RESUMO
Deep learning (DL) has been demonstrated to be a valuable tool for analyzing signals such as sounds and images, thanks to its capabilities of automatically extracting relevant patterns as well as its end-to-end training properties. When applied to tabular structured data, DL has exhibited some performance limitations compared to shallow learning techniques. This work presents a novel technique for tabular data called adaptive multiscale attention deep neural network architecture (also named excited attention). By exploiting parallel multilevel feature weighting, the adaptive multiscale attention can successfully learn the feature attention and thus achieve high levels of F1-score on seven different classification tasks (on small, medium, large, and very large datasets) and low mean absolute errors on four regression tasks of different size. In addition, adaptive multiscale attention provides four levels of explainability (i.e., comprehension of its learning process and therefore of its outcomes): 1) calculates attention weights to determine which layers are most important for given classes; 2) shows each feature's attention across all instances; 3) understands learned feature attention for each class to explore feature attention and behavior for specific classes; and 4) finds nonlinear correlations between co-behaving features to reduce dataset dimensionality and improve interpretability. These interpretability levels, in turn, allow for employing adaptive multiscale attention as a useful tool for feature ranking and feature selection.
RESUMO
The security of modern smartphones is related to the combination of Continuous Authentication approaches, Touch events, and Human Activities. The approaches of Continuous Authentication, Touch Events, and Human Activities are silent to the user but are a great source of data for Machine Learning Algorithms. This work aims to develop a method for continuous authentication while the user is sitting and scrolling documents on the smartphone. Touch Events and Smartphone Sensor Features (from the well-known H-MOG Dataset) were used with the addition, for each sensor, of the feature called Signal Vector Magnitude. Several Machine Learning Models have been considered with different experiment setups, 1-class, and 2-class, for evaluation. The results show that the 1-class SVM achieves an accuracy of 98.9% and an F1-score of 99.4%, considering the selected features and the feature Signal Vector Magnitude very significant.
Assuntos
Percepção do Tato , Tato , Humanos , Smartphone , Atividades Humanas , AlgoritmosRESUMO
BACKGROUND AND OBJECTIVE: Neurodegenerative diseases are the most frequent age-related diseases. This type of disease, if not discovered in the initial stage, will compromise the quality of life of the affected subject. Thus, a timely diagnosis is of paramount importance. One of the most used tasks from neurologists to detect and determine the severity of the disease is analysing human gait. This work presents the dataset named "Beside Gait" containing timeseries of coordinates of extracted body joints of people with neurodegenerative diseases in various stages of the disease as well as control subjects. In addition, the novel Multi-Speed transformer technique will be presented and benchmarked against several other techniques making use of deep learning and Shallow Learning. The objective is to recognize subjects affected by some form of neurodegenerative disease in early stage using a computer vision technique making use of deep learning that can be integrated into a smartphone app for offline inference with the aim of promptly initiate investigations and treatment to improve the patient's quality of life. METHODS: The recorded videos were processed, and the skeleton of the person in the video was extracted using pose estimation. The raw time-series coordinates of the joints extracted by the pose estimation algorithm were tested against novel deep neural network architectures and Shallow Learning techniques. In this work, the proposed Multi-Speed Transformer is benchmarked against other deep neural networks such as Temporal Convolutional Neural Networks, Transformers, as well as Shallow Learning techniques making use of feature extraction and different classifiers such as Random Forests, K Nearest Neighbours, Ada Boost, Linear and RBF SVM. The proposed Multi-Speed Transformer architecture has been developed to learn short and long-term patterns to model the various pathological gaits. RESULTS: The Multi-Speed Transformer outperformed all other existing models reaching an accuracy of 96.9%, a sensitivity of 96.9%, a precision of 97.7%, and a specificity of 97.1% in binary classification. The accuracy in multi-class classification for detecting the presence of the disease in various stages is 71.6%, the sensitivity is 67.7%, and the specificity is 71.8%. In addition, tests have also been conducted against two other different activity recognition datasets, namely SHREC and JHMDB, in the exact same conditions. Multi-Speed Transformer has demonstrated to beat always all other tested techniques as well as the techniques reviewed in the state-of-the-art with respectively of accuracy 91.8% and 74%. Having those datasets more than two classes, specificity was not computed. CONCLUSIONS: The Multi-Speed Transformer is a valuable technique for neurodegenerative disease assessment through computer vision. In addition, the novel dataset "Beside Gait" here presented is an important starting point for future research work on automatic recognition of neurodegenerative diseases using gait analysis.
Assuntos
Aprendizado Profundo , Doenças Neurodegenerativas , Humanos , Doenças Neurodegenerativas/diagnóstico , Qualidade de Vida , Redes Neurais de Computação , AlgoritmosRESUMO
Human activity recognition (HAR) through gait analysis is a very promising research area for early detection of neurodegenerative diseases because gait abnormalities are typical symptoms of some neurodegenerative diseases, such as early dementia. While working with such biometric data, the performance parameters must be considered along with privacy and security issues. In other words, such biometric data should be processed under specific security and privacy requirements. This work proposes an innovative hybrid protection scheme combining a partially homomorphic encryption scheme and a cancelable biometric technique based on random projection to protect gait features, ensuring patient privacy according to ISO/IEC 24745. The proposed hybrid protection scheme has been implemented along a long short-term memory (LSTM) neural network to realize a secure early dementia diagnosis system. The proposed protection scheme is scalable and implementable with any type of neural network because it is independent of the network's architecture. The conducted experiments demonstrate that the proposed protection scheme enables a high trade-off between safety and performance. The accuracy degradation is at most 1.20% compared with the early dementia recognition system without the protection scheme. Moreover, security and computational analyses of the proposed scheme have been conducted and reported.
Assuntos
Demência , Doenças Neurodegenerativas , Humanos , Análise da Marcha , Marcha , Biometria , Demência/diagnósticoRESUMO
This study presents the Auditory Cortex ResNet (AUCO ResNet), it is a biologically inspired deep neural network especially designed for sound classification and more specifically for Covid-19 recognition from audio tracks of coughs and breaths. Differently from other approaches, it can be trained end-to-end thus optimizing (with gradient descent) all the modules of the learning algorithm: mel-like filter design, feature extraction, feature selection, dimensionality reduction and prediction. This neural network includes three attention mechanisms namely the squeeze and excitation mechanism, the convolutional block attention module, and the novel sinusoidal learnable attention. The attention mechanism is able to merge relevant information from activation maps at various levels of the network. The net takes as input raw audio files and it is able to fine tune also the features extraction phase. In fact, a Mel-like filter is designed during the training, thus adapting filter banks on important frequencies. AUCO ResNet has proved to provide state of art results on many datasets. Firstly, it has been tested on many datasets containing Covid-19 cough and breath. This choice is related to the fact that that cough and breath are language independent, allowing for cross dataset tests with generalization aims. These tests demonstrate that the approach can be adopted as a low cost, fast and remote Covid-19 pre-screening tool. The net has also been tested on the famous UrbanSound 8K dataset, achieving state of the art accuracy without any data preprocessing or data augmentation technique.
RESUMO
This paper reviews the recent literature on technologies and methodologies for quantitative human gait analysis in the context of neurodegenerative diseases. The use of technological instruments can be of great support in both clinical diagnosis and severity assessment of these pathologies. In this paper, sensors, features and processing methodologies have been reviewed in order to provide a highly consistent work that explores the issues related to gait analysis. First, the phases of the human gait cycle are briefly explained, along with some non-normal gait patterns (gait abnormalities) typical of some neurodegenerative diseases. Then the paper reports the most common processing techniques for both feature selection and extraction and for classification and clustering. Finally, a conclusive discussion on current open problems and future directions is outlined.
Assuntos
Análise da Marcha , Doenças Neurodegenerativas , Algoritmos , Marcha , Humanos , Doenças Neurodegenerativas/diagnósticoRESUMO
Automatic traffic flow classification is useful to reveal road congestions and accidents. Nowadays, roads and highways are equipped with a huge amount of surveillance cameras, which can be used for real-time vehicle identification, and thus providing traffic flow estimation. This research provides a comparative analysis of state-of-the-art object detectors, visual features, and classification models useful to implement traffic state estimations. More specifically, three different object detectors are compared to identify vehicles. Four machine learning techniques are successively employed to explore five visual features for classification aims. These classic machine learning approaches are compared with the deep learning techniques. This research demonstrates that, when methods and resources are properly implemented and tested, results are very encouraging for both methods, but the deep learning method is the most accurately performing one reaching an accuracy of 99.9% for binary traffic state classification and 98.6% for multiclass classification.
RESUMO
Neurodegenerative diseases, for instance Alzheimer's disease (AD) and Parkinson's disease (PD), affect the peripheral nervous system, where nerve cells send messages that control muscles in order to allow movements. Sick neurons cannot control muscles properly. Handwriting involves cognitive planning, coordination, and execution abilities. Significant changes in handwriting performance are a prominent feature of AD and PD. This paper addresses the most relevant results obtained in the field of online (dynamic) analysis of handwritten trials by AD and PD patients. The survey is made from a pattern recognition point of view, so that different phases are described. Data acquisition deals not only with the device, but also with the handwriting task. Feature extraction can deal with function and parameter features. The classification problem is also discussed along with results already obtained. This paper also highlights the most profitable research directions.
Assuntos
Doença de Alzheimer/fisiopatologia , Escrita Manual , Destreza Motora/fisiologia , Doenças Neurodegenerativas/diagnóstico , Doença de Parkinson/fisiopatologia , Fenômenos Biomecânicos , Humanos , Músculo Esquelético/fisiopatologia , Doenças Neurodegenerativas/fisiopatologia , Sistema Nervoso Periférico/fisiopatologiaRESUMO
This work presents the practical design of a system that faces the problem of identification and validation of private no-parking road signs. This issue is very important for the public city administrations since many people, after receiving a code that identifies the signal at the entrance of their private car garage as valid, forget to renew the code validity through the payment of a city tax, causing large money shortages to the public administration. The goal of the system is twice since, after recognition of the official road sign pattern, its validity must be controlled by extracting the code put in a specific sub-region inside it. Despite a lot of work on the road signs' topic having been carried out, a complete benchmark dataset also considering the particular setting of the Italian law is today not available for comparison, thus the second goal of this work is to provide experimental results that exploit machine learning and deep learning techniques that can be satisfactorily used in industrial applications.
RESUMO
In the field of handwritten character recognition, image zoning is a widespread technique for feature extraction since it is rightly considered to be able to cope with handwritten pattern variability. As a matter of fact, the problem of zoning design has attracted many researchers who have proposed several image-zoning topologies, according to static and dynamic strategies. Unfortunately, little attention has been paid so far to the role of feature-zone membership functions that define the way in which a feature influences different zones of the zoning method. The result is that the membership functions defined to date follow nonadaptive, global approaches that are unable to model local information on feature distributions. In this paper, a new class of zone-based membership functions with adaptive capabilities is introduced and its effectiveness is shown. The basic idea is to select, for each zone of the zoning method, the membership function best suited to exploit the characteristics of the feature distribution of that zone. In addition, a genetic algorithm is proposed to determine-in a unique process-the most favorable membership functions along with the optimal zoning topology, described by Voronoi tessellation. The experimental tests show the superiority of the new technique with respect to traditional zoning methods.