Search

This article presents an ambience intelligence application for smart home systems for efficient use of electricity, enhance comfort zone, independence of living and security. The system integrates smart home occupant's identification, sensors-actuators deployment, a gateway Hub, machine learning, and cloud computing components to realize the objectives of smart living. A Mobile phone MAC-address based occupant identification and machine learning algorithms are proposed to address the multiple smart home occupant problems and an instant user control versus rule-based control conflicts. Results show that machine learning algorithm could learn the ambience preferences of multiple occupants when trained on a large enough dataset. The proposed system can implement ambient intelligence applications in smart home.

This paper presents findings from a study of five healthy subjects performing 50% maximum voluntary contraction until complete fatigue of the muscle. An overlapping window technique was used to find the values for mean frequency (MNF), median frequency (MDF) of the power spectrum, root mean square (RMS) and muscle fibre conduction velocity (MFCV). The surface electromyography signal (sEMG) was collected from the vastus lateralis muscle using a three channel Laplacian electrode. The results show the MNF and MDF values showed a consistent trend with each other where they remained at steady values between 20-30% and 75-80% of the signal after which they fell 15-30% of this value. The RMS showed a linear increase in value. The MFCV showed a similar trend to that found in the MNF and MDF values. 

Conventional collection of surface electromyography signals requires the surface electrodes, amplifier and data acquisition card to all be wired together, restricting the movement of the test subject. With the advancement of wireless technology such as Bluetooth and XBee with ZigBee, the wire link between the electrodes and computer storing the data can be removed. Using Bluetooth configuration will require new circuitry of an analogue-to-digital convertor with a microcontroller to a Bluetooth module with the wireless link to an USB Bluetooth modem dongle. The XBee configuration will also require an analogue-to-digital convertor with a microcontroller to a XBee transceiver for the wireless link to an USB XBee dongle transceiver. XBee with ZigBee configuration will allow multichannel collection of signals as a wireless sensor network.

The data collection of surface electromyography signals has required the sensor, amplifier and data acquisition card to be all wired together restricting the movement of the subject being tested. With the advancement of wireless technology such as Bluetooth, IEEE 802.15.4 and ZigBee the wire link between the amplifier and computer analysing and storing the data can be removed. Using Bluetooth will require new circuitry of a microcontroller with an analogue-digital convertor, a RS232 serial link, transceiver and a USB dongle transceiver for the wireless link. The IEEE 802.15.4 will require a single chip microcontroller to perform the analogue-digital convertor and also a transceiver for the wireless link to an USB dongle transceiver. ZigBee will build on the IEEE 802.15.4 configuration to allow multichannel collection of signals as a wireless sensor network.

To date various signal processing techniques have been applied to surface electromyography (SEMG) for feature extraction and signal classification. Compared with traditional analysis methods which have been used in previous application, continuous wavelet transform (CWT) enhances the SEMG features more effectively. This paper presents methods of analysing SEMG signals using CWT and LabVIEW for extracting accurate patterns of the SEMG signals. We used the scalogram and frequency-time based spectrum to plot the power of the wavelet transform and enhance the diagnosis features of the signal. As a result, clinical interpretation of SEMG can be improved by extracting time-based information as well as scales, which can be converted to frequencies. Using the extracted features of the dominant frequencies of the wavelet transform and the related scales, we were able to train and validate an artificial neural network (ANN) for SEMG classification.

A number of Digital Signal Processing (DSP) techniques are being applied to Surface Electromyography (SEMG) for classification using signal feature extraction. This research is aimed at using Continuous Wavelet Transform (CWT) analysis of SEMG signals to develop and adopt a sound methodology for classification of the signals at different force levels. Traditional analysis methods such as Fast Fourier Transform (FFT) could not be used alone because muscle diagnosis requires time-based information. Therefore CWT was selected for this research as it includes time-based information as well as scales that can be converted into frequencies, making muscle diagnosis easier. CWT produces a scalogram plot along with its corresponding time-based frequency spectrum plot. Using both of these plots, extracted features of the dominant frequencies and the related scales can be used to train and validate a signal classifier based on an Artificial Neural Network (ANN). SEMG signals were obtained for a 10 second period sampled at 2048 Hz and digitally filtered using a Butterworth bandpass filter (5 to 500 Hz, 4th order). Signals were collected from the vastus medialis muscle of both legs of 45 healthy male subjects at 25%, 50% and 75% of their Maximum Voluntary Isometric Contraction (MVIC) force of the quadriceps. The extracted features selected for the two second period of the signal were the mean and median frequencies of the average power spectrum, and the RMS values at scale 8, 16, 32, 64 and 128 of the scalogram. The signals were analysed using CWT in LabVIEW with its Signal Processing Toolset. In this paper, the results are presented to show that the selected extracted features are suitable for the classification of SEMG signals at different force levels.

A number of digital signal processing (DSP) techniques are being applied to surface electromyography (SEMG) signals to extract detailed features of the signal. Fast Fourier transform (FFT) is one of the most common methods for analyzing the signal whether it is filtered or not. Another DSP technique is referred to as wavelet analysis, a method that is gaining more use in analyzing SEMG signals. This research focuses on using the discrete wavelet transform (DWT) and the wavelet package transform (WPT). Both DWT and WPT use analytical wavelets called "mother wavelet" which comes in different sets or "families". Wavelet analysis has the advantage over FFT as it provides the frequency contents of the signal over the time period that is being analyzed. SEMG signals were collected from a muscle under sustained contractions for 4 seconds with different loads. The raw signals were analyzed using FFT, DWT and WPT in LabVIEW/spl reg/ using its signal processing toolset. Using wavelet analysis the SEMG signal was decomposed into its frequency content form and then was reconstructed. In this paper the results are presented to show that certain families of mother wavelets of wavelet analysis are more suitable than others for analyzing SEMG signals.