Control System for Indoor Safety Measures Using a Faster R-CNN Architecture

This paper presents a control system for indoor safety measures using a Faster R-CNN (Region-based Convolutional Neural Network) architecture. The proposed system aims to ensure the safety of occupants in indoor environments by detecting and recognizing potential safety hazards in real time, such as capacity control, social distancing, or mask use. Using deep learning techniques, the system detects these situations to be controlled, notifying the person in charge of the company if any of these are violated. The proposed system was tested in a real teaching environment at Rey Juan Carlos University, using Raspberry Pi 4 as a hardware platform together with an Intel Neural Stick board and a pair of PiCamera RGB (Red Green Blue) cameras to capture images of the environment and a Faster R-CNN architecture to detect and classify objects within the images. To evaluate the performance of the system, a dataset of indoor images was collected and annotated for object detection and classification. The system was trained using this dataset, and its performance was evaluated based on precision, recall, and F1 score. The results show that the proposed system achieved a high level of accuracy in detecting and classifying potential safety hazards in indoor environments. The proposed system includes an efficiently implemented software infrastructure to be launched on a low-cost hardware platform, which is affordable for any company, regardless of size or revenue, and it has the potential to be integrated into existing safety systems in indoor environments such as hospitals, warehouses, and factories, to provide real-time monitoring and alerts for safety hazards. Future work will focus on enhancing the system's robustness and scalability to larger indoor environments with more complex safety hazards.

Face Mask Detector for Raspberry Pi Based on Computer Vision and Edge Computing

The pandemic of the coronavirus disease 2019 has shown weakness and threats in various fields of human activity. In turn, the World Health Organization has recommended different preventive measures to decrease the spreading of coronavirus. Nonetheless, the world community ought to be ready for worldwide pandemics in the closest future. One of the most productive approaches to prevent spreading the virus is still using a face mask. This case has required staff who would verify visitors in public areas to wear masks. The aim of this paper was to identify persons remotely who wore masks or not, and also inform the personnel about the status through the message queuing telemetry transport as soon as possible using the edge computing paradigm. To solve this problem, we proposed to use the Raspberry Pi with a camera as an edge device, as well as the TensorFlow framework for pre-processing data at the edge. The offered system is developed as a system that could be introduced into the entrance of public areas. Experimental results have shown that the proposed approach was able to optimize network traffic and detect persons without masks. This study can be applied to various closed and public areas for monitoring situations. © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

Vaccination Identification System using Raspberry Pi

The Severe Acute Respiratory Syndrome Coronavirus-2 (SARS-CoV-2) causes Covid-19, an infectious illness. A methodology was created to track the vaccination history of people with the Severe Acute Respiratory Syndrome Coronavirus-2 (SARS-CoV-2) that causes Covid-19, an infectious illness. The system operates on a Raspberry Pi processor that is designed to authenticate the vaccination records of individuals. The Vaccination Identification System consists of various components connected to the Raspberry Pi Zero 2W microprocessor, Pi camera, an LCD display, LED indicators, a buzzer, a DC servo motor, and a PCB converter. The proposed system grants access to vaccinated individuals and denies access to those who are not vaccinated.

Automated Contactless Continuous Temperature Monitoring System for Pandemic Disease Controlling Infrastructures

People are being thermally screened in hospitals and in such facilities, all the data collected must be stored and displayed. The person responsible for keeping track of people's body temperatures must put in more time and effort. This approach is a tedious task, especially during times of dealing with the pandemic diseases like Covid-19. Hence, in this paper, an automated contactless continuous temperature monitoring system is designed to eliminate this time-consuming process. If a person's temperature is too high, that is, higher than the usual temperature range, the system records it and monitors it continuously via a mobile application. In this paper, we present the development of an Automated contactless continuous body temperature monitoring system using a Raspberry Pi camera and mobile application. © 2023 IEEE.

Automated Contactless Attendance System

Attendance marking in a classroom is a tedious and time-consuming task. Due to a large number of students present, there is always a possibility of proxy. In recent times, the task of automatic attendance marking has been extensively addressed via the use of fingerprint-based biometric systems, radio frequency identification tags, etc. However, these RFID systems lack the factor of dependability and due to COVID-19 use of fingerprint-based systems is not advisable. Instead of using these conventional methods, this paper presents an automated contactless attendance system that employs facial recognition to record student attendance and a gesture sensor to activate the camera when needed, thereby consuming minimal power. The resultant data is subsequently stored in Google Spreadsheets, and the reports can be viewed on the webpage. Thus, this work intends to make the attendance marking process contactless, efficient and simple. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Internet of Things Based Intelligent Transportation of Food Products During COVID.

Transportation management plays a vital role in the development of the country, with the help of IoT smart transportation has become a reality. Developing a smart and secured transportation system of food products to various shops during this pandemic period is an important task. The vehicle tracking system is the technology that is used by many companies and individuals to track a vehicle by using many ways like GPS that operates using satellites and ground-based stations. In this paper an Internet of Things based application is developed to monitor the moving vehicle, this proposed model provides a monitoring solution for a moving vehicle with the help of sensors Blind Spot Assist sensor, Collision Prevention sensor, Fuel Monitoring sensor, Door Sensor, and GPS/GPRS tracking module are integrated to make a smart vehicle prototype using raspberry pi. In this model, a Blind spot sensor is used to monitor the nearby vehicles, a Collision Prevision sensor is used to avoid the collision between the vehicles, a Fuel monitoring sensor is used to monitor the fuel level in the vehicle, the Door sensor is used to check the status of the door and GPS/GPRS tracking module is used to track the current location of the moving vehicle during the COVID-19 Pandemic period.

Remote laboratory for microcontroller programming course

this paper describes experience of changing microcontroller related course from face-to-face to remote format, which took place in Riga Technical University during the COVID- 19 pandemic during years 2020 and 2021. The name of the subject is Laboratory exercises in electronics. The primary ideology of that course is to let students touch and feel electronics without using any virtual stuff like simulators. Therefore, replacing everything with simulation is not a solution to such kind of course. In this publication, we want to describe system that is mixture of real physical system installed in the laboratory and remote interface interacting with the physical system.

Gadgets Made for Preventing the Spread of COVID-19 infection in a Small University

Development of gadgets, which are an easy input system in the health survey and a simple carbon dioxide (CO2) alarm, for preventing infection of COVID-19 in a university's campus is discussed. Cluster infection did not occur in the rooms where a gadget of them was installed, until summer of 2022. © 2023 Owner/Author.

AI Enabled Smart Campus for Health Safety and Monitoring

COVID 19 has had a major effect on society. In order to keep people's spacing, new requirements have been placed in place regarding the amount of users authorized in individual rooms in offices, shops, etc. Along with social distance, regular temperature verification at mall entrances are indeed permitted. An excellent embedded machine learning system is proposed in this work to identify face masks automatically and detect the body's temperature in a real-time application. The proposed system, in particular, utilizes a raspberry pi camera to capture real-time video simultaneously by identifying face masks with the help of a classification technique. The face mask detector is constructed by utilizing mobilenetv2 and imaging net pre-trained weights to consider three scenarios: wearing a mask correctly, wearing a mask incorrectly, and not wearing any at all. By placing a temperature gauge on a Raspberry Pi, a framework has also been developed for determining a person's body temperature. The numerical outcomes show the feasibility and performance of our integrated devices in compared to many cutting-edge research. This temperature and facemask detection device monitors a person's body heat and detects whether or not that person is wearing a facemask. Consequently, any organization's entrance could contain this device. In this study, the door is only released if the temperature is below 99° F, which would be calculated by the Electro Selective Pattern-32 images, the MLX sensor, and the fact that a person's face is 80% protected by a facemask. © 2023 IEEE.

Management of an Automatic System to Generate Reports on the Attendance Control of Teachers in a Educational Center

Many countries were affected by the appearance of SARS-COV-2 that was spreading rapidly, causing damage to humanity and causing a global crisis, this generated a generalized quarantine to avoid the physical approaches recommended by the health system, affecting all students in the world, since it was wanted to avoid forming foci of contagion in educational centers, for this reason, some automated systems that are marketed in the markets were applied to combat the pandemic in educational centers, but they are inefficient when registering the work attendance of teachers, causing loss of time in the registration process and causing an agglomeration of people due to the failure in the registration process, in addition to not allowing to manage the reports of the teacher's work attendance. In view of this problem, in this article the management of an automatic system was carried out to generate reports on the attendance control of the teaching staff in the educational center and control the working hours of each teacher to be visualized through a user interface, being able to control the labor discipline of each teacher since all the records will be stored in a database. Through the development of the system, it was observed that the system works effectively since an efficiency of 98.87% was obtained in its operation to control the time of entry and exit of each teacher, being an accepted value since the process is conducted safely. © 2023 International Journal on Recent and Innovation Trends in Computing and Communication. All rights reserved.

Crowd Size Estimation and Detecting Social Distancing using Raspberry Pi and OpenCV

In this covid19 pandemic the number of people gathering at public places and festivals are restricted and maintaining social distancing is practiced throughout the world. Managing the crowd is always a challenging task. It requires monitoring technology. In this paper, we develop a device that detects and provide human count and detects people who are not maintaining social distancing. The work depicted above was finished using a Raspberry Pi 3 board with OpenCV-Python. This method can effectively manage crowds. © The Author(s). This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0, https://creativecommons.org/licenses/by/4.0/), which permits use, distribution, and reproduction in any medium, provided that the Article is properly cited.

Automatic Door Opening with Face Recognition and Temperature Detecting Device

In this pandemic period, social distancing is essential to avoid the spreading of the Covid-19 disease. Also, vaccination is one of the critical aspects. According to that, there is aninnovate idea of a project which fulfills all the above aspects such as Social Distancing, Physical touch, Vaccination details, and also Temperature detection. During this Covid-19, people were suffered a lot, so on a social and noble cause, it's our responsibility to think and develop products that will help us to prevent this disease as much as possible, which is going to be our primary goal and also by using advanced technologies like face recognition and temperature measuring device, so there is need to make our model much more efficient and trustworthy. In today's era, security has played a pivotal role in many of our places, like offices, institutions, libraries, laboratories, etc., to keep our data confidential so that no other unauthorized person could access them. This project presents a face-recognition-based door opening system that provides security and can be used for many banks, institutes, organizations, etc. For verifying the authentification, there are various methods like passwords and RFID, but this method is the most efficient and reliable. Temperature is sensed by the sensor and is validated for security purposes. If the temperature matches, then a camera is open, and after face-Recognition, the door will be get opened automatically.

Tele-Snap: a joint impedance estimation system using snap motor and openPose for remote rehabilitation diagnosis

We propose a remote joint impedance estimation system called Tele-snap for a rehabilitation diagnosis under the COVID-19 pandemic. Dynamic resistance of the human joint is essential physical information reflecting the motor function. The resistance is assessed based on the touching sensation of the doctor (physiotherapist), but the pandemic restricts such an in-person manner. Our proposing system aims to provide this physical information quantified by the joint impedance for a diagnosis in the telerehabilitation context. The proposed system employs a compact impulsive perturbation generator called the snap motor and a marker-less motion capture technology called the OpenPose. The subsystem installed in the patient's place is then simplified remarkably, which consists of the wearable snap motor and Raspberry Pi with a built-in camera module. The proposed system can collect the dataset for impedance estimation through the examiner's teleoperation of the snap motor and camera via a virtual private network, with no need for the operation by the patient. We verify the proposed system through an in-person experiment and then demonstrate the remote impedance estimation scheme. [ FROM AUTHOR] Copyright of Advanced Robotics is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full . (Copyright applies to all s.)

Production of Modified Nucleosides in a Continuous Enzyme Membrane Reactor.

Nucleoside analogues are important compounds for the treatment of viral infections or cancers. While (chemo-)enzymatic synthesis is a valuable alternative to traditional chemical methods, the feasibility of such processes is lowered by the high production cost of the biocatalyst. As continuous enzyme membrane reactors (EMR) allow the use of biocatalysts until their full inactivation, they offer a valuable alternative to batch enzymatic reactions with freely dissolved enzymes. In EMRs, the enzymes are retained in the reactor by a suitable membrane. Immobilization on carrier materials, and the associated losses in enzyme activity, can thus be avoided. Therefore, we validated the applicability of EMRs for the synthesis of natural and dihalogenated nucleosides, using one-pot transglycosylation reactions. Over a period of 55 days, 2'-deoxyadenosine was produced continuously, with a product yield >90%. The dihalogenated nucleoside analogues 2,6-dichloropurine-2'-deoxyribonucleoside and 6-chloro-2-fluoro-2'-deoxyribonucleoside were also produced, with high conversion, but for shorter operation times, of 14 and 5.5 days, respectively. The EMR performed with specific productivities comparable to batch reactions. However, in the EMR, 220, 40, and 9 times more product per enzymatic unit was produced, for 2'-deoxyadenosine, 2,6-dichloropurine-2'-deoxyribonucleoside, and 6-chloro-2-fluoro-2'-deoxyribonucleoside, respectively. The application of the EMR using freely dissolved enzymes, facilitates a continuous process with integrated biocatalyst separation, which reduces the overall cost of the biocatalyst and enhances the downstream processing of nucleoside production.

A Remote Visiting and Monitoring System for Neonatal Intensive Care Units via Internet of Things

To meet the visiting needs of families of children in neonatal intensive care unit and reduce the burden of hospital management during the COVID-19 epidemic, we developed a remote visiting and monitoring system using the internet of things. The Raspberry Pi is used as the core hardware platform. The real-time signal of the bedside monitor is converted into a virtual camera, and is connected to the Raspberry Pi which has a real camera with CMOS Serial Interface (CSI). The frames of the two cameras are collected via FFmpeg technology, and then are pushed to the cloud server through Real-Time Messaging Protocol (RTMP). The video streams are then transferred and distributed via a Nginx server running RTMP protocol, and finally are displayed on the web page via the Flask framework. When tested, the system ran stably, and the real-time pictures from the camera and the bedside monitor screen in the hospital were clearly shown on a personal computer or a mobile phone in a remote distance out of the hospital, just by click the link of the associated web page. We think this system is helpful for families to remotely visit the babies anywhere any time, and it is also helpful for hospitals to reduce the human workload and the financial expenditure. © 2022 ACM.

Covid-19 Indoorsafety Monitoring System Using Machine Learning

The covid-19 epidemic is causing a world pandemic crisis. The powerful device in these situations is to wear a mask in public entry, schools, and super markets to reduce the Covid-19 spread. There are many convolutions face recognition technologies to distinguish effective images for monitoring the discovery of a face mask. Therefore, it is very important to improve the effectiveness of the acquisition methods available in the existing system. The data set value increases in the proposed input to improve the maximum accuracy. The proposed method is used to determine body temperature, face mask, and social retention using advanced machine learning methods. Using the EM8RFID scanner personal data such as temperature value, face mask identification and public distance detection are collected. It is used to indicate the state of human health in a cloud platform. A wireless heat sensor issued to determine a person's body temperature using MLX90614 without anyone. The Raspberry integrated with the pi camera is used in detecting a face mask and a social distance. Raspberrypi captures the image and detects with the convolution neural network algorithm verifying a person is wearing a face mask, following social distance. Therefore, authorities should monitor the human condition in the cloud platform area. By applying this concept, the spread of Covid-19 can be greatly reduced and it is easier to identify peoplewith Covid-19symptoms. © 2022 IEEE.

Social Distancing Monitoring and Alerting System using YOLO Deep Learning Algorithm

The Covid-19 disease is caused by the severe acute respiratory (SAR) syndrome coronavirus-2 and becomes the reason for the Global Pandemic since 2019. Until July 2022, the total reported cases were 572 million and reported deaths were 6.38 million around the world. In many countries the infections caused severe damages. It not only took the precious lives but also caused few other national damages like economic crisis. The only solution to stop this pandemic is to increase the vaccination and reducing the spreads. The covid 19 virus is an airborne disease and spread when people breathe virus contaminated air. The WHO and all the nations were insisting to maintain social distance to control the virus spreading. But maintaining the social distance in public places is very hard. In this project we developed a method for detecting social distance. The system uses Raspberry Pi processor to detect the distance between two people from the live video stream. The YOLOv3 technique is used to detect the object from single frame of the video. © 2022 IEEE

IoT Based Intelligent System for Covid - 19 hotspot detection by CNN Crowd Density Algorithm

The worldwide health crisis is caused by the widespread of the Covid-19 virus. The virus is transmitted through droplet infection and it causes the common cold, coughing, sneezing, and also respiratory distress in the infected person and sometimes becomes fatal causing death. As the world battles against covid-19, the proposed approach can help to contain the clustering of covid hotspot areas for the treatment of over a million affected patients. Drones/ Unmanned Aerial Vehicles (UAVs) offer a great deal of support in this pandemic. As suggested in this research, they can also be used to get to remote places more quickly and efficiently than with conventional means. In the hospital's control room, there would be a person in command of the ambulance drone. For hotspot area detection, the drone would be equipped with FLIR camera and for detection and recognition of face the video transmission is used by raspberry pi camera. The detection of face is done by Haar cascade Classifier and recognition of the face with LBPH algorithm. This is used for identify the each individual's medical history or can be verified by Aadhar Card. Face recognition between still and video photos was compared, and the average accuracy of still and video images was 99.8 percent and 99.57 percent, respectively. To find the hotspot area is to use the CNN Crowd counting algorithm. If the threshold value is less than equal to 0.5 than it is hotspot area , if it is greater than 0.5 and less than equal to 0.75 than it is semi-normal area , if it is greater than 0.75 and less than equal to 1 than it is normal area. © 2022 IEEE.

An Intelligent Food Serving Robot Prototype with Android Application for Canteens

As the world faces a COVID epidemic, one of the most critical rules to observe is social separation. There are some situations where social separation is difficult to maintain, such as canteens. The proposed technology equips a college canteen with an autonomous food serving robot, allowing us to preserve social distance. People in canteens confront challenges such as long lines and food service delays. When it comes to college canteens, students only have a limited amount of time for refreshment, resulting in a rush at the canteen. Our self-serving food robot will serve the food to the clients without fail;all they have to do is order meals using the mobile app. The system relies on a mobile application to place orders and a robot to deliver the food. Users will be able to summon the robot using the help button in the mobile app, which will result in canteen trash management. For routing and finding the best way to the table, we employ a combination of sensors and Radio Frequency Identifier (RFID) technology. Our solution will benefit the admin in addition to keeping the customers happy. Making a robot will be less expensive than hiring a human waiter. The system not only has a rechargeable wallet payment interface, but also net banking, card payment, and UPI payment possibilities. © 2022 IEEE.

Implementation of Deep Learning Models for Real-Time Face Mask Detection System Using Raspberry Pi

Amidst this COVID-19 pandemic, it is of utmost importance to wear facemasks and follow precautionary and preventive measures to decrease the further spread of this virus. In recent years Convolutional Neural networks (CNN) has impacted tremendously in various fields for classification and detection systems. In this paper we propose a facemask detection system using deep learning algorithms and a comparative study of various metrics for these deep learning algorithms. Algorithms like VGG, Resnet, Inception, Nasnet and Densenet, and its variations have been used. Using these deep learning models as a base and fine tuning the output layers of these models we construct an architecture for deep learning. Hyperparameter tuning and other methods like data augmentation have also helped in achieving better results. Various metrics like precision, recall, F1score, Average precision, accuracy and hamming loss has been evaluated for the models trained. An accuracy of 93.76% and average precision of 90.99% is achieved for the Denset201. Furthermore, we propose a standalone facemask detection system using the Raspberry Pi and a camera by fitting in the Nasnet mobile model into the detection system. Many applications for this system can be foreseen in places like hospitals, malls, restaurants and other places of public interest as an authentication or entry access criteria system. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.