Artificial Neural Network or simply Neural Network (ANN) is a machine learning technique that is modeled loosely after the human brain. It is a powerful, scalable and versatile technique that has been used to solve highly complex problems such as pattern recognition, machine translation and e-mail spam filtering. A neural network composes of layers of…
All posts in Notes
Backpropagation and Gradient Descent
A neural network needs to be trained to solve a prediction problem. The training (or learning) is a process of finding the weight and bias values that will produce the desired output at the output layer when a certain input is given to the network. How does a neural network learn? For a human to…
Focus areas of context-aware research
1. Activity recognition [1][4][5][8][13] 2. Specific activity [2] 3. System [3][9][11] 4. Energy management [6][15] 5. Augmentation [7] 6. Data intepretation/Processing [10][19] 7. Reasoning [1][12][16][17][18] 8. Modeling [14] [1] F. Zhou, J. Jiao, S. Chen, and D. Zhang, ‘A Case-Driven Ambient Intelligence System for Elderly in-Home Assistance Applications’, IEEE Transactions on Systems, Man, and Cybernetics,…
Context Modeling
One of the method of context modeling is by using ontologies. Ontologies facilitate structuring data and representing knowledge. It define a given domain in a graph structure which contains concepts present in the modelled domain, the relationship between concepts and potentially classification axioms which specify generic knowledge about the domain. The ontologies is exploited by…
Input for Context Aware System
Not every input to context aware system is information. It could be raw data. For example, location and temperature. Temperature is a raw data from temperature sensor and location is an information which generated by processing raw data from accelerometer, gyrosensor? and magnetometer?. Both values could be inputs to context aware system. Therefore there is…
Taxonomy of Context Aware IoT middleware solution
Context acquisition -> Context Modeling -> Context Reasoning -> Context Distribution
Context Aware Computing
A survey has been conducted by Perera et al. [1] on the functionalities of Middleware for IoT. Functionalities that have been considered are device management, interoperation, platform portability, context-awareness, and security and privacy. The survey shows majority of Middleware solution do not provide context-awareness functionality. According to Abowd and Dey [2], context is defined as…
Sensors for Context Aware System
There are two categories of sensors for healthcare application. The first category is called ambient sensors. Ambient sensor is used to monitor the general activity patterns based on spatial and temporal information processing. Examples of ambient sensors are fall detectors, door monitors, bed alerts, pressure mats, smoke and heat alarms etc. More recent works on…
Middleware for Networked Embedded Systems for IOT
Amount of different devices (sensor nodes) interacting in an IOT environment is big. These devices must be able to connect to each other despite their different network technologies. Furthermore, the devices also require service discovery procedures as well as means to enforce semantic compatibility between devices. These requirement create a demand for a software layer…
Wireless Sensor Networks (WSN)
Wireless sensor networks is a wireless network that consists of spatially distributed autonomous devices using sensors to monitor environment condition such as temperature, humidity, sound, image and etc.