Wahyudi Martono

Keystroke pressure-based typing biometrics authentication system using support vector machines

Security of an information system depends to a large extent on its ability to authenticate legitimate users as well as to withstand attacks of various kinds. Confidence in its ability to provide adequate authentication is, however, waning. This is largely due to the wrongful use of passwords by many users. In this paper, the design and development of keystroke pressure-based typing biometrics for individual users verification which based on the analysis of habitual typing of individuals is discussed. The combination of maximum pressure exerted on the keyboard and time latency between keystrokes is used as features to create typing patterns for individual users so as to recognize authentic users and to reject impostors. Support vector machines (SVMs), which is relatively new machine learning, is used as a pattern matching method. The effectiveness of the proposed system is evaluated based upon False Reject Rate (FRR) and False Accept Rate (FAR). A series of experiment shows that the proposed system is effective for biometric-based security system.

Improved intelligent identification of uncertainty bounds: design, model validation and stability analysis

Identification of uncertainty bounds in robust control design is known to be a critical issue that attracts the attention of research in robust control field recently. Nevertheless, the practical implementation involves a trial and error procedure, which depends on the designer prior knowledge and the available information about the system under study. Artificial intelligent techniques provide a suitable solution to such a problem. In this paper a new intelligent identification method of uncertainty bound utilises an adaptive neuro-fuzzy inference system (ANFIS) in an enhanced feedback scheme is proposed. The proposed ANFIS structure enables accurate determination of the uncertainty bounds and guarantees robust stability and performance. In our proposed technique, the validation of the intelligent identified uncertainty weighting function is based on the measurement of both the v-gap metric and the stability margin that result from the corresponding robust controller design. Additionally, these two indices are used to improve the accuracy of the intelligent estimation of uncertainty bound in conjunction with the robust control design requirements. The enhanced intelligent identification of uncertainty bound is demonstrated on a servo positioning system. Simulation and experimental results proves the validity of the applied approach; more reliable and highly efficient estimation of the uncertainty weighting function for robust controller design.

Active engine mounting control algorithm using neural network

This paper proposes the application of neural network as a controller to isolate engine vibration in an active engine mounting system. It has been shown that the NARMA-L2 neurocontroller has the ability to reject disturbances from a plant. The disturbance is assumed to be both impulse and sinusoidal disturbances that are induced by the engine. The performance of the neural network controller is compared with conventional PD and PID controllers tuned using Ziegler-Nichols. From the result simulated the neural network controller has shown better ability to isolate the engine vibration than the conventional controllers.

Active engine mounting controller using extended minimal resource allocating networks

The application of the Extended Minimal Resource Allocation Network (EMRAN) in the field of active vibration isolation for an automotive engine system is presented. As the source of disturbance the engine is mounted on a two passive mounts in parallel with an active force actuator. EMRAN is implemented to control the force actuator and to isolate this disturbance. The characteristic of EMRAN and the criteria for growing and pruning of hidden layers are presented. EMRANs capability is compared with a PID controller and NARMA-L2 neural controller and shows superior performance in rejecting sinusoidal disturbances and achieving the chassiss vibration isolation.

Vibration control of two-mass rotary system using improved NCTF controller for positioning systems

In this paper, a nominal characteristic trajectory following (NCTF) controller for point-to-point (PTP) positioning system for two mass rotary system is introduced and its performance is evaluated. Generally, the NCTF controller consists of a nominal characteristic trajectory (NCT) and a compensator. The objective of the NCTF controller is to make the object motion follow the NCT and end at its origin. The NCTF controller is designed based on a simple open-loop experiment of the object. The parameters and an exact model of the plant are not necessary for controller design. This paper presents a method to improve the existing NCTF controller for two mass rotary positioning system by adding a notch filter as a compensator to eliminate the vibration due to the mechanical resonance. They can often remove resonance without compromising performance. The improved NCTF controller is evaluated and discussed based on results of simulation. The effect of the design parameters on the robustness of the NCTF controller to inertia and friction variations is evaluated and compared with conventional PID controller. It is shown that improved NCTF controller is better than conventional PID controller.

Design of Fusion Classifiers for Voice-Based Access Control System of Building Security

Secure buildings are currently protected from unauthorized access by a variety of devices. Nowadays, there are many kinds of devices to guarantee the building security such as PIN pads, keys both conventional and electronic, identity cards, cryptographic and dual control procedures. In this paper, voice-based biometric system is introduced for access control. The ability to verify the identity of a person by analyzing his/her speech, or speaker verification, is an attractive and relatively unobtrusive means of providing security for admission into an important or secured place. An individual’s voice cannot be stolen, lost, forgotten, guessed, or impersonated with accuracy. In the field of speaker verification, the main objective is to achieve the highest possible classification accuracy. The proposed system focused on combining the classification scores. In score fusion, each feature set is modeled separately, and the output score of the classifiers are combined to give the overall match score. Furthermore, for each classifier score, an a priori weight is set based on the level of confidence of the feature set and the classifier. The classifiers involved in this work are Gaussian Mixture Models (GMMs), Multilayer Feedforward Network (MFN) and Support Vector Machines (SVMs). Experimental result confirms that in terms of false acceptance rate (FAR) and false rejection rate (FRR), the Fusion Classifiers is effective to use in the proposed system.

Enhanced servo performance of a single axis positioning system in an intelligent robust framework

This paper proposes an optimized performance of an intelligent H∞ robust controller of a single axis positioning system. The objective is to achieve wider bandwidth, better resolution, and robustness to modeling uncertainties. The main contribution is the combination of intelligent uncertainty weighting function and optimized weighting function in an H∞ robust controller design. The main distinguishing features of this approach are: the accurate, fast identification of the uncertainty bounds using an adaptive neuro fuzzy inference system and the automatic tuning of the performance weighting function in accordance to performance requirements. v-gap measure is utilized to validate the intelligent identified uncertainty bounds for wider stability region. Then the methodology is demonstrated through both simulation and experiments on the practical system. Experimental results also demonstrate the robustness against load variations.

Robust identification of a single axis high precision positioning system

Robust control has been studied in recent years as an efficient methodology for the design of highly performing controllers of positioning systems. However, it is necessary to provide accurate nominal model and associated uncertainty bounds to design this type of controllers. The aim of this paper is to robustly identify a single axis high precision positioning system with uncertainties. For a given data set a nominal model is identified then model error modeling techniques are used to handle uncertainties in modeling. To examine the quality of the identified nominal and modeling error models H∞ is designed based on the identified uncertainties. Computer simulation and experimenting with the high precision positioning system verify that the obtained nominal model and modeling error model are reliable and the implemented approach can be used to develop an integrated identification and robust controller.

Design of Post-Mapping Fusion Classifiers for Voice-Based Access Control System

This paper introduced voice-based biometric system for access control. The ability to verify the identity of a person by analyzing his/her speech, or speaker verification, is an attractive and relatively unobtrusive means of providing security for admission into an important or secured place. In the field of speaker verification, the main objective is to achieve the highest possible classification accuracy. The proposed system focused on combining the classification scores. Features are extracted from raw data and can be diverse. Therefore, in post-mapping fusion, each feature set is modeled separately, and the output score of the classifiers are combined to give the overall match score. Furthermore, for each classifier score, an a priori weight is set based on the level of confidence of the feature set and the classifier. Three different feature extractions involved in this work are Liner Prediction Cepstral Coefficients (LPCCs), Mel Frequency Cepstral Coefficients (MFCCs) and Perceptual Linear Prediction (PLP) coefficients. While the classifier used in this study is Support Vector Machines (SVMs). Experimental result confirms that in terms of false acceptance rate (FAR) and false rejection rate (FRR), the Post-Mapping Fusion Classifiers is effective to use in the proposed system.

Intelligent identification of uncertainty bounds for robust servo controlled system

In this paper a new intelligent identification method of uncertainty bound utilizes an adaptive neuro-fuzzy inference system (ANFIS) in a feedback scheme is proposed. The proposed ANFIS feedback structure performs better in determining the uncertainty bounds with minimum number of iterations and error. In our proposed technique, the intelligent identified uncertainty weighting function is validated utilizing v-gap to ensure the stability of the designed H∞ controlled system. Our proposed intelligent identification of uncertainty bound is demonstrated on a servo motion system. Simulation and experimental results show that the new ANFIS identifier is more reliable and highly efficient in estimating the best uncertainty weighting function for robust controller design.