Guido Bologna

University of Applied Sciences and Arts Western Switzerland · Software and complex systems

Deep Learning (DL), a groundbreaking branch of Machine Learning (ML), has emerged as a driving force in both theoretical and applied Artificial Intelligence (AI). DL algorithms, rooted in complex and non-linear artificial neural systems, excel at extracting high-level features from data. DL has demonstrated human-level performance in real-world tas...

Blindness is likely to double in the next fifteen years due to ageing. Our prototype for vision substitution has a first module denoted as "sensory" which transmits colors to the user through spatialized sounds of musical instruments. As color is not always sufficient to identify an object, we added an object recognition module by means of deep con...

The explainability of connectionist models is nowadays an ongoing research issue. Before the advent of deep learning, propositional rules were generated from Multi Layer Perceptrons (MLPs) to explain how they classify data. This type of explanation technique is much less prevalent with ensembles of MLPs and deep models, such as Convolutional Neural...

Groundbreaking advances in theoretical and applied Artificial Intelligence (AI). Deep Learning (DL) algorithms are grounded in non-linear and complex artificial neural systems that progressively extract higher-level features from data. DL is frequently compared with human-level performance in real-world tasks, such as clinical diagnostics. It is al...

So far, propositional rules have been extracted from Multi Layer Perceptrons to explain how they achieve to classify data. This type of explanation technique is much less prevalent with deep models, such as convolutional neural networks (CNNs). In this work, we propose to transfer the feature maps generated by a CNN to a simpler neural network mode...

In machine learning, ensembles of models based on Multi-Layer Perceptrons (MLPs) or decision trees are considered successful models. However, explaining their responses is a complex problem that requires the creation of new methods of interpretation. A natural way to explain the classifications of the models is to transform them into propositional...

A natural method aiming at explaining the answers of a black-box model is by means of propositional rules. Nevertheless, rule extraction from ensembles of Machine Learning models was rarely achieved. Moreover, experiments in this context have rarely been evaluated by cross-validation trials. Based on stratified tenfold cross-validation, we performe...

A natural method aiming at explaining the answers of a black-box model is by means of propositional rules. Nevertheless, rule extraction from ensembles of Machine Learning models was rarely achieved. Moreover, experiments in this context have rarely been evaluated by cross-validation trials. Based on stratified 10-fold cross-validation, we performe...

The explanation of the decisions provided by a model are crucial in a domain such as medical diagnosis. With the advent of deep learning, it is very important to explain why a classification is reached by a model. This work tackles the transparency problem of convolutional neural networks(CNNs). We propose to generate propositional rules from CNNs,...

Artificial intelligence and all its supporting tools, e.g. machine and deep learning in computational intelligence-based systems, are rebuilding our society (economy, education, life-style, etc.) and promising a new era for the social welfare state. In this paper we summarize recent advances in data science and artificial intelligence within the in...

Classification responses provided by Multi Layer Perceptrons (MLPs) can be explained by means of propositional rules. So far, many rule extraction techniques have been proposed for shallow MLPs, but not for Convolutional Neural Networks (CNNs). To fill this gap, this work presents a new rule extraction method applied to a typical CNN architecture u...

So far, many rule extraction techniques have been proposed to explain the classifications of shallow Multi Layer Perceptrons (MLPs), but very few methods have been introduced for Convolutional Neural Networks (CNNs). To fill this gap, this work presents a new technique applied to a CNN architecture including two convolutional layers. This neural ne...

Convolutional Neural Networks (CNNs) lack an explanation capability in the form of propositional rules. In this work we define a simple CNN architecture having a unique convolutional layer, then a Max-Pool layer followed by a full connected layer. Rule extraction is performed after the Max-Pool layer with the use of the Discretized Interpretable Mu...

Rule extraction from neural networks represents a difficult research problem, which is NP-hard. In this work we show how a special Multi Layer Perceptron architecture denoted as DIMLP can be used to extract rules from ensembles of DIMLPs and Quantized Support Vector Machines (QSVMs). The key idea for rule extraction is that the locations of discrim...

One way to make the knowledge stored in an artificial neural network more intelligible is to extract symbolic rules. However, producing rules from Multilayer Perceptrons (MLPs) is an NP-hard problem. Many techniques have been introduced to generate rules from single neural networks, but very few were proposed for ensembles. Moreover, experiments we...

Rule extraction from neural networks is a fervent research topic. In the last 20 years many authors presented a number of techniques showing how to extract symbolic rules from Multi Layer Perceptrons (MLPs). Nevertheless, very few were related to ensembles of neural networks and even less for networks trained by deep learning. On several datasets w...

Assistive technologies aim at improving personal mobility of individuals with disabilities, increasing their independence and their access to social life. They include mechanical mobility aids that are increasingly employed amongst the older people who rely on them. However, these devices might fail to prevent falls due to the under-estimation of a...

Rule extraction from neural networks is a fervent research topic. In the last 20 years many authors presented a number of techniques showing how to extract symbolic rules from Multi Layer Perceptrons (MLPs). Nevertheless, very few were related to ensembles of neural networks and even less for networks trained by deep learning. In this work the Disc...

The purpose of this study was to generate more concise rule extraction from the Recursive-Rule Extraction (Re-RX) algorithm by replacing the C4.5 program currently employed in Re-RX with the J48graft algorithm. Experiments were subsequently conducted to determine rules for six different two-class mixed datasets having discrete and continuous attrib...

Rule extraction from neural networks represents a difficult research problem, which is NP-hard. In this work we show how a special Multi Layer Perceptron architecture denoted as DIMLP can be used to extract rules from ensembles of DIMLPs and Quantized Support Vector Machines (QSVMs). The key idea for rule extraction is that the locations of discrim...

Millions of elderly people around the world use the walker for their mobility; nevertheless, these devices may lead to an accident. One of the cause of these accidents is misjudge the terrain. The main objective of this work is the implementation of a ground change detector in real time on a small and light embedded system that can be clipped on a...

This study investigates the design of a novel real-time system to detect walking behavior changes using an accelerometer on a rollator. No sensor is required on the user. We propose a new non-invasive approach to detect walking behavior based on the motion transfer by the user on the walker. Our method has two main steps; the first is to extract a...

« EyeWalker » est un projet qui a pour but de développer un appareil léger et compact s’adaptant facilement à n’importe quel déambulateur et alertant un/e utilisateur/trice avant qu’il/elle se trouve dans une situation dangereuse pouvant entraîner sa chute. Dans ce travail, nous traitons la détection de deux types de situations présentant un risque...

With the increasing proportion of senior citizens, many mobility aid devices were developed such as the rollator. However among walker’s users, 87% of their falls is attributed to rollators. The EyeWalker project aims at developing a small device for rollators to protect elderly people from such dangers. Descending stairs are ones of the potential...

Purpose – The purpose of this paper is to overcome the limitations of sensory substitution methods (SSDs) to represent high-level or conceptual information involved in vision, which are mainly produced by the biological sensory mismatch between sight and substituting senses. Thus, provide the visually impaired with a more practical and functional S...

Purpose - overcome the limitations of SSDs to represent high-level or conceptual information involved in vision, which are mainly produced by the biological sensory mismatch between sight and substituting senses. Thus, provide the visually impaired with a more practical and functional SSD. Design/methodology/approach - unlike any other approach, o...

Nowadays, there are many different types of mobility aids for elderly people. Nevertheless, these devices may lead to accidents, depending on the terrain where they are being used. In this paper, we present a robust ground change detector that will warn the user of potentially risky situations. Specifically, we propose a robust classification algor...

With the increasing proportion of senior citizens, many mobility aid devices have been developed such as the rollator. However, under some circumstances, the latter may cause accidents. The EyeWalker project aims to develop a small and autonomous device for rollators to help elderly people, especially those with some degree of visual impairment, av...

We present a simple yet highly efficient method to register range and color images. This method does not rely upon calibration parameters nor does it use visual features analysis. Our assumption is that if the transformation that registers the images is a mathematical function, we can approximate with little number of samples. To this end, thin-pla...

See ColOr is a mobility aid for visually impaired people that uses the auditory channel to represent portions of captured images in real time. A distinctive feature of the See ColOr interface is the simultaneous coding of colour and depth. Four main modules were developed, in order to replicate a number of mechanisms present in the human visual sys...

Exploring unfamiliar environments is a challenging task in which additionally, unsighted individuals frequently fail to gain perception of obstacles and make serendipitous discoveries. This is because the mental depiction of the context is drastically lessened due to the absence of visual information. It is still not clear in neuroscience, whether...

In line with the boom of 3D movies and cutting edge technologies, range cameras are increasingly common. Among others, time-of-flight (TOF) cameras give it the ability to capture three-dimensional images that reveal object's distances. A shortcoming of these sensors however, lies in that the majority does not provide color information (not even gra...

Many people with visual disabilities mainly use audio feedback as a primary modality for interaction. Representing the visual environment with appropriate sounds contributes to make it intelligible to the blind. This audio-encoded environment still needs to be accessed in the same way as sighted people scan visual contents with their gaze. A finger...

Microsoft's Kinect 3-D motion sensor is a low cost 3D camera that provides color and depth information of indoor environments. In this demonstration, the functionality of this fun-only camera accompanied by an iPad's tangible interface is targeted to the benefit of the visually impaired. A computer-vision-based framework for real time objects local...

The See ColOr project aims at developing a mobility system for blind persons based on image color sonification. Within this project the present work addresses the optimal use of auditory-multi-touch interaction, and in particular the matter of the number of fingers needed for efficient exploration. To determine the actual significance of mono and m...

In the human proteome, about 5’000 proteins lack experimentally validated functional information. In this work we propose to tackle the problem of human protein function prediction by three distinct supervised learning schemes: one-versus-all classification; tournament learning; multi-label learning. Target values of supervised learning models are...

Although retinal neural implants have considerably progressed they raise a number of questions concerning user acceptance, risk rejection and cost. For the time being we support a low cost approach based on the transmission of limited vision information by means of the auditory channel. The See ColOr mobility aid for visually impaired individuals t...

Providing the blind with substitute visual perception is a relentless challenge confronting researchers of diverse areas. The See ColOr (Seeing Color with an Orchestra) system translates aimed-at regions of a color scene into 2D-spatialized sound signals represented by musical instruments. Associating sounds with colors is achieved thanks to an eff...

In this demo, we present the detection module of the See ColOr (Seeing Colors with an Orchestra) mobility aid for visually impaired persons. This module points out areas that present either particular interest or potential threat. In order to detect object and obstacles, we propose a bottom-up approach based on visual saliency: objects that would a...

The See Color interface transforms a small portion of a colored video image into sound sources represented by spatialized musical instruments. Basically, the conversion of colors into sounds is achieved by quantization of the HSL color system. Our purpose is to provide visually impaired individuals with a capability of perception of the environment...

The See ColOr interface transforms a small portion of a coloured video image into sound sources represented by spatialized musical instruments. This interface aims at providing visually impaired people with a capability of perception of the environment. In this work, the purpose is to verify the hypothesis that it is possible to use sounds from mus...

The See Color interface transforms a small portion of a colored video image into sound sources represented by spatialized musical instruments. Basically, the conversion of colors into sounds is achieved by quantization of the HSL color system. Our purpose is to provide visually impaired individuals with a capability of perception of the environment...

This article presents the multi-touch See ColOr interface that will permit the interpretation of static pictures by visually impaired persons. Images are represented on a special paper emphasizing object contours by palpable roughness. With this multi-modal interface, user fingers can explore an image by listening to the sounds of classical musical...

The See Color interface transforms a small portion of a coloured video image into sound sources represented by spatialised musical instruments. Basically, the conversion of colours into sounds is achieved by quantisation of the HSL (Hue, Saturation and Luminosity) colour system. Our purpose is to provide visually impaired individuals with a capabil...

The context of this work is the development of a mobility aid for visually impaired persons. We present here an original approach for a real time alerting system, based on the detection of visual salient parts in videos. The particularity of our approach lies in the use of a new feature map constructed from the depth gradient. A distance function i...

In the context of vision substitution by the auditory channel several systems have been introduced. One such system that is presented here, See ColOr, is a dedicated interface part of a mobility aid for visually impaired people. It transforms a small portion of a colored video image into spatialized instrument sounds. In this work the purpose is to...

The context of this work is the development of a mobility aid for visually impaired persons. We present here an original approach for a real time alerting system, based on the detection of visual salient parts in videos. The particularity of our approach lies in the use of a new feature map constructed from the depth gradient. A distance function i...

This paper reviews the state of the art in the field of assistive devices for sight-handicapped people. It concentrates in particular on systems that use image and video processing for converting visual data into an alternate rendering modality that will be appropriate for a blind user. Such alternate modalities can be auditory, haptic, or a combin...

The goal of the See ColOr project is to achieve a non-invasive mobility aid for blind users that will use the auditory pathway to represent in real-time frontal image scenes. More particularly, we have developed a prototype which transforms HSL coloured pixels into spatialized classical instrument sounds lasting for 300 ms. Hue is sonified by the t...

This work presents an application example of text document filtering. We compare the DIMLP neural hybrid model to several machine learning algorithms. The clear advantage of this neural hybrid system is its transparency. In fact, the classification strategy of DIMLPs is almost completely encoded into the extracted rules. During cross-validation tri...

The goal of the See ColOr project is to achieve a noninvasive mobility aid for blind users that will use the auditory pathway to represent in real-time frontal image scenes. We present and discuss here two image processing methods that were experimented in this work: image simplification by means of segmentation, and guiding the focus of attention...

We present our recent project on visual substitution by Ambisonic 3D-sound fields. Ideally, our system should be used by blind or visually impaired subjects having already seen. The original idea behind our targeted prototype is the use of an eye tracker and musical instrument sounds encoding coloured pixels. The role of the eye tracker is to activ...

Although many authors generated comprehensible models from individual networks, much less work has been done in the explanation of ensembles. DIMLP is a special neural network model from which rules are generated at the level of a single network and also at the level of an ensemble of networks. We applied ensembles of 25 DIMLP networks to several d...

N-terminal myristoylation is a post-translational modification that causes the addition of a myristate to a glycine in the N-terminal end of the amino acid chain. This work presents neural network (NN) models that learn to discriminate myristoylated and nonmyristoylated proteins. Ensembles of 25 NNs and decision trees were trained on 390 positive s...

The inherent black-box nature of neural networks is an important drawback with respect to the problem of explanation of neural network responses. Although several articles have tackled the problem of rule extraction from a single neural network, just a few papers have investigated rule extraction from several combined neural networks. In this artic...

This work presents ensembles of neural network models that learn to discriminate images from different categorical scenes. The basic idea was to use ICA filter energies and to train neural network ensem- bles. The presented results improved the predictive accuracy of previ- ously published work on the second classification problem. Finally, rules g...

Although two proteins may be structurally similar, they may not have significant sequence similarity. The recognition of protein fold structures without relying on sequence similarity is a complex task. This work presents a comparison study on the recognition of 3-dimensional protein folds by Machine Learning models. Combinations of neural networks...

Rules are extracted from the DIMLP neural network in polynomial time with respect to the size of the classification problem and the size of the network. With rules is possible to ask how well do inferences made compare with knowledge and heuristics of experts. Although fidelity of generated rules from the training set is 100%, perfect fidelity on n...

In this work the purpose is to determine discriminant hyperplanes of a neural network in order to extract possible valuable knowledge by means of symbolic rules. We define a special neural network model denoted to as Discretized Interpretable Multi Layer Perceptron (DIMLP). As a result, rules are extracted in polynomial time with respect to the siz...

The problem of rule extraction from neural networks is NP-hard. This work presents a new technique to extract "if-then-else" rules from ensembles of DIMLP neural networks. Rules are extracted in polynomial time with respect to the dimensionality of the problem, the number of examples, and the size of the resulting network. Further, the degree of ma...

We present a neuro-fuzzy model called fuzzy discretized interpretable multi-layer perceptron (FDIMLP). Fuzzy rules are extracted in polynomial time with respect to the size of the problem and the size of the network. We applied our model to three classification problems of the public domain. It turned out that FDIMLP networks compared favorably wit...