23 research outputs found
Allergic diseases of the skin and drug allergies – 2033. Metronidazole skin testing associated with systemic reaction
No full textStock prediction, trading simulation and options volatility prediction using FASCOM++ (fuzzy associative cortical maps architecture)
No full textFuzzy Associative Cortical Maps Architecture (FASCOM) is inspired from the cortical maps found in many biological and artificial neural systems. The cortical maps organise and represent information obtained from sensory inputs and play important roles in learning and memory processes. FASCOM uses features inspired by the structure and functions of cortical maps and is integrated a linguistic fuzzy model to perform associative learning of input-output pairs. The project undertakes to improve the architecture of FASCOM to incorporate a learning mechanism, so that the network is capable of modifying its properties on the basis of the incoming data leading to better prediction and higher accuracy.
The author aims to validate the modified architecture of FASCOM by conducting benchmarking experiments and observing the improvement in the performance of the system over other systems. For this purpose, various classical datasets for classification and regression problems were used.
The author worked on many real-life application to observe FASCOM++’s performance on real-life data. One of the applications is stock data prediction where the author used Hong Kong stock data and predicted prices using FASCOM++ and compared the results with the actual prices. The analysis of FASCOM++’s performance helps in gauging its practical use in real-life applications such as stock trading. The author simulated a simple stock trading algorithm to compare and evaluate FASCOM++’s performance against other architectures.
The author explored other areas of applications and worked on options volatility prediction which is one of the core areas of research in the financial industry. By exploiting on the online learning capabilities FASCOM++ was able to perform better than the other architectures and demonstrated its capability to be a potential architecture for real-life purpose.Bachelor of Engineering (Computer Science
Método para el diagnóstico, pronóstico y/o tratamiento del lupus eritematoso sistémico
No full text[EN] The present invention relates to the field of biomedicine. Specifically, the invention provides methods that allow
the diagnosis, prognosis and/or treatment of systemic lupus erythematosus (SLE) disease..[ES] La presente invención se encuadra dentro del campo de la biomedicina. Especificamente, provee de métodos que
permiten el diagnóstico, el pronóstico y/o el tratamiento de la enfermedad del Lupus Eritematoso Sistémico (LES).Peer reviewedConsejo Superior de Investigaciones Científicas (España), Tan Tock Seng HospitalA1 Solicitud de patente con informe sobre el estado de la técnic
BBIPS : a blackboard based intergrated process supervision
No full textThe research effort undertaken by the author attempts to investigate the use of the blackboard architecture to realize the Integrated Process Supervision paradigm in a heterogeneous control environment that supports dynamic switching of control regimes and their corresponding techniques.Master of Engineering (SCE
Recurrent correlation associative memories
No full textThe online technique of neuro-fuzzy system has been increasing in popularity in the recent years. In actuality external factors play an important role in the time-variant dataset, changing its pattern. This change in pattern is known as drift and shift. To tackle these changes, Hebbian learning was introduced. However this learning is characterised by uni-directional learning, resulting in the instability of the model.
Hence, the BCM theory was developed to overcome the problem of Hebbian learning through the provision of Hebbian and Anti-Hebbian learning.
However, time variant data possesses both dynamic and temporal problems. The purpose of the author is to address this issue through the modification of the current recurrent fuzzy neural network. The underlying principle is to store past information to be recalled later for application in the current context.
The existing recurrent neuro-fuzzy system shows promising results that motivates the author to further the efficacy of the recurrent neuro-fuzzy system.
This report proposes a recurrent neuro-fuzzy system that uses the BCM theory of online learning with self-organizing effectiveness. In addition, rules are represented using the Takagi Sugeno Kang model to achieve a better accuracy compared to the Mamdani model which focuses on interpretability.
The performance of Recurrent SeroTSK is evaluated and compared against neuro-fuzzy systems through various time-series benchmark experiments and prediction for cancer diagnosis which is a classification data. The results show that Recurrent SeroTSK is better for time-series prediction and it works for classification data as well.Bachelor of Engineering (Computer Science
Ventilator control with ieRSPOP++ and ieRSPOP (FRI/E) using interpolative and extrapolative reasoning
No full textArtificial Intelligent is the rising technique that have been widely used in expert task domain, like trading analysis/decision and medical sector. Many different learning algorithm have emerged over past few decades. Fuzzy logic is known for its high interpretability. Therefore, Fuzzy logic & Neural Network are combined to have an understandable reasoning and conclusion.
Pseudo outer-Product Fuzzy Neural Network (POPFNN) with Rough Set attribute reduction (RSPOP) have shown to have achieved high interpretability with moderately high accuracy. The improved online learning ieRSPOP (incremental ensemble learning RSPOP) handle well time series data and the result are promising. ieRSPOP is further improved into two ways, ieRSPOP++ and ieRSPOP with interpolation and extrapolation (ieRSPOP FRI/E). The former method is to improve accuracy and interpretability with anti-hebbian learning and Ebbinghaus theory for dynamic updating of ensemble weights. The latter is used interpolation and extrapolation method to handle sparse rule based condition.
ieRSPOP FRI/E have shown that its achievement over time series data like Mackey Glass time series and stock market prediction to other methods. However, the application of it to medical sector is still lacking.
In this paper, author investigated these two architectural functionalities, providing the actual implemental architectural flow of ieRSPOP FRI/E, it will server a better understanding for the existing ieRSPOP family structure and deep insight of the method explained. The ieRSPOP FRI/E experiment on artificial ventilation modelling is done and strength and weakness of existing system is identified.
Recent researches have shown that people are interested in handling sparse data because these data can make an impactful decision for financial and medical expert task. Therefore, how these two architectural can be further improvement when dealing with sparse data is discussed for future development as well.Bachelor of Engineering (Computer Science
