Muhammad Imran Ahmad
Thumbnail Image
Preferred name
Muhammad Imran Ahmad
Official Name
Muhammad Imran, Ahmad
Alternative Name
Ahmad, Muhammad Imran
Ahmad, M. I.
Imran Ahmad, Muhammad
Ahmad, Muhamad Imran
Main Affiliation
Scopus Author ID
57214845678
Researcher ID
GBE-1471-2022

Research Output

Filters

2
20
Reset filters

Settings
Now showing 1 - 10 of 20
  • Publication
    Optimizing ant colony system algorithm with rule-based data classification for smart aquaculture
    ( 2024)
    Mohd Mizan Munif
    ;
    Husna Jamal Abdul Nasir
    ;
    Muhammad Imran Ahmad
    <span>Aquaculture is one of many industries where the use of artificial intelligence (AI) techniques has increased dramatically in recent years. Internet of things (IoT), AI, and big data are just a few of the technologies being used in smart aquaculture to increase productivity, efficiency, and system sustainability of aquaculture systems. Data classification, which involves finding patterns and relationships in huge datasets, is one of the most important tasks in smart aquaculture. The ant colony system (ACS) has been used to solve a number of optimization issues, including data classification. To provide a more practical and successful solution, this study proposes an improved ACS algorithm for rule-based data classification in smart aquaculture. The proposed algorithm combines the advantages of ACS and rule-based classification to optimize the number of rules and accuracy. The experimental results showed that the proposed algorithm outperformed the traditional AntMiner algorithm in terms of the number of rules and accuracy. The improved pheromone update technique could potentially increase data classification accuracy and convergence in smart aquaculture systems.</span>
  • Publication
    Comparison between machine learning classifier based on face recognition
    (IEEE, 2023)
    Ibrahim Mahmood Rashid Al-Bakri
    ;
    Muhammad Imran Ahmad
    ;
    Mohd Nazrin Md Isa
    ;
    Mustafa Zuhaer Nayef Al-Dabagh
    With face recognition, machine learning is one of the computer sciences fields that is getting bigger the quickest. The goal of this study is to give a basic overview of machine learning and the algorithmic paradigms it provides. The study gives a detailed explanation of the basic ideas behind machine learning and the math that turns these ideas into methodologies that can be used in the real world, and discusses and compares the performance of various face recognition methods. Machine learning, a field of AI, has emerged as an important part of the digitizing approaches that have attracted a lot of interest. The purpose of this work is to provide a high-level overview of several of the most widely utilized and commonly used algorithmic techniques for machine learning currently available. The goal of this work is to help readers make educated decisions about the best algorithm for machine learning they should employ for a given task by highlighting the benefits and drawbacks of each method from an implementation point of view.
  • Publication
    Improving subset linear discriminant analysis algorithm using overlapping clustering
    (IEEE, 2023-08)
    Thulfiqar H. Mandeel
    ;
    Muhammad Imran Ahmad
    ;
    Noor Aldeen A. Khalid
    ;
    Mustafa Hamid Hassan
    ;
    Mohammed Hayder Kadhim
    In recent years, there have been many proposals to improve the performance of traditional linear discriminant analysis (LDA). One of these is subset-improving linear discriminant analysis (S-LDA), which is based on clustering the whole set of classes into subsets and performing the LDA locally on these subsets. However, this algorithm suffers from an improper mapping of the classes to the corresponding subset during the testing procedure due to the inevitable discrepancy between the images used for training and those for testing. This discrepancy is caused either by spatial distortion or noise. The wrong mapping is severe when the number of data samples is small which is a common scenario in biometric datasets. In this paper, overlapping clustering is proposed for class clustering, to overcome the aforementioned problem. The proposed algorithm outperforms the S-LDA by 35.4% in mapping accuracy when using the PolyU palmprint database, 36.96%, resp. 33.92% when using left resp. Right palm images from the IIT Delhi Touchless Palmprint Database.
  • Publication
    Aquaculture monitoring system using multi-layer perceptron neural network and adaptive neuro fuzzy inference system
    ( 2024-01-01)
    Abu Hassan Abdullah
    ;
    Sukhairi Sudin
    ;
    Saad F.S.A.
    ;
    Muhamad Khairul Ali Hassan
    ;
    Muhammad Imran Ahmad
    ;
    bin Abdul Khalid K.A.
    The water quality is the most important parameter for aquatic species health and growth. The condition is very critical and is essential to monitor continuously. Poor water quality will affect health, growth and ability of the animal to survive. These also affected their harvesting yields based on the amount and size of the animal. The main water parameters such dissolved oxygen (DO), pH, temperature, salinity and turbidity are monitored and control for good water quality. The data were acquired by the developed instrument and send wirelessly through GPRS/GSM module to cloud-based database. The data were retrieved and the water quality is predicted using fuzzy logic and multi-layer perceptron. MATLAB software was used for the model which is developed based on Mamdani fuzzy interface system. The membership functions of fuzzy were generated, as well as the simulation and analysis of the water quality system. Results show that the performance of fuzzy method can improve system performance in monitoring the water quality. This system also provides alert signals to farmers based on specific limit value for the water quality parameters. This will help the breeders to make certain adjustment to ensure suitable water quality for the aquaculture system.
      1  42
  • Publication
    Dct image compression implemented on raspberry pi to compress image captured by cmos image sensor
    ( 2021-01-01)
    Mohsin I.S.
    ;
    Muhammad Imran Ahmad
    ;
    Salman S.M.
    ;
    Al-Dabagh M.Z.N.
    ;
    Isa M.N.M.
    ;
    Raja Abdullah Raja Ahmad
    The purpose of compression is to reduce the amount of data at the same time maintain the quality of image and signal for the other purpose. Discrete Cosine Transform (DCT) is a family of image compression where the raw image is transformed to the other domain to produce smaller size of data. DCT transform has low computational complexity and fast processing algorithm. In this project, DCT transform will be implemented using PI camera and Raspberry Pi SBC development board running on an ARM based processor. The raspberry Pi board has an advantage of image processing implementation due to the existing software development tool offered a rich feature for image processing such as OPENCV. The result of applying DCT compression algorithm on images with six compression rate level which are 10, 20, 50, 100, 170 and 200. The best performance can be achieved with compression rate level 200. However, on reducing the quality level of compression rate, the error measurements start becoming worse until a point is reached, where the perceptual difference from the original image can be easily noted.
      5  23
  • Publication
    e-PADI: an iot-based paddy productivity monitoring and advisory system
    ( 2019)
    M.A.F. Ismail
    ;
    Mohd Nazrin Md Isa
    ;
    S. N. Mohyar
    ;
    Muhammad Imran Ahmad
    ;
    M. N. M. Ismail
    ;
    Rizalafande Che Ismail
    ;
    A. Harun
    ;
    Sohiful Anuar Zainol Murad
    Rice is source of food calories and protein.  This second most widely grown cereal crop is the staple food for more than half the world’s population especially in developing countries.  The ability of global rice production to meet population demands (now estimated at more than 5 billion and projected to rise to 8.9 billion by 2050) remains in uncertainty in the near future unless challenges in rice production are properly addressed [1-3]. This paper proposed an IoT (Internet of things)-based paddy productivity monitoring and advisory system Using Dash7 Wireless Network Protocol. All collected data will be stored in a database management system to enable users to retrieve data either from tablets, smartphones or computers. The heart of the system is the ATmega328p microcontroller that will control the payload of the wireless network of dash7 and read data from sensor nodes. Results show all data from sensor nodes in representation of graph for analysis purpose.
      33  7
  • Publication
    Biological sequence alignments: A review of hardware accelerators and a new PE computing strategy
    ( 2014)
    Mohd Nazrin Md Isa
    ;
    Muhammad Imran Ahmad
    ;
    Sohiful Anuar Zainol Murad
    ;
    Rizalafande Che Ismail
    ;
    Khaled Benkrid
    One of the most challenging tasks in sequence alignment is its repetitive and time-consuming alignment matrix computations. In addition, performing sequence alignment in hardware, i.e. FPGA requires more hardware resources as the number of processing elements is replicated to increase performance throughput. This paper first reviews the existing FPGA-based biological sequence alignment core architectures and then proposed an efficient scheduling strategy, the so-called overlap computation and configuration (OCC) towards realizing optimized biological sequence alignment core architecture targeting for pairwise sequence alignment. In this research work, double buffering-based core architecture have been proposed and implemented on Xilinx Virtex-5 FPGA. Results have shown that this approach gained more than 10K times speed-up as compared to the GPP solution.
      3  17
  • Publication
    Image data compression using fast Fourier transform (FFT) technique for wireless sensor network
    ( 2024-02-08)
    Haron M.H.
    ;
    Mohd Nazrin Md Isa
    ;
    Muhammad Imran Ahmad
    ;
    Arshad M.A.M.
    ;
    Asral Bahari Jambek
    ;
    Siti Zarina Md Naziri
    ;
    Hussin R.
    ;
    Harun A.
    ;
    Rizalafande Che Ismail
    ;
    Shaiful Nizam Mohyar
    Agricultural settings present unique challenges for the transmission of huge amounts of images over long-range wireless networks. It is challenging to remotely gather data for transmission over a wireless network in research areas due to a lack of basic amenities like internet connections, especially in distant agricultural areas. In this research, the Fast Fourier Transform (FFT) method was used in conjunction with the Discrete Cosine Transform (DCT) method of image compression to achieve a higher compression ratio. In order for a Wireless Sensor Network (WSN) to provide compressed image data to a wireless based station, a LoRaWAN network has been identified. Low-power LoRaWAN networks may regularly transmit compressed images from an agricultural region to a monitoring system up to 15 km away. Images of golden apple snails were collected for this study from a variety of sources. The procedure was coded in MATLAB so that it could be run with input images being judged by the created algorithm. The input images can be compressed with a range of compression ratios (CR) from 3.00 to 50.00, as shown by the simulation results. Compressed image quality is measured not only by the above-mentioned criteria, but also by Mean Square Error (MSE) and Peak Signal to Noise Ratio (PSNR). According to the numbers, the best achievable compression ratio is 49.04, with an MSE of 172.72 and a PSNR of 25.75 at its highest.
      26  4
  • Publication
    IoT Enabled Mushroom Farm Automation with Machine Learning
    (Universiti Malaysia Perlis, 2024-06-03)
    Shafie Omar
    ;
    Wan Mohd Faizal Wan Nik
    ;
    Muhammad Imran Ahmad
    ;
    Tan Shie Chow
    ;
    Mohd Nazri Abu Bakar
    ;
    Shahrul Fazly Man@Sulaiman
    ;
    Fadhilnor Abdullah
    ;
    Vikneshwara Ram Suppiah
    Mushroom farming has gained prominence due to its significant contribution to the global market. One major challenge for mushroom cultivation is maintaining optimal environmental conditions, specifically temperature and humidity. Traditional farming methods, prevalent in many parts of the world, lack precise control over these parameters, often leading to poor yield. This paper presents an innovative approach combining the Internet of Things (IoT) and Machine Learning (ML) for mushroom farm automation. The proposed system employs the ESP8266 microcontroller with specific agricultural sensors for smart monitoring. To regulate the farm's environmental conditions, ML algorithms predict mushroom farm weather states: mild, normal, and hot. The ensemble ML model, comprising five classifiers – Decision Tree, Logistic Regression, K-nearest neighbor, Support Vector Machine, and Random Forest – delivers a commendable accuracy of 100% when combining predictions, surpassing the performance of individual classifiers. This integrated IoT and ML approach promises to revolutionize real-time automation and cultivation practices in the mushroom industry.
      23  3