Shaharil Mad Saad

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.

Method to convert Kinect's 3D depth data to a 2D map for indoor SLAM

Mobile robotics has been strongly linked to localization and mapping especially for navigation purpose. A robot needs a sensor to see objects around it, avoid them and also map the surrounding area. The use of 1D and 2D proximity sensors such as ultrasonic sensor, sonar and laser range finder for area mapping is believed to be less effective since they do not provide information in Y or Z (horizontal and vertical) direction. The robot may miss an object due to its shape and position; thus increasing the risk of collision as well as inaccurate map. In this paper, a 3D visual device particularly Microsoft Kinect was used to perform area mapping. The 3D depth data from the devices depth sensor was retrieved and converted into 2D map using the presented method. A Graphical User Interface (GUI) was also implemented on the base station to depict the real-time map. It was found that the method applied has successfully mapped the potentially missing objects when using 1D or 2D sensor. The convincing results shown in this paper suggest that the Kinect is suitable for indoor SLAM application given that the devices limitations are solved.

Indoor air quality monitoring system using wireless sensor network (WSN) with web interface

Indoor air quality (IAQ) is a term that describes the air quality of the building occupants. IAQ can be influenced by physical factors like dust particles, chemical or gaseous pollutants (including carbon dioxide, carbon monoxide and volatile organic compounds) and biological factors like molds and bacteria growth which largely depend on temperature and humidity condition of a room. These kinds of pollutants can induce a bad health effects to building occupants. In this study, a web-based system for monitoring indoor air quality is presented. The system has been developed to monitor the environmental parameters of air quality like gaseous pollutants, particulate matter, temperature and humidity that can affect the occupants comfort, health and indoor work environment if not properly maintained. Generally, the system consists of a desktop computer acting as base station, an array of metal oxide gas sensor, temperature and humidity sensor, particle dust sensor and wireless sensor network (WSN) node as a wireless transmitter. The measured data from sensors are sent to base station via WSN node. The computer will log the collected data using a self-developed server program which can be accessed through the web.

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.

A real-time greenhouse monitoring system for mango with Wireless Sensor Network (WSN)

Harumanis or its scientific name as Mangifera indica is a popular mango in Malaysia due to its unique aroma and taste, despite its expensive price. The high demand for this mango and its potential in export has been the reason why this tropical fruit being a national agenda for the Malaysian government to classify it as the specialty fruit from Perlis (smallest state in Malaysia). As the sole university in Perlis, University of Malaysia Perlis (UniMAP) has taken the initiative to develop greenhouse specifically for Harumanis mango. To support this, a real-time greenhouse monitoring system has been proposed. The system was developed based on Wireless Sensor Networks technology which consists of three parts: sensing module, radio communication module and gateway module. This system is able to provide real time monitoring of the important factors in plant growth such as the carbon dioxide, temperature, humidity level in the greenhouse. The performance result shows that the temperature inside the greenhouse is slightly higher compared to the open field; which meets the crop requirements. At night, the greenhouse microclimate drops and equilibrates to the surrounding temperature and humidity. This condition ensures good flowering and fruiting of sweet and juicy mangoes.

Flexible and autonomous integrated system for characterizing metal oxide gas sensor response in dynamic environment

Characterization and calibration of gas sensor is a complex problem due to the dynamic behavior of gases and the limitations of current technology. This article reports a flexible, robust, and autonomous integrated system that is able to perform characterization on metal oxide-based gas sensors in dynamic environments. The system controls the concentration and flow of the relevant gases into the gas chamber and simultaneously measuring the sensor response. This feature allows the characterization of the sensor under continuous dynamic flow of gases similar to conditions on a robot or flow pipes. Several experiments have been performed on the system using hydrogen sulfide. The results provide information on the general characteristics of the sensor as well as its sensitivity. The noise levels were studied with different reference voltages. Overall, the results verify that the system is reliable and able to produce repeatable measurements.

Implementation of index for real-time monitoring indoor air quality system

Indoor air quality is a rising issue these days. People are becoming are of the importance of indoor air quality. This paper further advances the technology for indoor air quality surveillance by adding an index feature to it. The index feature, accompanied with real-time monitoring system is very useful in giving the real-time alert to the users on the conditions of the current indoor air quality. This index is very handy because human beings ability to detect the changes in the air quality is limited while the changes in the air quality may be rapid. The index helps the users to recognize the conditions of the air instantly by giving four signals, good, normal, unhealthy and hazardous. The index is developed based on the index used in the outside environment but by emphasizing on the internal air quality elements.

Braitenberg swarm vehicles for odour plume tracking in laminar airflow

This paper presents an algorithm to trace an odour plume using swarm robots in laminar airflow. The algorithm proposed here aims to bridge the gap between single and multiple element systems by mimicking and enhancing biologically derived strategies for odor plume tracking. Simulations were carried out on Webots to verify the potential of the algorithm. A simple gas sensor model was introduced to mimic the response of a real metal oxide sensor in the simulation. A gas sensor model was introduced based on the response of metal oxide sensor (MOS) to closely mimic and provide real environment condition. Different weightage configurations of the gas sensor, kg and wind sensor, kw are compared to find its effects on the performance and behavior of the purposed algorithm. It was found that robots separated from the swarm can still perform the plume tracking task. Also, multiple entity systems show an increase in performance compared to single entity robots.

Odour and Hazardous Gas Monitoring System for Swiftlet Farming Using Wireless Sensor Network (wsn)

Odour and Hazardous Gas Monitoring System for Swiftlet Farming using Wireless Sensor Network (WSN) Syed M. Mamduh*, Ali Y. Md. Shakaff, Shaharil M. Saad, Kamarulzaman Kamarudin, Latifah M. Kamarudin, Ammar Zakaria, H. Kamarudin, A. M. M. Ezanuddin, Fathinul S.A. Sa’ad,, W.M. Nooriman, Abu H. Abdullah Center of Excellence for Advanced Sensor Technology (CEASTech), Universiti Malaysia Perlis (UniMAP), Pusat Pengajian Jejawi 2, Taman Muhibah, Jalan Jejawi-Permatang, 02600, Perlis, Malaysia ceastech@unimap.edu.my

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...