Now showing 1 - 10 of 23
  • Publication
    An Experimental Study of Deep Learning Approach for Indoor Positioning System Using WI-FI System
    ( 2021-01-01)
    Sa’ahiry A.H.A.
    ;
    ; ; ;
    Nishizaki H.
    Global navigation satellite system (GNNS) is known for its capability to detect the whereabouts of any desired target such as vehicles and places. However, there is some disadvantage of these technologies as it can only get a precise location outside of the building because as the signal goes to indoor building, the signal becomes weaker due to attenuation. The Wi-Fi systems are the best alternative to GNNS in an indoor environment since the architecture is massively deployed in many recent buildings. However, Wi-Fi also has its disadvantage where its signal is non-linear due to various factors such as multipath and signal blockage indoors thus limiting the system accuracy. In this paper, a deep learning approach with standalone Wi-Fi technologies will be used to have a precise indoor positioning by using the fingerprinting method. The overall result shows that the average distance error between actual and estimated location is 20-cm and the highest error is 62-cm in an experimental area of 180-cm and 120-cm in x and y axis. This shows that deep learning is a possible method to have accurate and precise indoor positioning.
      1
  • Publication
    Robot Face and Its Integration to the Mobile Robot for Wireless Signal Collection in the Fingerprinting-Based Indoor Positioning System
    The wireless data collection for instance the Received Signal Strength (RSS) of the Wireless Fidelity (Wi-Fi) remained unfavourable in the Indoor Positioning System utilizing the signal fingerprinting approach. This is because the enormous sampling time and routines works making it tedious human labour. To alleviate this issue, we propose to use a robot for wireless data collection. The robot, named 'ICSiBOT' is a service robot with multiple purpose such as assisting human in daily lives, guest or hospitality robot and man others. This paper mainly describes the ICSiBOT robot face with speech recognition technology and the integration of the robot face to the motion controller. The experimental was conducted to see the correlation between the synthesized instructions from the speech in terms of distance need to be travelled i.e., the location for wireless signal collection and translate them into actual distance travelled. The results showed that the robot is able to travel to the specific distance as instructed to the robot face.
      1
  • Publication
    Analysis of WiFi Spatio-Temporal Data for Organic Fingerprinting-based Indoor Positioning System
    The mobile robot navigation is the next huge topic after positioning utilizing fingerprinting-based Wireless Positioning System (WPS). Many of recent works does not discuss this topic yet since many open problems in positioning topic are not yet solved, for instance the issues on multi-devices heterogeneity, instability of WiFi signals, granularity problems in grid-based indoor environment and many others. However, we anticipate that both positioning and navigation works must run in parallel so that the succession are guaranteed. This paper describes the analysis of spatio-temporal data of the signal obtained from the WiFi Access Point. Initial results suggest that the difference between transmitter heights have an effect on the spatio-temporal data while the handover of maximum signal strengths is inherent when three WiFi APs are used.
      1
  • Publication
    Determination of blind spot zone for motorcycles
    The problem of the blind spot zone (BSZ) for motorcycles is common, as it causes many accidents that occur between motorcycles and cars, or motorcycles with other vehicles. The problem of BSZ is occurring for many reasons, such as if the motorcyclist wants to change the lane or manoeuvre or turn without realizing the presence of other vehicle which may cause a terrible collision and leads to casualties, either because of darkness, the full dependence on side mirrors that give a limited scope of vision, or due to a malfunction in the front lights of the car that prevented the motorcyclists from recognizing it. However there were limited research on identifation of BSZ for motorcycle, even though most vehicle accidents in Malaysia involved motorcycles. This paper discusses the initial works on the identification of BSZ for motorcyles. Three types of motorcycles were used to determine the BSZ using grid-based technique. From the data collected, the BSZ was identified for the motorcycles.
      2
  • Publication
    A Device-to-Device (D2D) Communication between Mobile Robots using Wireless Communication Protocol in Dynamic Environments
    ( 2024-03-11)
    Sarhan M.A.H.
    ;
    Hashim M.S.M.
    ;
    ; ; ; ;
    Othman S.M.
    ;
    Kanafiah S.N.A.M.
    ;
    Mobile robots must have the ability to guarantee safety for operation in a dynamic environment and close to other moving objects. There are many research had been conducted to make the robot safer by utilizing sensors and big data technology to make the mobile robot able to navigate autonomously and intelligently. One of the key elements in autonomous robots is communication between robots. In this paper, device-to-device (D2D) technology has been used to develop communication between robots. To establish the algorithm for D2D communications, radio frequency (RF) used as communication protocols that can perform D2D communication in real-time applications. The performance of D2D communication was then be assessed in terms of distance and latency. RF transceiver module has been mounted on the robot with Arduino to allow communication between mobile robot to other mobile robots in order to transfer data from robot's sensors to the other mobile robots. By utilizing the gathered information and data, the robot can assess its surroundings and predict the movement of other robots to avoid collisions between robots. The results show that the RF transceiver module is capable to send and receive data between two robots with latency up to 4.865s. It is envisaged that the proposed module can be very useful for developing D2D communication between robots to operate in dynamic environments.
  • Publication
    Numerical evaluation of aluminium 6026-T9 fracture toughness
    Fracture is the separation of an object into two or more pieces caused by crack growth under the action of applied stress. There are many different methods for fracture evaluation has been made but still lacks information on properties of Aluminium 6026-T9. Aluminium 6026 is non-toxic since it does not contain Tin (Sn) and features a great corrosion resistance. This study focuses on the mechanical properties and fracture toughness of Aluminium 6026-T9. The material is cut and shaped into dog-bone specimens by referring the ASTM E8 and was eventually undergoing a tensile test to evaluate the mechanical properties. A linear elastic analysis of three different crack characteristics which are single edge crack, double edge crack and center crack were performed in Mode I analysis to evaluate its fracture toughness. The stress intensity factor (SIF) value near the crack tip obtained from the simulation process were then compared with analytical value and had been discussed. The percentage of error found that the numerical and analytical values are closed to each other.
      1
  • Publication
    An IoT Agricultural System for Harumanis Farm
    Internet of Things (IoT) is a revolutionary technology that represents the future of communication and computing. The field of IoT implementation is vast and can be applied in every field. This project is about to develop an IoT system for Harumanis Farm as agriculture is becoming an essential growing sector throughout the world due to the increasing population. The major challenge in the Harumanis sector is to improve the productivity and quality of Harumanis without continuous manual monitoring. IoT improves crop management, cost-effectiveness, crop monitoring and also improves the quality and quantity of the crop. This IoT system completes with several sensors to monitor the Harumanis farm, such as temperature and humidity sensor, pH level sensor, soil moisture sensor, also nitrogen, phosphorous, and potassium (NPK) sensor. The system is a simple IoT architecture where sensors collect information and send it over the Wi-Fi network to the mobile applications.
      4
  • Publication
    Effect of Sample Sizes in Fingerprinting Database for Wi-Fi System
    Indoor positioning system has been an essential work to substitute the Global Positioning System (GPS). GPS utilizing Global Navigation Satellite Systems (GNSS) cannot provide an accurate positioning in the indoor due to the multipath effect and shadow fading. Fingerprinting method with Wi-Fi technology is a promising system to solve this issue. However, there are several problems with the fingerprinting method. The fingerprinting database collected has different sample sizes where the previous researcher does not indicate any standard for the sample size to be used. In this paper, the effect of the sample sizes in fingerprinting database for Wi-Fi technology has been discussed deeply. The statistical analyzation for different sample sizes has been analyzed. Furthermore, two methods which are K- Nearest Neighbor (KNN) and Deep Neural Network (DNN) are being used to examine the effect of the sample sizes in term of accuracy and distance error. The discussion in this paper will contribute to the better sample size selection depending on the method taken by the user. The result shows that sample sizes are an important metrics in developing the indoor positioning system as it effects the result of the location estimation.
      1
  • Publication
    Short Range Radio Frequency (RF) Data Acquisition Unit for Agricultural Product Monitoring System
    ( 2024-01-01)
    Shatir S.M.N.S.
    ;
    Elmi A.B.
    ;
    Akhtar M.N.
    ;
    Abdullah M.N.
    ;
    This research emphasized on the experimentation performed on the 2.4 Ghz radio frequency (RF) module, utilized on Standstill Monitoring System (SMS), to discover the factors hindering the capabilities of the RF range and data stability in plantation environment, then proposed a signal enhancement technique. The architecture of SMS consists of sensor modules such as temperature, humidity, soil moisture and soil nutrition sensor to analyze as well as monitor real-time data on agriculture parameters through an IoT dashboard. The experiments were carried out, where the transmitter (Tx) was placed at the three ground stations with three different surrounding condition which is no obstruction, mild obstructions and full obstructions. The receiver (Rx) module was moved away from the ground station and transmission status was monitored. Findings showed that the transmission range without no obstruction is 70 m, with partial blockage is 50 m and total blockage is 10 m. By applying signal enhancement method which is implementing capacitor and breakout board, the range has been boosted to 350 m, 320 m and 160 m respectively. With this findings, wireless communication waypoint can be plotted out at a Harumanis plantation which allows farmers to supervise their plantation at distance.
      1
  • Publication
    The Characterization of J-Integral for Elastic-Plastic Crack Growth Evaluation using Finite Element Analysis
    J-integral is a fracture mechanic parameter that can be used to characterize elastic-plastic fracture mechanic (EPFM) behavior. The path independent characteristic in J-integral is proposed by Rice [1], and it is widely used in a lot of research. Another approach is the load-displacement approach, where the J-integral is calculated by the area under the load-displacement curve. However, the validity of the J-integral value by load-displacement approach is yet to be confirmed. This paper is aimed to investigate the effect of crack length ratio of CT specimen to J-integral value by two approaches: path-integral approach and load-displacement approach. Finite element analysis of compact tension (CT) model with crack length ratio a/W between 0.2 to 0.5 was carried out under displacement δ between 0.2 to 1.0 mm using ANSYS parametric design language (APDL). The J value by path integral approach, Jpath is compared to the value calculated from load-displacement approach, Jp-d. It was found that path independency occurs for J value evaluated from path integral approach. A correction factor needs to be introduced since the load-displacement approach cannot be used for shallow crack cases
      1