Projects - User contributions [en]

Projects:2015s2-209 Automated Classification of Brain Activity During Sleep

2016-05-30T23:12:30Z

A1643783:

== Project Description ==

The project ‘Automated classification of brain activity during sleep’ has been assigned as a requirement to complete the master’s coursework in electronic engineering. The assigned project entails the group members to create a suitable sleep cycle classification to enable researchers to identify the sleep stages and use the data to further their research.

There are increasing number of cases where people are suffering from sleeplessness and chronic sleep ailments. Such ailments have to potential to jeopardise the lives of people as they are likely to lose alertness alongside weakening their immune system. These negative changes make them susceptible to various disorders. The most serious disorders that have been identified to affect the healthy mind and body are sleep apnoea and depression. These ailments are difficult to be corrected by a simple check-up.

Therefore, it is recommended to perform a sleep study to knowing the diseases affecting a healthy person before they further deteriorate the health. The project aims to capture the sleeping patterns spread out over the entire sleeping duration. The patterns are extracted from the brain sensors by an electroencephalogram (EEG). The EEG records the pattern to a European Data Format (EDF) file. The file becomes crucial in evaluating the factors that might be causing wakefulness. What is more, the anomalies in the sleeping pattern can be detected by comparing the EEG with a standard sleep cycle. The standard reference is available in an Extensive Mark-up Language (XML) format. The deviations of the actual sleep cycle from the ones displayed on the format are pivotal to capture and detect the sleep related signals.

The main objective of the project is to automatically classify the sleep stages of the data and detect any abnormality in the sleep cycle. Although the analysis of the time varying signal from the EEG may look out to be suitable to observe various sleep signals, the signal is time varying and would not be a true representation of the actual signals. Hence, the signal classification has to be done by implementing a suitable signal analysis approach to make the analysis of the data more meaningful to academicians.

Evidently, the most pivotal point of the project is the use of an appropriate signal analysis technique in order to have a high degree of accuracy in demonstrating the sleep stages. After taking into account many factors, signal processing is done by short term Fourier transformation (STFT) and wavelet transformation.It aids in extracting the critical components of the complex time varying signal making it easy to assess the frequency components. STFT enables us to break the lengthy time domain signal into smaller segments called windows, which can be subjected to fast Fourier transformation to simultaneously bring the frequency and amplitude information out of the signal. Even so, it has certain shortcomings considering that the window size is fixed. Therefore, wavelet analysis is used to eliminate these weaknesses. This evaluation gave certain features which were being trained by a neural network.

The final stage has been the training of the neural network in order to classify the sleep stages. These stages were automatically classified by the network. A high degree of accuracy was obtained while training the network. This can be attributed to the four layer neural network, which has given very precise results. Different records are tested and have been found to give a consistent result.

== Project Results ==

- Using Wavelet Transform
- Decompse the alpha, beta, theta and delta waves
- Features Extraction
[[File:图片1.jpg]]

- ICA (Independent Component Analysis)
[[File:图片2.jpg]]

- Use Neural Network
- Use Features as Input
- Set the Target
- Training
[[File:图片3.jpg]]

== Project Conclusion ==
- For non-stationary signal, wavelet transform processing a good effect.
- The ICA can remove most of the artifacts.
- After using ICA, the accuracy of classification for sleep stages by using neural network will increase significantly.

File:图片3.jpg

2016-05-30T23:07:39Z

A1643783:

File:图片2.jpg

2016-05-30T23:07:28Z

A1643783:

File:图片1.jpg

2016-05-30T23:06:53Z

A1643783:

Projects:2015s2-209 Automated Classification of Brain Activity During Sleep

2016-05-30T12:35:41Z

A1643783: Created page with "content"

content

Projects:2014s2-83 A Testing and Characterising Device for batteries of various chemistries

2015-06-03T02:19:00Z

A1643783: /* References */

Contents
1. Project introduction
1.1 Project aims
1.2 Project overview
1.2.1 Hardware overview
1.2.2 Software overview
2. Project result analysis
3. Team management
4. Acknowledgements
5. References

== Project introduction ==
This design uses the microcontroller to control the system voltage, current and temperature. It can achieve the process of constant current, constant voltage and trickle charge. In sofeware, the design contains different function of each module. According to the work demands of the system, low power consumption and sofeware anti-interference are designed, which ensure the safety and reliability of the system. The design can improve the intellectualization level of the battery charger, realize the control to the charger process more precisely, protect the battery and extend the using time.

== Project aims ==
The aim of the project is to develop a testing and characterising device that can be used with different battery chemistries (primary or secondary (rechargeable)). The device should have the following characteristics:
- Mobile, low cost and easy to move around
- Useable to characterise batteries that have cell capacity of sub-1 Volt up to 4 Volts
- Able to handle up to 6-cell series connected batteries with independent cell characterisation
- Able to provide a programmable testing and characterisation waveforms to allow various use scenarios using an easy to use interface,
- Able to work independently on its own or when connected to a computer or a tablet
- Able to log measured information in a format that is can be stored locally or communicated to a computer using a wired/wireless interface, possibly USB, Wi-Fi or Bluetooth.

== Buck converter ==

[[File:图片1.png]]

Buck Converter is a step down converter operates with lower output voltage with high input voltage. Varying value of load voltage. The circuit exists in two modes, depending on whether the MOSFET is switched on or off. When the switch is on (short circuited), the supply voltage is applied to the inductor, which causes the inductor current to increase with time. In this state, energy from the source is partly stored in the inductor, and partly delivered to the load. When the MOSFET is switched off (open circuited), the inductor current flows through the diode and the load, causing this current to reduce.

== Amplifier ==

[[File:图片2.png]]

A method of measuring the output current Io and converting it to a value of voltage is required to implement some form of maximum power point tracking using a microcontroller. The simplest method of achieving this is to place a small resistance which is called shunt resistance in series with the negative side of the load, and measure the voltage drop across this resistor. Figure 6 shows an example of how this can be achieved. Given that this voltage will be very small, some form of amplification is required. This can be achieved using a differential amplifier

== Balanced circuit ==

[[File:图片4.png]]

This figure shows a charge balance circuit for N batteries connected in series. The battery bank is charged by constant current. Each battery is shunted by a sub-circuit which is a rearranged buck-boost convertor is battery.

== Software Overview ==
[[File:图片3.png]]

Microcontroller Arduino Mega 2560
Operating Voltage 5V
Input Voltage (recommended) 7-12V
Input Voltage (limits) 6-20V
Digital I/O Pins 54 (of which 15 provide PWM output)
Analog Input Pins 16
DC Current per I/O Pin 40mA
DC Current for 3.3V Pin 50mA
Flash Memory 256 KB of which 8 KB used by bootloader
SRAM 8Kb
EEPROM 4Kb
Clock Speed 16MHz

== Project result analysis ==
[[File:图片5.jpg]]
[[File:图片6.jpg]]

The Ni-Cd battery using here is 1000mAh. Hence when the charging current 1A, it will take about 1 hour to finish the charging. In the experiment, the terminal method is using the negative delta V( NDV) that means when the voltage of the Ni-Cd battery has began to drop the charging will stop. NDV is the recommended full-charge detection for “open-lead” nickel-based chargers. NDV offers a quick response time and works well with a partially or fully charged battery. When inserting a fully charged battery, the terminal voltage rises quickly, and then drops sharply to trigger the ready state. The charge lasts only a few minutes and the cells remain cool. NiCd chargers based on the NDV full-charge detection typically respond to a voltage drop of 10mV per cell.
To obtain the needed voltage, the charge rate must be 0.5C and higher. Slower charging produces a less defined voltage drop, especially if the cells are mismatched and each reaches full charge at a different time. Most chargers combine NDV with a voltage plateau detector that terminates the charge when the voltage remains in a steady state for a given time. For additional safety, advanced chargers also include delta temperature, absolute temperature and a time-out timer.
From this graph can be seen that in the beginning of 15 minutes, the voltage of the battery becomes very faster from 1.3V to 1.6V. Then the voltage will increase very slowly to 1.8V. At the end of charging, the Ni-Cd battery will have a very small voltage drop about 0.01V to 0.05V. When the microcontroller has checked the voltage drop it will stop the charging immediately.

== Team management ==
[[File:图片7.jpg]]

== References ==
1] Park Hae-Woo. Han Chang-Seok Ni-MH battery charger with a compensatorforelectric vehicles [R] SAE 9604477, 1996

[2] Niggemann E .High performance nickel－metal hydride battery for electric and hybrid vehicles［Z］E VS-15.Bruxelles.1998.

[3] K.Hirakawa，A.Measuring and Analyzing Method for Battery Conditions Using a New Field Data Collection system，evsl17，2000.

[4] MAXIM.Datasheet：Stand-Alone.Switch-Mode Li+ Battery Charger，2001.

[5] Omagawa Takuya.Manufacture of Secondary Alkaline Batteries [P].JP 0353461.1991-07.

[6] ZHANGShuyun,SUNJiangbei,HUOZhiming. The serial port communication of the computer and single chip[J]. Chinese Science and Technology Information,2005 (10): 130-131.

Projects:2014s2-83 A Testing and Characterising Device for batteries of various chemistries

2015-06-03T02:18:41Z

A1643783: /* References */

Contents
1. Project introduction
1.1 Project aims
1.2 Project overview
1.2.1 Hardware overview
1.2.2 Software overview
2. Project result analysis
3. Team management
4. Acknowledgements
5. References

== Project introduction ==
This design uses the microcontroller to control the system voltage, current and temperature. It can achieve the process of constant current, constant voltage and trickle charge. In sofeware, the design contains different function of each module. According to the work demands of the system, low power consumption and sofeware anti-interference are designed, which ensure the safety and reliability of the system. The design can improve the intellectualization level of the battery charger, realize the control to the charger process more precisely, protect the battery and extend the using time.

== Project aims ==
The aim of the project is to develop a testing and characterising device that can be used with different battery chemistries (primary or secondary (rechargeable)). The device should have the following characteristics:
- Mobile, low cost and easy to move around
- Useable to characterise batteries that have cell capacity of sub-1 Volt up to 4 Volts
- Able to handle up to 6-cell series connected batteries with independent cell characterisation
- Able to provide a programmable testing and characterisation waveforms to allow various use scenarios using an easy to use interface,
- Able to work independently on its own or when connected to a computer or a tablet
- Able to log measured information in a format that is can be stored locally or communicated to a computer using a wired/wireless interface, possibly USB, Wi-Fi or Bluetooth.

== Buck converter ==

[[File:图片1.png]]

Buck Converter is a step down converter operates with lower output voltage with high input voltage. Varying value of load voltage. The circuit exists in two modes, depending on whether the MOSFET is switched on or off. When the switch is on (short circuited), the supply voltage is applied to the inductor, which causes the inductor current to increase with time. In this state, energy from the source is partly stored in the inductor, and partly delivered to the load. When the MOSFET is switched off (open circuited), the inductor current flows through the diode and the load, causing this current to reduce.

== Amplifier ==

[[File:图片2.png]]

A method of measuring the output current Io and converting it to a value of voltage is required to implement some form of maximum power point tracking using a microcontroller. The simplest method of achieving this is to place a small resistance which is called shunt resistance in series with the negative side of the load, and measure the voltage drop across this resistor. Figure 6 shows an example of how this can be achieved. Given that this voltage will be very small, some form of amplification is required. This can be achieved using a differential amplifier

== Balanced circuit ==

[[File:图片4.png]]

This figure shows a charge balance circuit for N batteries connected in series. The battery bank is charged by constant current. Each battery is shunted by a sub-circuit which is a rearranged buck-boost convertor is battery.

== Software Overview ==
[[File:图片3.png]]

Microcontroller Arduino Mega 2560
Operating Voltage 5V
Input Voltage (recommended) 7-12V
Input Voltage (limits) 6-20V
Digital I/O Pins 54 (of which 15 provide PWM output)
Analog Input Pins 16
DC Current per I/O Pin 40mA
DC Current for 3.3V Pin 50mA
Flash Memory 256 KB of which 8 KB used by bootloader
SRAM 8Kb
EEPROM 4Kb
Clock Speed 16MHz

== Project result analysis ==
[[File:图片5.jpg]]
[[File:图片6.jpg]]

The Ni-Cd battery using here is 1000mAh. Hence when the charging current 1A, it will take about 1 hour to finish the charging. In the experiment, the terminal method is using the negative delta V( NDV) that means when the voltage of the Ni-Cd battery has began to drop the charging will stop. NDV is the recommended full-charge detection for “open-lead” nickel-based chargers. NDV offers a quick response time and works well with a partially or fully charged battery. When inserting a fully charged battery, the terminal voltage rises quickly, and then drops sharply to trigger the ready state. The charge lasts only a few minutes and the cells remain cool. NiCd chargers based on the NDV full-charge detection typically respond to a voltage drop of 10mV per cell.
To obtain the needed voltage, the charge rate must be 0.5C and higher. Slower charging produces a less defined voltage drop, especially if the cells are mismatched and each reaches full charge at a different time. Most chargers combine NDV with a voltage plateau detector that terminates the charge when the voltage remains in a steady state for a given time. For additional safety, advanced chargers also include delta temperature, absolute temperature and a time-out timer.
From this graph can be seen that in the beginning of 15 minutes, the voltage of the battery becomes very faster from 1.3V to 1.6V. Then the voltage will increase very slowly to 1.8V. At the end of charging, the Ni-Cd battery will have a very small voltage drop about 0.01V to 0.05V. When the microcontroller has checked the voltage drop it will stop the charging immediately.

== Team management ==
[[File:图片7.jpg]]

== References ==
1] Park Hae-Woo. Han Chang-Seok Ni-MH battery charger with a compensatorforelectric vehicles [R] SAE 9604477, 1996
[2] Niggemann E .High performance nickel－metal hydride battery for electric and hybrid vehicles［Z］E VS-15.Bruxelles.1998.
[3] K.Hirakawa，A.Measuring and Analyzing Method for Battery Conditions Using a New Field Data Collection system，evsl17，2000.
[4] MAXIM.Datasheet：Stand-Alone.Switch-Mode Li+ Battery Charger，2001.
[5] Omagawa Takuya.Manufacture of Secondary Alkaline Batteries [P].JP 0353461.1991-07.
[6] ZHANGShuyun,SUNJiangbei,HUOZhiming. The serial port communication of the computer and single chip[J]. Chinese Science and Technology Information,2005 (10): 130-131.

Projects:2014s2-83 A Testing and Characterising Device for batteries of various chemistries

2015-06-03T02:18:18Z

A1643783: /* Team management */

File:图片7.jpg

2015-06-03T02:17:33Z

A1643783:

Projects:2014s2-83 A Testing and Characterising Device for batteries of various chemistries

2015-06-03T02:16:47Z

A1643783: /* Project result analysis */

Projects:2014s2-83 A Testing and Characterising Device for batteries of various chemistries

2015-06-03T02:14:52Z

A1643783: /* Project result analysis */

File:图片6.jpg

2015-06-03T02:13:40Z

A1643783:

File:图片5.jpg

2015-06-03T02:13:23Z

A1643783:

Projects:2014s2-83 A Testing and Characterising Device for batteries of various chemistries

2015-06-03T02:11:12Z

A1643783: /* Hardware Overview */

Projects:2014s2-83 A Testing and Characterising Device for batteries of various chemistries

2015-06-03T02:09:48Z

A1643783: /* Software Overview */

Projects:2014s2-83 A Testing and Characterising Device for batteries of various chemistries

2015-06-03T01:55:11Z

A1643783: /* Software Overview */

Projects:2014s2-83 A Testing and Characterising Device for batteries of various chemistries

2015-06-03T01:53:03Z

A1643783: /* Balanced circuit */

Projects:2014s2-83 A Testing and Characterising Device for batteries of various chemistries

2015-06-03T01:52:46Z

A1643783: /* Amplifier */

Projects:2014s2-83 A Testing and Characterising Device for batteries of various chemistries

2015-06-03T01:52:29Z

A1643783: /* Buck converter */

Projects:2014s2-83 A Testing and Characterising Device for batteries of various chemistries

2015-06-03T01:52:13Z

A1643783: /* Buck converter */

Projects:2014s2-83 A Testing and Characterising Device for batteries of various chemistries

2015-06-03T01:51:18Z

A1643783: /* Hardware Overview */

Projects:2014s2-83 A Testing and Characterising Device for batteries of various chemistries

2015-06-03T01:48:29Z

A1643783: /* Hardware Overview */

File:图片4.png

2015-06-03T01:42:55Z

A1643783:

File:图片3.png

2015-06-03T01:42:41Z

A1643783:

File:图片2.png

2015-06-03T01:35:09Z

A1643783:

File:图片1.png

2015-06-03T01:34:38Z

A1643783:

Projects:2014s2-83 A Testing and Characterising Device for batteries of various chemistries

2015-06-03T01:30:13Z

A1643783:

Projects:2014s2-83 A Testing and Characterising Device for batteries of various chemistries

2015-06-03T01:25:36Z

A1643783: Created page with "Contents 1. Project introduction 1.1 Project aims 1.2 Project overview 1.2.1 Hardware overview 1.2.2 Software overview 2. Project result analysis 3. Team management 4. Acknowl..."

Contents
1. Project introduction
1.1 Project aims
1.2 Project overview
1.2.1 Hardware overview
1.2.2 Software overview
2. Project result analysis
3. Team management
4. Acknowledgements
5. References

Help:Contents

2015-06-03T01:16:55Z

Contents
1. Project introduction
1.1 Project aims
1.2 Project overview
1.2.1 Hardware overview
1.2.2 Software overview
2. Project result analysis
3. Team management
4. Acknowledgements
5. References