Search

In wireless sensor networks (WSNs), a number of outlier detection (OD) methods have been established over time to identify data that do not match the rest of the data. These data are anomalies, outliers, or irregularities because they result from hostile attacks or sensor node malfunctions. OD is difficult due to the classification process and the challenges in feature development. The limitations of conventional OD include insufficient feature learning, noise, excessive dimensionality, and a lack of training data. Unsupervised outlier detection (UOD) in WSNs is a new research area that has been ascertained to perform exceptionally well in terms of detection accuracy. The fact that prior knowledge of abnormal data is unknown, i.e., the ground truth of data is unknown for the classification of outlier instances, is a substantial barrier in UOD. This made it possible for researchers to examine flexible deep learning methods for domain-specific UOD, like Variational AutoEncoder (VAE). In order to achieve an appropriate categorization of anomalous data, this research suggests using a Modified Variational AutoEncoder (ModVAE) model with a rule-based approach. In the first stage of the proposed system, an adaptive VAE model is developed to produce modified latent space vector samples suitable for reproducing the data with reasonable reconstruction loss, and in the second stage, fuzzy rules are generated to precisely classify abnormal data with fewer false positives. The suggested model's efficiency is demonstrated with experiments done using benchmark datasets. The experimental results show improved performance when compared with other approaches available in the literature. [ABSTRACT FROM AUTHOR]

Echocardiographic strain imaging is used to quantify cardiac deformation noninvasively through various techniques including non-rigid image registration. However, non-rigid image registration should be strong enough to deal with the poor spatiotemporal resolution of echocardiographic images. Extracting relevant features and calculating a suitable geometric transformation for the relevant features are the main parts of a registration problem. This paper aims to introduce a suitable geometric transformation for quantifying cardiac deformation based on a modified fuzzy inference system (FIS). The proposed method extracts relevant features of two echocardiographic images to generate proper rules for registration of two echocardiographic images. The modified FIS comprises two FISs in a series structure. We evaluated the performance of the proposed method for echocardiographic motion estimation with both in silico and in vivo databases. Applying the proposed method to the well-known STRAUS database resulted in 0.68 mm tracking error and 0.5 ± 3.78 relative circumferential strain error, which indicate the competitiveness of the proposed method with the state-of-the-art algorithms. In addition, the obtained results from in vivo database, CETUS, expressed the potential of the suggested algorithm for clinical application. [ABSTRACT FROM AUTHOR]

Common interventions to control the spread of cholera include improving sanitation, hygiene, and access to safe drinking water and providing epidemic regions with sufficient treatment kits and oral vaccines. Due to resources limitation, these interventions should be guided by a risk assessment of cholera-affected regions, thereby targeting regions based on their risk level. Cholera risk assessment is very challenging because of the lack of precise and reliable data. This study proposes an approach for cholera risk assessment and vaccine allocation, which consists of two phases: (i) cholera risk assessment, where a fuzzy inference system (FIS) is proposed to evaluate the risk level of cholera-affected regions based on five cholera risk indicators: (1) attack rate, (2) case fatality rate, (3) the number of internally displaced persons, (4) accessibility of water, sanitation and hygiene, and (5) accessibility of cholera treatment; (ii) cholera vaccine allocation, where a mixed-integer programming model is used to optimize the allocation of limited vaccine doses among multiple regions over multiple periods while considering the risk level, population of regions, and vaccine efficacy. The model answers the questions of where, what amounts, and when to send vaccines during a 2-year horizon. Implementation of the proposed approach is illustrated using a case study from Yemen, which is currently experiencing the world's worst cholera outbreak according to the World Health Organization. The results reveal the usefulness of the proposed approach in mapping the cholera risk, which in turn is used as effective guidance for the allocation of cholera vaccine. [ABSTRACT FROM AUTHOR]

This paper aims to propose an efficient algorithm for the synchronization of 4-D memristive chaotic systems and their applications for audio secure communication. A dual-function-link (DFL) fuzzy brain emotional controller (DFFBEC) is produced for synchronizing two types of 4-D memristive chaotic systems that are a 4-D hyperjerk memristive chaotic system and a 4-D memristive hyper-chaotic system. The proposed DFFBEC consists of three main networks that are a DFL network, a prefrontal cortex, and an amygdala. The gradient descent algorithm is used to derive the online learning laws for the proposed DFFBEC. Simulation studies of two 4-D memristive chaotic systems including external perturbations and non-deterministic perturbations, and an application for audio secure communication are studied to validate the capability and performance of the proposed DFFBEC. The results show that the proposed method can accommodate the system perturbation very well. Finally, the comparative results with some recent controllers and some other analytical results are used to illustrate the capability and performance of the proposed DFFBEC. [ABSTRACT FROM AUTHOR]

This study proposed the application of a nanofluid/ultrasonic atomization minimum quantity lubrication (MQL) method to grind Inconel 718 alloys. This is a grinding manufacturing innovation on lubrication technology. Multiwall carbon nanotubes (MWCNTs) and molybdenum disulfide (MoS2) nanoparticles were used as the nanofluid additives. Specifically, MWCNTs exhibit excellent thermophysical properties to effectively remove the heat generated by cutting and reduce the friction coefficient, and MoS2 has excellent lubricating properties to generate film layers with high wear resistance to protect the workpiece and avoid plowing. The parameters of multiple performance characteristics were optimized through applications of the Taguchi robust design method, grey relational analysis, and a fuzzy inference system. The control parameters comprised nozzle angle, distance of the nozzle, type of nanoparticle, fraction of the nanofluid, value of atomization, tangential velocity, table rate, and air pressure. Subsequently, the optimized result was compared with basefluid/ultrasonic atomization MQL and nanofluid MQL. The results revealed that nanofluid/ultrasonic atomization MQL yields the optimal grinding force ratio, grinding temperature, and surface roughness. [ABSTRACT FROM AUTHOR]

This study proposes an efficient estimator and uses it to estimate the health of a lithium-ion battery and a supercapacitor in the hybrid energy storage system (HESS). A new type of online health estimator that uses a fuzzy brain emotional learning neural network (FBELNN) is proposed. This neural network is different to a conventional brain emotional learning neural network where the fuzzy inference system and a new reward signal are used. The effect capacity fading on the output of energy storage components is also determined. The proposed method uses a discrete wavelet transform (DWT) and principal component analysis (PCA) to extract features from the response signal for the impulse load. The DWT-PCA can reduce the workload for feature extraction. The parameter adaptation laws and convergence analysis for the FBELNN are derived and the internal parameters for the FBELNN are optimized using a genetic algorithm (GA). A neural network estimates the capacity of a supercapacitor and lithium-ion battery in real-time to better ensure the safety of HESS. The sample set is collected from the voltage response signal in the HESS simulation platform and practical experimental platform. Simulation and experimental results show that the proposed method has a faster learning speed and is more accurate than other methods. [ABSTRACT FROM AUTHOR]

The older population faces a high probability of experiencing age-related problems, such as osteoporosis, immobility, gait disturbances, stroke, Parkinson's disease, and cognitive behavioral functional difficulties. Such problems negatively affect their lives. Thus, access to long-term care is a critical issue for older adults. In response to the aforementioned serious health issues, society must strive to provide a supportive and effective rehabilitation environment for older adults. This study designed an intelligent active and passive limb rehabilitation system to track and quantify the effectiveness of joint movements in patients automatically. The proposed method uses a camera and PoseNet to capture key feature information regarding human skeleton nodes and identify rehabilitation actions through joint movements. In addition, to solve the problem of joint occlusion during joint angle measurement, the designed system is equipped with a self-designed inertial measurement unit with GY-85 nine-axis sensors, which are mounted on the occluding part of the joints. A fuzzy inference system was developed to provide scores, suggestions, and encouragement for each rehabilitation session. This system also provides an interactive interface for users to monitor each rehabilitation session and examine whether rehabilitation is performed accurately. [ABSTRACT FROM AUTHOR]

The current state of sustainability is promoting the status of the supply chain from traditional economic objectives related to the cost, quality, and time to the multidimensional opportunities in terms of economic, social and environmental fronts. The paper deals with the development of a decision support framework for the prioritization of suppliers on sustainability factors. The framework is based on the combined approach of the analytical hierarchical process (AHP) and the fuzzy inference system (FIS) to evaluate the supplier for the benefit of the manufacturer. The role of AHP is to select the significant factors as criteria, while the FIS mechanism works to measure the sustainability index of each supplier for prioritization from the combined effect of the selected factors. In the ranking process, experts' opinions on the importance of deciding the criteria (developed by the AHP) are considered in linguistic terms. To handle the subjectivity of decision makers assessments, fuzzy logic has been applied using FIS. In addition, uncertainties in the decision making support system are overcome by considering the fuzzy set theory for the selected sustainable factors. A numerical experiment is carried out to consider seven suppliers working with the goalkeeping gloves manufacturing firm for the pragmatic application of the proposed framework. The methodology of the integrated AHP–FIS approach is utilized to rank the suppliers by calculating the sustainability index value. The proposed approach provides a platform for the manufacturer to better understand the capability, sustainable suppliers must possess to continue working with them for the sustainable supply chain management. [ABSTRACT FROM AUTHOR]

This paper displays how to use fuzzy inference system (FIS) to control the individual uniform diversity for differential evolution algorithm (DE). DE solves nonlinear optimization problems, and a successful control mechanism for population diversity enhances the performance of DE. This study proposed a control mechanism that contains a novel mutation strategy and FIS because FIS is suitable for consecutive and hard classified inputs. The proposed control mechanism does not fix the target vector and controls the ratio of mutating toward the whole best individual by FIS. The FIS decides the F values for this novel mutation strategy. The experiments compared the winner of each evaluated functions among four uniform diversity goals (UDGs) with conventional strategies. From experimental results, the proposed method finds superior solutions to conventional mutation strategies at least 11 out of 15 evaluated functions in 10, 30, and 50 dimensions. Furthermore, not only the diversity curves confirm the control ability of FIS, but also different paths of convergence curves indicate the fast convergence and mitigation of evolutionary stagnation. [ABSTRACT FROM AUTHOR]

Face recognition addresses identification, verification, and authentication in biometric-based security systems. This work enhances the contrast and edges in face images and recognizes the face using contourlet transform and fuzzy rules. Contourlet transformed image provides multiscale and directional information. The transformed image is divided into low-pass image (low-frequency image) and band-pass image (high-frequency image). The low-pass image is enhanced using fuzzy-based histogram specification since it deals with contrast. Band-pass image contains detailed information about the edges of the image and are enhanced using fuzzy rules and morphological gradient operators. The proposed system achieves the accuracy rate of 99.81% and 99.35% on Yale-B and JAFEE dataset, respectively, which is better than the existing curvelet and wavelet transform-based recognition. The incorporation of fuzzy rules enhances the mean intensity value of the edges to 34.19, which is better than Canny, Sobel, Prewitt, Robert and Laplacian edge detection techniques. Finally Discriminant Correlation Analysis (DCA) feature level fusion is applied to fuse enhanced edge intensities and histogram features for Support Vector Machine (SVM) classification. [ABSTRACT FROM AUTHOR]

Mobile ad hoc network comprises of wireless nodes which are mobile in nature and have short lifespan. They join together to create a self-configured infrastructure-less network where routing is an important challenge. In AODV routing, the hello messages are broadcast periodically by nodes for monitoring the link connectivity to neighbors and for maintaining routing table. The broadcasting of hello messages increases when link failure occurs due to node mobility, which leads to higher consumption of node energy and increases overhead within network. This paper proposes an energy-efficient routing approach (EE-RA), which calculates optimal hello interval for reducing the unnecessary broadcasting of hello messages that further reduces node’s energy consumption and network overhead. This is achieved by using Mamdani-based fuzzy inference system and adaptive neuro-fuzzy inference system (ANFIS) to calculate the resultant optimal hello interval in which energy and mobility of node are taken as inputs. Moreover, simulation results illustrate that the performance of EE-RA outperforms AODV and achieve better results for ANFIS in hello message fraction, network overhead, average energy consumption, packet delivery ratio, end-to-end delay and throughput, especially in highly mobile and dense environment. [ABSTRACT FROM AUTHOR]

A coating collapse occurs when large parts of coating break away from the refractory of a rotary kiln in a cement plant. If the collapse is more conspicuous, the cooler may become filled with excessive material, causing the clinker transport systems to overload and the temperature in the cooler outlet to rise excessively. An unstable coating quickly causes problems with the refractory material, resulting in a loss of energy that disturbs the stable operation of the kiln. Variable amounts of coating in the burning zone also influence the kiln torque. A coating collapse is normally detected by the operator through the trend curve of kiln drive amps. This paper explains the application of empirical mode decomposition with a fuzzy inference system and a fuzzy neural network to identify a kiln coating collapse and predict refractory failure in the cement process. The results show that the proposed method improved considerably upon the original. [ABSTRACT FROM AUTHOR]

This paper aims to propose a more efficient control algorithm to select suitable firing nodes, improve the computational efficiency, reduce the number of firing rules and achieve good performance for nonlinear chaotic systems. A novel function-link fuzzy cerebellar model articulation controller (FLFCMAC) is designed by using a multiple attribute decision-making method named as technique for order of preference by similarity to ideal solution (TOPSIS). The TOPSIS is used to determine the optimal threshold values for receptive-field basis function in association memory space such that the firing fuzzy rules can be effectively reduced. In the TOPSIS design, the Shannon entropy index is used to derive the objective weights of the evaluation attribute. The proposed control system is composed of a TOPSIS-based FLCMAC (TFLFCMAC) and a fuzzy compensator. The TFLFCMAC is the main tracking controller employed to mimic an ideal controller, and the fuzzy compensator can eliminate the approximation error between the TFLFCMAC and the ideal controller. The parameters of the proposed TFLFCMAC are tuned online using the adaptation laws that are derived from a Lyapunov stability theorem, so that the system’s stability is guaranteed. Finally, the proposed control system is applied to a Duffing-Holmes chaotic system and a gyro chaotic system to illustrate its favorable control performance and to show its superiority to the other control techniques. [ABSTRACT FROM AUTHOR]

Skeletal age assessment is applied as an indicator of skeletal development for finding out growth pathologies related to hormonal diseases, and in endocrine and nutritional diagnosis. Other more recent applied methods include the Tanner and Whitehouse method as well as the Greulich and Pyle method. However, both methods need an expert to manually compare and assess the stages of skeletal growth. This is a time-consuming process involving subjective decision-making in pediatric radiology. The objective of this research is to develop a new fully automated and highly accurate approach based on a fuzzy inference system for the assessment of skeletal age in a living individual. Fuzzy logic as an intelligent computing technique is presented to deal with uncertainty as well as incomplete data. The system is implemented using MATLAB's fuzzy tool box. Our system attempts to quantify eight features that correlate highly with growth and maturity of skeletal age. The system was evaluated with standard cases of hand radiographs for subjects between 11 and 17 years old. It has conclusively been found that there was a high linear relation between the system age assessment and chronological age, and our new method provides reliable results in the estimation of the skeletal age. [ABSTRACT FROM AUTHOR]

Prostate cancer is one of the main causes of death among men in the world. In the first stage, the authors have proposed a mathematical modeling for the early detection of prostate cancer using the measurement of prostate-specific antigen (PSA) level in blood, age, and prostate volume (PV) of patients. These are used as input parameters into fuzzy tools and using fuzzy rules we evaluate the risk status as output variable. This paper presents a gradation and staging system of prostate cancer using PSA level in blood of patients and Gleason score which provides a useful platform to physicians in determining the status of the disease. In the second stage, the authors present an investigative study on prostate cancer disease and used the neuro-fuzzy classification system for pattern recognition for earliest possible treatment planning. [ABSTRACT FROM AUTHOR]

This paper proposes a novel evolutionary computation (EC) algorithm, fuzzy scaled mutation evolutionary computation (FSMEC), for solving nonlinear numerical optimization problems. Although EC has been typically used for obtaining nonlinear optimal solutions for several years, users are required to determine the parameters of the algorithm. In this study, a fuzzy inference system (FIS) was used to determine the mutation factor of the FSMEC algorithm according to the change in the solution and the distance between the whole best and each individual. The experimental results revealed that the FIS operates effectively. CEC2013 numerical optimization problems without rotation and shift were used as test functions. The FSMEC algorithm determined optimal solutions in 10, 30, and 50 dimensions for all unimodal functions. The convergence generations were less than 100 in 10 dimensions. The FSMEC algorithm obtains 16, 11, and 10 optimal values for 28 functions in 10, 30, and 50 dimensions, respectively. Moreover, statistical hypothesis tests demonstrated that the performance of the FSMEC algorithm in deriving optimal solutions was 68 %, which was higher than those of the FADE and SMEC algorithms for 28 test functions. [ABSTRACT FROM AUTHOR]

This study develops an electrical detection method for the diagnosis and fault detection of induction motors. An experiment constructs two types of defect models: broken bar and dynamic eccentricity. Electrical signals acquired during the operation of a motor are transformed through a fast Fourier transform to obtain the feature frequency components for identifying the type of motor fault. Subsequently, the Clark-Concordia transform is used to compare the stator current Concordia pattern between faulty and healthy motors. Finally, a fuzzy inference system is designed for assessing the severity of motor faults. The proposed method not only can diagnose the type of motor fault, but can also assess the operational state of a motor. The method is suitable for preparing a maintenance program for induction motors and for reducing their excessive maintenance cost. [ABSTRACT FROM AUTHOR]

In this paper, we investigate the multi-user performance in a two-dimensional (2-D) spreading orthogonal frequency coded division multiplexing (OFCDM) communication system over frequency and time selective fading channels. To compromise between diversity gain and multiple access interference (MAI), we propose an adaptive fuzzy inference system to infer adequate 2-D spreading factors and to assign the orthogonal variable spreading factor (OVSF) codes to active users for OFCDM mobile communication systems. Simulation results show that the proposed fuzzy-based code allocation (FBCA) scheme not only suppresses the MAIs induced by non-orthogonality but also exploit the diversity gain over time and frequency selective fading channels and then outperforms the orthogonal code allocation (OCA) scheme at all system loads. [ABSTRACT FROM AUTHOR]

Cognitive ability screening instrument (CASI) is a cross-cultural mental screening test to evaluate the severity of dementia of Alzheimer's disease. In this research, a characteristic-point-based fuzzy inference system (CPFIS) is proposed to predict the CASI scores from the single-photon emission computed tomography (SPECT) volumes. Experiment results showed that CPFIS could provide a rough estimation of CASI scores that the P value for the hypothesis that the average of absolute errors of CPFIS is less than the average of absolute differences from the mean values was 0.0447. For comparison, a weighted support vector regression (SVR) machines was also tried. The performance of CPFIS was slightly better than SVR in this study (P=0.068). [ABSTRACT FROM AUTHOR]