Latifah Munirah Kamarudin
Thumbnail Image
Preferred name
Latifah Munirah Kamarudin
Official Name
Kamarudin, Latifah Munirah
Alternative Name
Kamarudin, Latifah Munirah
Kamarudin, Latifah M.
Kamarudin, L. M.
Kamarudin, Munirah L.
Kamarudin, L.
Main Affiliation
Scopus Author ID
57192974774
Researcher ID
G-8267-2016

Research Output

Filters
34
Reset filters

Settings
Now showing 1 - 10 of 34
  • Publication
    Rf-based moisture content determination in rice using machine learning techniques
    ( 2021-03-01)
    Azmi N.
    ;
    Latifah Munirah Kamarudin
    ;
    Ammar Zakaria
    ;
    Ndzi D.L.
    ;
    Mohd Hafiz Fazalul Rahiman
    ;
    Syed Muhammad Mamduh Syed Zakaria
    ;
    Latifah Mohamed
    Seasonal crops require reliable storage conditions to protect the yield once harvested. For long term storage, controlling the moisture content level in grains is challenging because existing moisture measuring techniques are time-consuming and laborious as measurements are carried out manually. The measurements are carried out using a sample and moisture may be unevenly distributed inside the silo/bin. Numerous studies have been conducted to measure the moisture content in grains utilising dielectric properties. To the best of authors’ knowledge, the utilisation of low-cost wireless technology operating in the 2.4 GHz and 915 MHz ISM bands such as Wireless Sensor Network (WSN) and Radio Frequency Identification (RFID) have not been widely investigated. This study focuses on the characterisation of 2.4 GHz Radio Frequency (RF) transceivers using ZigBee Standard and 868 to 915 MHz UHF RFID transceiver for moisture content classification and prediction using Artificial Neural Network (ANN) models. The Received Signal Strength Indicator (RSSI) from the wireless transceivers is used for moisture content prediction in rice. Four samples (2 kg of rice each) were conditioned to 10%, 15%, 20%, and 25% moisture contents. The RSSI from both systems were obtained and processed. The processed data is used as input to different ANNs models such as Support Vector Machine (SVM), K-Nearest Neighbour (KNN), Random Forest, and Multi-layer Perceptron (MLP). The results show that the Random Forest method with one input feature (RSSI_WSN) provides the highest accuracy of 87% compared to the other four models. All models show more than 98% accuracy when two input features (RSSI_WSN and RSSI_TAG2) are used. Hence, Random Forest is a reliable model that can be used to predict the moisture content level in rice as it gives a high accuracy even when only one input feature is used.
  • Publication
    Design and deployment of LoRaWAN smart streetlight for smart city
    ( 2024-02-08)
    Zakaria S.M.M.S.
    ;
    Ammar Zakaria
    ;
    Latifah Munirah Kamarudin
    ;
    Visvanathan R.
    ;
    Rahim Y.A.
    ;
    Kamarudin K.
    ;
    Azmi N.
    ;
    Mohammad N.S.
    Streetlights are one of the major contributors of a city's energy usage, creating a large carbon footprint especially for highly populated areas. Current streetlights are turned on and off based on fixed schedule or by light sensors. Previous works have suggested the dimming of streetlights during zero traffic conditions to reduce energy consumption. This requires a reliable and economical communication backbone to ensure minimal service disruption. This work presents the design and performance evaluation of LoRa-based smart streetlight controllers in an urban environment. The deployment was designed to provide stress test, simulate communication connectivity, maintenance routine, firmware test and environmental conditions. The setup may also be used for staff training purposes and demonstration. The results of this work may be used achieve the effective control method for power saving, system stability, robustness and long-term performance. The deployed system includes test controllers, nodes, application server, database, gateway server and visualization dashboard. The system design demonstrated low packet error rates of approximately 1% and command response time of less than 3s in real world conditions.
  • Publication
    A new method of rice moisture content determination using voxel weighting-based from radio tomography images
    ( 2021-06-01)
    Ramli N.A.M.
    ;
    Mohd Hafiz Fazalul Rahiman
    ;
    Latifah Munirah Kamarudin
    ;
    Latifah Mohamed
    ;
    Ammar Zakaria
    ;
    Anita Ahmad
    ;
    Rahim R.A.
    This manuscript presents a new method to monitor and localize the moisture distribution in a rice silo based on tomography images. Because the rice grain is naturally hygroscopic, the stored grains’ quality depends on their level of moisture content. Higher moisture content leads to fibre degradation, making the grains too frail and possibly milled. If the moisture is too low, the grains become brittle and are susceptible to higher breakage. At present, the single-point measurement method is unreliable because the moisture build-up inside the silo might be distributed unevenly. In addition, this method mostly applies gravimetric analysis, which is destructive. Thus, we proposed a radio tomographic imaging (RTI) system to address these problems. Four simulated phantom profiles at different percentages of moisture content were reconstructed using Newton’s One-Step Error Reconstruction and Tikhonov Regularization algorithms. This simulation study utilized the relationship between the maximum voxel weighting of the reconstructed RTI image and the percentage of moisture content. The outcomes demonstrated promising results, in which the weighting voxel linearly increased with the percentage of moisture content, with a correlation coefficient higher than 0.95 was obtained. Therefore, the results support the possibility of using the RTI approach for monitoring and localizing the moisture distribution inside the rice silo.
  • Publication
    Case study of LoRaWAN-based smart elements in urban environment
    ( 2024-02-08)
    Zakaria S.M.M.S.
    ;
    Ammar Zakaria
    ;
    Latifah Munirah Kamarudin
    ;
    Visvanathan R.
    ;
    Rahim Y.A.
    ;
    Azmi N.
    ;
    Elham M.F.
    Communication is one of the enablers for smart elements in a smart city. The ability of these smart elements to communicate with each other enables them to react intelligently to dynamically changing conditions. Most communication radios like Zigbee, BLE, and WiFi, among others, are short-ranged and while others such as 3G and 4G LTE, are power-hungry and subscription-based. While these protocols and communication modes work for certain applications, it carries two main limitations; difficulties in deploying IoT solutions in areas without cellular (GPRS, EDGE, 3G, LTE/4G) coverage and reduction in battery life. Thus, the future implementation of IoT and the connection of all kinds of "things"located in all kinds of places, needs a communication medium tailor-made for IoT which is low power, significantly long range, cheap, secure, and easy to deploy. This work presents the results of LoRaWAN coverage tests in Selangor Cyber Valley which is a greenfield development area where smart systems are designed into the blueprint. The data collected are during the early development phase with minimal buildings and foliage. The data demonstrates that the LoRaWAN covers a maximum radius of 2.49 km reliably with less than 10% packet loss. This strongly suggests that LoRaWAN is a reliable connection protocol for outdoor end-devices in urban environments. Future data collection after further developments may demonstrate the impact of buildings and foliage in urban environments on LoRaWAN.
  • Publication
    Adaptive threshold determination for efficient channel sensing in cognitive radio network using mobile sensors
    ( 2017-03-13)
    Mohammad Nayeem Morshed
    ;
    Sabira Khatun
    ;
    Latifah Munirah Kamarudin
    ;
    Syed Alwee Aljunid Syed Junid
    ;
    R Badlishah Ahmad
    ;
    Ammar Zakaria
    ;
    Moslem Fakir
    Spectrum saturation problem is a major issue in wireless communication systems all over the world. Huge number of users is joining each day to the existing fixed band frequency but the bandwidth is not increasing. These requirements demand for efficient and intelligent use of spectrum. To solve this issue, the Cognitive Radio (CR) is the best choice. Spectrum sensing of a wireless heterogeneous network is a fundamental issue to detect the presence of primary users' signals in CR networks. In order to protect primary users (PUs) from harmful interference, the spectrum sensing scheme is required to perform well even in low signal-to-noise ratio (SNR) environments. Meanwhile, the sensing period is usually required to be short enough so that secondary (unlicensed) users (SUs) can fully utilize the available spectrum. CR networks can be designed to manage the radio spectrum more efficiently by utilizing the spectrum holes in primary user's licensed frequency bands. In this paper, we have proposed an adaptive threshold detection method to detect presence of PU signal using free space path loss (FSPL) model in 2.4 GHz WLAN network. The model is designed for mobile sensors embedded in smartphones. The mobile sensors acts as SU while the existing WLAN network (channels) works as PU. The theoretical results show that the desired threshold range detection of mobile sensors mainly depends on the noise floor level of the location in consideration.
  • Publication
    Inline 3D Volumetric Measurement of Moisture Content in Rice Using Regression-Based ML of RF Tomographic Imaging
    ( 2022-01-01)
    Almaleeh A.A.
    ;
    Ammar Zakaria
    ;
    Latifah Munirah Kamarudin
    ;
    Mohd Hafiz Fazalul Rahiman
    ;
    Ndzi D.L.
    ;
    Ismail I.
    The moisture content of stored rice is dependent on the surrounding and environmental factors which in turn affect the quality and economic value of the grains. Therefore, the moisture content of grains needs to be measured frequently to ensure that optimum conditions that preserve their quality are maintained. The current state of the art for moisture measurement of rice in a silo is based on grab sampling or relies on single rod sensors placed randomly into the grain. The sensors that are currently used are very localized and are, therefore, unable to provide continuous measurement of the moisture distribution in the silo. To the authors’ knowledge, there is no commercially available 3D volumetric measurement system for rice moisture content in a silo. Hence, this paper presents results of work carried out using low-cost wireless devices that can be placed around the silo to measure changes in the moisture content of rice. This paper proposes a novel technique based on radio frequency tomographic imaging using low-cost wireless devices and regression-based machine learning to provide contactless non-destructive 3D volumetric moisture content distribution in stored rice grain. This proposed technique can detect multiple levels of localized moisture distributions in the silo with accuracies greater than or equal to 83.7%, depending on the size and shape of the sample under test. Unlike other approaches proposed in open literature or employed in the sector, the proposed system can be deployed to provide continuous monitoring of the moisture distribution in silos.
  • Publication
    An Experimental Study of Deep Learning Approach for Indoor Positioning System Using WI-FI System
    ( 2021-01-01)
    Sa’ahiry A.H.A.
    ;
    Abdul Halim Ismail
    ;
    Latifah Munirah Kamarudin
    ;
    Ammar Zakaria
    ;
    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
    Non-Contact Breathing Signal Classification Using Hybrid Scalogram Image Representation Feature
    ( 2022-01-01)
    Muhammad Husaini
    ;
    Latifah Munirah Kamarudin
    ;
    Nishizaki Hiromitsu
    ;
    Kamarudin I.K.
    ;
    Ibrahim M.A.
    ;
    Ammar Zakaria
    ;
    Toyoura M.
    ;
    Mao X.
    When monitoring human vital signs, breathing is one of the most critical physiological metrics. In areas with limited resources and a shortage of trained medical professionals, automated analysis of abnormal breathing patterns may prove advantageous to healthcare systems. In this paper, we implemented the architecture of five transfer learning models to classify individuals' breathing patterns using our proposed method which uses hybrid scalogram image-based features. We implemented the Sleep Breathing Detection Algorithm (SBDA) for extracting the actual breathing signals from ultra-wideband (UWB) radar for the pre-processing method. Later, the signals were converted to hybrid scalogram image-based representations before being classified using the VGG16, DenseNet, Xception, ResNet, and MobileNet models. The performance of the proposed method was validated using two other image representations: a standard image and a spectrogram image. The overall result showed that the proposed method obtained the highest classification accuracy on the test set for all pre-trained models.
      4
  • Publication
    Predictive Analysis of In-Vehicle Air Quality Monitoring System Using Deep Learning Technique
    ( 2022-10-01)
    Abdul Syafiq Abdull Sukor
    ;
    Cheik Goh Chew
    ;
    Latifah Munirah Kamarudin
    ;
    Mao X.
    ;
    Nishizaki H.
    ;
    Ammar Zakaria
    ;
    Syed Muhammad Mamduh Syed Zakaria
    In-vehicle air quality monitoring systems have been seen as promising paradigms for monitoring drivers’ conditions while they are driving. This is because some in-vehicle cabins contain pollutants that can cause drowsiness and fatigue to drivers. However, designing an efficient system that can predict in-vehicle air quality has challenges, due to the continuous variation in parameters in cabin environments. This paper presents a new approach, using deep learning techniques that can deal with the varying parameters inside the vehicle environment. In this case, two deep learning models, namely Long-short Term Memory (LSTM) and Gated Recurrent Unit (GRU) are applied to classify and predict the air quality using time-series data collected from the built-in sensor hardware. Both are compared with conventional methods of machine learning models, including Support Vector Regression (SVR) and Multi-layer Perceptron (MLP). The results show that GRU has an excellent prediction performance with the highest coefficient of determination value (R2) of 0.97.
      2
  • Publication
    Non-Contact Breathing Signal Classification Using Hybrid Scalogram Image Representation Feature
    ( 2022-01-01)
    Muhammad Husaini
    ;
    Latifah Munirah Kamarudin
    ;
    Nishizaki H.
    ;
    Kamarudin I.K.
    ;
    Ibrahim M.A.
    ;
    Ammar Zakaria
    ;
    Toyoura M.
    ;
    Mao X.
    When monitoring human vital signs, breathing is one of the most critical physiological metrics. In areas with limited resources and a shortage of trained medical professionals, automated analysis of abnormal breathing patterns may prove advantageous to healthcare systems. In this paper, we implemented the architecture of five transfer learning models to classify individuals' breathing patterns using our proposed method which uses hybrid scalogram image-based features. We implemented the Sleep Breathing Detection Algorithm (SBDA) for extracting the actual breathing signals from ultra-wideband (UWB) radar for the pre-processing method. Later, the signals were converted to hybrid scalogram image-based representations before being classified using the VGG16, DenseNet, Xception, ResNet, and MobileNet models. The performance of the proposed method was validated using two other image representations: a standard image and a spectrogram image. The overall result showed that the proposed method obtained the highest classification accuracy on the test set for all pre-trained models.
      1