2022 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)最新文献

{"title":"Blended QR Code for Digital Advertising","authors":"Wan-Er Ho, Lee-Yeng Ong, M. Leow","doi":"10.1109/IICAIET55139.2022.9936832","DOIUrl":"https://doi.org/10.1109/IICAIET55139.2022.9936832","url":null,"abstract":"Quick Response (QR) code has been widely used in everyone's daily lives for advertising purpose. This is a new norm lifestyle for worldwide customers during the pandemic and post-pandemic. Due to the dull appearance of traditional QR code, blended QR code is created by overlaying an advertisement with a QR code to strengthen the advertising effectiveness. Creating pleasant visibility of blended QR codes can catch the attention of customers and thus able to further engage with them. However, the direct embedding of a traditional QR code with its black and white modules will negatively affect the advertising impact when the advertisement is distorted. Hence, these data modules are the major reason that affects the appearance and yet they are the most critical aspect of decoding capability. As a result, it is a challenge to identify the tradeoff between decoding capability and visual appearance. Therefore, this paper proposes an algorithm that manages the number of data modules and the size of each data module to increase the advertising impact. The proposed algorithm provides more weightage to the pixels that are closer to the center region of each module, which maintains the data on hold inside the modules. The performance comparison between advertisement visibility and decoding capability is presented to verify the robustness of the proposed algorithm.","PeriodicalId":142482,"journal":{"name":"2022 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132375390","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":"Traffic Signal Optimization using Cultural Algorithm","authors":"M. K. Tan, Hon Yang Vun, H. S. Chuo, Kit Guan Lim, Soo Siang Yang, K. Teo","doi":"10.1109/IICAIET55139.2022.9936759","DOIUrl":"https://doi.org/10.1109/IICAIET55139.2022.9936759","url":null,"abstract":"Traffic congestion is one of the major issues in most cities. Over time, traffic congestion is increasing due to the increasing number of road users. The conventional non-adaptive traffic signal control strategy is inadequate to optimize the traffic flow during peak hours. Thus, this paper explores the feasibility of optimizing traffic signal timing using cultural algorithm to minimize the traffic queue length at every intersection within a network. Since the traffic congestion can be propagated from upstream intersection to downstream intersection, the proposed algorithm will consider the traffic condition at neighboring intersections when computing the optimum traffic signal timing. The performance of the proposed algorithm is simulated and compared with the conventional fixed timing system. The results show the proposed cultural algorithm is able to improve the traffic flow by 20 %.","PeriodicalId":142482,"journal":{"name":"2022 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122862390","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 Analysis of Lumpy Skin Disease Prediction Through Machine Learning Approaches","authors":"Dibyo Fabian Dofadar, Hasnat Md. Abdullah, Riyo Hayat Khan, Rafeed Rahman, M. Ahmed","doi":"10.1109/IICAIET55139.2022.9936742","DOIUrl":"https://doi.org/10.1109/IICAIET55139.2022.9936742","url":null,"abstract":"Lumpy Skin Disease is a highly infectious, fatal illness that is commonly observed in cattle. The common symptoms of this disease are fever, infertility, reduced milk production, and so on. Furthermore, the mortality rate of cattle infected by Lumpy Skin Disease is quite low, hence predicting the outcome of this disease earlier can reduce economic loss significantly. This research was conducted to predict if cattle are infected with Lumpy Skin Disease or not with the use of various machine learning models. A total of ten machine learning classifiers have been used and evaluation metrics were calculated for determining how well the classifiers have performed. Among all the classifiers, Random Forest Classifier and Light Gradient Boosted Machine Classifier have outperformed the other models with the F1 score of 98%.","PeriodicalId":142482,"journal":{"name":"2022 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)","volume":"129 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124229650","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 Microcontroller-based and Cost-efficient Computer Numerical Control (CNC) Soldering Station","authors":"Bryan Christopher T. Wong, Mario G. Laureta, Olwyn S. Barcoma, Angelino A. Pimentel, R. Baldovino","doi":"10.1109/IICAIET55139.2022.9936773","DOIUrl":"https://doi.org/10.1109/IICAIET55139.2022.9936773","url":null,"abstract":"Soldering is already a hazard as it may cause burns to whoever touches it. The fumes are dangerous and toxic when inhaled. An unskilled solderer most likely will run into health or quality of work problems while soldering. This research aims to design and develop a cost-efficient automated computer numerical- controlled soldering station equipped with temperature controls, an emergency stop button, and a ventilation system capable of vacuuming the soldering fumes out of the system. Circuits made in ExpressPCB can be converted to a g-code file using bCNC and a Python code programmed by the researchers. Then, this g-code was processed by the program, Pronterface, and was uploaded to the Arduino MEGA + RAMPS vl.4 CNC Shield. The g-code was executed by stepper motors and servo motors holding the soldering iron at an angle. Analyzing the results statistically using Minitab software, the prototype was able to match the time of the test subjects proving that it was time efficient. It was also consistent in its accuracy - being on par with the test subjects in their soldering capabilities. The integrated ventilation system of the prototype was able to vacuum out the soldering fumes in the system. It is capable of meeting the standards of proper and quality soldering techniques based on literature reviews and experimentations. Nonetheless, with a final cost of around 20,000 PHP, it was fourteen times (14x) cost-efficient with improved capabilities compared to the commercially available automated soldering station.","PeriodicalId":142482,"journal":{"name":"2022 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)","volume":"203 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121154182","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 COVID-19 CT Image Synthesis using GAN and CycleGAN","authors":"Kin Wai Lee, R. Chin","doi":"10.1109/IICAIET55139.2022.9936810","DOIUrl":"https://doi.org/10.1109/IICAIET55139.2022.9936810","url":null,"abstract":"Generative adversarial networks (GANs) have been very successful in many applications of medical image synthesis, which hold great clinical value in diagnosis and analysis tasks, especially when data is scarce. This study compares the two most adopted generative modelling algorithms in recent medical image synthesis tasks, namely the traditional Generative Adversarial Network (GAN) and Cycle-consistency Generative Adversarial Network (CycleGAN) for COVID-19 CT image synthesis. Experiments show that very plausible synthetic COVID-19 images with a clear vision of artificially generated ground glass opacity (GGO) can be generated with CycleGAN when trained using an identity loss constant at 0.5. Moreover, it is found that the synthesis of the synthetic GGO features is generalized across images with different chest and lung structures, which suggests that diverse patterns of GGO can be synthesized using a conventional Image-to- Image translation setting without additional auxiliary conditions or visual annotations. In addition, similar experiment setting achieves encouraging perceptual quality with a Fréchet Inception Distance score of 0.347, which outperforms GAN at 0.383 and CycleGAN at 0.380 with an identity loss constant of 0.005. The experiment outcomes postulate a negative correlation between the strength of the identity loss and the significance of the synthetic instances manifested on the generated images, which highlights an interesting research path to improve the quality of generated images without compromising the significance of synthetic instances upon the image translation.","PeriodicalId":142482,"journal":{"name":"2022 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117237416","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":"Open Agricultural Burning Detection with Natural Inspired Swarm-based Detection Platform","authors":"Liew Jia Jun, K. Yap, K. Eu, Q. Ni","doi":"10.1109/IICAIET55139.2022.9936849","DOIUrl":"https://doi.org/10.1109/IICAIET55139.2022.9936849","url":null,"abstract":"Agriculture often plays a big part in economic growth in most countries such as India, Indonesia, Thailand as well as Malaysia. Countries such as Thailand and Indonesia contribute a large volume of rice imports and export, however, in Indonesia, this major rice production comes with a large setback. Agriculture practices in Indonesia utilize open burning to process by-products of harvested rice fields to process it into bio-fertilizers which later fertilize the crop field. This is a problem as open burning on large scale causes major haze storms which spreads from Indonesia to the majority of parts of Malaysia annually. The composition of haze which includes carbon monoxide and nitrogen dioxide is hazardous to the human body when inhaled, they also contribute to the cause of air pollution. To reduces the severity of illegal open burning, we must first understand the overall characteristic of the smoke plume before introducing detection methods. Platforms such as drones and gliders with olfaction sensors can detect the plume thus locating the fire source. With the introduction of Swarm intelligence (SI), a drone detection platform can be deployed at large volumes to cover larger areas while localizing fire sources in a much more efficient fashion. Thus, this paper provides a review of swarm intelligence with the collaboration of sensors in optimizing plume dispersion problems and suggestions for future research ideas in collaborating detection platforms and SI. Open Burning has been a decade-long issue that the world trying to tackle when it comes to climate change. In Southeast Asia countries often, left-over crops are burnt openly, and the by-product of these open burning are utilized as bio-fertilizers which nourishes the crop fields. This has not only addressed the source of global warming but contributes to annual haze storm that affects countries like Malaysia and Thailand severely. To reduce the severity of open burning problems, we must first tackle the source of the problem, thus detecting the smoke plume emitted by these open burning can be the key to shutting down the possibility of open burning. However, detecting a smoke plume can be challenging as it is a dynamic problem that changes over time with external influences. Introducing Swarm Intelligence (SI) into the drone platform can reduce the time taken to localize the source of these open burning, and thus distinguishing these fire sources can minimize the impact of already ongoing open burning.","PeriodicalId":142482,"journal":{"name":"2022 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115684955","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 Evaluation of Machine Learning Algorithms for Intrusion Detection in IoT Applications","authors":"Ng Yee Jien, Mohammad Tahir, M. Dabbagh, K. Yap, Ali Farooq","doi":"10.1109/IICAIET55139.2022.9936863","DOIUrl":"https://doi.org/10.1109/IICAIET55139.2022.9936863","url":null,"abstract":"It is estimated that the number of IoT devices will reach 50 billion by 2030, with its wide range of applications and ease of use. However, in recent years, it has been established that there are numerous attacks targeting IoT devices and various challenges to securing them due to their limited computing capacity. One of the main problems that need to be solved is detecting and reporting malicious packets that are attempting to enter the IoT device before they are executed, also known as intrusion detection. An Intrusion Detection System (IDS) is a tool that monitors the network for potentially malicious packets and raises an alert when one is detected. With the usage of technologies such as machine learning and published datasets of IoT traffic that contain malicious traffic and normal traffic, an optimal approach to intrusion detection can be identified. This paper provides an overview of existing machine learning approaches for intrusion detection and evaluates different approaches using multiple datasets. The available datasets were evaluated on several machine learning models based on accuracy, F1-score, and efficiency.","PeriodicalId":142482,"journal":{"name":"2022 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116188963","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":"Development of a Virtual Vehicle Identification for Tracking Hit-and-Run Vehicle","authors":"Khoo Boon Sheng, A. A. Saad, M. Ishak","doi":"10.1109/IICAIET55139.2022.9936747","DOIUrl":"https://doi.org/10.1109/IICAIET55139.2022.9936747","url":null,"abstract":"In general, the vehicle registration plate number and the witness are essential clues for police investigating hit-and-run accidents. Without these clues, it will be difficult for police to trace the suspect and lead to a closed case even though a fatal victim is involved. In this work, the virtual vehicle identification tracking system is developed by using wireless communication interfaces to transfer useful data for road accidents and traffic surveillance. This system uses vehicle access points and employs Vehicular Ad Hoc Network (VANET) to assist the vehicle identity tracking system. The IoT development board scans all the vehicle Wi-Fi access points within the beacon frames. With the characteristics of different positions of signal strength and the distance of station to access point, it is difficult to accurately determine the offender's vehicle identity. Hence, this paper proposes a hybrid tracking method to combine pre-accident and post-accident tracking methods to track vehicle identity. Moreover, this paper shows unique Wi-Fi access point identities such as Service Set Identifier (SSID) and Media Access Control (MAC) addresses can be used as virtual vehicle identities for vehicle tracking and traffic surveillance systems. Overall, the result shows this system can track the suspect vehicle's identity with positive detection. The maximum distance for the system to track vehicle access point signal can be up to 45 meters and is workable above 50 km/h of driving speed.","PeriodicalId":142482,"journal":{"name":"2022 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114222348","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":"Comparisons of DNA Sequence Representation Methods for Deep Learning Modelling","authors":"Shu En Chia, Nung Kion Lee","doi":"10.1109/IICAIET55139.2022.9936754","DOIUrl":"https://doi.org/10.1109/IICAIET55139.2022.9936754","url":null,"abstract":"Learning the enhancer sequence grammar from protein-DNA interaction via a computational approach is a challenging task because the features associated with the recognition codes are ill-defined. While sequence features are not the only way to define the sequence characteristics, they are the most effective. Deep learning neural networks have become the key technique for modeling those features for the classification task. Nevertheless, effective learning of deep learning requires enhancer sequence features to be represented and encoded into suitable matrix form. The aims of this paper is to evaluate six sequence feature representation/encoding methods for convolutional neural networks modelling. Using a histone marks dataset as input data, our results indicate k-mer feature achieved the best performance, followed by word-based features, which performed favorably better than one-hot encoding. The random-walk feature, nevertheless, performed the worst. Moreover, our finding provides strong evidence to use kmer/word features instead of the popular one-hot encoding for histone sequence in CNN modeling.","PeriodicalId":142482,"journal":{"name":"2022 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126801982","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":"Visual Odometry Based Vehicle Lane-changing Detection","authors":"D. Salleh, E. Seignez, K. Kipli","doi":"10.1109/IICAIET55139.2022.9936799","DOIUrl":"https://doi.org/10.1109/IICAIET55139.2022.9936799","url":null,"abstract":"Lane-changing detection is necessary for accurate positioning, to allow vehicle navigation system to generate more specific path planning. Lane-changing detection method in this paper is more of a deterministic task, proposed based on curve analysis obtained from visual odometry. From the visual odometry trajectory, we have the estimation of vehicle lateral/longitudinal position, yaw, and speed. We also used the road lane information from digital map provided by OpenStreetMap to narrow the lane-changing event possibility. The analysis is conducted on sequences from KITTI dataset that contains lane-changing scenarios to study the potential of lane-changing detection by using visual odometry trajectory curve. Cumulative sum and curve fitting methods were utilized for the lane-changing detection from visual odometry curve. The detection was conducted on several visual odometry approaches for comparison and system feasibility. Our analysis shows that trajectory generated by visual odometry is highly potential for a low-cost and effective lane-changing detection with 90.9% precision and 93.8% recall accuracy to complement more accurate routing service and safety application in Advanced Driver Assistance System.","PeriodicalId":142482,"journal":{"name":"2022 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127780645","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}