International Journal of Intelligent Systems and Applications @ijisa
Journal articles - International Journal of Intelligent Systems and Applications
All articles: 1251
Acoustic Signal Classification from Monaural Recordings
Scientific article
Acoustic domain contains signals related to sound. Speech and music though are included in this domain, both the signals differ with various features. Features used for speech separation does not provide sufficient cue for music separation. This paper covers musical sound separation for monaural recordings. A system is proposed to classify singing voice and music from monaural recordings. For classification, time and frequency domain features along with Mel Frequency Cepstral Coefficients (MFCC) applied to input signal. Information carried by these signals permit to establish results Quantitative experimental results shows that the system performs the separation task successfully in monaural environment.
Free
Adaptation of Induced Fuzzy Cognitive Maps to the Problems Faced by the Power Loom Workers
Scientific article
The Indian textile industry has a significant presence in the economy as well as in the international textile economy. In this research Paper we study the socio economic problems faced by power loom workers in Avinashi in Tamilnadu, India, using Induced Fuzzy Cognitive Maps (IFCMs). We have interviewed 50 households in the study area using a linguistic questionnaire. As the problems faced by them at large, involved so much of feelings and uncertainties. We felt it to fit to use fuzzy theory in general and induced fuzzy cognitive maps in particular. For IFCMs is the best suited tool when the data is an unsupervised one.
Free
Scientific article
This research involved developing a surgical robot assistant using an articulated PUMA robot running on a linear or nonlinear axis. The research concentrated on studying the artificial intelligence based switching computed torque controller to localization of an endoscopic tool. Results show that the switching artificial nonlinear control algorithm is capable to design a stable controller. For this system, error was used as the performance metric. Positioning of the endoscopic manipulator relative to the world coordinate frame was possible to within 0.05 inch. Error in maintaining a constant point in space is evident during repositioning however this was caused by limitations in the robot arm.
Free
Adaptive Inverse Model of Nonlinear Systems
Scientific article
This paper proposes nonlinear adaptive filter-bank (NAFB) based algorithm for inverse modeling of nonlinear systems. Inverse modeling has been an important component for sensor linearization, adaptive control, channel equalization in communication system and active noise control. Under practical situations, the plant/system behaves nonlinearly which can be modeled as both parallel and cascaded structures of linear and nonlinear transfer functions. These linear and nonlinear transfer functions can be either static or dynamic, time variant or time invariant. The proposed NAFB algorithms are applied to generate the inverse model of different types of nonlinear systems and their convergence performances are evaluated. These nonlinear inverse models can be suitably applied to many engineering applications.
Free
Adaptive Neuro-Fuzzy Inferential Approach for the Diagnosis of Prostate Diseases
Scientific article
In this study, Adaptive Neuro-fuzzy Inferential System (ANFIS) is adapted for diagnosing prostate diseases. The system involves generating and tuning a fuzzy inference system to handle the imprecise terms used for describing prostate cases and severity. Several diagnostic variables were used to learn the feature statistics present in a typical data, while the trained model was validated and adapted for testing new prostate cases. A total of 335 data from patients’ records were collected at the Medi Moses Prostate Centre, Kumasi Ghana. The dataset was partitioned into 70% which was used for model training, and the other 30% was utilized in the validation phase. The proposed model was implemented in the MATLAB environment. Evaluation result from the proposed system demonstrated that the system achieved an accurate diagnostic result with an RMSE value of 11%. This indicates that the system has a relatively high accuracy and could be accepted for prostate diagnosis. Furthermore, the model was able to learn well and generalize the features in the data set, making the proposed ANFIS model suitable for new cases. Performance analysis showed that the ANFIS is well suited for handling the crispy values used in prostate diagnosis; thus, it can be extensively employed in other similar areas of medical diagnosis.
Free
Adaptive Observers for Linear Time-Varying Dynamic Objects with Uncertainty Estimation
Scientific article
The method for construction adaptive observ-ers (AO) time-varying linear dynamic objects at non-fulfillment of condition excitation constancy (EC) is pro-posed. Synthesis of the adaptive observer is given as the solution of two tasks. The solution first a problem is a choice of the constant matrix decreasing the effect of EC condition. Procedures for obtaining of this matrix are proposed. The matrix specifies restrictions for a vector of parameters AO. The solution of the second problem gives a method of design adaptive multiplicative algorithms in the presence of the obtained restrictions. Procedures for an estimation uncertainty in an object are proposed. They are based on obtaining of static models giving the forecast change of uncertainty. Optimum estimations of the uncertainty are obtained which minimize an error between outputs of the object and AO. An exponential dissipativity of adaptive system is proved. The results of the modeling confirming the effectiveness of designed methods and procedures are presented.
Free
Adaptive Observers with Uncertainty in Loop Tuning for Linear Time-Varying Dynamical Systems
Scientific article
The method of construction adaptive observers for linear time-varying dynamical systems with one input and an output is offered. Adaptive algorithms for identification are designed. Adaptive algorithms not realized as an adaptive system contains parametric uncertainty (PU). Realized adaptive algorithms of identification parameters system are offered. They on the procedure of the estimation PU and algorithm of signal adaptation are based. The algorithm of velocity change system parameters estimation is proposed. Estimations PU and its misalignments are obtained. Boundedness of trajectories an adaptive system is proved. Exponential stability conditions of the adaptive system are obtained. Iterative procedure of construction a parametric restrictions area is proposed. Simulation results have confirmed the efficiency of the method construction an adaptive observer.
Free
Scientific article
This paper proposes a novel metaheuristic optimization algorithm and suggests an adaptive artificial neural network controller that based on the proposed optimization algorithm. The purpose of the neural controller is to track desired proposed velocities and path trajectory with the minimum error, in the presence of mobile robot parameters time variation and system model uncertainties. The proposed controller consists of two sub-neural controllers; the kinematic neural feedback controller, and the dynamic neural feedback controller. The external feedback kinematic neural controller was responsible of generating the velocity tracking signals that track the mobile robot linear and angular velocities depending on the robot posture error, and the desired velocities. On the other hand, the internal dynamic neural controller has been used to enhance the mobile robot against parameters uncertainty, parameters time variation, and disturbance noise. However, the proposed grass root population-based metaheuristic optimization algorithm has been used to optimize the weights of the neural network to have the behavior of an adaptive nonlinear trajectory tracking controller of a differential drive wheeled mobile robot. The proposed controller shows a very good ability to prepare an appropriate dynamic control left and right torque signals to drive various mobile robot platforms using the same offline optimized weights. Grass root optimization algorithms have been used due to their unique characteristics especially, theirs derivative free, ability to optimize discretely and continuous nonlinear functions, and ability to escape of local minimum solutions.
Free
Scientific article
This paper presents a fault tolerant control (FTC) based on Radial Base Function Neural Network (RBFNN) using an adaptive control law for double star induction machine (DSIM) under broken rotor bars (BRB) fault in a squirrel-cage in order to improve its reliability and availability. The proposed FTC is designed to compensate for the default effect by maintaining acceptable performance in case of BRB. The sufficient condition for the stability of the closed-loop system in faulty operation is analyzed and verified using Lyapunov theory. To proof the performance and effectiveness of the proposed FTC, a comparative study within sliding mode control (SMC) is carried out. Obtained results show that the proposed FTC has a better robustness against the BRB fault.
Free
Adaptive Random Link PSO with Link Change Variations and Confinement Handling
Scientific article
Particle Swarm Optimization is swarm based optimization technique. Swarm consists of particles and the particles fly through the problem space in Particle Swarm Optimization (PSO). Confinement methods and parameters such as Inertia Weight, Neighborhood of the particle have major impact on PSO performance. The paper presents variations of the PSO with adaptive random link neighborhood. The work carried out considers linearly decreasing inertia weight and different confinement methods. The performance of adaptive random link PSO by geometrical updation of velocity with confinement methods is tested here.
Free
Adaptive algorithm design for cooperative hunting in multi-robots
Scientific article
The multi-robot cooperative planning is gained significant attention in recent past mainly for the evaders hunting task. In evaders hunting, the robot nodes required to recognize their other team members and considering their current positions and capabilities to catch the stationary or moving evaders effectively through the cooperating path planning approach. The primary challenge to design cooperative multi-robot evader hunting system is efficient and adaptive coordination of multiple autonomous mobile robots with less delay and communication overhead in presence of big-size obstacles. The current solutions suffered from repeated hunting problem under the inaccessible network conditions due to the presence of big-size obstacles and ineffective utilization of known nodes information. In this paper, to alleviate the problem of repeated hunting and inefficient catching of all evaders in the network, we proposed the adaptive Bio-inspired Neural Network (ABNN) using the new shunting equation with the capability of adaptive hunting of all evaders in the system. We design ABNN based on the implicit robot to predict the next path to catch evaders efficiently by real robots. The use of implicit robot helps to prevent the big sized evaders and efficiently utilize the evader’s information. The simulation results demonstrate that ABNN performs efficient evaders hunting under the presence of big size obstacles.
Free
Adaptive finite-time convergence fuzzy ARX-laguerre system estimation
Scientific article
Convergence speed for system identification and estimation is a popular topic for determining the kinematics and dynamic identification/estimation of the parameters of robot manipulators. In this paper, adaptive fuzzy inverse dynamic system estimation is used to improve robust modeling, especially for a serial links robot manipulator. The Lyapunov technique is used to analyze the convergence rate of the tracking error and increase the accuracy response of the parameter estimation. Performance of robot estimation is conducted, and the results show fast convergence of the proposed finite time technique for a 6-DOF robot manipulator.
Free
Scientific article
Due to freedom to express views, opinions, news, etc and easier method to disseminate the information to large population worldwide, social media platforms are inundated with big streaming data characterized by both short text and long normal text. Getting the glimpse of ongoing events happening over social media is quintessential from the viewpoint of understanding the trends, and for this, topic modeling is the most important step. With reference to increase in proliferation of big data streaming from social media platforms, it is crucial to perform large scale topic modeling to extract the topics dynamically in an online manner. This paper proposes an adaptive framework for dynamic topic modeling from big data using deep learning approach. Approach based on approximation of online latent semantic indexing constrained by regularization has been put forth. The model is designed using deep network of feed forward layers. The framework works in an adaptive manner in the sense that model is extracts incrementally according to streaming data and retrieves dynamic topics. In order to get the trends and evolution of topics, the framework supports temporal topic modeling, and enables to detect implicit and explicit aspects from sentences also.
Free
Advanced Adaptive Particle Swarm Optimization based SVC Controller for Power System Stability
Scientific article
The interconnected systems is continually increasing in size and extending over whole geographical regions, it is becoming increasingly more difficult to maintain synchronism between various parts of the power system. This paper work presents an advanced adaptive Particle swarm optimization technique to optimize the SVC controller parameters for enhancement of the steady state stability & overcoming the premature convergence & stagnation problems as in basic PSO algorithm & Particle swarm optimization with shrinkage factor & inertia weight approach (PSO-SFIWA). In this paper SMIB system along with PID damped SVC controller is considered for study. The generator speed deviation is used as an auxiliary signal to SVC, to generate the desired damping. This controller improves the dynamic performance of power system by reducing the steady-state error. The controller parameters are optimized using basic PSO, PSO-SFIWA & Advanced Adaptive PSO. Computational results show that Advanced Adaptive based SVC controller is able to find better quality solution as compare to conventional PSO & PSO-SFIWA Techniques.
Free
Scientific article
Heart attacks continue to be one of the primary causes of death globally, highlighting the critical need for advanced predictive models to improve early diagnosis and timely intervention. This study presents a comprehensive machine learning (ML) approach to heart attack prediction, integrating multiple datasets from diverse sources to construct a robust and accurate predictive model. The research employs a stacking ensemble model, which combines the strengths of individual ML algorithms to improve overall performance. Extensive data preprocessing steps were carefully undertaken to preserve the dataset's integrity and maintain its quality. The results demonstrate a superior accuracy of 97.48%, significantly outperforming state-of-the-art approaches. The high level of accuracy indicates the model’s potential effectiveness in the clinical setting for early detection of heart attack and prevention. However, the proposed model is influenced by the quality and diversity of the integrated datasets, which could affect its generalizability across broader populations. Challenges encountered during the model's development include optimizing hyperparameters for multiple classifiers, ensuring data preprocessing consistency, and balancing computational efficiency with model interpretability. The results underscore the pivotal contribution of advanced ML approaches in revolutionizing the management of cardiovascular attack. By addressing the complexities and variabilities inherent in heart attack prediction, the work provides a pathway towards more effective and personalized cardiovascular disease management strategies, demonstrating the transformative potential of ML in healthcare.
Free
Advanced Mobile Surveillance System for Multiple People Tracking
Scientific article
The paper develops an efficient people surveillance system capable of tracking multiple people on different terrains. Recorded video on rough terrains is affected by jitters resulting into significant error between the desired and captured video flow. Video stabilization is achieved by calculating the motion and compensational parameters using the LSE analytical solution to minimize the error between present and desired output video captured from an autonomous robot’s camera moving on a rough terrain used for surveillance of unidentified people. This is the first paper to the best of our knowledge which makes use of this method to design mobile wireless robot for human surveillance applications. As the method used is fast then conventional methods, making the proposed system a highly efficient surveillance system as compared to previous systems. The superiority of the method used is demonstrated using different evaluation parameters like RMCD, variability and reliability. The system can be used for surveillance of people under different environmental conditions.
Free
Advances in Multimodal Biometric Authentication: A Classifier Fusion and Deep Learning Perspective
Scientific article
The rapid advancements in deep learning and classifier fusion techniques offer promising solutions to enhance the accuracy and robustness of biometric authentication systems in this paper we propose the integration of these methodologies, specifically in multimodal biometric systems that utilize face and fingerprint recognition. The research investigates various deep learning architectures, highlighting their effectiveness in processing diverse biometric datasets. Additionally, it examines classifier fusion techniques, which combine multiple classifiers to improve person identification performance. A significant focus of this research is on spoofing and anti-spoofing measures. Biometric systems, especially those involving facial and fingerprint recognition, are vulnerable to spoofing attacks such as the use of photographs, videos, or artificial fingerprints to impersonate legitimate users. We developed various anti-spoofing strategies that are integrated into the biometric authentication process to mitigate these risks. These include techniques like texture analysis, motion analysis, and liveness detection, which help differentiate between genuine biometric traits and spoofed samples. We benchmarked a comparative analysis of deep learning models and classifier fusion, demonstrated their strengths, weaknesses, and best practices. Additionally, performance evaluations focus on key metrics such as accuracy, computational efficiency, scalability, and the system’s ability to resist spoofing attacks. Ultimately, the paper emphasizes the potential of these advanced techniques to revolutionize biometric systems, with a particular focus on future research directions for optimizing these methodologies, particularly in the context of improving robustness against spoofing and enhancing the overall security of biometric authentication systems. overall system Equal Error Rate (EER), the True Acceptance Rate at a specified False Acceptance Rate (e.g., TAR @ 0.1% FAR), and the accuracy of the anti-spoofing module.
Free
Agent-Based Buyer-Trader Interaction Model of Traditional Markets
Scientific article
One problem in simulating crowds in traditional markets is calculating the interaction duration between traders and buyers. This problem can be solved in a simple way by doing field observation to obtain some samples to find the average interaction duration between traders and buyers. This method is simple. On the other hand, the result will be less valid if the parameters are change. The purpose of this research is to develop an interaction model between traders and buyers by looking deeper into the negotiation process. This model is developed based on multi-agent system. Output of this model is the interaction duration. This model has been implemented in a traditional market crowd simulation. Based on the simulation, by adjusting the parameters in this model, the interaction duration by the model matches the real condition in traditional markets.
Free
Agent-Based Crowd Simulation of Daily Goods Traditional Markets
Scientific article
In traditional market, buyers are not only moving from one place to another, but also interacting with traders to purchase their products. When a buyer interacts with a trader, he blocks some space in the corridor. Besides, while buyers are walking, they may be attracted by non-preferred traders, though they may have preferred traders. These situations have not been covered in most existing crowd simulation models. Hence, these existing models cannot be directly implemented in traditional market environments since they mainly focus on crowd members' movement. This research emphasizes on a crowd model that includes simplified movement and unplanned purchasing models. This model has been developed based on intelligent agent concept, where each agent represents a buyer. Two traditional markets are used for simulation in this research, namely Gedongkuning and Ngasem, in Yogyakarta, Indonesia. The simulation shows that some places are visited more frequently than others. Overall, the simulation result matches the situation found in the real world.
Free
Agent-based Models in Synthetic Biology: Tools for Simulation and Prospects
Scientific article
We describe a multiset of agents based modeling and simulation paradigm for synthetic biology. The multiset of agents –based programming paradigm, can be interpreted as the outcome arising out of deterministic, nondeterministic or stochastic interaction among elements in a multiset object space, that includes the environment. These interactions are like chemical reactions and the evolution of the multiset can emulate the system biological functions. Since the reaction rules are inherently parallel, any number of actions can be performed cooperatively or competitively among the subsets of elements, so that the elements evolve toward equilibrium or emergent state. Practical realization of this paradigm for system biological simulation is achieved through the concept of transactional style programming with agents, as well as soft computing (neural- network) principles. Also we briefly describe currently available tools for agent-based-modeling, simulation and animation.
Free
