The aim of this research is an exhaustive analysis of the various factors that may influence the recognition rate of the human activity using wearable sensors data. We made a total of 1674 simulations on a publically released human activity database by a group of researcher from the University of California at Berkeley. In a previous research, we analyzed the influence of the number of sensors and their placement. In the present research we have examined the influence of the number of sensor nodes, the type of sensor node, preprocessing algorithms, type of classifier and its parameters. The final purpose is to find the optimal setup for best recognition rates with lowest hardware and software costs.
BCI (Brain-Computer Interface) is a technology which goal is to create and manage a connection between the human brain and a computer with the help of EEG signals. In the last decade consumer-grade BCI devices became available thus giving opportunity to develop BCI applications outside of clinical settings. In this paper we use a device called NeuroSky MindWave Mobile. We investigate what type of information can be deducted from the data acquired from this device, and we evaluate whether it can help us in BCI applications. Our methods of processing the data involves feature extraction methods, and neural networks. Specifically, we make experiments with finding patterns in the data by binary and multiclass classification. With these methods we could detect sharp changes in the signal such as blinking patterns, but we could not extract more complex information successfully.
This paper presents an Open Platform Activity and health monitoring systems which are also called e-Health systems. These systems measure and store parameters that reflect changes in the human body. Due to continuous monitoring (e.g. in rest state and in physical effort state), a specialist can learn about the individual's physiological parameters. Because the human body is a complex system, the examiner can notice some changes within the body by looking at the physiological parameters. Six different sensors ensure us that the patient's individual parameters are monitored. The main components of the device are: A Raspberry Pi 3 small single-board computer, an e-Health Sensor Platform by Cooking-Hacks, a Raspberry Pi to Arduino Shields Connection Bridge and a 7-inch Raspberry Pi 3 touch screen. The processing unit is the Raspberry Pi 3 board. The Raspbian operating system runs on the Raspberry Pi 3, which provides a solid base for the software. Every examination can be controlled by the touch screen. The measurements can be started with the graphical interface by pressing a button and every measured result can be represented on the GUI’s label or on the graph. The results of every examination can be stored in a database. From that database the specialist can retrieve every personalized data.
Personal activity tracker are nowadays part of our lives. They silently monitor our movements and can provide valuable information and even important alerts. But usually the user’s data is stored only on the activity tracker device and the processing done is limited by this modest processing power device. Thus it is very important that the user’s data can be stored and processed in the cloud, making the activity tracker an IOT node. This paper proposes a simple IOT gateway solution for a custom user monitoring device.
Nowadays SoC’s miniaturization provide smaller yet more powerful devices that are perfect to be used as local hubs for small to medium sensor networks. Although sensors can now be easily connected directly to the cloud, a hub can simplify the process of bringing sensor to the IoT cloud. One of the most popular SoC board, Raspberry PI, is perfect for the hub role due to its small form factor, price, processing power and connectivity. Our proposed system consists in a SoC based low cost raspberry pi hub that connects two Bluetooth sensortag CC2650 modules to a mongoDB cloud database.
Machine-learning techniques allow to extract information from electroencephalographic (EEG) recordings of brain activity. By processing the measurement results of a publicly available EEG dataset, we were able to obtain information that could be used to train a feedforward neural network to classify two types of volunteer activities with high efficiency.