A low cost multipoint, multipurpose temperature data logger was designed and fabricated in this study. The design was done using Max6675 temperature sensors and linear monolithic (LMs) temperature sensors. This data logger is an electronic device that records data over time based on microcontroller. The utilization of data logger in this work is to accomplish the task of monitoring the temperature measurement of the 160Wpeak hybrid photovoltaic/thermal (PV/T) flat plate solar air heater. This data logger is just customized for this equipment – the hybrid photovoltaic/thermal solar air heater. The developed prototype was internally or externally powered and has a retrievable memory card module. The sensor’s response time was observed to be one minute leading to a time series analysis. It was observed from the graphical plots that the temperature patterns were in consonance with the solar radiation patterns. The trend of the temperature flow pattern measured from the hybrid photovoltaic/thermal (PV/T) flat plate solar air heater was in consonance with the solar radiation flow pattern. This indicates that the peaks of the temperature plots fall at the peaks of the plots of solar radiation.sss

The monitoring of epileptic seizures is mainly done by means of electroencephalogram (EEG) monitoring. Although this method is accurate, it is not comfortable for the patient as the EEG-electrodes have to be attached to the scalp which hampers the patient's movement. This makes long-term home monitoring not feasible. Epilepsy is one of the most common neurological disorders, affecting almost 60 million people all over the world. Most of the affected people can be treated successfully with drug therapy (67%) or neurosurgical procedures (7%-8%). Nevertheless 25% of the affected people cannot be treated by any available therapy. For refractory patients who continue to have frequent seizures, it has been shown that intensive monitoring with electroencephalogram (EEG) and video over a long period, contributes to the management of daily care and the adjustment of drug therapy. The long-term monitoring with EEG and video can be very unpleasant for patients, and analyzing large amounts of EEG/video-data is very labor intensive for medical personnel. Furthermore, this method cannot yet be applied in real-time procedures. All the above-mentioned factors have made it necessary to look for sensors that are patient friendly and can be used for a reliable automatic detection of epileptic seizures. One of these sensors is the accelerometer. Accelerometers are used in many medical research areas for activity recognition. For instance, in Parkinson's disease, studies aim at distinguishing pathological (periods of hypokinesia, bradykinesia and dyskinesia) and normal movements. In this paper, the aim is to develop a seizure detection system based on accelerometry for the detection of epileptic seizure. The proposed seizure detection system based on Wireless Sensor Network (WSN) that can determine the location of the patient when a seizure is detected and sends an alarm to hospital staff or the patient's relatives. A hand-band that detects seizures, comes equipped with a pulse, gyro sensor and connects to Wi-Fi to report events. In this system there are 2 parts; first one is the detection part and second is the notification part. This system is very user friendly.

Liquefied Petroleum Gas (LPG) is a main source of fuel especially in urban areas because it is clean compared to firewood and charcoal. There is always a danger of the gas leakage as a result of negligence or failure on the regulating valve on the gas cylinder which pose a great danger due to highly flammable nature of the gas. Cases of gas related fire has been on the rise and this can be avoided using a gas leakage detection system and thus the need for development of a microcontroller based cooking gas detector. The use of microcontroller enables development of a high accurate and fast response detection system. The detector incorporate MQ-6 sensor (with gas detection range of 300-10000ppm) as the LPG gas sensor, PIC16F690 microcontroller as the control unit, LCD for displaying gas concentration, a buzzer as an alarm and a number of LEDs to indicate the gas leakage status. The microcontroller senses the presence of a gas when the voltages signal from the MQ-6 sensor goes beyond a certain level and gives an audiovisual alarm. The microcontroller is programmed using PIC assembly language and all the peripherals connected to it through it pins. When the system is powered on the microcontroller lit a green LED to show the absence of a gas leakage. LPG gas is released and the sensor voltage signal monitored using a digital multimeter. Below 2.0V, the green LED is kept lit and when the voltage is more or equal to 2.0V, the microcontroller blinks a red LED and set off an alarm to show the presence of a gas. The detector has a button with which the alarm can be acknowledged. The sensor as a high resistance in clean air. In the presence of LPG gas, the sensor conductivity increases and the characteristic of the sensor is that at 2.0V output from the sensor, the gas concentration is 300ppm, thus the trigger level is 2.0V. Therefore, the microcontroller based gas leakage detector based on PIC16F690 microcontroller and MQ-6 sensor is able to detect gas leakage concentration from 300ppm and give an audiovisual signal.

There is an emerging field of new materials, including, but not limited to, fibre-metal laminates, foam materials, and materials processed by additive manufacturing, highly related to space applications. Typically, material properties such as yield strength or inelastic behaviour are determined from tensile tests. The main disadvantage of tensile testing is the irreversible modification of the device under test (only one experiment possible!). We develop and investigate the training of approximating predictor functions by Machine Learning (ML) and simple Artificial Neural Networks (ANN) for inelastic and fatigue prediction by history recorded data. The predictor functions should be able to predict irreversible effects like inelastic behaviour and material damage by data measured from simple tensile tests within the elastic range of the materials. We show some preliminary results from a broad range of materials and outline the challenges to derive such predictor functions by using recurrent neural networks and Long-short-term Memory cells (LSTM). The neural network is activated by a linearized sequence of sensor samples measured either from laboratory tensile tests or by using strain-gauge and force sensors at run-time. The predictor functions outputs an extrapolation of the development of the measured variables (e.g., force, tension).

Dealing with complex engineering problems characterized by Big Data, particularly in the structural engineering area, has recently received considerable attention due to its high societal importance. Data-driven structural health monitoring (SHM) methods aim at assessing the structural state and detecting any adverse change caused by damage, so as to guarantee structural safety and serviceability. These methods rely on statistical pattern recognition, which provides opportunities to implement a long-term SHM strategy by processing measured vibration data. However, the successful implementation of the data-driven SHM strategies when Big Data are to be processed, is still a challenging issue since the procedures of feature extraction and/or feature classification may result time-consuming and complex. To enhance the current damage detection procedures, in this work we propose an unsupervised learning method based on time series analysis, deep learning and Mahalanobis distance metric for feature extraction, dimensionality reduction and classification. The main novelty of this strategy is the simultaneous dealing with the significant issue of Big Data analytics for damage detection, and distinguishing damage states from the undamaged one in an unsupervised learning manner. Large-scale datasets relevant to a cable-stayed bridge have been handled to validate the effectiveness of the proposed data-driven approach. Results have shown that the approach is highly successful in detecting early damage, even when Big Data are to be processed.