2021 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)最新文献

{"title":"Short-term Power Prediction using ANN","authors":"G. Perveen, P. Anand, Amod Kumar","doi":"10.1109/ICSIPA52582.2021.9576813","DOIUrl":"https://doi.org/10.1109/ICSIPA52582.2021.9576813","url":null,"abstract":"An accurate prediction of solar energy becomes imperative for the planning and optimization of solar-based energy systems. The present research involves the implementation of Artificial Neural Network (ANN) models employing a cascade forward backpropagation algorithm for predicting short-term PV power using meteorological parameters based on distinct weather conditions. Prediction of solar energy during clear weather is easily done; however, the challenge lies in prediction under cloudy weather conditions. Therefore, the present work involves the prediction of power in solar PV systems for clear, hazy, partly and fully cloudy weather in composite climatic zone. Models are developed by simulating in MATLAB platform and for validating the accuracy of the results, statistical evaluation indices are used. The model can be used easily for predicting power for the preliminary design of solar-based applications.","PeriodicalId":326688,"journal":{"name":"2021 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126507019","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":"Class 1 and Class 2 Underwater Image Enhancement and Restoration Under Turbidity Conditions","authors":"M. K. Awang, Halimatun Saidah Aminuddin, Nurul Kamilah Mat Kamil, K. Mustafa","doi":"10.1109/ICSIPA52582.2021.9576782","DOIUrl":"https://doi.org/10.1109/ICSIPA52582.2021.9576782","url":null,"abstract":"Poor visibility in underwater images is commonly attributed to the presence of impurities and the absorbed light being scattered while travelling through impure water. In this paper, image enhancement and restoration techniques are applied to TURBID image datasets. The TURBID dataset consists of three different types of underwater image conditions where blue solution, milk solution, or chlorophyll solution is added to water. The images undergo Histogram equalization (HE) and are filtered with a Wiener filter for image enhancement and image restoration, respectively. HE as the chosen enhancement method proved that it could enhance the image quality as the water surface can be seen clearer after enhancement by visual inspection. Three Wiener filter classes are chosen as the restoration method to reduce the Mean Square Error (MSE) value and to get high Peak Signal-to-Noise-Ratio (PSNR) with desired SNR value. Finally, these two image processing techniques, enhancement, and restoration are combined and the image quantitative values are compared to show that the image performance can be improved with combined enhancement and restoration techniques. It is found that Class 1 Wiener Filter with Enhance then Restore (ER) method has a value of 0 for MSE which is the lowest compared to other studied methods and has infinity values for PSNR and SNR.","PeriodicalId":326688,"journal":{"name":"2021 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126522558","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":"Dynamic Modeling of COVID-19 Disease with Impact of Lockdown in Pakistan & Malaysia","authors":"G. M. Abro, S. Zulkifli, V. Asirvadam, Nirbhay Mathur, Rahul Kumar, Vipin Kumar Oad","doi":"10.1109/ICSIPA52582.2021.9576795","DOIUrl":"https://doi.org/10.1109/ICSIPA52582.2021.9576795","url":null,"abstract":"Being researchers, it is an utmost responsibility to provide insight on social issues thus, this work addresses the dynamic modeling of first and most contagious disease named as COVID-19 caused by coronavirus. The first case of COVID-19 appeared in Pakistan was on 26th February 2020 and in Malaysia on 27th February 2020; both patients had foreign travel history. In the paper, the number of total affected cases and total deaths in both countries, are quite the same up till 12th April 2020 but the frequency of new cases per day and recovery rate are different from one another. The movement control approach had also been imposed on 18th March 2020 by both countries. Keeping these facts and figures, the paper proposes a mathematical model based on Lotka-Volterra equations and provides numerical solution of differential equations using the suspectable, exposed, infected, and recovered people data to estimate future consequences and address the difference in the growth rate of COVID-19 patients before and after locked down to reduce the spread further by taking pro-active approaches i.e., social distancing and being quarantined for the essential time frame.","PeriodicalId":326688,"journal":{"name":"2021 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115828576","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":"Modeling, Controlling & Stabilization of An Underactuated Air-Cushion Vehicle (ACV)","authors":"G. M. Abro, S. Zulkifli, V. Asirvadam, Z. Ali, Nirbhay Mathur, Rahul Kumar","doi":"10.1109/ICSIPA52582.2021.9576785","DOIUrl":"https://doi.org/10.1109/ICSIPA52582.2021.9576785","url":null,"abstract":"Underactuated systems are very difficult to control and stabilize due to fewer number of control inputs as compared to degrees of freedom (DOF). Thus, this research manuscript presents a comparative analysis of two major control schemes for an underactuated air cushion vehicle (ACV) commonly known as hovercraft. By studying the translational and angular dynamics of proposed underactuated mechatronic system, the mathematical model had been derived using Newton Euler formalism. The validity and effectiveness of proportional integrated differentiator (PID) control design is compared with the Fuzzy based PID (F-PID) scheme. Thus, with provided simulation results, paper concludes that the proposed algorithm of fuzzy based PID (F-PID) is better solution for achieving robust transient and steady state performances than simple PID control scheme even in the availability of bounded uncertainties with quick convergence rate.","PeriodicalId":326688,"journal":{"name":"2021 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134061072","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":"Affect Recognition Using Dynamic Characteristics of Motion","authors":"Saba Baloch, S. Abu-Bakar, M. Mokji, Saima Waseem","doi":"10.1109/ICSIPA52582.2021.9576772","DOIUrl":"https://doi.org/10.1109/ICSIPA52582.2021.9576772","url":null,"abstract":"Recently, there has been a lot of work on affect recognition which is a relatively new research field. Here the detection and recognition of multiple emotions such as anger, joy, fear, etc. are being carried out. Furthermore, the research on affective computing is being conducted using various modalities, such as; facial expressions, bodily expressions, and speech, with facial expressions being the most researched modality. However, many researchers have lately highlighted the significance of bodily expressions in affect detection. In this paper, we have considered bodily expressions for recognizing affect and proposed a modified approach using dynamic characteristics of motion. The experiments were performed in MATLAB using the MPIIEmo dataset and results were compared with the existing research.","PeriodicalId":326688,"journal":{"name":"2021 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130933527","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Comparative Study of In-Domain vs Cross-Domain Learning for Porn Cartoon Classification","authors":"Nouar Aldahoul, H. A. Karim, A. Wazir, Mhd Adel Momo, Mohd Haris Lye Abdullah","doi":"10.1109/ICSIPA52582.2021.9576769","DOIUrl":"https://doi.org/10.1109/ICSIPA52582.2021.9576769","url":null,"abstract":"Detection of adult contents such as pornography, sex, and nudity has been investigated extensively in the literature. Recently, content moderator is a significant component for social platforms to be integrated in their software applications and services. Cartoon content moderator is a specific kind of moderators that should be highly accurate to reduce the classification error and increase the model’s sensitivity to adult contents. This paper aims to compare the models pre-trained on natural adult images and called cross-domain learning models with ones pre-trained on cartoon images and called in-domain learning models for adult content detection in cartoons. The paper utilized pre-trained convolutional neural networks such as ResNet and EfficientNet to extract features that were applied to support vector machine for porn/normal classification. It was found that in-domain models outperformed cross-domain model in terms of performance metrics to improve the accuracy by 13 %, recall by 2 %, precision by 18 %, F1 score by 14 %, false negative rate by 2 %, and false positive rate by 16 %.","PeriodicalId":326688,"journal":{"name":"2021 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121450818","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":"Training Convolutional Neural Networks to Detect Waste in Train Carriages","authors":"Nathan Western, X. Kong, Mustafa Erden","doi":"10.1109/ICSIPA52582.2021.9576771","DOIUrl":"https://doi.org/10.1109/ICSIPA52582.2021.9576771","url":null,"abstract":"This research constitutes a systematic investigation of the effect of image view on Convolutional Neural Networks (CNNs) when trained to detect waste in train carriages. Additionally, this research identifies neural network architecture and training conditions for use in an automated train cleaning robot. Specifically, we investigate the relationship between the size of the CNN training dataset, whether these images are taken from a view sympathetic to the CNN application, and the effectiveness of the trained networks. Three datasets were constructed specifically for this research; a large dataset of 58,300 studio images of waste in a variety of conditions, a smaller dataset of 4,515 images taken of actual waste items on trains, and a dataset of 7,290 images of actual waste on trains used to test the CNNs. The images taken on trains were captured from the perspective of a hypothetical cleaning robot that would use these networks. Additionally, we provide a comparison of MobileNetV2, ShuffleNet, and SqueezeNet CNNs based on their suitability for implementation in an automated train cleaning system, and the optimum conditions to do so. Training with a smaller dataset of images taken from a “robot-eye view” resulted in an average increase in classification accuracy of 10.5%, with the largest increase being 26%, when compared to training with a larger dataset of images of waste items in various poses. ShuffleNet was identified as the optimally performing CNN for waste detection, achieving an accuracy of 88.61% when trained with a small dataset of images sympathetic to the end use. MobileNetV2 was found to perform optimally with a larger dataset of training images, even if these are less specific to the application of the network.","PeriodicalId":326688,"journal":{"name":"2021 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122500183","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":"Local File Inclusion Vulnerability Scanner with Tor Proxy","authors":"Ku Ahmad Haziq Hezret Bin Che Ku Mohd Sahidi, Muhammad Azizi Mohd Ariffin, Muhammad Izzad Ramli, Z. Kasiran","doi":"10.1109/ICSIPA52582.2021.9576783","DOIUrl":"https://doi.org/10.1109/ICSIPA52582.2021.9576783","url":null,"abstract":"Web applications have made communication and services for users extremely simple because of the user-friendly interface, global accessibility, and ease of management. However, careless web application design and implementation are crucial to a security compromise that is incredibly troubling both to the user and web administrators. The weakness in Local File Inclusion (LFI) currently exists in many web applications that result in remote code execution in a host server. Hence, detecting the vulnerability of LFI is becoming extremely important to the web owner in taking effective risk mitigation action. Meanwhile, the current vulnerability scanner that is available nowadays focuses more on SQL injection and cross site scripting but fewer over Local File Inclusion vulnerability. Other than that, users cannot observe what sort of sensitive file or data could be obtained by an attacker and maintain the anonymity of the user because current Vulnerability scanner on the market does not integrate with TOR network out-of-the-box. This project proposed an automated system for the identification of LFI vulnerabilities with obscure for web applications. Therefore, the objective of this project is to develop a system that can detect LFI vulnerabilities within the web application and while still able to maintain user anonymity across the network by covering the source IP address of the scanner using the Tor network and simulates how a real-world hacker attacks web application using LFI vulnerability. Furthermore, there are six phases involved in the methodology to complete this project: information gathering, requirement analysis, system design, development, testing, and documentation. Lastly for documentation, is to make a report about Local File Inclusion Vulnerability Scanner with Tor Onion Router Proxy. From the result testing, it indicates that the project can identify any local file inclusion vulnerabilities that exist over the web application while also having the advantage to observe the point of view of an attacker capable of hiding the scanner source of IP address.","PeriodicalId":326688,"journal":{"name":"2021 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121536047","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":"Active Stereo Matching Benchmark for 3D Reconstruction using Multi-view Depths","authors":"M. Jang, Seongmin Lee, Jiwoo Kang, Sanghoon Lee","doi":"10.1109/ICSIPA52582.2021.9576787","DOIUrl":"https://doi.org/10.1109/ICSIPA52582.2021.9576787","url":null,"abstract":"With the advance of 3D entertainment, 3D reconstruction has been widely researched. Recently, for the 3D reconstruction, multi-view depth images are generally used due to the wide availability of commercial RGBD sensors. The depth image can be directly acquired from the specific sensor or estimated from the stereo images by using a stereo matching algorithm. The performance of the depth estimation using a specific sensor is only dependent on the sensor performance. However, since the stereo matching method is dependent on stereo matching accuracy, a more accurate depth can be obtained from the high accuracy stereo matching method. Therefore, we focus on the stereo matching method for estimating the depth image. In this paper, we present the benchmark on the active stereo matching method for 3D reconstruction. Through the quantitative and qualitative benchmarks, we analyze and visualize the depth estimation and 3D reconstruction results. By presenting the active stereo matching benchmark, we provide guidance for 3D reconstruction using multi-view depths.","PeriodicalId":326688,"journal":{"name":"2021 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128178377","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":"An Insight Into the Rise Time of Exponential Smoothing for Speech Enhancement Methods","authors":"S. Low","doi":"10.1109/ICSIPA52582.2021.9576801","DOIUrl":"https://doi.org/10.1109/ICSIPA52582.2021.9576801","url":null,"abstract":"Exponential smoothing is a widely used averaging function to estimate the speech and noise statistics. However, the setting of the smoothing constant has been inconsistent or to a certain extent arbitrarily set. This paper aims to fill the gap by formulating the smoothing constant as a function of rise time to better reflect the variability of the signal to be smoothed. Experimental results with real world noise reveal that the performance is very sensitive to the rise time of the short term averaging function, whilst less so for the longer term averaging function. The results provide a guideline for speech enhancement methods to set the smoothing constant for the estimation of speech and noise statistics.","PeriodicalId":326688,"journal":{"name":"2021 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115448311","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}