Allan Melvin Andrew

Classifying Sources Influencing Indoor Air Quality (IAQ) Using Artificial Neural Network (ANN)

Monitoring indoor air quality (IAQ) is deemed important nowadays. A sophisticated IAQ monitoring system which could classify the source influencing the IAQ is definitely going to be very helpful to the users. Therefore, in this paper, an IAQ monitoring system has been proposed with a newly added feature which enables the system to identify the sources influencing the level of IAQ. In order to achieve this, the data collected has been trained with artificial neural network or ANN—a proven method for pattern recognition. Basically, the proposed system consists of sensor module cloud (SMC), base station and service-oriented client. The SMC contain collections of sensor modules that measure the air quality data and transmit the captured data to base station through wireless network. The IAQ monitoring system is also equipped with IAQ Index and thermal comfort index which could tell the users about the room’s conditions. The results showed that the system is able to measure the level of air quality and successfully classify the sources influencing IAQ in various environments like ambient air, chemical presence, fragrance presence, foods and beverages and human activity.

Multi-Stage Feature Selection Based Intelligent Classifier for Classification of Incipient Stage Fire in Building

In this study, an early fire detection algorithm has been proposed based on low cost array sensing system, utilising off- the shelf gas sensors, dust particles and ambient sensors such as temperature and humidity sensor. The odour or “smellprint” emanated from various fire sources and building construction materials at early stage are measured. For this purpose, odour profile data from five common fire sources and three common building construction materials were used to develop the classification model. Normalised feature extractions of the smell print data were performed before subjected to prediction classifier. These features represent the odour signals in the time domain. The obtained features undergo the proposed multi-stage feature selection technique and lastly, further reduced by Principal Component Analysis (PCA), a dimension reduction technique. The hybrid PCA-PNN based approach has been applied on different datasets from in-house developed system and the portable electronic nose unit. Experimental classification results show that the dimension reduction process performed by PCA has improved the classification accuracy and provided high reliability, regardless of ambient temperature and humidity variation, baseline sensor drift, the different gas concentration level and exposure towards different heating temperature range.

Vehicle noise comfort level indication: A psychoacoustic approach

Nowadays, the studies and researches related to the improvement of the passenger comfort in the car are carried out vigorously. The comfort in the car interior is already become a need for the passengers and the buyers. Due to high competition in car industries, all the car manufacturers are concentrating in improving the interior noise comfort of the car. Vehicle Noise Comfort Index (VNCI) has been developed recently to evaluate the sound characteristics of passenger cars. VNCI indicates the interior vehicle noise comfort using a numeric scale from 1 to 10. Most of the researches are relating the vehicle interior sound quality to psychoacoustics sound metrics such as loudness and sharpness for the frequency between 20 Hz to 20 kHz. In this present paper, a vehicle comfort level indication is proposed to detect the comfort level in cars using artificial neural network. Determination of vehicle comfort is important because continuous exposure to the noise and vibration leads to health problems for the driver and passengers. The database of sound samples from 15 local cars is used. The sound samples are taken from two states, while the car is in stationary condition and while it is moving at a constant speed. Features such as the psychoacoustics criterions are extracted from the signals. The correlation between the subjective and the objective evaluation is also tested. The relationship between the VNCI and the sound metrics is modelled using a feed-forward neural network trained by back-propagation algorithm.

Analysis of feature selection with Probabilistic Neural Network (PNN) to classify sources influencing indoor air quality

There are various sources influencing indoor air quality (IAQ) which could emit dangerous gases such as carbon monoxide (CO), carbon dioxide (CO2), ozone (O3) and particulate matter. These gases are usually safe for us to breathe in if they are emitted in safe quantity but if the amount of these gases exceeded the safe level, they might be hazardous to human being especially children and people with asthmatic problem. Therefore, a smart indoor air quality monitoring system (IAQMS) is needed that able to tell the occupants about which sources that trigger the indoor air pollution. In this project, an IAQMS that able to classify sources influencing IAQ has been developed. This IAQMS applies a classification method based on Probabilistic Neural Network (PNN). It is used to classify the sources of indoor air pollution based on five conditions: ambient air, human activity, presence of chemical products, presence of food and beverage, and presence of fragrance. In order to get good and best classification accur...

Classification of Domestic Burning Smell using Covariance k- Nearest Neighbour Algorithm for Early Fire Detection Application

Fire is one of the most common hazards in households. It is the fifth leading unintentional cause of injury and death, behind motor vehicle crashes, falls, poisoning by solids or liquids, and drowning. It also ranks as the first cause of death for children under the age of 15 at home. Roughly, 80 percent of all fire deaths occur in places where people sleep, such as in homes, dormitories, barracks, or hotels. 74% of the deaths result from fires in homes with no smoke alarms or no working smoke alarms while surveys report that 96% of all homes have at least one smoke alarm. Nearly all home and other building fires are preventable. No fire is inevitable. Determination of burning smell is important because it can help in early fire detection and prevention. This preliminary study discusses the development of a fire sensing system that is not only capable of detecting fire in its early stage but also of classifying the fire based on the smell of the smoke in the environment. A domestic burning smell classification system for early fire detection application has been proposed using new covariance k-nearest neighbour (Ck-NN) algorithm. The experiments were performed on recorded smell samples from combustion of ten different commonly available domestic odour sources, including candle, joss sticks, air freshener, mosquito coil, newspaper, card board, plastic materials, Styrofoam and wood. All the experiments were done in a test chamber with humidity and temperature sensors. Portable Electronic Nose (PEN3) from AirSense Analytics is used as the measurement device. The smell source is placed 0.3m from the PEN3 and the time-series signal is measured for two minutes. The odour metrics consist of 66000 odour samples are modelled using Ck-NN algorithm. It is found that the average mean classification accuracy for the model is 99.63%.

Classification of interior noise comfort level of proton model cars using artificial neural network

Vehicle Noise Comfort Index (VNCI) has been developed recently to evaluate the sound characteristics of passenger cars. VNCI indicates the interior vehicle noise comfort using a numeric scale from 1 to 10. Determination of vehicle comfort is important because continuous exposure to the noise and vibration leads to health problems for the driver and passengers. In this paper, a vehicle comfort level classification system has been proposed to detect the comfort level in cars using artificial neural network. The database of sound samples from 30 local cars is used. In the stationary condition, the sound pressure level is measured at 1300 RPM, 2000 RPM and 3000 RPM. In the moving condition, the sound is recorded while the car is moving at 30 km/h up to 110 km/h. Subjective test is conducted to find the jurys evaluation for the specific sound sample. The correlation between the subjective and the objective evaluation is also tested. The relationship between the subjective results and the sound metrics is modelled using feedforwardtrained by backpropagation algorithm, Elman and Probabilistic neural network.

Development of indoor environmental index: Air quality index and thermal comfort index

In this paper, index for indoor air quality (also known as IAQI) and thermal comfort index (TCI) have been developed. The IAQI was actually modified from previous outdoor air quality index (AQI) designed by the United States Environmental Protection Agency (US EPA). In order to measure the index, a real-time monitoring system to monitor indoor air quality level was developed. The proposed system consists of three parts: sensor module cloud, base station and service-oriented client. The sensor module cloud (SMC) contains collections of sensor modules that measures the air quality data and transmit the captured data to base station through wireless. Each sensor modules includes an integrated sensor array that can measure indoor air parameters like Carbon Dioxide, Carbon Monoxide, Ozone, Nitrogen Dioxide, Oxygen, Volatile Organic Compound and Particulate Matter. Temperature and humidity were also being measured in order to determine comfort condition in indoor environment. The result from several experiments...

Probabilistic neural network based olfactory classification for household burning in early fire detection application

Determination of burning smell is important because it can help in early fire detection and prevention. In this paper, a household burning smell classification system for early fire detection application has been proposed using Probabilistic Neural Network (PNN) and PCA analysis. The experiments were performed on recorded smell samples from combustion of ten different commonly available household, including candle, joss sticks, air freshener, mosquito coil, newspaper, card board, plastic materials, Styrofoam and wood. All the experiments were done in a test chamber with humidity and temperature sensors. Portable Electronic Nose (PEN3) from Airsense Analytics is used as the measurement device. The smell source is placed 0.3m from the PEN3 and the time-series signal is measured for two minutes. The odour metrics is modelled using Probabilistic Neural Network. It is found that the average classification accuracy for the model is 99.62%.

Comparison of Mechanical Properties of Polypropylene/Acrylonitrile Butadiene Rubber/Rice Husk Powder Composites Modified with Silane and Acetic Anhydride Compound

Polypropylene (PP)/Acrylonitrile butadiene rubber (NBRr)/rice husk powder (RHP) composites was fabricated with silane and acetic anhydride treatment agent. The in-situ formed RHP filled PP/NBRr composites were prepared by melt mixing technique using Haake internal mixer at 180 °C. The tensile properties of the both treatment methods were invesigated with Instron mechanical analysis. The results indicated that acetic anhydride treatment was found to exhibit better mechanical properties for RHP filled PP/NBRr composites. Good compatibility and stronger interaction between anhydride moieties with PP/NBRr was resulted.