Hiram Ponce

A novel robust liquid level controller for coupled-tanks systems using artificial hydrocarbon networks

A fuzzy-molecular based controller for coupled-tanks systems is proposed.Performance of our controller is higher over conventional PID controllers.Our controller is robust for different discharge rate levels at the secondary tank.Tracking and robustness experiments showed a steady-state error of 1?mm, in average. This paper proposes a robust liquid-level controller for coupled-tanks systems when dealing with variable discharge rates at the secondary tank, based on a hybrid fuzzy inference system that uses artificial hydrocarbon networks at the defuzzification step, so-called fuzzy-molecular control. The design methodology of the proposed controller is presented and discussed. In addition, a case study was run over the CE105 TecQuipment coupled-tanks system in order to implement and validate the fuzzy-molecular controller proposed in that work. A comparative evaluation with the proposed controller, a conventional PID controller specifically designed for this system and a QFT robust controller, was done. Also, a performance evaluation in terms of robustness, reference-tracking in a fixed operating point and reference-tracking in a variable operating point on-the-fly was run and analyzed. Results conclude that the proposed fuzzy-molecular controller deals with uncertainty and noise, can handle dynamics in operating point, a model of the plant is not required, and it is easy and simple to implement in comparison with other controllers in literature. To this end, the proposed fuzzy-molecular liquid-level controller inherits characteristics from fuzzy controllers and artificial hydrocarbon networks in order to implement an advanced robust and intelligent control system.

A Flexible Approach for Human Activity Recognition Using Artificial Hydrocarbon Networks

Physical activity recognition based on sensors is a growing area of interest given the great advances in wearable sensors. Applications in various domains are taking advantage of the ease of obtaining data to monitor personal activities and behavior in order to deliver proactive and personalized services. Although many activity recognition systems have been developed for more than two decades, there are still open issues to be tackled with new techniques. We address in this paper one of the main challenges of human activity recognition: Flexibility. Our goal in this work is to present artificial hydrocarbon networks as a novel flexible approach in a human activity recognition system. In order to evaluate the performance of artificial hydrocarbon networks based classifier, experimentation was designed for user-independent, and also for user-dependent case scenarios. Our results demonstrate that artificial hydrocarbon networks classifier is flexible enough to be used when building a human activity recognition system with either user-dependent or user-independent approaches.

A Novel Wearable Sensor-Based Human Activity Recognition Approach Using Artificial Hydrocarbon Networks

Human activity recognition has gained more interest in several research communities given that understanding user activities and behavior helps to deliver proactive and personalized services. There are many examples of health systems improved by human activity recognition. Nevertheless, the human activity recognition classification process is not an easy task. Different types of noise in wearable sensors data frequently hamper the human activity recognition classification process. In order to develop a successful activity recognition system, it is necessary to use stable and robust machine learning techniques capable of dealing with noisy data. In this paper, we presented the artificial hydrocarbon networks (AHN) technique to the human activity recognition community. Our artificial hydrocarbon networks novel approach is suitable for physical activity recognition, noise tolerance of corrupted data sensors and robust in terms of different issues on data sensors. We proved that the AHN classifier is very competitive for physical activity recognition and is very robust in comparison with other well-known machine learning methods.

Comparative Analysis of Artificial Hydrocarbon Networks and Data-Driven Approaches for Human Activity Recognition

In recent years computing and sensing technologies advances contribute to develop effective human activity recognition systems. In context-aware and ambient assistive living applications, classification of body postures and movements, aids in the development of health systems that improve the quality of life of the disabled and the elderly. In this paper we describe a comparative analysis of data-driven activity recognition techniques against a novel supervised learning technique called artificial hydrocarbon networks (AHN). We prove that artificial hydrocarbon networks are suitable for efficient body postures and movements classification, providing a comparison between its performance and other well-known supervised learning methods.

Artificial Hydrocarbon Networks for Online Sales Prediction

Online retail sales have been growing worldwide in the last decade. In order to cope with this high dynamicity and market share competition, online retail sales prediction and online advertising have become very important to answer questions of pricing decisions, advertising responsiveness, and product demand. To make adequate investment in products and channels it is necessary to have a model that relates certain features of the product with the number of sales that will occur in the future. In this paper we describe a comparative analysis of machine learning techniques against a novel supervised learning technique called artificial hydrocarbon networks (AHN). This method is a new type of machine learning that have proved to adapt very well to a wide spectrum of problems of regression and classification. Thus, we use artificial hydrocarbon networks for predicting the number of online sales, and then we compare their performance with other ten well-known methods of machine learning regression, obtaining promising results.

A Novel Artificial Organic Controller with Hermite Optical Flow Feedback for Mobile Robot Navigation

This chapter describes a novel nature-inspired and intelligent control system for mobile robot navigation using a fuzzy-molecular inference (FMI) system as the control strategy and a single vision-based sensor device, that is, image acquisition system, as feedback. In particular, FMI system is proposed as a hybrid fuzzy inference system with an artificial hydrocarbon network structure as defuzzifier that deals with uncertainty in motion feedback, improving robot navigation in dynamic environments. Additionally, the robotics system uses processed information from an image acquisition device using a realtime Hermite optical flow approach. This organic and nature-inspired control strategy was compared with a conventional controller and validated in an educational robot platform, providing excellent results when navigating in dynamic environments with a single-constrained perception device.

Doubly fed induction generator (DFIG) wind turbine controlled by artificial organic networks

The main goal of this paper is to show the control capabilities of artificial organic networks when they are applied to variable speed wind generators. Since doubly fed induction generator (DFIG) is one of the most important variable wind generators, it requires to include advanced controllers which allow to improve its performance during operation. On the other hand, the artificial organic controllers (AOC) are intelligent controllers based on ensembles of fuzzy inference systems and artificial hydrocarbon networks. To understand AOC, this paper introduces the fundamentals of artificial hydrocarbon networks, describes the fuzzy-molecular inference ensemble, and discusses artificial organic controllers when they are deployed in variable speed wind generators. Additionally, DFIG wind turbine model is completely derived in order to test the AOC. A conventional proportional–integral–derivative (PID) controller is compared with the proposed PID-based AOC (PID-AOC) for wind generators under linear and nonlinear wind profiles. Five parameters were used for evaluation: pitch angle, stator power, rotor power, generator’s speed and power coefficient. Results showed the superior control performance in wind generators when artificial organic networks are implemented. Particularly, the PID-AOC response obtained higher values of rotor and stator powers, small pitch angle response meaning less energy consumption, high power coefficient values, and smooth starting phase minimizing risks of damage in the DFIG. The proposed PID-AOC can be applied in DFIG to minimize the undesired fluctuation on the electric grid, to reduce the mechanical stress in the blades preventing mechanical damages and to perform good sensitivity when noise in the wind is included.

A novel methodology for optimizing display advertising campaigns using genetic algorithms

Abstract Online advertising campaigns have attracted the attention of many advertisers willing to promote their business on the Internet. One of the main problems faced by advertisers, especially by those who have little experience in Internet advertising, is configuring their campaigns in an efficient way. To configure a campaign properly it is required to select the appropriate target, so it is guaranteed a high acceptance of users to adverts. It is also required that the number of visits that satisfy the configuration requirements is high enough to cover the advertisers’ campaigns. Thus, this paper presents a novel methodology for optimizing the micro-targeting technique in direct response display advertising campaigns by using genetic algorithms as the basis optimization model and a machine-learning based click-through rate (CTR) model. We implement our methodology to optimize display advertising campaigns on mobile devices using a real dataset. Results show that our methodology is feasible to optimize the campaigns by selecting the set of the best features required. Also, customization of the advertising campaign selecting some features by an advertiser, e.g. applying micro-targeting, can be optimized efficiently.

Advances in applied computational intelligence: MICAI 2016

This special issue of the Journal Computing offers original contributions in all areas of artificial intelligence. Most of the research works included in this issue are extended papers presented in the 15th Mexican International Conference on Artificial Intelligence, MICAI 2016, held in Cancún, Quintana Roo, Mexico on October 23–29, 2016, under the organization of the Mexican Society for Artificial Intelligence (SMIA) in cooperation with the Instituto Tecnológico de Cancún. Other papers included were received through the open call for papers. MICAI is an annual conference that disseminates and promotes growth of outstanding research works in all areas of artificial intelligence (AI), including but not limited to: expert systems and knowledge-based systems, knowledge representation and acquisition, multi-agent systems and distributed AI, natural language processing, intelligent interfaces, computer vision, machine learning, pattern recognition, soft computing, reasoning, robotics, planning and scheduling, among others. In MICAI 2016, we received over 350 submissions with an acceptance rate around 25%. Based on the reviewers’ comments from the conference, 15 papers were initially invited to submit to the special issue after substantial extension. Additionally, three manuscripts from the open call for papers were received. Each submission was

Analysis of Constraint-Handling in Metaheuristic Approaches for the Generation and Transmission Expansion Planning Problem with Renewable Energy

A multiperiod generation and transmission expansion planning (G&TEP) problem is considered. This model integrates conventional generation with renewable energy sources, assuming a stochastic approach. The proposed approach is based on a centralized planned transmission expansion. Due to the worldwide recent energy guidelines, it is necessary to generate expansion plans adequate to the forecast demand over the next years. Nowadays, in most energy systems, a public entity develops both the short and long of electricity-grid expansion planning. Due to the complexity of the problem, there are different strategies to find expansion plans that satisfy the uncertainty conditions addressed. We proposed to address the G&TEP problem with a pure genetic algorithm approach. Different constraint-handling techniques were applied to deal with two complex case studies presented. Numerical results are shown to compare the strategies used in the test systems, and key factors such as a prior initialization of population and the estimated minimum number of generations are discussed.