Zulkifli Husin
Thumbnail Image
Preferred name
Zulkifli Husin
Official Name
Zulkifli, Husin
Alternative Name
Husin, Zulkifli
Husin, Z.
Husin, Zulkifli Bin
Main Affiliation
Scopus Author ID
57201059019
Researcher ID
EXV-4088-2022

Research Output

Filters

14 1
3 2
14
Reset filters

Settings
Now showing 1 - 10 of 14
Thumbnail Image
Publication

Study on leave image processing with application in herbal classification and early detection of chili plant disease

2016 , Zulkifli Husin

Herbs have been widely used in food preparation, medicine and cosmetic industry. Knowing which herbs to be used would be very important in these applications. The current way of identification and determination of the types of herbs however, is still being done manually and prone to human error. Designing a convenient and automatic recognition system of herbs species is essential since this will improve herb species classification efficiency. Chili (Capsicum Annum and Capsicum Frutescen) is an important fruiting vegetable used in majority of Asian dishes. Chili cultivation has been a very difficult and meticulous task due to its vulnerability to various attacks frommicro-organisms, bacterial disease and pests which leave distinguished marks on leaves, stems or fruits. Current manual method applies pesticides and chemicals indiscriminately throughout the farm. To improve the process, development of an automated disease detection is essential. There are a few research that have been done in classification of the plant species using certain factors (leaf shape and size). The classification are accomplished through several image processing techniques. However, the literature shows that there are still a gap in classifying the herb plants species. Therefore, this research focuses on classification approach to the shape, texture features and colors of the herbs leaves. The combination of techniques used in morphology image processing i.e. SVD and skeleton would be able to classify the species of herb regardless of the shape and size. In addition, the techniques demonstrate the capability to detect early plant chili disease through leaf features inspection using HSV colour model technique. The proposed herbs species recognition system employs neural networks algorithm and image processing techniques to perform classification on twenty herbs species. One hundred samples for each species went through the system and the recognition accuracy was at 98.9%. Most importantly the system is capable of identifying the herbs leaves species even though they are dried, wet, torn or deformed. Additionally, a novel method of early automatic recognition for plant chili disease based on color and texture features using a HSV color model and BPNN technique via intelligent decision support system is presented in this research. The proposed system employs image processing technique on one thousand chili plant samples and the recognition accuracy was at 97.7%. The efficiency and effectiveness of the proposed methods in recognizing herbs plant and detecting early plant chili disease are demonstrated by the experiments.

View
Thumbnail Image
Publication

Development of automated hybrid intelligent system for herbs plant classification and early herbs plant disease detection

2020-08-01 , Muhamad Sani Mustafa , Zulkifli Husin , Tan Wei Keong , Mavi Muhamad Farid , Rohani S Mohamed Farook

Plants such as herbs are widely used in the medical and cosmetic industry. Recognizing a species and detecting an early disease of a plant are quite challenging and difficult to implement as an automated device. The manual identification process is a lengthy process and requires a prior understanding about the plant itself, such as shape, odour, and texture. Thus, this research aimed to realize the computerized method to recognize the species and detect early disease of the herbs by referring to these characteristics. This research has been developed a system for recognizing the species and detecting the early disease of the herbs using computer vision and electronic nose, which focus on odour, shape, colour and texture extraction of herb leaves, together with a hybrid intelligent system that are involved fuzzy inference system, naïve Bayes (NB), probabilistic neural network (PNN) and support vector machine (SVM) classifier. These techniques were used to perform a convenient and effective herb species recognition and early disease detection on ten different herb species samples. The species recognition accuracy rate among ten different species using computer vision and electronic nose is archived 97% and 96%, respectively, in SVM, 98% and 98%, respectively, in PNN and both 94% in NB. In the early disease detection, the detection rate among ten different herb’s species using computer vision and electronic nose are 98% and 97%, respectively, in SVM, both 98% in PNN, 95% and 94%, respectively, in NB. Integrated three machine learning approaches have successfully achieved almost 99% for recognition and detection rate.

View
Thumbnail Image
Publication

Velocity Based Performance Analysis of GreedLea Routing Protocol in Internet of Vehicle (IoV)

2024-12-01 , Normaliza Omar , Naimah Yaakob , Mohamed Elshaikh Elobaid Said Ahmed , Zulkifli Husin , Iszaidy Ismail , Alaa KY Dafhalla

Intelligent routing protocols for IoV have also been made possible by the convergence of IoT and machine learning algorithm. In order to make informed routing decisions, these intelligent routing protocols examine data gathered from IoT devices like vehicle sensors and traffic monitoring systems using machine learning algorithms. Moreover, as the number of vehicles increases and road networks become more complex, traditional routing protocols for ad hoc networks are being replaced by more advanced and efficient protocols. The purpose of this study is to concentrate on these unique qualities of IoVs network scenario. A combined routing method has been developed to construct periodic connectivity and find routes on-demand in order to save route data as graphs. The simulation's findings show that GreedLea routing protocol outperforms GPSR and AODV routing protocols in terms of delay and packet delivery ratio (PDR). The results demonstrate that the average AODV latency is significantly higher when there are fewer vehicles on the network. This is due to the fact that connections are frequently lost at higher speeds and lower densities, and re-establishing new channels takes a lot of time. As the number of vehicles rises, efficiency improves and the wait gets shorter. The average latency, yet, keeps increasing as vehicle density increases due to the additional overheads related with routing.

View
Thumbnail Image
Publication

Automated Chilli Pesticide Residues Detection Using Odour Gas Sensors (OGS) and Deep Learning (DL) Algorithm

2023-01-01 , Tan W.K. , Hakin Ismail M.A. , Zulkifli Husin , Yasruddin M.L.

Detection of excessive pesticide residue detection is a serious problem for food regulators, suppliers, and consumers. It is very important to determine which chilli are contaminated with pesticides, and the current method of identifying and determining pesticide residues in chilli is still done using laboratory equipment. To overcome this problem, this study attempted to develop a method to detect pesticide residues in chilli samples using an eight different type of electronic nose based on a readily available metal oxide gas sensor. The proposed system used noise filtering, Long Short-Term Memory (LSTM) and Principal Component Analysis (PCA) algorithm along with a realtime data acquisition system that uses a computer to perform pesticide residue detection on the chilli sample. Two hundred forty samples of chilli sample with different pesticide concentrations went through the system and the accuracy rate achieved a success rate of 89.58% using the LSTM algorithm. The proposed method is expected to help the food processing industry to determine food contamination for producing clean and healthy food. The validation and feasibility of the proposed method for the determination of pesticide residues in chilli have been demonstrated by experiments.

View
Thumbnail Image
Publication

Recent technology for food and beverage quality assessment : A review

2022-06 , Wei Keong Tan , Zulkifli Husin , Muhammad Luqman Yasruddin , Muhammad Amir Hakim Ismail

Food and beverage assessment is an evaluation method used to measure the strengths and weaknesses of a food and beverage system to make improvements. These assessments had become crucial, especially in the issues of adulteration, replacement, and contamination that happened in artificial adjustment relating to the quality, weight and volume. Thus, this review will examine and describe features recently applied in image, odour, taste and electromagnetic, relevant to the food and beverages assessment. This review will also compare and discuss each technique and provides suggestions based on the current technology. This review will deliberate technology integration and the involvement of deep learning to enable several types of current technologies, such as imaging, odour and taste senses, and electromagnetic sensing, to be used in food evaluation applications for inspection and packaging.

View
Thumbnail Image
Publication

Feasibility Study of Beef Quality Assessment using Computer Vision and Deep Neural Network (DNN) Algorithm

2020-08-24 , Tan Wei Keong , Zulkifli Husin , Hakim Ismail Muhammad Amir

The beef quality relies upon the colour score of muscle during the grading stage. Colour scoring to be used in beef grading would be very critical and the current way of identification and determination of the quality of beef is still being done manually and susceptible to human error. The ability to automate the prediction of the beef quality will assist the meat industry through the grading phase to establish the colour score. Therefore, computer vision and deep neural network (DNN) were used to predict the beef quality by determining colour scores of beef muscle. Four hundred of beef rib-eye steaks were chosen and acquired for each image, which is the colour score of beef were assigned by expertise according to the standard colour cards. The image was processed and went through DNN classifier for determining beef quality. The proposed DNN classifier achieved the best performance percentage of 90.0%, showing that the computer vision integrated with the DNN algorithm can deliver an efficient implementation for predicting beef quality using colour scores of beef muscle.

View
Thumbnail Image
Publication

Recent technology for food and beverage quality assessment: a review

2023-06-01 , Tan W.K. , Zulkifli Husin , Yasruddin M.L. , Ismail M.A.H.

Food and beverage assessment is an evaluation method used to measure the strengths and weaknesses of a food and beverage system to make improvements. These assessments had become crucial, especially in the issues of adulteration, replacement, and contamination that happened in artificial adjustment relating to the quality, weight and volume. Thus, this review will examine and describe features recently applied in image, odour, taste and electromagnetic, relevant to the food and beverages assessment. This review will also compare and discuss each technique and provides suggestions based on the current technology. This review will deliberate technology integration and the involvement of deep learning to enable several types of current technologies, such as imaging, odour and taste senses, and electromagnetic sensing, to be used in food evaluation applications for inspection and packaging.

View
Thumbnail Image
Publication

Design and Development of GreedLea Routing Protocol for Internet of Vehicle (IoV)

2020-03-20 , Normaliza Omar , Naimah Yaakob , Zulkifli Husin , Mohamed Elshaikh Elobaid Said Ahmed

In Internet of Vehicle (IoV), each vehicle uses a routing protocol to find a path for sending its messages to the last destination. Nowadays, the studies of IoV routing protocols and their impact on the performances of network with different network scenarios has significantly developed a precise understanding of the requirements and goals for designing an IoV routing protocol. In IoV, topology of network diverse promptly which leads to the fragmentation of network, frequent route breakage, and packet loss. This paper discusses on the development of an integrated routing protocol for IoV scenario. Greedy Perimeter Stateless Routing (GPSR) and Reinforcement Learning (RL) is integrate to determine a route based on demand. Then, the mobility model has been designed to reduce road collision. Lastly, traffic management also been focused to deal with the loss, mobility and network delay to meet the application demands.

View
Thumbnail Image
Publication

Performance Analysis of GreedLea Routing Protocol in Internet of Vehicle (IoV) Network

2021-08-27 , Normaliza Omar , Naimah Yaakob , Saidahmed M.E.E. , Zulkifli Husin

The Internet of Vehicles (IoV) network transforms smart life on the wheels through several connections between vehicles, highways, people and networks, providing a safer, more effective and more energy-efficient driving experience. In a specific field, the reliable arrival of independent vehicles and the typical enhancement of traffic safety change through a fast and consistent distribution of messages. It is important to disseminate messages between vehicles that make up the IoV network and to be exploit of the quick and effective transmission of multi-hop communication for the information broadcasting. This study introduces the standardization method and summarizes the primary technologies of IoV network. This study provides a set of traditional research developments, analyses key innovations to date and, eventually, proposes solutions to common use cases that could provide valuable references for the development and implementation of potential IoVs network. The simulation has been done using OMNET++ platform to evaluate the GreedLea routing protocol with the standard Greedy Perimeter Stateless Routing (GPSR) and Ad-hoc On-demand Distance Vector (AODV) routing protocol in IoV network scenario. In the performance analysis varied parameters for example direction, node and speed has been take into account. This study also proposed to evaluate GreedLea in a crowded city situation and in a highway situation to provide further realistic simulations. From the simulation results, it shown that the GreedLea presented better performance compared to the traditional GPSR and AODV in term of end-To-end latency, packet loss rate and path loss.

View
Thumbnail Image
Publication

Automated tomato grading system using Computer Vision (CV) and Deep Neural Network (DNN) Algorithm

2022-01-01 , Tan Wei Keong , Muhammad Amir Hakim Ismail , Zulkifli Husin , Muhammad Luqman Yasruddin

The tomato grading is based on the skin colour at the grading stage. The evaluation of the colour used to classify tomatoes is very important, and the current methods of identifying and determining tomato varieties are still manual and prone to human error. The ability to automate tomato grading helps the food industry determine colour grades during the evaluation phase. Therefore, Computer Vision (CV) and Deep Neural Network (DNN) are utilised to grade tomatoes by determining their maturity colour. Three hundred tomatoes were selected and its maturity level are assigned by expertise. The tomato images are captured, processed and passed to the DNN classifier to determine the tomato grade. The proposed DNN classifier achieved the mAP percentage of 95.52%. This shows that the computer vision built into the DNN algorithm can provide an efficient implementation for predicting tomato grade.

View