Search

Spectroscopy including Near infrared spectroscopy (NIRS) is a non-destructive and rapid technique applied increasingly for food quality evaluation, medical diagnosis, manufacturing, etc. The qualitative or quantitative information using NIRS is only obtained after spectra data calibration process based mathematical knowledge in chemometrics and statistics. This process naturally involves multivariate statistical analysis. Machine learning as a subset of AI (artificial intelligence), in addition to conventional multivariate statistical tools, seems to get more popularity for chemometric calibration of NIRS data nowadays. However, often the software/toolboxes in chemometrics are commercialized version which is not free. For the free versions, programming skills are required to deal with applications of machine learning in spectra data calibration. Therefore, this paper introduces a different approach of spectra data calibration based on visual programming approach using Orange data mining, a free software which is still rarely used by the research community in spectroscopy. The data used namely: pesticide sprayed on cabbage (to classify between pure cabbage and pesticide-sprayed cabbage with different level of pesticide solution), mango sweetness assessment (to predict sugar soluble content in mango based on Brix degree value). These two data represent classification and regression respectively. This approach is intended more for researchers who want to apply machine learning calibration in their spectroscopy data but don’t want to have rigorous programming jobs, i.e. for non-programmers.

This paper discusses an application of metaheuristic optimization algorithms for a single-objective constrained optimization in a robust feedback controller design of anti-swing gantry crane control. A set robust feedback controller gains is optimized based on plant’s linear model having structured parametric uncertainty, i.e. gantry crane system. A wedge region is assigned as the optimization constraint to specify the desired closed-loop poles location which is directly related to desired time-domain response. The simulation results of the proposed robust control design using multiswarm particle swarm optimization without velocity (MPSOWV) is presented. The control performance of the feedback system optimized with MPSOWV are compared with that of PSO (particle swarm optimization), DE (differential evolution) and TLBO-PSO (improved teaching-learning-based optimization with the social character of particle swarm optimization). The simulation studies show that the controller optimized by the proposed MPSOWV demonstrates the most robust performance as compared to the other peer algorithms used in this paper for being able to produce the largest stability radius \(\left( {r_{c} } \right)\) consistently, i.e. \(r_{c} = 3.4325\) in average for 20 runs.

K-means clustering algorithms of wireless sensor networks are potential solutions that prolong the network lifetime. However, limitations hamper these algorithms, where they depend on a deterministic K-value and random centroids to cluster their networks. But, a bad choice of the K-value and centroid locations leads to unbalanced clusters, thus unbalanced energy consumption. This paper proposes X-means algorithm as a new clustering technique that overcomes K-means limitations; clusters constructed using tentative centroids called parents in an initial phase. After that, parent centroids split into a range of positions called children, and children compete in a recursive process to construct clusters. Results show that X-means outperformed the traditional K-means algorithm and optimized the energy consumption.

Food fraud continues to be a global issue. In recent years, fraudulent rice draws attention to the public agency where rice substituted with look-alike substance, low-quality rice, or impure substances due to profit motive. However, the techniques used to determine fraudulent rice, such as DNA profiling and physicochemical properties, are laborious, inconvenient, and time-consuming. The Near-Infrared Spectroscopy (NIRS) increased acceptance in fraud detection in recent years due to its good feasibility, accuracy and non-destructive. This study utilizes NIRS, Principal Component Analysis (PCA), and Logistic Regression (LR) to explore the correlated variable and to determine the linear relationship between the spectral of adulteration of rice sample. A total of 123 near infrared (NIR) spectral data collected from 31 unadulterated rice samples and ten adulterated rice samples in 3 different lightning condition places. Based on the processed data in PCA, the LR model achieved good accuracy of 94.4% on training and 99.4% on the independent test set. This study indicated that the combination of NIRS, PCA, and LR is feasible and effective in fraud detection in rice.

Food fraud had become a global food safety concern. Food adulteration is the top of the concern list when talking about food fraud. For example, the melamine incident obtained significant attention from worldwide due to its misuse as a food adulterant. It is a nitrogen-rich substance always added purposely to food such as milk powder to increase the apparent protein content and the profit without using expensive materials. It may lead to serious illness or death if the melamine content exceeds the permitted amount. Thus, the demanding safety and quality of the milk powder increased. This research will study effective and rapid fraud detection in milk powder by using near-infrared spectroscopy (NIR). Melamine was added to milk powder with different concentrations and detected it by near-infrared spectroscopy. The total of 130 spectral data from 10 adulterated samples and 30 unadulterated samples with 3 different lighting condition. The results data will be interpreted by using Principal Component Analysis (PCA) and Logistics Regression (LR) to discriminate between adulterated and unadulterated samples. From the results, detection accuracy of 100 % can be achieved on training and independent test set after spectra pre-processing. The results show the feasibility of NIR with the combination of PCA and LR as it can use as a fast screening tool for fraud detection in milk powder.

Adulterated foods are causing health-related issues since there is no rapid method available for the detection of food fraud. The main objective of this study is to determine the feasibility of using near-infrared (NIR) spectroscopy in differentiating pure palm oil from palm oil adulterated with recycled cooking oil in varying concentrations. The deep-frying process was carried out for chicken nuggets and French fries as fried items using palm oil as a frying medium to produce used frying oil. The refining and bleaching process was applied to used frying oil to generate recycled cooking oil. Adulterated samples were developed with different concentrations of recycled cooking oil in pure palm oil (1%, 2%, 3%, 5%, 10%, 15%, 20%, 30%, 40% and 50%). Principal component analysis was applied to analyze the distribution of pure and adulterated palm oil samples. The classification accuracy of the proposed method using handheld NIR spectroscopy in distinguishing adulterated samples of lower concentrations was found to be low (below 50%). Adulterated palm oil samples of recycled cooking oil (RCO) concentration (15% and above) were found to show classification accuracy of 100% when detected through handheld NIR spectroscopy.

Increase in population and urbanisation alongside demands from agricultural sector towards meeting fresh produce needs of the growing population has put severe pressure on the available natural water sources all over the world. Thus, water is undoubtedly the most contemporary crucial resources in the world. Aquatic weed plants are generally seen as a global threat to humans and aquatic ecosystem as they cannot be wholly eliminated easily. Still, various researchers and investigations have shown that they are instrumental in the field of wastewater phytoremediation, either in constructed wetlands, open ponds or hydroponic systems in an eco-friendly and economical manner with little or no sludge waste. In view of the increasing search for an alternative source of a sustainable method for wastewater reclamation, this study presents a concise review of relevant literatures on the roles of constructed wetlands and hydroponic systems in phytoremediation of wastewater. Also in the course of this study, the authors discovered that constructed wetlands and hydroponic systems have proven to be productive in remediating an array of water quality problems, with merits over the regular wetlands and conventional methods. Nonetheless, these methods are endowed with drawbacks such as inconsistency in the absorption of contaminants, large area space requirement, over dependency on environmental conditions and energy requirement. However, we suggest the use of engineered hybrid to improve its efficiency in wastewater treatment and bioenergy generation. In the case of hydroponic systems, an alternative sustainable solar energy or devices can be used to power the systems to obtain effective results at a low cost. Additionally, further studies can be employed in the use of phytoremediation technique for synchronous remediation of wastewater and production of biomass on industrial scale.

Near infrared (NIR) spectroscopy has been widely used in many fields of application as a rapid and non-destructive (non-invasive) approach of qualitative and quantitative assessment of a substance. This is performed by collecting many samples of real measurement of the substance’s property and its NIR spectrum for calibration purpose. Thus, in the future, laborious real measurement is not necessary and is substituted by non-destructive (non-invasive) predictive approach using multivariable regression methods. This paper presents an observation on different multivariable regression methods, i.e. partial least square (PLS), competitive adaptive reweighted sampling PLS (CARS-PLS) and support vector regression (SVR) for various NIR spectra data. Different pre-treatment methods of NIR spectra data are also observed in this research. The goal is therefore to obtain robust and reliable calibration method for NIR spectra data in the future. Initial results show that CARS-PLS improves the prediction quality of that obtained by PLS provided that appropriate data preprocessing is applied.

Every region of foot is not equally divided in terms of plantar pressure distribution (PPD) during free standing. This paper is focusing on studying PPD on flat plane and inclined plane and the results obtained from this study may contribute to biomedical researcher in designing orthotic devices. 24 healthy young adults age ranging from 19 to 24 years old and weigh between 50 to 80 kg were invited for experiments purpose. Six regions of both feet were measured which were hallux, medial forefoot, central forefoot, lateral forefoot, lateral midfoot and hindfoot. Remarkable differences were seen in the result as right foot exerted more pressure generally in every region of the foot as to compared with left foot respectively. This is true especially for region such as hallux, medial forefoot and lateral forefoot. On a flat surface, PPD on the hindfoot is the highest. However, at an elevation of 25°, test subjects began to shift their PPD to forefoot regions. While studies of PPD are common, this study provides a new insight for the first time into PPD while standing on different angle of walking plane.

This paper presents a brief survey on multi-legged robots and their applications in agriculture such as for harvesting. Multi-legged robots have the benefit of more flexibility and adapt to different rough terrain in a better way. They also have very important applications in fulfilling the dangerous tasks such as mine detecting.

Quality determines the shelf-life and selling prices of fresh mango, and therefore quality observation and control of fresh mango are of utmost significance in the processing and management of its supply chain. Mango fruit (mangifera indica) quality methods are mostly destructive in nature. Different mechanical, electromagnetic and non-destructive methods are increasingly important nowadays because of the ease of operation, speed, and reliability of the process. This project aims to develop a non-destructive assessment of mango quality using handheld micro NIR (near-infrared) spectroscopic device. NIR spectra data and Brix levels, which indicate the sugar content of the plant, i.e. indicating the sweetness of the mango, were collected from three different types of Mango (Chokanan, Rainbow, and Kai Te), resulting 80 samples (i.e. 60 samples for training and 20 samples for testing) in this project. NIR spectra can be converted mathematically to obtain quantitative information of chemical and physical nature by multivariate calibration. The spectra data is pre-processed using Gaussian smoothing and extended multiplicative signal correction (EMSC) for the elimination of uncontrollable path length or scattering effects. These samples were then used to develop a predictive model using both Support Vector Machine (SVM) regression and Partial Least Squares regression (PLS) methods. The coefficient of determination (R2) obtained from SVM for training/calibration and testing dataset are 0.96 and 0.95 respectively. Meanwhile, the coefficient of determination (R2) obtained from PLS for calibration/training and testing dataset are 0.89 and 0.86 respectively. The results obtained from this project indicate that the handheld NIR has potential use for non-destructive assessment of mango fruits quality.

PID (proportional+integral+derivative) controller is well known as a simple and easy-to-implement controller. However, the design procedure is not straightforward for multi-input multi-output (MIMO) systems. It is even more complicated when robustness criterion must be handled. In this paper, a stable robust PID controller for anti-swing control of automatic gantry crane is proposed. The proposed method employs an automatic tuning using DE (differential evolution) to search for a set of PID controller gains that satisfy Kharitonovs polynomials robust stability criterion. This robust stability criterion is used to deal with parametric uncertainty occurs in gantry crane model. The simulation results show that a satisfactory robust PID control performance can be achieved. The PID controller is able to quickly move the cart of the crane while suppressing the swing of the payload for various conditions, i.e. payload mass and cable length variations.

Back-Propagation Neural Network (BPNN) has been widely used in solving nonlinear problems. However, there are some limitations in using conventional BPNN especially for high order nonlinear problems. Dynamic Back-Propagation Neural Network (DBPNN) is proposed in this paper to improve the performance of conventional BPNN. Its adaptive learning ability is closer to human being learning behavior in comparing to conventional BPNN. Few simulations have been run to test the robustness of DBPNN and the results are compared to the conventional BPNN.

Swarm robotics come into the picture of replacing humans on life-risking jobs because of its decentralization concept, i.e. a damaged unit do not affect the entire system performance. Airborne type swarm robotics have high flexibility since they can bypass most obstacles. Swarm robotics can be utilized to scout unknown terrain, target searching or S.A.R applications. In this project, simulation to visualize the swarm quadcopters’ performance onto an assigned environment using robotic software simulator called V-REP software is presented. Robotic simulator software take account of real-life physics which increases the accuracy for simulation and retrieves reliable results from the simulation. Hence, robotic simulator software could replace real-life testing for at least initial ideas exploration to real-life situation.

Petrol and diesel engine have a significantly different way to convert chemical energy into mechanical energy. In this work, the intelligent system approach is used to automatically identify the type of engine based on the sound of the engine. The combination of signal processing and machine learning technique for automatic petrol and diesel engine sound identification is presented in this work. After a signal preprocessing step of the engine sound, a Fast Fourier Transform (FFT)-based frequency characteristic modelling technique is applied as the feature extraction method. The resulting features extracted from the sound signal, in the form of frequency in the FFT matrix, are used as the inputs for the machine learning, the Support Vector Machine (SVM), step of the proposed approach. The experiment of FFT with SVM-based diesel and petrol engine sound identification has been carried out. The results show that the proposed approach produces a good accuracy in the relatively short training time. Experimental results show the training and testing accuracy of 100 % and 100 % respectively. They confirm the effectiveness of the proposed intelligent automatic diesel and petrol engine sound identification based on Fast Fourier Transform (FFT) and Support Vector Machines (SVMs).

The sound of V6 or V8 engines has its own cultural appeal that cannot be replaced by the modern four-cylinder naturally aspirated or turbocharged engines. The identification of the type of engine by the sound is not an easy task, even for the professionals. An intelligent system that can identify V6 to V8 engines from various cars will give an insight of the features in the engine sounds that characterized the two different engines. In this work, an Artificial Neural Network (ANN) approach is applied for identifying cylinder of the engine based on the engine sound identification is proposed. The recorded sound of the engine is then processed in order to get some features which later be used in the proposed system. The Fast Fourir Transform (FFT) is adopted as a feature and later used as input to the Artificial Neural Network (ANN) based identifier. The Experimental results confirm the effectiveness of the proposed intelligent automatic six cylinder and eight cylinder engine based on Fast Fourier Transform (FFT) and Artificial Neural Network (ANN), since it resulting the training and testing accuracy of 100 % and 100 %, respectively.

Anti-swing control is a well-known term in gantry crane control. It is designed to move the payload of gantry crane as fast as possible while the payload swing angle should be kept as small as possible at the final position. A number of studies have proposed anti-swing control using the well-known proportional, integral, derivative (PID) control method. However, PID controllers cannot always effectively control systems with changing parameters. Some studies have also proposed intelligent-based control including fuzzy control. However, the designers often have to face the problem of tuning many parameters during the design to obtain optimum performance. Thus, a lot of effort has to be taken in the design stage. In this paper Fuzzy-tuned PID controller design for anti-swing gantry crane control is presented. The objective is to design a practical anti-swing control which is simple in the design and also robust. The proposed Fuzzy-tuned PID utilizes fuzzy system as PID gain tuners to achieve robust performance to parameters’ variations in the gantry crane. A complex dynamic analysis of the system is not needed. PID controller is firstly optimized in MATLAB using a rough model dynamic of the system which is identified by conducting a simple open-loop experiment. Then, the PID gains are used to guide the range of the fuzzy outputs of the Fuzzy-tuned PID controllers. The experimental results show that the proposed anti-swing controller has satisfactory performance. In addition, the proposed method is straightforward in the design.

Grasp stability is considered to be an important aspect in object manipulation of a multifingered robot hand. Multifingered hand contacts the object at some arbitrary locations during the object manipulation and applies the gripping force to hold and manipulate the object without slip. It is desirable to use the optimum gripping force during the grasp manipulation for two reasons; firstly, to prevent the object from damages, secondly, to decrease the cost of the manipulation. With these objectives in mind, a three-fingered soft hand is designed, and gripping force and stability analysis are done experimentally. DC motors are used to actuate the joints of fingers and force sensors are used to measure the internal force at contact points. PID controller is used to controlling the internal force exerted at the contact points, and the control parameters are tweaked until a satisfactory response is achieved. The minimum gripping force required to handle the object with / without external disturbances is measured. The position variables and frictional coefficients are evaluated from the contact forces at the contact points. In future, the optimization algorithm will be integrated to carry out these tasks in constrained and unconstrained environments.

Cuckoo Search (CS) and Differential Evolution (DE) algorithms are considerably robust meta-heuristic algorithms to solve constrained optimization problems. In this study, the performance of CS and DE are compared in solving the constrained optimization problem from selected benchmark functions. Selection of the benchmark functions are based on active or inactive constraints and dimensionality of variables (i.e. number of solution variable). In addition, a specific constraint handling and stopping criterion technique are adopted in the optimization algorithm. The results show, CS approach outperforms DE in term of repeatability and the quality of the optimum solutions.

This paper presents a robust feedback controller design for parametric uncertainty systems via constrained optimization. The proposed controller design employs modern optimization tools (Particle Swarm Optimization and Differential Evolution) in a single objective constrained optimization. The objective of the optimization is to search for a set of robust controller gains such that the stability radius of the closed-loop system is maximized. The constraint of the optimization is a closed-loop poles region which is directly related to the desired time-domain control performance. The proposed controller design is applied to control of pendulum-like systems (gantry crane, flexible joint and inverted pendulum). The results show the robust performance of the designed controller.

In this paper, the state feedback control design problem for tracking control of a flexible link manipulator is considered. The calculation of state feedback control gains is conventionally handled by pole placement method or LQR method via Riccati equation. Unfortunately, they still possess trial and error approach of choosing some parameters. Particularly, choosing elements of Q and R matrices in the state feedback control using LQR method has to be done by trial. Therefore, an intelligent method to resolve this problem is proposed by adopting PSO algorithm. The experimental work is carried out to evaluate the effectiveness of the proposed method.

This paper discusses terminal sliding mode control for active engine mounting (AEM) system to isolate vehicle engine body vibration. The engine vibration may occur due to road irregularities, at low frequency, and also reciprocating mechanism of the piston in the engine, at high frequency about 20 – 40 Hz. Active engine mounting system is designed to deal with isolation of vibration in high level frequency. A number of controllers for AEM system have been proposed. One of them is sliding mode control. However, there is no systematic method to determine sliding surface for conventional sliding mode technique to assure the system will be asymptotically stable. The main advantage of the proposed controller compared to the conventional (linear) sliding mode control is that the sliding motion to the origin (stable condition) can be reached in finite time by introducing the nonlinear sliding surface based on the concept of terminal attractors. The result shows that terminal sliding mode control not only able to attenuate the vibration but also robust to the different type of disturbance and parametric uncertainties such as mass, stiffness, and damping coefficient.

PID (proportional+integral+derivative) control is known as simple and easy-to-implement controller. However, the robustness performance is often not satisfactory when dealing with parameter variations of the plant. In addition, its design procedure is not straightforward for the system which is non-SISO (Singe Input Single Output) system like a gantry crane. In this paper, a stable robust PID controller for anti-swing control of automatic gantry crane is proposed. The proposed method employs Genetic Algorithm (GA) in min-max optimization to find the stable robust PID. In the optimization, the robustness of the controller is tested using Kharitonov's polynomials robust stability criterion to deal with parametric uncertainty appears in gantry crane model. For practicality, the model is identified by conducting simple open-loop experiment in the beginning. The experimental results show that a satisfactory robust PID control performance can be achieved. The controller is able to effectively move the trolley of the crane in short time while canceling the swing of the payload for different conditions of payload mass and cable length variations.

The main objective of this paper is to design a state feedback controller for stabilizing and tracking control of self-erecting inverted pendulum employing intelligent method using particle swarm optimization (PSO). This is motivated by the fact that one has to face trial and error approach in conventional feedback control design by pole placement method or linear quadratic regulator (LQR) method via Riccati equation. The simulation results show the effectiveness of the proposed method. The proposed state feedback controller works jointly with swing-up controller in the self-erecting inverted pendulum system.

In this paper, a novel method for tuning PID controller of automatic gantry crane control using particle swarm optimization (PSO) is proposed. PSO is one of the most recent optimization techniques based on evolutionary algorithm. PSO is also known as computationally efficient method. This work presents in detail how to apply PSO method in finding the optimal PID gains of gantry crane system in the fashion of min-max optimization. The simulation results show that with proper tuning a satisfactory PID control performance can be achieved to drive nonlinear plant. The controller is able to effectively move the trolley of the crane in short time while canceling the swing angle of the payload hanging on the trolley at the end position. The robustness of the controller is also tested.

Gantry cranes are widely used in various applications to transfer a payload from one position to desired position. Gantry crane system is an underactuated system where the number of inputs is less than the number of outputs. When the input signal is given to the actuator, the trolley starts to accelerate whilst causing a swing of payload hanging on a flexible cable. Many researchers have proposed anti-swing controls of gantry crane using PID+PD structure where PID controller is used for trolley positioning control and PD controller is used to dampen the swing oscillation. This is because of the simplicity of PID control structure. Some have combined intelligent methods such as fuzzy and neural networks to improve the performance of the proposed PID control structure. This paper discusses GA-based PID+PD controller tuning for automatic gantry crane system. The discussion is emphasized on the selection of the objective function since the objective function is the key to use the GA (genetic algorithm). The optimized PID gains would be mainly due to the appropriate objective/fitness function. The simulation results show that a good anti-swing control performance can be obtained from the proposed objective function.

This paper discusses fuzzy-tuned PID controller design for anti-swing gantry crane control. The objective is employing simple structure of PID control by utilizing fuzzy system as gain tuners to improve its robustness to cope with parameters variations in the crane system. The proposed fuzzy-tuned PID system has simple structure. Instead of fixed PID gains, the gains are determined by means of a fuzzy inference system. Weighting factors are also added to fuzzy output. The simulation result shows that the proposed Fuzzy-tuned PID controllers has similar performance with PID controllers with advantage of robustness to parameters variations for anti-swing gantry crane control.

To attain a good control performance of automatic gantry crane system, sensors are indispensable instrument for feedback signals. However, sensing the payload motion of a real gantry crane, particularly swing motion, is not easy and sometimes costly. Therefore, a sensorless automatic gantry crane system is developed and proposed in this paper. A soft sensor based on artificial neural network is introduced to eliminate the real sensor. Instead, a sensor measuring armature current of DC motor driving the cart is used to provide dynamic information for the soft sensor. A simulation study using dynamic model of lab-scale automatic gantry crane is carried out to evaluate the effectiveness of the proposed soft sensor. The results show that the soft sensor can estimate effectively the unmeasured state. Moreover, the proposed method has robustness to deal with parameter variations.

In this paper, a two-degree of freedom (2DOF) controller is designed for a ball and beam system. The controller is developed based on the algebraic method. The ball and beam system is one of the most popular laboratory experiments for control education. The controller is designed such that the ball can track a square wave with a certain design specification. The advantages of 2DOF controller are the feedback controller takes care of the uncertainty and the feedforward filter ensures the tracking of the reference command. Though the control method is not new, the application of the technique on such unstable system is of interest. Controlling the ball on the beam is a challenging task because of the instability of the system and the fact that the output, i.e. the ball position, increases almost without limit for a fixed input beam angle. The controller needs to regulate the position of the ball by changing the angle of the beam at the pivot point. It is a difficult control task as the ball moves with an acceleration which is proportional to the tilt angle of the beam. Two types of 2DOF controllers are considered; based on dominant pole design and based on integral time absolute error (ITAE) design. The performances of the resulting controllers are compared. Simulations were run over various frequencies. The results indicate the effectiveness of the designed 2DOF controllers in achieving the design specification.

The aim of this research is to design a PID Controller using PSO algorithm. The model of a DC motor is used as a plant in this paper. The conventional gain tuning of PID controller (such as Ziegler-Nichols (ZN) method) usually produces a big overshoot, and therefore modern heuristics approach such as genetic algorithm (GA) and particle swarm optimization (PSO) are employed to enhance the capability of traditional techniques. However, due to the computational efficiency, only PSO will be used in this paper. The comparison between PSO-based PID (PSO-PID) performance and the ZN-PID is presented. The results show the advantage of the PID tuning using PSO-based optimization approach.

This paper presents a robust control design based on constrained optimization using Differential Evolution (DE). The feedback controller is designed based on state space model of the plant considering structured uncertainty such that the closed-loop system would have maximum stability radius. A wedge region is assigned as a constraint for desired closed loop poles location. The proposed control technique is applied to a two-mass system that is known as benchmark problem for robust control design. The simulation results seem to be interesting in which the robustness performance is achieved in the presence of parameter variations of the plant.