The objective of this study is to identify spatial and temporal patterns in the air quality at three selected Malaysian air monitoring stations based on an eleven-year database (January 2000-December 2010). Four statistical methods, Discriminant Analysis (DA), Hierarchical Agglomerative Cluster Analysis (HACA), Principal Component Analysis (PCA) and Artificial Neural Networks (ANNs), were selected to analyze the datasets of five air quality parameters, namely: SO2, NO2, O3, CO and particulate matter with a diameter size of below 10 μm (PM10). The three selected air monitoring stations share the characteristic of being located in highly urbanized areas and are surrounded by a number of industries. The DA results show that spatial characterizations allow successful discrimination between the three stations, while HACA shows the temporal pattern from the monthly and yearly factor analysis which correlates with severe haze episodes that have happened in this country at certain periods of time. The PCA results show that the major source of air pollution is mostly due to the combustion of fossil fuel in motor vehicles and industrial activities. The spatial pattern recognition (S-ANN) results show a better prediction performance in discriminating between the regions, with an excellent percentage of correct classification compared to DA. This study presents the necessity and usefulness of environmetric techniques for the interpretation of large datasets aiming to obtain better information about air quality patterns based on spatial and temporal characterizations at the selected air monitoring stations.
Patients with hand tremors may find routine activities such as writing and holding objects affected. In response to this problem, an active control technique has been examined in order to lessen the severity of tremors. In this article, an online method of a hybrid proportional-integral control with active force control strategy for tremor attenuation is presented. An intelligent mechanism using iterative learning control is incorporated into the active force control loop to approximate the estimation mass parameter. Experiments were conducted on a dummy hand model placed horizontally in a tremor test rig. When activated by a shaker in the vertical direction, this resembles a postural tremor condition. In the proportional-integral plus active force control, a linear voice coil actuator is used as the main active tremor suppressive element. A sensitivity analysis is presented to investigate the robustness of the proposed controller in a real-time control environment. The findings of this study demonstrate that the intelligent active force control and iterative learning controller show excellent performance in reducing tremor error compared to classic pure proportional, proportional-integral and hybrid proportional-integral plus active force control controllers.
This paper explores the migration of adaptive filtering with swarm intelligence/evolutionary techniques employed in the field of electroencephalogram/event-related potential noise cancellation or extraction. A new approach is proposed in the form of controlled search space to stabilize the randomness of swarm intelligence techniques especially for the EEG signal. Swarm-based algorithms such as Particles Swarm Optimization, Artificial Bee Colony, and Cuckoo Optimization Algorithm with their variants are implemented to design optimized adaptive noise canceler. The proposed controlled search space technique is tested on each of the swarm intelligence techniques and is found to be more accurate and powerful. Adaptive noise canceler with traditional algorithms such as least-mean-square, normalized least-mean-square, and recursive least-mean-square algorithms are also implemented to compare the results. ERP signals such as simulated visual evoked potential, real visual evoked potential, and real sensorimotor evoked potential are used, due to their physiological importance in various EEG studies. Average computational time and shape measures of evolutionary techniques are observed 8.21E-01 sec and 1.73E-01, respectively. Though, traditional algorithms take negligible time consumption, but are unable to offer good shape preservation of ERP, noticed as average computational time and shape measure difference, 1.41E-02 sec and 2.60E+00, respectively.
Recently, the greatest statistical computational challenge in genetic epidemiology is to identify and characterize the genes that interact with other genes and environment factors that bring the effect on complex multifactorial disease. These gene-gene interactions are also denoted as epitasis in which this phenomenon cannot be solved by traditional statistical method due to the high dimensionality of the data and the occurrence of multiple polymorphism. Hence, there are several machine learning methods to solve such problems by identifying such susceptibility gene which are neural networks (NNs), support vector machine (SVM), and random forests (RFs) in such common and multifactorial disease. This paper gives an overview on machine learning methods, describing the methodology of each machine learning methods and its application in detecting gene-gene and gene-environment interactions. Lastly, this paper discussed each machine learning method and presents the strengths and weaknesses of each machine learning method in detecting gene-gene interactions in complex human disease.
When the amount of data and information is said to double in every 20 months or so, feature selection has become highly important and beneficial. Further improvements in feature selection will positively affect a wide array of applications in fields such as pattern recognition, machine learning, or signal processing. Bio-inspired method called Bat Algorithm hybridized with a Naive Bayes classifier has been presented in this work. The performance of the proposed feature selection algorithm was investigated using twelve benchmark datasets from different domains and was compared to three other well-known feature selection algorithms. Discussion focused on four perspectives: number of features, classification accuracy, stability, and feature generalization. The results showed that BANB significantly outperformed other algorithms in selecting lower number of features, hence removing irrelevant, redundant, or noisy features while maintaining the classification accuracy. BANB is also proven to be more stable than other methods and is capable of producing more general feature subsets.
We describe the work on infusion of emotion into a limited-task autonomous spoken conversational agent situated in the domestic environment, using a need-inspired task-independent emotion model (NEMO). In order to demonstrate the generation of affect through the use of the model, we describe the work of integrating it with a natural-language mixed-initiative HiFi-control spoken conversational agent (SCA). NEMO and the host system communicate externally, removing the need for the Dialog Manager to be modified, as is done in most existing dialog systems, in order to be adaptive. The first part of the paper concerns the integration between NEMO and the host agent. The second part summarizes the work on automatic affect prediction, namely, frustration and contentment, from dialog features, a non-conventional source, in the attempt of moving towards a more user-centric approach. The final part reports the evaluation results obtained from a user study, in which both versions of the agent (non-adaptive and emotionally-adaptive) were compared. The results provide substantial evidences with respect to the benefits of adding emotion in a spoken conversational agent, especially in mitigating users' frustrations and, ultimately, improving their satisfaction.
Machine learning techniques are becoming useful as an alternative approach to conventional medical diagnosis or prognosis as they are good for handling noisy and incomplete data, and significant results can be attained despite a small sample size. Traditionally, clinicians make prognostic decisions based on clinicopathologic markers. However, it is not easy for the most skilful clinician to come out with an accurate prognosis by using these markers alone. Thus, there is a need to use genomic markers to improve the accuracy of prognosis. The main aim of this research is to apply a hybrid of feature selection and machine learning methods in oral cancer prognosis based on the parameters of the correlation of clinicopathologic and genomic markers.
Breast cancer is the most common form of cancer among women worldwide. Early detection of breast cancer can increase treatment options and patients' survivability. Mammography is the gold standard for breast imaging and cancer detection. However, due to some limitations of this modality such as low sensitivity especially in dense breasts, other modalities like ultrasound and magnetic resonance imaging are often suggested to achieve additional information. Recently, computer-aided detection or diagnosis (CAD) systems have been developed to help radiologists in order to increase diagnosis accuracy. Generally, a CAD system consists of four stages: (a) preprocessing, (b) segmentation of regions of interest, (c) feature extraction and selection, and finally (d) classification. This paper presents the approaches which are applied to develop CAD systems on mammography and ultrasound images. The performance evaluation metrics of CAD systems are also reviewed.
Tool life of the cutting tools is considered as one of the factors which has effects on machining costs and the quality of machined parts. The topic of tool life prediction has been an interesting and important research topic attracting the attention of a wide number of researchers in this particular area. In terms of the suitable methods used in this research topic, it is stated that both statistical and artificial intelligence (AI) approaches can be employed to model tool life. For further justifying the capability of the ANN model in predicting tool life, the current study was based on conducting experimental work for collecting the experimental data. After carrying out the experiment, 17 data sets were collected and they were divided into two subsets; the first one for training and the second for testing. Since the data sets seemed to be lower than the number of data sets used in previous studies, we attempted to make verification of the ability of the ANN model in learning and adapting with low training and testing data. Diverse topologies accompanied with single and two hidden layers were created for modeling the tool life. For choosing the best and most effective network, the study adopted the mean square error function as criteria for the evaluation of the network selection. Thus, based on the data generated from the same experiment, a regression model (RM) was constructed employing the SPSS software. A comparison between the ANN model and RMs in terms of their accuracy was carried out and the findings revealed that the accuracy of the ANN was higher than that of the RM.
Elderly people are commonly affected by Parkinson's disease (PD) which is one of the most common neurodegenerative disorders due to the loss of dopamine-producing brain cells. People with PD's (PWP) may have difficulty in walking, talking or completing other simple tasks. Variety of medications is available to treat PD. Recently, researchers have found that voice signals recorded from the PWP is becoming a useful tool to differentiate them from healthy controls. Several dysphonia features, feature reduction/selection techniques and classification algorithms were proposed by researchers in the literature to detect PD. In this paper, hybrid intelligent system is proposed which includes feature pre-processing using Model-based clustering (Gaussian mixture model), feature reduction/selection using principal component analysis (PCA), linear discriminant analysis (LDA), sequential forward selection (SFS) and sequential backward selection (SBS), and classification using three supervised classifiers such as least-square support vector machine (LS-SVM), probabilistic neural network (PNN) and general regression neural network (GRNN). PD dataset was used from University of California-Irvine (UCI) machine learning database. The strength of the proposed method has been evaluated through several performance measures. The experimental results show that the combination of feature pre-processing, feature reduction/selection methods and classification gives a maximum classification accuracy of 100% for the Parkinson's dataset.
A theoretical framework is developed based on the premise that brains evolved into sufficiently complex adaptive systems capable of instantiating genomic consciousness through self-awareness and complex interactions that recognize qualitatively the controlling factors of biological processes. Furthermore, our hypothesis assumes that the collective interactions in neurons yield macroergic effects, which can produce sufficiently strong electric energy fields for electronic excitations to take place on the surface of endogenous structures via alpha-helical integral proteins as electro-solitons. Specifically the process of radiative relaxation of the electro-solitons allows for the transfer of energy via interactions with deoxyribonucleic acid (DNA) molecules to induce conformational changes in DNA molecules producing an ultra weak non-thermal spontaneous emission of coherent biophotons through a quantum effect. The instantiation of coherent biophotons confined in spaces of DNA molecules guides the biophoton field to be instantaneously conducted along the axonal and neuronal arbors and in-between neurons and throughout the cerebral cortex (cortico-thalamic system) and subcortical areas (e.g., midbrain and hindbrain). Thus providing an informational character of the electric coherence of the brain - referred to as quantum coherence. The biophoton field is realized as a conscious field upon the re-absorption of biophotons by exciplex states of DNA molecules. Such quantum phenomenon brings about self-awareness and enables objectivity to have access to subjectivity in the unconscious. As such, subjective experiences can be recalled to consciousness as subjective conscious experiences or qualia through co-operative interactions between exciplex states of DNA molecules and biophotons leading to metabolic activity and energy transfer across proteins as a result of protein-ligand binding during protein-protein communication. The biophoton field as a conscious field is attributable to the resultant effect of specifying qualia from the metabolic energy field that is transported in macromolecular proteins throughout specific networks of neurons that are constantly transforming into more stable associable representations as molecular solitons. The metastability of subjective experiences based on resonant dynamics occurs when bottom-up patterns of neocortical excitatory activity are matched with top-down expectations as adaptive dynamic pressures. These dynamics of on-going activity patterns influenced by the environment and selected as the preferred subjective experience in terms of a functional field through functional interactions and biological laws are realized as subjectivity and actualized through functional integration as qualia. It is concluded that interactionism and not information processing is the key in understanding how consciousness bridges the explanatory gap between subjective experiences and their neural correlates in the transcendental brain.
The cluster-based compound selection is used in the lead identification process of drug discovery and design. Many clustering methods have been used for chemical databases, but there is no clustering method that can obtain the best results under all circumstances. However, little attention has been focused on the use of combination methods for chemical structure clustering, which is known as consensus clustering. Recently, consensus clustering has been used in many areas including bioinformatics, machine learning and information theory. This process can improve the robustness, stability, consistency and novelty of clustering. For chemical databases, different consensus clustering methods have been used including the co-association matrix-based, graph-based, hypergraph-based and voting-based methods. In this paper, a weighted cumulative voting-based aggregation algorithm (W-CVAA) was developed. The MDL Drug Data Report (MDDR) benchmark chemical dataset was used in the experiments and represented by the AlogP and ECPF_4 descriptors. The results from the clustering methods were evaluated by the ability of the clustering to separate biologically active molecules in each cluster from inactive ones using different criteria, and the effectiveness of the consensus clustering was compared to that of Ward's method, which is the current standard clustering method in chemoinformatics. This study indicated that weighted voting-based consensus clustering can overcome the limitations of the existing voting-based methods and improve the effectiveness of combining multiple clusterings of chemical structures.
Active appearance model (AAM) is one of the most popular model-based approaches that have been extensively used to extract features by highly accurate modeling of human faces under various physical and environmental circumstances. However, in such active appearance model, fitting the model with original image is a challenging task. State of the art shows that optimization method is applicable to resolve this problem. However, another common problem is applying optimization. Hence, in this paper we propose an AAM based face recognition technique, which is capable of resolving the fitting problem of AAM by introducing a new adaptive ABC algorithm. The adaptation increases the efficiency of fitting as against the conventional ABC algorithm. We have used three datasets: CASIA dataset, property 2.5D face dataset, and UBIRIS v1 images dataset in our experiments. The results have revealed that the proposed face recognition technique has performed effectively, in terms of accuracy of face recognition.
This paper describes the acquisition setup and development of a new gait database, MMUGait. This database consists of 82 subjects walking under normal condition and 19 subjects walking with 11 covariate factors, which were captured under two views. This paper also proposes a multiview model-based gait recognition system with joint detection approach that performs well under different walking trajectories and covariate factors, which include self-occluded or external occluded silhouettes. In the proposed system, the process begins by enhancing the human silhouette to remove the artifacts. Next, the width and height of the body are obtained. Subsequently, the joint angular trajectories are determined once the body joints are automatically detected. Lastly, crotch height and step-size of the walking subject are determined. The extracted features are smoothened by Gaussian filter to eliminate the effect of outliers. The extracted features are normalized with linear scaling, which is followed by feature selection prior to the classification process. The classification experiments carried out on MMUGait database were benchmarked against the SOTON Small DB from University of Southampton. Results showed correct classification rate above 90% for all the databases. The proposed approach is found to outperform other approaches on SOTON Small DB in most cases.
Over the last few years, particle swarm optimization (PSO) has been extensively applied in various geotechnical engineering including slope stability analysis. However, this contribution was limited to two-dimensional (2D) slope stability analysis. This paper applied PSO in three-dimensional (3D) slope stability problem to determine the critical slip surface (CSS) of soil slopes. A detailed description of adopted PSO was presented to provide a good basis for more contribution of this technique to the field of 3D slope stability problems. A general rotating ellipsoid shape was introduced as the specific particle for 3D slope stability analysis. A detailed sensitivity analysis was designed and performed to find the optimum values of parameters of PSO. Example problems were used to evaluate the applicability of PSO in determining the CSS of 3D slopes. The first example presented a comparison between the results of PSO and PLAXI-3D finite element software and the second example compared the ability of PSO to determine the CSS of 3D slopes with other optimization methods from the literature. The results demonstrated the efficiency and effectiveness of PSO in determining the CSS of 3D soil slopes.
This paper presents a novel features mining approach from documents that could not be mined via optical character recognition (OCR). By identifying the intimate relationship between the text and graphical components, the proposed technique pulls out the Start, End, and Exact values for each bar. Furthermore, the word 2-gram and Euclidean distance methods are used to accurately detect and determine plagiarism in bar charts.
Greenhouse gas emitted by the transport sector around the world is a serious issue of concern. To minimize such emission the automobile engineers have been working relentlessly. Researchers have been trying hard to switch fossil fuel to alternative fuels and attempting to various driving strategies to make traffic flow smooth and to reduce traffic congestion and emission of greenhouse gas. Automobile emits a massive amount of pollutants such as Carbon Monoxide (CO), hydrocarbons (HC), carbon dioxide (CO2), particulate matter (PM), and oxides of nitrogen (NO x ). Intelligent transport system (ITS) technologies can be implemented to lower pollutant emissions and reduction of fuel consumption. This paper investigates the ITS techniques and technologies for the reduction of fuel consumption and minimization of the exhaust pollutant. It highlights the environmental impact of the ITS application to provide the state-of-art green solution. A case study also advocates that ITS technology reduces fuel consumption and exhaust pollutant in the urban environment.
Cognitive radio (CR) enables unlicensed users to exploit the underutilized spectrum in licensed spectrum whilst minimizing interference to licensed users. Reinforcement learning (RL), which is an artificial intelligence approach, has been applied to enable each unlicensed user to observe and carry out optimal actions for performance enhancement in a wide range of schemes in CR, such as dynamic channel selection and channel sensing. This paper presents new discussions of RL in the context of CR networks. It provides an extensive review on how most schemes have been approached using the traditional and enhanced RL algorithms through state, action, and reward representations. Examples of the enhancements on RL, which do not appear in the traditional RL approach, are rules and cooperative learning. This paper also reviews performance enhancements brought about by the RL algorithms and open issues. This paper aims to establish a foundation in order to spark new research interests in this area. Our discussion has been presented in a tutorial manner so that it is comprehensive to readers outside the specialty of RL and CR.
In smart antenna applications, the adaptive beamforming technique is used to cancel interfering signals (placing nulls) and produce or steer a strong beam toward the target signal according to the calculated weight vectors. Minimum variance distortionless response (MVDR) beamforming is capable of determining the weight vectors for beam steering; however, its nulling level on the interference sources remains unsatisfactory. Beamforming can be considered as an optimization problem, such that optimal weight vector should be obtained through computation. Hence, in this paper, a new dynamic mutated artificial immune system (DM-AIS) is proposed to enhance MVDR beamforming for controlling the null steering of interference and increase the signal to interference noise ratio (SINR) for wanted signals.