ABSTRACT
Transportation problems have always been a global concern. The challenges in traffic congestion were easily observed during pre-pandemic times. However, traffic congestion still persists even during the COVID-19 pandemic (2020 and present) where there has been less number of vehicles because of travel restrictions. The emergence of wireless communication technologies and intelligent transportation systems (ITS) pave the way for solving some of the problems found in the transportation industry. Subsequently, traffic control systems are used at various intersections to manage the flow of traffic and reduce car collisions. However, some intersections are better off without these traffic control systems. The proposed study will analyze a T-junction road in five different setups using different types of traffic controllers. The simulation tool used is SUMO. The study found that an adaptive or vehicle-actuated traffic controller is the ideal method for regulating traffic flow in a T-junction with a one-way or two-way main road. It was observed in the simulation that it reduced the potential car collisions in the non-TL junction. However, the average speed and completion time of the road network was affected by the method. © 2022 IEEE.
ABSTRACT
Face masks have been widely used since the start of the COVID-19 pandemic. Facial detection and recognition technologies, such as the iPhone's Face ID, heavily rely on seeing the facial features that are now obscured due to wearing a face mask. Currently, the only way to utilize Face ID with a mask on is by having an Apple Watch as well. As such, this paper intends to find initial means of a reliable personal facial recognition system while the user is wearing a face mask without having the need for an Apple Watch. This may also be applicable to other security systems or measures. Through the use of Multi-Task Cascaded Convolutional Networks or MTCNN, a type of neural network which identifies faces and facial landmarks, and FaceNet, a deep neural network utilized for deriving features from a picture of a face, the masked face of the user could be identified and more importantly be recognized. Utilizing MTCNN, detecting the masked faces and automatically cropping them from the raw images are done. The learning phase then takes place wherein the exposed facial features are given emphasis while the masks themselves are excluded as a factor in recognition. Data in the form of images are acquired from taking multiple pictures of a certain individual's face as well as from repositories online for other people's faces. Images used are taken in various settings or modes such as different lighting levels, facial angles, head angles, colors and designs of face masks, and the presence or absence of glasses. The goal is to recognize whether it is the certain individual or not in the image. The training accuracy is 99.966% while the test accuracy is 99.921%. © 2022 IEEE.
ABSTRACT
The Philippines has consumed over 108,000 and 101,000 GWh of energy in the years 2019 and 2020, respectively. These consumed energy is generated by different providers such as the Manila electric, Visayan electric, and Negros Occidental electric cooperative which mainly provides for the residential, commercial, and industrial sectors. Moreover, the country utilizes four main energy generation types namely, coal, oil-based, natural gas, and renewable energy. As reported in the Department of Energy's 2020 Power Statistics Report, figures show that the recent COVID-19 pandemic resulted in an increase in generated energy for the household sector. Inversely, the generated energy for commercial and industrial sectors dropped. This is due to the lockdown urging people to have a work or study from home set-up rather than face to face. With this shift in energy distribution may come cases of incorrectly measured power consumption that increases electricity bills of each sector and the companies involved. Therefore, this study aims to apply linear programming to optimize the allocation of energy generation and consumption of power plants in the country. The results of the program will then be compared to the results from and several mathematical models, such as the Gauss-Jordan, M-Method, and Two-Phase Methods to verify its results. © 2021 IEEE.
ABSTRACT
The covid-19 pandemic has severely affected the economy of the Philippines. With 90% of the labor force being affected, hundreds of thousands of families turn to their respective local government units for assistance. LGUs have begun distributing food box assistance to every family under the Food Security Program to ease the economic burden. However, such a program having a vast number of recipients will require a large budget. This study presents the optimization of the content of the food packs used for food aid distribution through linear programming using Matlab. The study's goal is to maximize the nutritional content of the food pack while being under the constraint of a limited budget to ensure the best utilization of scarce resources. © 2021 IEEE.
ABSTRACT
The Philippines' Land Transportation Office (LTO) has the task of evaluating and processing citizen's applications for driver's license for professional and non-professional purposes. The office sees many customers each day and the need for an efficient waiting sitting was needed. Several process optimization and productivity improvements will be discussed in this research. Improvements along the lines of robotic process optimization, social media bots, existing efficient and effective processes, and the like, will be considered in developing suggestions for optimizing waiting line management in the LTO. In addition, existing congestion surveillance methods are explored to consider more solutions. The LTO currently implements a multi-channel, multi-phase line management system for all branches in the country. The research aims to evaluate its effectiveness in processing new driver's license applications in the National Capital Region within a set period of days. The system has proven inefficient based on recent data taken between 2019-2020 [1], even considering the decline in applications because of the COVID-19 pandemic. There is an expected spike in citizens applying for driver's licenses once the quarantine restrictions are lifted entirely, and an effective waiting line management system will be needed. A solution can be created by taking inspiration from efficient process systems from the United States and United Kingdom. © 2021 IEEE.
ABSTRACT
The COVID-19 pandemic has brought crisis to people from around the world resulting to a transition from face-to-face classes to an online class in the academic sector. Graduation ceremonies also transition into an online ceremony where students passively attend the session. In this study, a Social Robot named 'Gradbot' is developed to help the students participate actively in their online ceremonies. The Body frame was designed using Fusion360. The Gradbot is compose of the Arduino microcontroller, servo motors, Bluetooth module, mounted on a 2WD car chassis and was simulated using Tinkercad and MATLAB. This study also includes the investigation of the degrees of freedom, type of joints, workspace, and the cartesian product of the developed Gradbot. © 2021 IEEE.
ABSTRACT
With the novel coronavirus, social distancing and crowd monitoring became vital in managing the spread of the virus. This paper presents a desktop application that utilizes Tiny-YOLOv4 and DeepSORT tracking algorithm to monitor crowd count and social distancing in a top-view camera perspective. The application is able to process video files or live camera feed such as CCTV or surveillance cameras and generate reports indicating people detected per unit time, percentage of social distancing per unit time, detection and social distancing logs as well as color-coded bounding boxes to indicate if the detected people are following social distancing protocols. © 2021 IEEE.
ABSTRACT
Open-source ventilators (OSVs) are considered as an immediate response for the shortages of ventilator equipment in hospitals due to the ongoing global pandemic caused by the Coronavirus disease 2019 (COVID-19). One of the designs explored for OSVs utilizes a bag-valve-mask as a source for mechanical ventilation. Despite its availability for use and being medically accepted, proper calibration must be observed in measuring ventilator scalars such as inspiratory pressure, inspiratory flow, and tidal volume to promote the safe use of the OSV and prevent OSV users to do more harm to the patient. This study discusses different calibration techniques to properly acquire ventilator scalar measurements using an integrated ventilator scalar measurement module. All in all, different calibration setups and bag-valve-mask-based mechanisms were tested and documented to determine an effective means to acquire accurate and precise ventilator scalar measurements.
ABSTRACT
Automation is considered as the driving force of Fourth Industrial Revolution (Industry 4.0) to develop smart and automated devices for existing manufacturing processes. However, the global medical outbreak perpetrated by the Coronavirus Disease 2019 (COVID-19) challenged researchers to explore new concepts and innovate existing technologies whilst resolving the ongoing health crisis. Thus, the demand for utilizing the automation concept in biomedical devices is reasonably high. For this study, the researchers have successfully implemented an industrial-grade programmable logic controller that will control the mechanical ventilation process of a bag-valve-mask-based emergency ventilator. Various mechanisms were observed, and the results have been documented. © 2020 IEEE.
ABSTRACT
In response to COVID-19 pandemic, universities and related institutions around the world came up with various mechanical ventilator designs to help cope with the expected shortages of ventilators as the pandemic rages. Many of these designs are based on automating the manual operation of the Bag Valve Mask (BVM), a ubiquitous resuscitator device used for emergency ventilation or resuscitation of patients with breathing problems. In this paper, the mechanical design and development process for a BVM-based emergency ventilator is discussed. In particular, the evolution of the design from a simple, low-cost device to a more sophisticated system acceptable to pulmonologists and related medical practitioners is documented. © 2020 IEEE.