- 10:30 SysMART Indoor Services: A System of Smart and Connected Supermarkets
Smart gadgets are being embedded almost in every aspect of our lives. From smart cities to smart watches, modern industries are increasingly supporting the Internet-of- Things (IoT). SysMART aims at making supermarkets smart, productive, and with a touch of modern lifestyle. While similar implementations to improve the shopping experience exists, they tend mainly to replace the shopping activity at the store with online shopping. Although online shopping reduces time and effort, it deprives customers from enjoying the experience. SysMART relies on cutting-edge devices and technology to simplify and reduce the time required during grocery shopping inside the supermarket. In addition, the system monitors and maintains perishable products in good condition suitable for human consumption. SysMART is built using state-of-the-art technologies that support rapid prototyping and precision data acquisition. The selected development environment is LabVIEW with its world-class interfacing libraries. The paper comprises a detailed system description, development strategy, interface design, software engineering, and a thorough analysis and evaluation.
Presenter bio: Omar Raad received his B.E. in Computer Engineering from the American University of Kuwait (AUK), Salmiya, Kuwait in 2016.
Since graduation, he is working as a research assistant in AUK on various topics including Chaos theory (Lorenz) with FPGA and Particle Swarm Optimization (PSO) on GPUs. During his undergraduate years, he worked as a teacher/lab assistant for Embedded Systems (FPGA & VHDL) and Electric Circuits courses. Additionally, he implemented several projects such as Secure Hash on a Chip (SHA1 on FPGA), Arcduino (Arduino based Arcade Video game) and SysMART.
His main interests are robotics and embedded systems.
- 10:48 Remote Condition Monitoring of Elevator's Vibration and Acoustics Parameters for Optimised Maintenance Using IoT Technology
Remote Condition Monitoring (RCM) of machines deploys condition monitoring of machine conditions with reduced manning to enhance proactive maintenance. Vibration and acoustics parameter of the machine helps in diagnosing the condition of the machine for early detection of faults in the system. This paper employs a Remote Condition Monitoring approach of two elevator parameters, vibration and acoustics, using an Internet of Things (IoT) device for Remote Data Acquisition (RDA) and Remote Fault Indication (RFI). A remote monitoring set-up was developed comprising of augmented sensors networked connections and Arduino Yun microcontroller, installed on the elevator system to remotely monitor the deterioration in the working condition. The set-up was configured to monitor the conditions online, through email application service. The data from the email were analyzed and notifications generated at the severity level of each parameter. The result showed that, vibration and acoustics parameters are complimentary in fault diagnosis, and that RCM enables faster repair and maintenance decision and prevent the catastrophic breakdown of the machine.
- 11:06 Toward Understanding Hidden Patterns in Human Mobility Using Wi-Fi
A reliable model for identifying spatial-temporal regularities of human dynamics is rewarding in many applications such as computer networking and mobile communication. These hidden patterns are inherited from our repeating behaviours with respect to three primary contexts of time, space, and social environments. Thus, selecting a suitable source of sensor data that is scalable, multidimensional, and social network illustrative can enable us to develop a reliable human mobility model and potentially prediction system. We first demonstrate that Wi-Fi network scans collected from mobile phone devices share a similar set of characteristics to real-world large-scale networks. One particularly is the long-tailed property of node degree distribution of projection networks. This feature can be interpreted as the robustness of this system against structural changes of removing a set of nodes or connections. Later, we transform Wi-Fi events into a tabular data format containing different time granularities and location-tagged information. However, the new data is sparse and difficult to analyze. Thus, we reduce the dimensionality of data by extracting its structural patterns using principal component of new features. Our analysis shows that we can reconstruct original data with more than 90% accuracy using only a set of top eigenvectors with the quarter size of original features, while the outliers with noisy data are filtered out. Our proposed technique help to visualize users similarities, behaviour dynamics, and reduce computation complexity of further analysis.
Presenter bio: Ali Farrokhtala received the B.S. degree in information technology from Azad University, Tehran, Iran, in 2011 and the M.S degree in Computer Science from University Technology Malaysia, Skudai, Malaysia, in 2013. He is currently pursuing the Ph.D. degree in computer science at Memorial University, St. John's, Canada.
He has been Research with the WineMocol team, computer science department of Memorial University, St. John's, Canada. His research interest includes the study of human behavior and mobility using techno-social systems and mobile phones, social network study with respect the time dimension, and the development of delay-tolerant network framework among mobile phone users in a packet switched network.
- 11:24 Observing Friendship Patterns Through Smart Phone Radios
Social network can rebuild human society and analyze it as well. Social interactions and activities increase dramatically. A common way to construct networks is to generalize a single dataset, such as location and proximity data. Due to restrictions on location-based services and the telecommunication radio range, it is paramount to find a universal method obtaining a highly accurate network to represent social society. We design a combined scheme with multiple datasets in order to settle this problem. Moreover, structures of networks vary with different definitions of nodes and edges. The relationships between human mobility and human relationship were mainly studied so far. In this study, the effect of friendship on human social interactions and activities is also analyzed. We show the proposed combined network model provides a highly efficient way to construct social networks. We evaluate the performance of the model with centralities and coefficients. Finally, the relationships among networks are shown as well.
- 11:42 An IoT-Based Data Collection Platform for Situational Awareness-Centric Microgrids
This paper presents a data collection architecture for situational awareness (SA)-centric microgrids. A prototype has been developed which can provide enormous data collection capabilities from smart meters, in order to realise an adequate SA level in microgrids. A communication framework based on the publish-subscribe model is also proposed and implemented for the communication layer of the SA using the message queuing telemetry transport (MQTT) protocol over two different physical (PHY) layers (i.e., WiFi and GPRS). An Internet of things (IoT) platform (i.e., Thingsboard) is used for the SA visualisation with a customised dashboard. It is shown by using the developed system, an adequate level of SA can be achieved with a minimum installation and hardware cost. Moreover, the Modbus protocol over the RS-485 is applied for the smart meter communication.
- 12:00 Assessment of Amplified Parkinsonian Speech Quality Using Deep Learning
In this paper, deep neural networks (DNNs) are applied to features extracted from Parkinsonian speech recordings to predict their perceived quality. This procedure was also used to benchmark the electroacoustic characteristics of speech amplifiers used by people impaired with Parkinson Disease (PD). Speech recordings were obtained 11 PD subjects and 10 normal controls, with and without the assistance of 7 different speech amplifiers, and their quality was assessed subjectively by normal hearing listeners. Mel-frequency and Gammatone=frequency cepstral coefficients (MFCCs and GFCCs respectively) and their first order derivatives were extracted as features, and given as input to the DNN. Two optimizers are used to train the neural network, namely stochastic gradient descent (SGD) and Adam optimizers. The paper also shows the effect of feature reduction in enhancing the performance of the objective metrics. Experimental results showed that the reduced model of GFCC outperforms other objective metrics in terms of correlation with the subjective measures.