The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
We present a deep learning architecture for learning fuzzy logic expressions. Our model uses an innovative, parameterized, differentiable activation function that can learn a number of logical operations by gradient descent. This activation function allows a neural network to determine the relationships between its input variables and provides insight into the logical significance of learned network...
Magnetorheological (MR) damper is a semi-active actuator, it responds to a variable control signal very fast in the meanwhile it requires a very low power. Due to the highly nonlinear dynamic nature, it is difficult to characterize the behavior of this actuator. The existing parametric modeling methods require to identify so many parameters that are difficult to implement. So the paper puts forward...
Autonomy, adaptability and reactivity are key capabilities of intelligent agents. Many applications of intelligent agents, such as control of ubiquitous computing environments or autonomous robotic systems, demand not only high performance and modeling capability but also the appropriate device or architecture (hardware and related software) for implementing the agent in a real environment. To deal...
Transfer learning based method, which utilizes plenty labeled data in the source domain to build an accuracy classifier for the target domain, serves as an effective means in the epileptic detection by using electroencephalogram (EEG) signals. Among existing approaches, Fuzzy logic system (FLS) based on transductive transfer learning is an efficient method due to its superior interpretability and...
This paper presents an approach based on Artificial Bee Colony (ABC) to optimize the parameters of membership functions of Sugeno based Adaptive Neuro-Fuzzy Inference System (ANFIS). The optimization is achieved by Artificial Bee Colony (ABC) for the sake of achieving minimum Root Mean Square Error of ANFIS structure. The proposed ANFIS-ABC model is used to build a system for predicting the wind speed...
This work introduces an Artificial Neuro-Fuzzy Inference System functioning as a selector of color constancy algorithms for the enhancement of dark images. The system selects among three algorithms, the White-Patch, the Gray-World and the Gray-Edge according to real content of an image. These three algorithms have been considered due to their simplicity and accurate remotion of the illuminant, further...
The status of any state of India depends significantly on various natural resources. The status may be developed, developing and under developed while natural resources may be climate, rivers flowing and the length of rainfall etc. In this paper, two natural resources such as number of rivers flowing and rainfall in that state have been taken at different times and their dependencies on the development...
The result of training parameters described Adaptive Neuro-Fuzzy Inference System (ANFIS) performance. The speed and reliability of training effect depend on the training mechanism. There have been many methods used to train the parameters of ANFIS as using GD, metaheuristic techniques, and LSE. But there are still many methods developed to achieve efficiently. One of the proposed algorithm to improve...
Recurrent drift, as a specific type of concept drift, is characterised by the appearance of previously seen concepts. Therefore, in those cases the learning process could be saved or at least minimized by applying an already trained classification model. In this paper we propose Fuzzy-Rec, a framework that is able to deal with recurrent concept drifts by means of a repository of classification models...
The development of Interval Type-2 Fuzzy Logic Systems has brought great improvements in the non-linear system modeling domain. However, in what concerns to the development of control systems, the approaches found in literature of Type-2 Fuzzy Sets do not seem to be taking fully advantage of the advances achieved by adaptive self-tuning algorithms, already well established in both academic and industrial...
The paper proposes a novel, simple and faster learning approach named ‘Extreme-ANFIS’ to tune premise and consequent parameters of Takagi-Sugeno Fuzzy Inference System (TS-FIS). Further the Extreme-ANFIS is used to design inverse model of nonlinear dynamical system. In this paper, the product concentration of non-isothermal Continuous Stirred Tank Reactor (CSTR) is controlled effectively by controlling...
Thenon-linear characteristics of wet scrubbing process have led to the application of intelligent control technique to adequately deal with these complexities by manipulating the liquid droplet size for the effective control of particulate matter (PM) contaminants. This includes the use of adaptive neuro-fuzzy inference system (ANFIS) to design an intelligent controller based on direct inverse model...
In the field of physical activity a significant importance is held by aerobic endurance training, which is a relatively low intensity exercise that depends primarily on aerobic energy generating processes. This type of training is used for the overall endurance and fitness of the body by engaging all the major systems of the body and pushing the limits of their functions with the ultimate goal of...
This paper present a novel approach to crude oil price prediction based on co-active neuro-fuzzy inference systems (CANFIS) instead of the commonly use fuzzy neural network and adaptive network-based fuzzy inference systems due to superiority and robustness of the CANFIS model. Monthly data of West Texas Intermediate crude oil price and organization for economic co-operation and development (OECD)...
Landslides are processes of erosion of catastrophic character which alter the morphology of the landscape and affect people, productive land and infrastructure. Recently, there have been several attempts to apply neural networks to predict landscape susceptibility to landslides. However, the knowledge of the neural network is expressed in a mathematical model that does not allow establishing, intuitively,...
It is important to predict battle damage level timely and accurately for operation commander to adjust firing action intent, issue command, control situations, and make decisions correctly. Adaptive neural fuzzy inference system (ANFIS) architecture and the hybrid-learning algorithm by applying back-propagation and least mean squares procedure are studied. ANFIS model for battle damage level prediction...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.