Ponciano Jorge Escamilla-Ambrosio

Multi-sensor data fusion architecture based on adaptive Kalman filters and fuzzy logic performance assessment

In this work a novel multi-sensor data fusion (MSDF) architecture is presented. First, each measurement-vector coming from each sensor is fed to a fuzzy logic-based adaptive Kalman filter (FL-AKF); thus there are N sensors and N FL-AKFs working in parallel. The adaptation in each FL-AKF is, in the sense of dynamically tuning the measurement noise covariance matrix R, employing a fuzzy inference system (FIS) based on a covariance matching technique. A second FIS, called a fuzzy logic assessor (FLA), monitors and assesses the performance of each FL-AKF. The FLA assigns a degree of confidence, a number on the interval [0, 1], to each of the FL-AKF outputs. Finally, a defuzzification scheme obtains the fused state-vector estimate based on confidence values. The effectiveness and accuracy of this approach is demonstrated using a simulated example. Two defuzzification methods are explored and compared, and results show good performance of the proposed approach.

Hybrid Kalman filter-fuzzy logic adaptive multisensor data fusion architectures

In this work the recently developed fuzzy logic-based adaptive Kalman filter (FL-AKF) is used to build adaptive centralized, decentralized, and federated Kalman filters for adaptive multisensor data fusion (AMSDF). The adaptation carried out is in the sense of adaptively adjusting the measurement noise covariance matrix of each local FL-AKF to fit the actual statistics of the noise profiles present in the incoming measured data. A fuzzy inference system (FIS) based on a covariance-matching technique is used as the adaptation mechanism. The effectiveness and accuracy of the proposed AMSDF approaches is demonstrated in a simulated example.

A hybrid Kalman filter-fuzzy logic architecture for multisensor data fusion

A novel hybrid multi-sensor data fusion (MSDF) architecture integrating Kalman filtering and fuzzy logic techniques is explored. The objective of the hybrid MSDF architecture is to obtain fused measurement data that determines the parameter being measured as precisely as possible. To reach this objective, first each measurement coming from each sensor is fed to a fuzzy-adaptive Kalman filter (FKF), thus there are n sensors and n FKFs working in parallel. Next, a fuzzy logic observer (FLO) monitors the performance of each FKF. The FLO assigns a degree of confidence, a number on the interval [0, 1], to each one of the FKFs output. The degree of confidence indicates to what level each FKF output reflects the true value of the measurement. Finally, a defuzzificator obtains the fused estimated measurement based on the confidence values. To demonstrate the effectiveness and accuracy of this new hybrid MSDF architecture, an example with four noisy sensors is outlined. Different defuzzification methods are explored to select the best one for this particular application. The results show very good performance.

A novel design and tuning procedure for PID type fuzzy logic controllers

In this work a new methodology for designing and tuning PID type fuzzy logic controllers (PID-FLC) is presented. The employed PID-FLC is a modified version of a hybrid structure constructed by integrating a PI type FLC and a PD type FLC. First, a direct relationship between the scaling factors of the modified hybrid PID-FLC (MHPID-FLC) and the proportional, integral and derivative actions of its traditional counterpart are established. Thus, based on this relationship, well-known methods used for tuning traditional PID controllers, i.e. the Ziegler-Nichols method, can be used to rind the scaling factors of their fuzzy counterparts. A fine tuning procedure, if necessary, can be followed to further improve the MHPID-FLC performance. This fine-tuning can be developed in two ways: (1) modifying the scaling factors, (2) modifying the control surface of the fuzzy control system inside the MHPID-FLC structure; general guidelines for these procedures are given. The effectiveness of this approach is shown in benchmark processes taken from the literature.

A multiple-sensor multiple-target tracking approach for the autotaxi system

The Autotaxi system is a safety critical sensor system that is being specially developed to perform the sensing required for an autonomous vehicle to drive safely along a dedicated paved guideway and to avoid collision. Therefore, the host vehicle is equipped with a set of sensors used to detect and track any object of interest in the field of view. In this work a multiple-sensor multiple-target tracking (MS-MTT) approach for the Autotaxi system is proposed. A decentralized MS-MTT system is considered for this application. It consists of two basic components: sensor-level tracking and multiple-sensor track fuser or fusion centre. Each sensor in the sensor-level is considered as an intelligent sensor which generates it own track file. Thus, the task of the fusion centre is to combine or fuse the local track files to produce a more accurate and reliable single system track file. This is performed in three stages: data alignment, track-to-track association, and track fusion.

Auto-tuning of fuzzy PID controllers

Abstract In this work the auto-tuning procedure proposed by Astrom and Hagglund is extended and developed for tuning the scaling factors of a modified hybrid PID type fuzzy logic controller (MHPID-FLC). This new procedure is based on two steps. First, mathematical expressions to link the scaling factors of the MHPID-FLC with the proportional, integral and derivative actions of its traditional counterpart are derived. Second, based on this relationship and using the Ziegler-Nichols tuning formulae, the scaling factors of the MHPID-FLC are obtained by means of a relay experiment. The effectiveness of this approach is shown in benchmark processes taken from the literature.

Distributing Computing in the Internet of Things: Cloud, Fog and Edge Computing Overview

The main postulate of the Internet of things (IoT) is that everything can be connected to the Internet, at anytime, anywhere. This means a plethora of objects (e.g. smart cameras, wearables, environmental sensors, home appliances, and vehicles) are ‘connected’ and generating massive amounts of data. The collection, integration, processing and analytics of these data enable the realisation of smart cities, infrastructures and services for enhancing the quality of life of humans. Nowadays, existing IoT architectures are highly centralised and heavily rely on transferring data processing, analytics, and decision-making processes to cloud solutions. This approach of managing and processing data at the cloud may lead to inefficiencies in terms of latency, network traffic management, computational processing, and power consumption. Furthermore, in many applications, such as health monitoring and emergency response services, which require low latency, delay caused by transferring data to the cloud and then back to the application can seriously impact their performances. The idea of allowing data processing closer to where data is generated, with techniques such as data fusion, trending of data, and some decision making, can help reduce the amount of data sent to the cloud, reducing network traffic, bandwidth and energy consumption. Also, a more agile response, closer to real-time, will be achieved, which is necessary in applications such as smart health, security and traffic control for smart cities. Therefore, this chapter presents a review of the more developed paradigms aimed to bring computational, storage and control capabilities closer to where data is generated in the IoT: fog and edge computing, contrasted with the cloud computing paradigm. Also an overview of some practical use cases is presented to exemplify each of these paradigms and their main differences.

Improving Android Mobile Application Development by Dissecting Malware Analysis Data

The explosive growth of mobile technology has brought uncountable benefits to consumers, but it also presents new concerns and provides a platform for cybercrime. In the case of devices running the Android Operating System (OS), concerns have raised as Android has become a major OS in the market. Moreover, even though there have been efforts from Google and the Open Handset Alliance (OHA), among others, towards reducing the impact of security threats in Android, malicious attacks continue to increase in frequency and complexity. Interestingly, bad software development practices still are being considered a major surface attack provider, mainly due to the lack of knowledge or misuse of Android security features. Therefore, this work presents a Web tool, named GARMDROID, aimed to provide security information that will helps Android developers to identify insecure development aspects, saving them from the nuisances associated to the learning of specialized security analysis tools and techniques.

Towards a 2-hybrid Android malware detection test framework

Current pervasive usage of mobile devices around the world has rose big security and data protection concerns both into the application development process as into the data security field. Although the long way of development in PC security malware treatment in the computer science and industrial areas, mobile devices security research and development have proved that in this area malware treatment goes far beyond PC malware analysis and prevention techniques replication. In this context, this paper provides a description of a current open-ended project aimed to produce a 2-hybrid malware detection test framework. Based on the current trends of hybrid malware analysis, in this work the term 2-hybrid implies both a local(host)-remote(server/cloud) implementation and a static-dynamic analysis approach.

Wavelet-fuzzy logic approach to structural health monitoring

In this work a novel wavelet-fuzzy logic approach to structural health monitoring is proposed based on wavelet transform theory and fuzzy logic technology. The proposed method combines the effectiveness of the Wavelet Packet Transform (WPT) as a tool for feature extraction and the capabilities of fuzzy sets to model vagueness and uncertainty. Two stages of operation are considered: pattern training and health monitoring. Pattern training is concerned with the determination of fuzzy sets based baseline patterns representing health condition states for which training data are available. Health monitoring is concerned with the classification of new data into the different structural health states. This classification problem is solved based on determining degrees of membership values to each one of the previously defined fuzzy patterns. In order to demonstrate the effectiveness and viability of the proposed approach, the method was applied to data collected from an experiment involving repeatedly impact excitations of an aluminum cantilever beam. Different damage cases in the beam where emulated by adding a lumped mass at different locations. The measured vibration response data provided by six accelerometers were analyzed. Results show that the method is effective in classifying the different damage cases.