Andres Perez-Uribe

Andres Perez-Uribe
La Haute Ecole d'Ingénierie et de Gestion du Canton de Vaud | HEIG-VD · TIC

PhD

About

82
Publications
12,784
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
1,206
Citations
Citations since 2017
13 Research Items
257 Citations
201720182019202020212022202301020304050
201720182019202020212022202301020304050
201720182019202020212022202301020304050
201720182019202020212022202301020304050

Publications

Publications (82)
Article
Full-text available
Upper limb impairment is one of the most common problems for people with neurological disabilities, affecting their activity, quality of life (QOL), and independence. Objective assessment of upper limb performance is a promising way to help patients with neurological upper limb disorders. By using wearable sensors, such as an egocentric camera, it...
Chapter
How to build machine learning models from few annotations is an open research question. This article shows an application of a meta-learning algorithm (REPTILE) to solve the problem of object segmentation. We evaluate how using REPTILE during a pre-training phase accelerates the learning process without loosing performance of the resulting segmenta...
Article
Full-text available
This study proposes DeepWriteSYN, a novel on-line handwriting synthesis approach via deep short-term representations. It comprises two modules: i) an optional and interchangeable temporal segmentation, which divides the handwriting into short-time segments consisting of individual or multiple concatenated strokes; and ii) the on-line synthesis of t...
Preprint
Full-text available
This study proposes DeepWriteSYN, a novel on-line handwriting synthesis approach via deep short-term representations. It comprises two modules: i) an optional and interchangeable temporal segmentation, which divides the handwriting into short-time segments consisting of individual or multiple concatenated strokes; and ii) the on-line synthesis of t...
Chapter
The current availability of the humanoid robots opens up a wide range of applications, for instance, in the domain of hospitality the humanoids can be programmed to behave autonomous ways to provide help to people. The aspect of the humanoids and the humanness of interaction are key components of success. We developed a system to endow the humanoid...
Conference Paper
Full-text available
Vision-based human activity recognition can provide rich contextual information but has traditionally been computationally prohibitive. We present a characterisation of five convolutional neural networks (DenseNet169, MobileNet, ResNet50, VGG16, VGG19) implemented with TensorFlow Lite running on three state of the art Android mobile phones. The net...
Chapter
ActiDote —activity as an antidote— is a system for manual wheelchair users that uses wireless sensors to recognize activities of various intensity levels in order to allow self-tracking while providing motivation. In this paper, we describe both the hardware setup and the software pipeline that enable our system to operate. Laboratory tests using m...
Article
Full-text available
ActiDote –activity as an antidote– is a system for manual wheelchair users that takes advantage of wireless sensors to recognize activities of various intensity levels in order to allow self-tracking of the physical activity. In this paper, we describe both the hardware setup and the software pipeline that enable our system to operate. Laboratory t...
Conference Paper
We present the co-design of a gaming scenario between an Artificial Evolution algorithm and a human designer. Such co-design is twofold, consisting of an initial stage in which a genetic algorithm is used to evolve the control parameters that define the behavior of a group of virtual agents. This produces interesting and unexpected results not only...
Article
Automatic recognition of user context is essential for a variety of emerging applications, such as context-dependent content delivery, telemonitoring of medical patients, or quantified life-logging. Although not explicitly observable as, e.g., activities, an important aspect towards understanding user context lies in the affective state of mood.Whi...
Article
Activity recognition is gaining a lot of interest given its direct use in applications like ambient assisted living and has been empowered by the increasing ubiquity of sensors (e.g., clothes, smartphones, watches). The machine learning approach to activity recognition consists on finding the signatures characterizing the activities to be recognize...
Chapter
Full-text available
18.1 Introduction Decision making in agriculture is based on knowledge of the behavior of crops under site-specific growing conditions at any given moment in time. For many tropical crops, research is limited, and there is a dearth of readily available information on where to grow many crops and how to manage them effectively. Small growers create...
Conference Paper
Activity recognition has recently gained a lot of interest and there already exist several methods to detect human activites based on wearable sensors. Most of the existing methods rely on a database of labelled activities that is used to train an offline activity recognition system. This paper presents an approach to build an online activity recog...
Conference Paper
Full-text available
Activity recognition has recently gained a lot of interest and appears to be a promising approach to help the elderly population pursue an independent living. There already exist several methods to detect human activities based either on wearable sensors or on cameras but few of them combine the two modalities. This paper presents a strategy to enh...
Article
In human activity recognition, gesture spotting can be achieved by comparing the data from on-body sensors with a set of known gesture templates. This work presents a semi-supervised approach to template discovery in which the Dynamic Time Warping distance measure has been embedded in a classic clustering technique. Clustering is used to find a set...
Method
Full-text available
Terra-i provides data about vegetation change (gain or loss). Secondary data (i.e. spatial distribution of natural coverage, forest plantations, crop areas, among others) must be used to get more proximate results about which sort of vegetation changed or which land-use activity could be associated with the change.
Conference Paper
The Multi-electrode Array (MEA) technology allows the in-vitro culture of neuronal networks that can be used as a simplified and accessible model of the central nervous system, given that they exhibit activity patterns similar to the in-vivo tissue. Current devices generate huge amounts of data, thus motivating the development of systems capable of...
Article
Full-text available
Foraging is a common benchmark problem in collective robotics in which a robot (the forager) explores a given environment while collecting items for further deposition at specific locations. A typical real-world application of foraging is garbage collection where robots collect garbage for further disposal in pre-defined locations. This work propos...
Article
Every time a farmer plants and harvests a crop represents a unique event or experiment. Our premise is that if it were possible to characterize the production system in terms of management and the environmental conditions, and if information on the harvested product were collected from a large number of harvesting events under varied conditions, it...
Article
Creating computational models from large and growing datasets is an important issue in current machine learning research, because most modelling approaches can require prohibitive computational resources. This work presents the use of incremental learning algorithms within the framework of an incremental modelling approach. In particular, it presen...
Conference Paper
Full-text available
This paper presents the final hardware platform developed in the Perplexus project. This platform is composed of a reconfigurable device called the ubichip, which is embedded on a pervasive platform called the ubidule, and can also be integrated on the marXbot robotic platform. The whole platform is intended to provide a hardware platform for the s...
Conference Paper
Full-text available
Foraging has been identified as a benchmark for collective robotics. It consists on exploring an area and gathering prespecified objects from the environment. In addition to efficiently exploring an area, foragers have to be able to find special targets which are common to the whole population. This work proposes a method to cooperatively perform t...
Article
The Andean blackberry (Rubus glaucus) is an important source of income in hillside regions of Colombia. However, growers have little reliable information on the factors that affect the development and yield of the crop, and therefore there is a dearth of information on how to effectively manage the crop. Site specific information recorded by small-...
Chapter
Vector quantization of large datasets can be carried out by means of an incremental modelling approach where the modelling task is transformed into an incremental task by partitioning or sampling the data, and the resulting datasets are processed by means of an incremental learner. Growing Neural Gas is an incremental vector quantization algorithm...
Chapter
Hierarchical Self-Organizing Networks are used to reveal the topology and structure of datasets. These methodologies create crisp partitions of the dataset producing tree structures composed of prototype vectors, permitting the extraction of a simple and compact representation of a dataset. However, in many cases observations could be represented b...
Article
Full-text available
This paper introduces the Perplexus hardware platform, a scalable computing substrate made of custom reconfig- urable devices endowed with bio-inspired capabilities. This platform will enable the simulation of large-scale complex systems and the study of emergent complex behaviors in a virtually unbounded wireless network of computing mod- ules. Th...
Conference Paper
Full-text available
The ubichip is a bio-inspired reconfigurable circuit developed in the framework of the european project Perplexus. The ubichip offers special reconfigurability capabilities as self-replication and dynamic routing. This paper describes how to exploit the dynamic routing capabilities of the ubichip in order to implement plastic neural networks. We pr...
Conference Paper
Growing Neural Gas is an incremental vector quantization algorithm with the capabilities of topology-preserving and distribution-matching. Distribution matching can produce overpopulation of prototypes in zones with high density of data. In order to tackle this drawback, we introduce some modifications to the original Growing Neural Gas algorithm b...
Article
Full-text available
One of the key implications of functionalism is that minds can, in principle, be implemented with any physical substra-tum provided that the right functional relations are preserved. In this paper we present an architecture that implements neural epigenesis, reinforcement learning, and mental rehearsal, some of the functional building blocks that m...
Conference Paper
Full-text available
The ubichip is a bio-inspired reconfigurable circuit developed in the framework of the European project Perplexus. The ubichip offers special reconfigurability capabilities, being the dynamic routing one of them. This paper describes how to exploit the dynamic routing capabilities of the ubichip in order to implement synaptogenetic neural networks....
Conference Paper
Full-text available
In this document we examine the evolutionary methods that may lead to the emergence of altruistic cooperation in robot collectives. We present four evolutionary algorithms that derive from biological theories on the evolution of altruism in nature and compare them systematically in two experimental scenarios where altruistic cooperation can lead to...
Chapter
Full-text available
Agroecological systems are difficult to model because of their high complexity and their nonlinear dynamic behavior. The evolution of such systems depends on a large number of ill-defined processes that vary in time, and whose relationships are often highly non-linear and very often unknown. According to Schultz et al. (2000), there are two major p...
Conference Paper
The reduction of input dimensionality is an important subject in modelling, knowledge discovery and data mining. Indeed, an appropriate combination of inputs is desirable in order to obtain better generalisation capabilities with the models. There are several approaches to perform input selection. In this work we will deal with techniques guided by...
Conference Paper
A technique called component planes is commonly used to visualize variables behavior with Self-Organizing Maps (SOMs). Nevertheless, when the component planes are too many the visualization becomes difficult. A methodology has been developed to enhance the component planes analysis process. This methodology improves the correlation hunting in the c...
Conference Paper
A technique called component planes is commonly used to visualize variables behavior with Self-Organizing Maps (SOMs). Nevertheless, when the component planes are too many the visualization becomes difficult. A methodology has been developed to enhance the component planes analysis process. This methodology improves the correlation hunting in the c...
Conference Paper
Full-text available
This paper introduces Perplexus, a European project that aims to develop a scalable hardware platform made of custom reconfigurable devices endowed with bio-inspired capabilities. This platform will enable the simulation of large-scale complex systems and the study of emergent complex behaviors in a virtually unbounded wireless network of computing...
Conference Paper
Full-text available
This paper introduces the ubichip, a custom reconfigurable electronic device capable of implementing bio- inspired circuits featuring growth, learning, and evolution. The ubichip is developed in the framework of Perplexus, a European project that aims to develop a scalable hardware platform made of bio-inspired custom reconfigurable devices for sim...
Conference Paper
Data incompleteness and data scarcity are common problems in agroecological modelling. Moreover, agroecological processes depend on historical data that could be fed into a model in a vast number of ways. This work shows a case study of modelling in agroecology using artificial neural networks. The variable to be modelled is sugar cane yield and fo...
Article
Full-text available
Ontogenetic hardware, along with epigenetic (neural) hardware and phylogenetic (evolvable) hardware, are the key rep-resentatives of a new hardware conception paradigm known as bio-inspired hardware. Ontogenesis is the process that allows living beings to develop by means of mechanisms as growing, self-replication, and self-repair. During the last...
Article
Full-text available
A technique called component planes is commonly used to visualize variables behavior with Self Organizing Map (SOM). A methodology to clustering the component planes based on the SOM distance matrix is presented. This methodology is used in order to classify zones with similar agro-ecological conditions in the sugar cane culture. Analyzing the obta...
Chapter
Full-text available
There is a growing evidence that the human brain follows an environmentally-guided neural circuit building that increases its learning flexibility. Similarly, it has been shown that artificial neural networks with dynamic topologies attempt to overcome the problem of determining the appropriate topology to optimally solve a given application. This...
Conference Paper
Full-text available
Since ants and other social insects have long generation time, it is very difficult for biologists to study the origin of complex social organization by guided evolution (a process where the evolution of a trait can be followed during experimental evolution). Here we use colonies of artificial ants implemented as small mobile robots with simple vis...
Article
Full-text available
We present SOS++, a bioinspired method combining evolution and learning, allowing the automatic design of the controller of autonomous agents, described as a finite-state machine. The application of this method to well-known problems, for example the follow-up of a trail or the resolution of a maze, led to the emergence of some behaviors we could q...
Conference Paper
We provide an overview of the evolutionary approach to the emergence of artificial intelligence in embodied behavioral agents. This approach, also known as Evolutionary Robotics, builds and capitalizes upon the interactions between the embodied agent and its environment. Although we cover research carried out in several laboratories around the worl...
Conference Paper
This chapter presents a neurocontroller architecture for autonomous mobile robot navigation. The main characteristic of such neurocontroller is that it is non-computationally-intensive. It provides a learning robot with the capability to autonomously categorize input data from the environment, to deal with the stability-plasticity dilemma, and to l...
Article
Full-text available
We provide an overview of the evolutionary approach to the emergence of artificial intelligence in embodied behavioral agents. This approach, also known as Evolutionary Robotics, builds and capitalizes upon the interactions between the embodied agent and its environment. Although we cover research carried out in several laboratories around the worl...
Conference Paper
Researchers in the new field of ”developmental robotics” propose to provide robots with so-called developmental programs. Similar to the development of human infants, robots might use those programs to interact with humans and their environment for extended periods of time, and become smarter autonomously. In this paper we show how a neural network...
Conference Paper
Neuroscientists have identified a neural substrate of prediction and reward in experiments with primates. The so-called dopamine neurons have been shown to code an error in the temporal prediction of rewards. Similarly, artificial systems can ”learn to predict” by the so-called temporal-difference (TD) methods. Based on the general resemblance betw...
Conference Paper
Finite state machines (FSM) have been successfully used to implement the control of an agent to solve particular sequential tasks. Nevertheless, finite state machines must be hand-coded by the engineer, which might be very difficult for complex tasks. Researchers have used evolutionary techniques to evolve finite state machines and find automatic s...
Conference Paper
This paper describes a networked FPGA-based implementation of the FAST (Flexible Adaptable- Size Topology) architecture, an Artificial Neural Network (ANN) that dynamically adapts its size. Most ANN models base their ability to adapt to problems on changing the strength of the interconnections between computational elements according to a given lea...
Article
Full-text available
Field-programmable gate arrays (FPGAs) are large, fast integrated circuits — that can be modified, or configured, almost at any point by the end user. Within the domain of configurable computing we distinguish between two modes of configurability: static—where the configurable processor’ s configuration string is loaded once at the outset, after wh...
Article
Full-text available
Field-programmable gate arrays (FPGAs) are large, fast integrated circuits-that can be modified, or configured, almost at any point by the end user. Within the domain of configurable computing, we distinguish between two modes of configurability: static-where the configurable processor's configuration string is loaded once at the outset, after whic...
Article
Thèse no 2052 sc. techn. EPF Lausanne. Literaturverz.
Article
Full-text available
Reinforcement learning is a computational approach to learning from interaction. Tabularimplementations of reinforcement learning methods are the most simple, though,they suffer from the curse of dimensionality problem; therefore, function approximationtechniques have been used to provide generalization across states and actions. Nevertheless,eligi...
Conference Paper
Full-text available
Blackjack or twenty-one is a card game where the player attempts to beat the dealer, by obtaining a sum of card values that is equal to or less than 21 so that his total is higher than the dealer's. The probabilistic nature of the game makes it an interesting test bed problem for learning algorithms, though the problem of learning a good playing st...
Conference Paper
If one considers life on Earth since its very beginning, three levels of organization can be distinguished: the phylogenetic level concerns the temporal evolution of the genetic programs within individuals and species, the ontogenetic level concerns the developmental process of a single multicellular organism, and the epigenetic level concerns the...
Conference Paper
A well known model of reinforcement learning is called Adaptive Heuristic Critic learning. It is composed of two so called “neuronlike adaptive elements” and has been used to solve difficult learning control problems. In this paper we present an FPGA design and implementation of such algorithm, and, furthermore, we describe a neurocontroller system...
Conference Paper
Neurocontrol is a crucial area of fundamental research within the neural network field. Adaptive heuristic critic learning is a key algorithm for real-time adaptation in neurocontrollers. In this paper, we show how an unsupervised neural network model with an adaptable structure can be used to speed-up adaptive heuristic critic learning, present it...
Article
Full-text available
If one considers life on Earth since its very beginning, three levels of organization can be distinguished: the phylogenetic level concerns the temporal evolution of the genetic programs within individuals and species, the ontogenetic level concerns the developmental process of a single multicellular organism, and the epigenetic level concerns the...
Conference Paper
Full-text available
. This paper presents a hardware-friendly approach for adaptingthe structure of a reinforcement, learning-based neurocontroller. Anunsupervised clustering algorithm is used to partition the state space ofa system and to adapt the size of its reinforcement module. In the wellknowninverted pendulum problem, the system has proven to be muchfaster than...
Article
Most neural network models base their ability to adapt to problems on changing their interconnection strengths according to a learning algorithm. Evolutionary technics and a special class of learning algorithms enable a neural network to have a dynamic structure too. While in the first case we obtain an optimized a-priori architecture the latter al...
Conference Paper
Living beings are complex systems exhibiting a range of desirable qualifications that have eluded realization by traditional engineering methodologies. In recent years we are witness to a growing interest in Nature exhibited by engineers, wishing to imitate the observed processes, thereby creating powerful problem-solving methodologies. If one cons...
Conference Paper
Most neural network models base their “learning” capability on changing the strengths of interconnection between computational elements. However, according to “neural constructivism”, an environmentally-guided neural circuit building offers powerful learning capabilities while minimizing the need for domain-specific structure prespecification. This...
Conference Paper
Artificial neural networks achieve fast parallel processing via massively parallel non-linear computational elements. Most neural network models base their ability to adapt to problems on changing the strength of the interconnections between computational elements according to a given learning algorithm. However, constrained interconnection structu...
Conference Paper
One of the central problems in the application of neural networks is finding the optimal network topology. This paper introduces the FAST architecture (flexible adaptable-size topology), an on-line, evolving neural network that dynamically adapts its topology through interactions with a problem-specific environment. We present a fully digital imple...
Article
Full-text available
In this paper, we propose a robotics framework for studying the coevolution of signaling. Our motiva-tion is twofold. First, we propose a situated and em-bodied framework for signaler-receiver interaction, and second, we provide a promising approach for t h e s t u d y o f m e c hanisms that would enable adap-tive systems to access new information...
Article
Full-text available
Honey-bees have long served as a model organismfor investigating insect navigation and collectivebehavior: they exhibit division of labor andare an example of insect societies where directcommunication between workers enable cooperationin the task of collecting nectar and pollen forthe colony. However, honey-bees seem to learnabout their environmen...
Article
An autonomous robot need not be given all the detailsof the environment in which it is going to act:it can acquire them by direct interaction. One approachto learn by interaction is reinforcement learning,though, the robot has also to be able to autonomouslycategorize the input data it receives fromthe environment, deal with the stability-plasticit...