2023 IEEE Region 10 Symposium (TENSYMP)最新文献

{"title":"Pressure optimization system for Varicose Veins management","authors":"Rithika K, S. Saranya, Chandramouli K, A. M","doi":"10.1109/TENSYMP55890.2023.10223642","DOIUrl":"https://doi.org/10.1109/TENSYMP55890.2023.10223642","url":null,"abstract":"Veins have one way valves inside them that open and close to keep the blood flowing towards the heart. Varicose veins represent a condition where the weak or damaged valves in the veins can cause blood to pool and even flow backwards. It is most common in pregnant women and the elderly. Compression therapy is an established treatment for varicose veins, where the applied pressure has to be in specific ranges in order to have an effective treatment. No method currently exists for monitoring the pressure applied in the leg while tying the compression bandage on the affected leg. Improper application of compression bandage can be ineffective or can cause issues such as skin irritation, discoloration, dent in skin and can also cause necrosis. This paper aims to provide a pressure indicating system with Force sensing resistor (FSR) and Light emitting diodes (LEDs) integrated with compression bandage for pressure optimization and management of varicose veins. The effectiveness of the pressure indicating system is validated by measuring the subject's vein length within a span of four weeks.","PeriodicalId":314726,"journal":{"name":"2023 IEEE Region 10 Symposium (TENSYMP)","volume":"226 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114247284","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":"Mobile Phone Decoder of Two-Cell Contracted Braille for Filipino Words Using Convolutional Neural Networks","authors":"Marck Herzon C. Barrion, Lorenz Andre C. Fernando, M. Cabatuan, A. Bandala","doi":"10.1109/TENSYMP55890.2023.10223615","DOIUrl":"https://doi.org/10.1109/TENSYMP55890.2023.10223615","url":null,"abstract":"This paper presents the results of using MobileNetV2, EfficientNetV1, and EfficientNetV2 for decoding 25 classes of two-cell contracted Filipino braille words. Test accuracies of 91.20% and 89.20%, and F1-scores of 0.91 and 0.89 for the top two models, the EfficientNetV1B0 and EfficientNetV2B0, respectively, were acquired. Transfer learning was used from these CNN models using the weights from ImageNet for pre-training. 1250 images were used for this research, with 50 images per class. For training the models, 70% of the images were allocated, 10% for validation, and 20% for testing. An equal number of samples were allocated for each class in this arrangement of the datasets. The model was implemented in an Android phone application through TensorFlow lite to allow mobile decoding of the braille codes. This output was aimed at creating a reliable and portable platform that will aid Special Education (SPED) teachers in the Philippines in studying and teaching two-cell contracted Filipino braille words.","PeriodicalId":314726,"journal":{"name":"2023 IEEE Region 10 Symposium (TENSYMP)","volume":"156 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114492242","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":"Food Rotting Prediction and Detection System for Warehouse","authors":"Nabilah Tabassum Oshin, Fardin Ahsan Shafi, Mahfuzur Rahman, Halima Khatun, Mohammad Rejwan Uddin, Mahady Hasan","doi":"10.1109/TENSYMP55890.2023.10223486","DOIUrl":"https://doi.org/10.1109/TENSYMP55890.2023.10223486","url":null,"abstract":"This paper presents an elementary approach to food spoilage detection and prediction in a warehouse setting, offering a practical and cost-effective solution to reduce food waste and improve food safety. This project develops a device that can predict and detect food spoilage in a timely and accurate manner by utilizing different gas sensors, temperature, and humidity sensor to predict and detect the presence of spoilage in stored food. The gathered data from the stored food is then processed and analyzed by the system. The output is displayed on an LED screen and a buzzer goes off to alert the food keepers. The project also involves the development of a user-friendly interface to allow for easy monitoring and management of the system. It uses a Bluetooth module to transmit the resulting data from the system. The findings of the study demonstrated the effectiveness of the Food Rotting Prediction and Detection System, with the sensors providing reliable data for predicting and detecting food spoilage. A mixed method analysis including thematic analysis and predictive modeling allows for more robust validation of the findings, as the results can be triangulated across different data sources.","PeriodicalId":314726,"journal":{"name":"2023 IEEE Region 10 Symposium (TENSYMP)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128460037","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":"Patch-Swap Based Approach for Face Anti-Spoofing Enhancement","authors":"Qiushi Guo, Shisha Liao, Yifan Chen, Shihua Xiao, Jin Ma, Tengteng Zhang","doi":"10.1109/TENSYMP55890.2023.10223630","DOIUrl":"https://doi.org/10.1109/TENSYMP55890.2023.10223630","url":null,"abstract":"Face Recognition system is widely used in recent years, however it is still vulnerable to various attacks, ranging from 2D presentation attacks(PA) to 3D masks attacks. Among them, part-cut print paper attack is an easy-of-use yet challenging fraud approach, which can imitate eyes-blick and mouth-open actions that are commonly used as living clues in face recognition system. Besides, the wide range of materials of print papers makes the task even harder. Existing approaches neglect to decouple the structure features from paper types. Though attack images which are similar to the training data can be detected, the accuracy drops dramatically when tested on unseen paper types. However, it's impossible to collect a face dataset covering all types of paper materials with sufficient identities. To alleviate these issues, we propose a Patch-Swap module, which generates synthetic images simulating part-cut print paper attacks. We randomly take two images from CelebA-HQ, crop the patches of eyes and mouth and swap the above patches respectively. With no extra images collected and annotated, the whole process is efficient and effective. We then train a resnet-based model PSRes with our synthetic data. To prove the robustness and effectiveness of our approach, we conduct several experiments on public datasets Rose and CelebA-Spoof, the results show that our PSRes outperforms the existing methods. Besides, our approach show better generalization capability even tested on unseen materials.","PeriodicalId":314726,"journal":{"name":"2023 IEEE Region 10 Symposium (TENSYMP)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129052191","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":"Contrastive Learning with Video Transformer for Driver Distraction Detection through Multiview and Multimodal Video","authors":"Hong Vin Koay, Joon Huang Chuah, C. Chow","doi":"10.1109/TENSYMP55890.2023.10223643","DOIUrl":"https://doi.org/10.1109/TENSYMP55890.2023.10223643","url":null,"abstract":"Distracted drivers are more likely to get involved in a fatal accident. Thus, detecting actions that may led to distraction should be prioritized to reduce road accidents. However, there are many actions that cause a driver to pivot his attention away from the road. Previous works on detecting distracted drivers are done through a defined set of actions that are considered as distraction. This type of dataset is known as ‘closed set’ since there are still many distraction actions that were not considered by the model. Being different from previous datasets and approaches, in this work, we utilize constructive learning to detect distractions through multiview and multimodal video. The dataset used is the Driver Anomaly Detection dataset. The model is tasked to identify normal and anomalous driving condition in an ‘open set’ manner, where there are unseen anomalous driving condition in the test set. We use Video Transformer as the backbone of the model and validate that the performance is better than convolutional-based backbone. Two views (front and top) of driving clips on two modalities (IR and depth) are used to train individual model. The results of different views and modalities are subsequently fused together. Our method achieves 0.9892 AUC and 97.02% accuracy with Swin-Tiny when considering both views and modalities.","PeriodicalId":314726,"journal":{"name":"2023 IEEE Region 10 Symposium (TENSYMP)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128069771","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":"IoT-Based Water Quality Monitoring and Automated Fish Feeder: Enhancing Aquaculture Productivity","authors":"Donna T. San Antonio, Jairuz Ren A. Rivera, Alexander Carl N. Balid, Rica Ridgette P. Belaos, Annie I. Brizuela, Julie A. Caballero","doi":"10.1109/TENSYMP55890.2023.10223636","DOIUrl":"https://doi.org/10.1109/TENSYMP55890.2023.10223636","url":null,"abstract":"Aquafarming is a rising industry that encourages developments and innovations in the technologies to be applied. As a response, the researchers decided to conduct this study to devise an IoT-based system that monitors water quality in fish ponds or fish pens and automatically feeds fishes. The system will be an aid in aquafarming which will benefit the following: for aquafarmers to have efficient aquafarming technology; for researchers to have a basis for future researches; for consumers to have healthy fish; and for the environment to be fit for fish farming. Literature and studies related to aquafarming, IoT, automatic feeder, and water quality monitoring were considered to be the basis in devising the methods and materials followed and used. The conceptual and methodological frameworks based on the set objectives are designed and presented. Following the experimental type of research design, the study's planning and methods were defined. The whole structure of the device was divided into its electronics design, the power source design, the software design involving the programs to be developed, and automatic feeder designs. Several trials for the testing were conducted to ensure the reliability and functionality of the device. The results discussed showed favorable results. The study's final output is an aid in aquafarming that has an automated feeder and water quality monitoring system based on IoT.","PeriodicalId":314726,"journal":{"name":"2023 IEEE Region 10 Symposium (TENSYMP)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125474254","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 2bit/stage Reusability based methodology for designing 8-bit Binary Search ADC","authors":"Sachin Kumar, Dipti, Kasi Bandla, D. Pal, M. Goswami","doi":"10.1109/TENSYMP55890.2023.10223612","DOIUrl":"https://doi.org/10.1109/TENSYMP55890.2023.10223612","url":null,"abstract":"This paper briefs a design of binary search (BS) analog-to-digital converter (ADC) using only N-2 comparators for N-bit resolution. The proposed design used efficient circuit design approach and reusability concept while designing the data converters. The post layout simulation done on UMC 180 nm CMOS technology using Cadence Spectre showed 21.1 mW of power-dissipation, 0.06 mm2 of chip area, 7.5ns of conversion time and achieves 1 pJ/step-conversion Walden Figure of Merit (FOM). The proposed design is suitable for RFID and in SOC-applications.","PeriodicalId":314726,"journal":{"name":"2023 IEEE Region 10 Symposium (TENSYMP)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132112455","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":"Innovative Colormap for Emphatic Imaging of Human Voice for UAV-Based Disaster Victim Search","authors":"Tomokichi Furusawa, C. Premachandra","doi":"10.1109/TENSYMP55890.2023.10223627","DOIUrl":"https://doi.org/10.1109/TENSYMP55890.2023.10223627","url":null,"abstract":"Unmanned aerial vehicles (UAVs) are being utilized for damage assessment in natural disasters and for search and rescue operations. Currently, the search for victims primarily relies on analyzing images captured by cameras mounted on UAVs. However, this approach has limitations when it comes to locating victims who are not within the camera's field of view. As a result, sound-based search methods are being considered. In this method, a voice message is transmitted to the disaster area through a speaker mounted on a UAV, and the presence of victims is confirmed by detecting their response using the onboard microphone of the UAV. Nevertheless, the UAV's microphone captures both the sound of the victim and the propeller rotation, posing a significant challenge in extracting the victim's voice from this combined audio. To address this issue, we propose a solution that involves generating spectrogram images of the sound mixture and the propeller sound, and extracting the human sound by subtracting them. We found that the conventional colormap was ineffective in emphasizing the human sound in the spectrogram images. To overcome this limitation, this paper introduces a new colormap based on the normal distribution. This colormap enhances human voices while attenuating propeller sounds by adjusting the mean and variance. Through the results of our experiments, we confirm that the proposed colormap effectively reduces propeller sound interference in the sound mixing and simultaneously emphasizes the voice of a disaster victim. By utilizing the proposed colormap, it becomes possible to visualize the victim's voice from the audio mixture acquired by the UAV's onboard microphone, enabling the identification of the victim.","PeriodicalId":314726,"journal":{"name":"2023 IEEE Region 10 Symposium (TENSYMP)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134094457","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 Hybrid QNN-Based Framework for Accurate Early Detection of HCV Liver Abnormalities from CT Scans Using Custom Transfer Learning and AI Edge Device","authors":"S. Vijayakumar","doi":"10.1109/TENSYMP55890.2023.10223624","DOIUrl":"https://doi.org/10.1109/TENSYMP55890.2023.10223624","url":null,"abstract":"The discovery of the Hepatitis C Virus (HCV) by Drs. Harvey J. Alter, Michael Houghton, and Charles M. Rice was recognized with the 2020 Nobel Prize in Medicine, and their groundbreaking work has paved the way for effective treatments for HCV [1]. Despite this, early detection and diagnosis remain critical for successful management of the disease. Computed Tomography (CT) is a widely used imaging technique that can detect liver lesions and other abnormalities associated with HCV infection. However, interpretation of CT scans can be challenging, time-consuming, and subject to interobserver variability, making it difficult for radiologists to accurately diagnose HCV. In recent years, the development of Artificial Intelligence (AI) and Computer Vision (CV) techniques has opened up new possibilities for medical image analysis, allowing for the development of AI-based diagnostic products that can assist radiologists in the interpretation of CT scans and improve the accuracy and speed of HCV diagnosis. In this paper, a novel end-to-end framework for the diagnosis of Hepatitis C Virus (HCV) is presented that leverages Transfer Learning and Hybrid Quantum Neural Networks (QNNs). By utilizing pre-trained models and transferring knowledge to new tasks, Transfer Learning significantly reduces the time required for training Deep Learning models for image analysis tasks, leading to improved accuracy and precision of the resulting models. The integration of hybrid QNNs in the training process further accelerates the training process and improves the accuracy of the models. The integration of hardware and software accelerators onto AI edge devices onboard CT scanners is proposed, enabling faster inferencing and offering a promising approach for developing an efficient early HCV diagnostic product assisting radiologists. This approach enables rapid analysis and classification of HCV-related liver lesions, potentially reducing the burden of HCV-related liver disease. By revolutionizing the field of medical imaging, this technology has the power to significantly improve the speed and accuracy of HCV detection and diagnosis, transforming the landscape of liver disease diagnosis and treatment.","PeriodicalId":314726,"journal":{"name":"2023 IEEE Region 10 Symposium (TENSYMP)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115707722","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":"RF Spectral Survey of Cellular Bands in Manila, Philippines Using Software-Defined Radio","authors":"Laurence Gabriel E. Arellano, Floren Christian D. Canceran, Aldridge Leroy Q. Chua Chong, Claudelle L. Fajardo, Colin Jumawan, Jehiel Santos","doi":"10.1109/TENSYMP55890.2023.10223661","DOIUrl":"https://doi.org/10.1109/TENSYMP55890.2023.10223661","url":null,"abstract":"A proper knowledge on the availability of ambient radio frequencies (RF) can be utilized for the design of efficient RF energy harvesters for low-powered devices. This paper presents the use of a software-defined radio (SDR) for measuring ambient cellular bands in Manila, Philippines. GNU radio companion is used to configure and test the SDR, which is designed to receive frequencies between the range of 1 MHz to 2 GHz. It was tested in different locations in Manila, Philippines. The paper describes the relative gain of the frequencies received and their relation to the test location and time of the day. Result shows that TDD-LTE followed by FDD-LTE frequency bands produced the highest relative gain levels that would be best utilized for RF energy harvesting in the selected locations.","PeriodicalId":314726,"journal":{"name":"2023 IEEE Region 10 Symposium (TENSYMP)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117283205","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}