IOT Based Baby Monitoring System

The current number of working mothers has increased dramatically. Later, child-rearing has become a daily challenge for many families. Thus, many parents send their children to grandparents' homes or to daycare centers. However, parents are not always able to monitor their children's every move. Therefore, the Internet of Things-based Baby Monitoring System (IoTBBMS) is being proposed as an efficient and inexpensive IoT-based monitoring system in real time. We also came up with a new algorithm for our system that plays a key role in providing better child care in the absence of parents. In the design process, the Node Micro-Controller Unit (NodeMCU) is used to collect sensor-readable data and upload it via Wi-Fi to the AdaFruit BLYNK server. The proposed system uses sensors to monitor important fetal parameters, such as ambient temperature, humidity, and crying. The system structure consists of a baby's crib that will automatically swipe using the engine when the baby cries. Parents can also monitor their children's condition with an external webcam and open a playful toy located on the baby's crib from a BLYNK server to entertain the baby. The proposed prototype of the system is designed and tested to prove its cost-effectiveness and simplicity and to ensure safe operation to enable child rearing anywhere and anytime via the network. Finally, the child monitoring system is proven to be effective in monitoring the child's condition and the environment in accordance with the model. All data taken from the sensors / modules will be stored in the Mobile application and periodically updated. The Health Algorithm is used in these databases to get information about useful physical conditions as any common symptoms of the disease can be easily identified. The proposed prototype of the system is designed and tested to prove its cost-effectiveness and simplicity and to ensure safe operation to enable child rearing anywhere and anytime via the network. Finally, the child monitoring system is proven to be effective in monitoring the child's condition and the environment according to the prototype. Keywords: IOT, Research, Node MCU, BLYNK, MQTT

Limiting COVID-19 infection by automatic remote face mask monitoring and detection using deep learning with IoT

During the current outbreak of the COVID-19 pandemic, controlling and decreasing the possibilities of infections are massively required. One of the most important solutions is to use Artificial Intelligence (AI), which combines both fields of deep learning (DL) and the Internet of Things (IoT). The former one is responsible for detecting any face, which is not wearing a mask. Whereas, the latter is exploited to manage the control for the entire building or a public area such as bus, train station, or airport by connecting a Closed-Circuit Television (CCTV) camera to the room of management. The work is implemented using a Core-i5 CPU workstation attached with a Webcam. Then, MATLAB software is programmed to instruct both Arduino and NodeMCU (Micro-Controller Unit) for remote control as IoT. In terms of deep learning, a 15-layer convolutional neural network is exploited to train 1,376 image samples to generate a reference model to use for comparison. Before deep learning, preprocessing operations for both image enhancement and scaling are applied to each image sample. For the training and testing of the proposed system, the Simulated Masked Face Recognition Dataset ( SMFRD) has been exploited. This dataset is published online. Then, the proposed deep learning system has an average accuracy of up to 98.98 %, where 80 % of the dataset was used for training and 20 % of the samples are dedicated to testing the proposed intelligent system. The IoT system is implemented using Arduino and NodeMCU_TX (for transmitter) and RX (for receiver) for the signal transferring through long distances. Several experiments have been conducted and showed that the results are reasonable and thus the model can be commercially applied

A smart mask for active defense against airborne pathogens

Face masks are a primary preventive measure against airborne pathogens. Thus, they have become one of the keys to controlling the spread of the COVID-19 virus. Common examples, including N95 masks, surgical masks, and face coverings, are passive devices that minimize the spread of suspended pathogens by inserting an aerosol-filtering barrier between the user’s nasal and oral cavities and the environment. However, the filtering process does not adapt to changing pathogen levels or other environmental factors, which reduces its effectiveness in real-world scenarios. This paper addresses the limitations of passive masks by proposing ADAPT, a smart IoT-enabled “active mask”. This wearable device contains a real-time closed-loop control system that senses airborne particles of different sizes near the mask by using an on-board particulate matter (PM) sensor. It then intelligently mitigates the threat by using mist spray, generated by a piezoelectric actuator, to load nearby aerosol particles such that they rapidly fall to the ground. The system is controlled by an on-board micro-controller unit that collects sensor data, analyzes it, and activates the mist generator as necessary. A custom smartphone application enables the user to remotely control the device and also receive real-time alerts related to recharging, refilling, and/or decontamination of the mask before reuse. Experimental results on a working prototype confirm that aerosol clouds rapidly fall to the ground when the mask is activated, thus significantly reducing PM counts near the user. Also, usage of the mask significantly increases local relative humidity levels.

Pemanfaatan Seamless Wireless (EoIP) dan GPS pada Sistem Peringatan Perlintasan Kereta Tanpa Palang Pintu

Perlintasan kereta liar tanpa palang pintu dan tanpa penjaga merupakan awal mula sering terjadinya kecelakaan di perlintasan kereta api. Salah satu solusi untuk menyelesaikan permasalahan ini dengan pembangunan sistem otomatis peringatan kedatangan kereta dengan memanfaatkan teknologi seamless wireless Ethernet over Internet Protocol (EoIP). Penelitian ini dilakukan dengan pengujian prototype di lingkungan UKDW dengan panjang pelintasan kurang lebih 70 - 80 meter, menggunakan 1 MCU(Micro Controller Unit) ESP8266 dan 1 GPS Module yaitu node kereta, 2 MCU, 2 unit LCD module, 2 Servo motor dan 2 Buzzer menjadi 2 node perlintasan kereta. Sistem ini diuji coba sebanyak 30 kali dengan checklist pengujian. Pengujian dimulai saat node kereta mengirimkan informasi dalam bentuk longitude dan latitude ke server lalu server akan menghitung jarak antara node kereta dengan setiap node perlintasan kemudian hasil jarak tersebut akan di kirim ke setiap node perlintasan kereta, akan terjadi pengecekan jarak di setiap node perlintasan kereta, pada jarak yang telah ditentukan palang akan ditutup ataupun dibuka. Dari 30 kali percobaan disimpulkan bahwa sistem otomatis peringatan kedatangan kereta dapat mendeteksi kedatangan kereta dan telah berhasil dibangun dengan benar dan berjalan sesuai flow sistem yang sudah dirancangkan. Dilengkapi dengan pemanfaatan Teknologi seamless wireless EoIP yang memungkinkan pembangunan jaringan bahkan di titik buta tidak dapat dijangkau oleh operator seluler ataupun GSM. Oleh karena itu seamless wireless EoIP ini sangat cocok dalam membantu pembangunan sistem peringatan kedatangan kereta api dengan palang otomatis dibuktikan dengan setiap alat dapat terhubung dan tidak terputus selama 30 kali percobaan.

Active-Sensing Epidermal Stretchable Bioelectronic Patch for Noninvasive, Conformal, and Wireless Tendon Monitoring

Sensors capable of monitoring dynamic mechanics of tendons throughout a body in real time could bring systematic information about a human body’s physical condition, which is beneficial for avoiding muscle injury, checking hereditary muscle atrophy, and so on. However, the development of such sensors has been hindered by the requirement of superior portability, high resolution, and superb conformability. Here, we present a wearable and stretchable bioelectronic patch for detecting tendon activities. It is made up of a piezoelectric material, systematically optimized from architectures and mechanics, and exhibits a high resolution of 5.8×10−5 N with a linearity parameter of R2=0.999. Additionally, a tendon real-time monitoring and healthcare system is established by integrating the patch with a micro controller unit (MCU), which is able to process collected data and deliver feedback for exercise evaluation. Specifically, through the patch on the ankle, we measured the maximum force on the Achilles tendon during jumping which is about 16312 N, which is much higher than that during normal walking (3208 N) and running (5909 N). This work not only provides a strategy for facile monitoring of the variation of the tendon throughout the body but also throws light on the profound comprehension of human activities.

ADAPT: A Smart Mask for Active Defense Against Air-Borne Pathogens

Face masks are a primary preventive measure against airborne pathogens. Thus, they have become one of the keys to controlling the spread of the COVID-19 virus. Common examples, including N95 masks, surgical masks, and face coverings, are passive devices that minimize the spread of suspended pathogens by inserting an aerosol-filtering barrier between the user’s nasal and oral cavities and the environment. However, the filtering process does not adapt to changing pathogen levels or other environmental factors, which reduces its effectiveness in real-world scenarios. This paper addresses the limitations of passive masks by proposing ADAPT, a smart IoT-enabled “active mask”. This wearable device contains a real-time closed-loop control system that senses airborne particles of different sizes near the mask by using an on-board particulate matter (PM) sensor. It then intelligently mitigates the threat by using mist spray, generated by a piezoelectric actuator, to load nearby aerosol particles such that they rapidly fall to the ground. The system is controlled by an on-board micro-controller unit (MCU) that collects sensor data, analyzes it, and activates the mist generator as necessary. A custom smartphone application enables the user to remotely control the device and also receive real-time alerts related to recharging, refilling, and/or decontamination of the mask before reuse. Experimental results on a working prototype confirm that aerosol clouds rapidly fall to the ground when the mask is activated, thus significantly reducing PM counts near the user. Also, usage of the mask significantly increases local relative humidity (RH) levels.

Robustifying the Deployment of tinyML Models for Autonomous Mini-Vehicles

Standard-sized autonomous vehicles have rapidly improved thanks to the breakthroughs of deep learning. However, scaling autonomous driving to mini-vehicles poses several challenges due to their limited on-board storage and computing capabilities. Moreover, autonomous systems lack robustness when deployed in dynamic environments where the underlying distribution is different from the distribution learned during training. To address these challenges, we propose a closed-loop learning flow for autonomous driving mini-vehicles that includes the target deployment environment in-the-loop. We leverage a family of compact and high-throughput tinyCNNs to control the mini-vehicle that learn by imitating a computer vision algorithm, i.e., the expert, in the target environment. Thus, the tinyCNNs, having only access to an on-board fast-rate linear camera, gain robustness to lighting conditions and improve over time. Moreover, we introduce an online predictor that can choose between different tinyCNN models at runtime—trading accuracy and latency—which minimises the inference’s energy consumption by up to 3.2×. Finally, we leverage GAP8, a parallel ultra-low-power RISC-V-based micro-controller unit (MCU), to meet the real-time inference requirements. When running the family of tinyCNNs, our solution running on GAP8 outperforms any other implementation on the STM32L4 and NXP k64f (traditional single-core MCUs), reducing the latency by over 13× and the energy consumption by 92%.

Wearable EMG Sensor for Gait Rehabilitation using IoT

Interventions for movement dysfunction, including radiography and rhythmic planning, have demonstrated a significant increase in gait mechanics. While the optimum criteria for gait training are still to be determined, previous research shown that the training duration facilitates neural restructuring, thereby promoting the design of wearable technology for gait recovery. This work provides evidence of the advanced tool used to acquire muscle activity. Muscle activity is recorded and analyzed on Node micro controller unit, then sent to remote service using internet of things concepts, where message queuing telemetry transport protocol is used in the cloud based telemetry of the received signals and is given to the thing speak. The live recordings, along with the frequency variation of the gait in moving and stable condition, are also obtained on the central monitor using the MATLAB. By creating a device that can be used at home, patients would be able to practice and sustain longer recovery services on a regular basis, thus encouraging neural reorganization. This can also help us to monitor patient treatment progress even if the physiotherapist is not able to come and recorded data can be sent directly to them.

Reliability of Flexible Wearable Band With Printed Sensors for Vital Sign Acquisition

Wearable electronics need a number of desirable attributes, such as being compact, flexible, and lightweight. Prior studies on reliability testing have examined the relationship between a flexible electronic and repetitive human body motions (i.e., stretching, bending, twisting, and folding). Such mechanical loads can cause fatigue failure in a wearable electronic. In regard to a wearable band, fatigue failure can be influenced by folding stress. This research study involved the assessment of wearable biometric bands that were calibrated and examined by a test device for folding reliability. The wearable band combines a biometric sensor unit, a micro-controller unit with a wireless connection, and a printed thermistor unit. The sensors have been calibrated by actual temperature and biometric signals. Furthermore, the folding test was conducted utilizing multiple boards. Due to multiple components and printed lines of the PCB, optical images were taken in order to confirm which parts failed and the reasons for the failures. An FEM analysis was conducted in order to understand how stress impacts the PCB and which parts are stressed during the folding process. Throughout the process, an equation was developed to predict the number of cycles necessary for reaching fatigue failure. Throughout this study, the fatigue failure analysis on folding reliability of the wearable biometric band was conducted using experimental analysis, microscopy analysis, and simulating analysis. The study provided further knowledge about the fatigue failure mechanism, which resulted from the prediction of fatigue life developed from the PCB.