This paper investigates and compares the performance of various behavioral modeling approaches, both analytical and machine learning-based, for Lithium-ion batteries. The analytical models rely exclusively on the genetic programming algorithm, while the machine learning-based models employ several well-known regression techniques, including multi-layer perceptron, support vector machine, and gradient boosting. These data-driven models are used to relate the battery's terminal voltage to its state of charge, charge/discharge rate, and temperature, using a consistent dataset for the case study. The study focuses on the transient discharge phase of a Lithium Iron Phosphate battery under realistic operating conditions, with a state of charge between 20% and 80%, discharge rates ranging from 0.25C to 1C, and temperatures between 5°C and 35°C.

Objective analysis of gait abilities (Gait Analysis, GAn) in clinic is an essential motor assessment to improve clinical decision-making and provide precision rehabilitation approaches to recover gait functions. GAn is usually based on wearable motion sensors or camera-based systems, which generate an extensive set of data which are challenging to manage, analyse, and interpret. This makes GAn a time-consuming unfeasible assessment approach in clinical practice. Machine Learning (ML) techniques can provide a viable solution, as they can handle massive time series and complex data. This study aims to correctly classify subjects’ physical activity levels, using as ground truth a self-reported questionnaire (International Physical Activity Questionnaire, IPAQ), via kinematic features provided by wearable wireless Inertial Measurement Unit (IMU) sensors. Kinematic gait data were collected from 37 healthy subjects (24 male and 13 female) while walking on a sensorised treadmill at natural speed. Velocity, acceleration, jerk, and smoothness were calculated using the kinematic features and used to perform statistical feature extraction. The Neighbourhood Component Analysis (NCA) algorithm was used to process the statistical features space and select the most significant ones. Several models have been trained and tested before and after the feature selection to validate the approach’s effectiveness. Feature reduction resulted in a significant increase in accuracy for K-Nearest Neighbours (KNN) (81.978 ± 0.368), Random Forest (84.044 ± 3.409) and Rough-Set-Exploration-System Library K-Nearest Neighbours (RSesLib KNN) (83.956 ± 0), with an improvement of ≈20%. The performance of the best-performing classifiers was then analysed, observing the behaviour of accuracy by varying the number of features considered.

The use of Machine Learning in IoT devices has become the only viable path in today's landscape, where millions of connected devices surround us and increasingly affect our lives. These resource-limited devices interact with the surrounding world via actuators and sensors. Many of these devices use Machine Learning techniques to be able to interpret the world and choose the appropriate action to take. Therefore the purpose of this work is to create a system that allows the application of Machine Learning algorithms directly to the ends of the network, where sensors and actuators reside. The system is designed to rely on the SENSIPLUS smart-sensor as a data acquisition device, and consists of an automatic code generation and compilation system, which through the use of a Toolchain, allows to run artificial intelligence algorithms directly on microcontroller devices.

The spilling of suspicious or illegal substances in wastewater poses a serious global threat to human health. Low-cost sensor technologies enabling wastewater continuous monitoring are an important tool that can help face this problem. In this paper, electrical impedance measurements on different sensors are proposed in order to have a dataset of raw data to be used to perform the classification of possible contaminants in a water environment. In detail, the sensor technology is based on a proprietary multi-sensing platform called SENSIPLUS, which is arranged in a suitable set-up able to carry out measurements in water for prolonged times. Sensors metalized with different materials are jointly used to exploit sensitivity diversity to different contaminants. An ad-hoc measurement procedure has been designed, including data acquisition during the warm-up period, contaminant injection, and steady-state conditions. The dataset proposed in this paper has been acquired in different European laboratories (Italy and Poland) and is made publicly available for testing new data analysis or machine learning techniques for the detection and classification of ten wastewater dangerous “contaminants” (https://aida.unicas.it/icprchallenge2022/).

Water monitoring systems continuously working ensure real–time pollutant detection capabilities according to their sensitivity and specificity. It is necessary to balance such features because, although being able to sense several substances is a desired feature, the reduction of false positives is a primary goal a classification system should have. High false positive makes the system unusable. The current solution enables a 24/7 service with a sampling rate equal to 0.6 Hz. Our goal is to limit false positives to 1 per day, thus achieving 99.99% accuracy at least. In this paper, we add a false positive reduction module to our pre-existent system, aiming to manage false positive boosters as sensor drift and signal oscillations. Obtained results, using a Multi Layer Perceptron classifier, confirm the false positive reduction while keeping high true positive rates.

Early diagnosis of neurodegenerative disorders, such as Alzheimer's Disease (AD), is very important to reduce their effects and to improve both quality and life expectancy of patients. In this context, it is generally agreed that handwriting is one of the first skills altered by the onset of AD. For this reason, the analysis of handwriting and the study of its alterations has become of great interest in order to formulate the diagnosis as soon as possible. A fundamental aspect for the use of these techniques is the definition of effective features, which allows the system to distinguish the natural alterations of handwriting due to age, from those caused by neurodegenerative disorders. Starting from these considerations, the aim of our study is to verify whether the combined use of both shape and dynamic features allows a decision support system to improve performance for AD diagnosis. To this purpose, starting from a database of on-line handwriting samples, we generated for each of them an off-line synthetic color image, where the color of each elementary trait encodes, in the three RGB channels, the dynamic information associated with that trait. To verify the role played by dynamic information, we also generated simple binary images, containing only shape information. Finally, we exploited the ability of Convolutional Neural Network (CNN) to automatically extract features on both color and binary images. The experimental results have confirmed that dynamic information allows a performance improvement with respect to the binary images.

Early detection of Alzheimer's Disease (AD) is essential in order to initiate therapies that can reduce the effects of such a disease, improving both life quality and life expectancy of patients. Among all the activities carried out in our daily life, handwriting seems one of the first to be influenced by the arise of neurodegenerative diseases. For this reason, the analysis of handwriting and the study of its alterations has become of great interest in this research field in order to make a diagnosis as early as possible. In recent years, many studies have tried to use classification algorithms applied to handwriting to implement decision support systems for AD diagnosis. A key issue for the use of these techniques is the detection of effective features, that allow the system to distinguish the natural handwriting alterations due to age, from those caused by neurodegenerative disorders. In this context, many interesting results have been published in the literature in which the features have been typically selected by hand, generally considering the dynamics of the handwriting process in order to detect motor disorders closely related to AD. Features directly derived from handwriting generation models can be also very helpful for AD diagnosis. It should be remarked, however, that the above features do not consider changes in the shape of handwritten traces, which may occur as a consequence of neurodegenerative diseases, as well as the correlation among shape alterations and changes in the dynamics of the handwriting process. Moving from these considerations, the aim of this study is to verify if the combined use of both shape and dynamic features allows a decision support system to improve performance for AD diagnosis. To this purpose, starting from a database of on-line handwriting samples, we generated for each of them a synthetic off-line colour image, where the colour of each elementary trait encodes, in the three RGB channels, the dynamic information associated to that trait. Finally, we exploited the capability of Deep Neural Networks (DNN) to automatically extract features from raw images, following the Transfer Learning approach. The experimental comparison of the results obtained by using standard features and features extracted according the above procedure, confirmed the effectiveness of our approach.

In smart city framework, the water monitoring through an efficient, low-cost, low-power and IoT-oriented sensor technology is a crucial aspect to allow, with limited resources, the analysis of contaminants eventually affecting wastewater. In this sense, common interfering substances, as detergents, cannot be classified as dangerous contaminants and should be neglected in the classification. By adopting classical machine learning approaches having a finite set of possible responses, each alteration of the sensor baseline is always classified as one out of the predetermined substances. Consequently, we developed an anomaly detection system based on one-class classifiers, able to discriminate between a recognized set of substances and an interfering source. In this way, the proposed detection system is able to provide detailed information about the water status and distinguish between harmless detergents and dangerous contaminants.

Nowadays water monitoring represents one of the most challenging global aims for the protection of people and environment health. In this paper we propose the application of an integrated system for the detection and recognition of contaminants in water. It is based on a two layer architecture: a sensing layer based on SENSIPLUS chip, and a data collection and classification layer, hereafter referred as SENSIPLUS Deep Machine (SDM). The SDM includes: a Micro Controller Unit (MCU), an optional host controller (e.g. laptop, smartphone, etc.) and different software components for data communication, analysis, and classification/regression based on machine learning techniques. Although the SDM classification/regression module can be potentially developed with any machine learning solution, in this paper we adopted an Artificial Neural Network with only one hidden layer to have a lightweight solution suitable to run (for inference) on ultra low power MCU. Aiming at further minimizing the network complexity, two alternative training sessions have been pursued: the first one using raw sensors' data and the second one applying a feature space dimensionality reduction through the Principal Component Analysis technique. Comparable and positive results (higher than 82% as average accuracy) have been obtained, confirming the validity and potentiality of the proposed system.

Indoor air monitoring represents one of the most challenging global aims for the protection of people health and safety. Lots of efforts, either in the academic or industrial field, are addressed to the development and integration of sensing technologies and Artificial Intelligence techniques for the realization of a smart system capable to detect and recognize gases. In this work, we propose a first prototype of an integrated system involving both sensing and Artificial Intelligence technologies, developed as a two layer architecture. The Hardware Layer is the SENSIPLUS® microchip, a smart sensor IoT ready node endowed with on board sensors and implementing novel measuring technique based on current/voltage correlations. The Software Layer is the SENSIPLUS®Deep Machine, a Deep Learning module based on a Long Short-Term Memory neural network, particularly suitable for times series analysis. The paper presents preliminary experiments for the recognition of three distinct gases with respect to air that demonstrates the proposed system effectiveness.

In this paper, we analyze how stabilizing the variance of intensity-dependent quantum noise in digital mammograms can significantly improve the computerized detection of microcalcifications (MCs). These lesions appear on mammograms as tiny deposits of calcium smaller than 20 pixels in diameter. At this scale, high frequency image noise is dominated by quantum noise, which in raw mammograms can be described with a square-root noise model. Under this assumption, we derive an adaptive variance stabilizing transform (VST) that stabilizes the noise to unitary standard deviation in all the images. This is achieved by estimating the noise characteristics from the image at hand. We tested the adaptive VST as a preprocessing stage for four existing computerized MC detection methods on three data sets acquired with mammographic units from different manufacturers. In all the test cases considered, MC detection performance on transformed mammograms was statistically significantly higher than on unprocessed mammograms. Results were also superior in comparison with a "fixed" (nonparametric) VST previously proposed for digital mammograms.

Microcalcifications are an early mammographic indicator of breast cancer. To assist screening radiologists in reading mammograms, machine learning techniques have been developed for the automated detection of microcalcifications. In the last few years, Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance in many computer vision and medical image analysis applications. A key step in CNN-based detection is image preprocessing, including brightness and contrast variations. In this work, we investigate the influence of preprocessing of digital mammograms on the microcalcification detection performance of two CNNs inspired by the popular AlexNet and VGGnet. We tested two preprocessing methods commonly applied to unprocessed raw digital mammograms: (i) the logarithmic transformation adopted by different manufacturers for the presentation of the image to the radiologists; and (ii) the square-root of image intensity that stabilizes the intensity-dependent noise present in the mammogram. Experiments were performed on 1,066 mammograms acquired with GE Senographe systems. Both preprocessing methods yielded statistically significantly better microcalcification detection performance. Results of the square-root transform were superior to those obtained with the log transform.

Assessment of retinal vessels is fundamental for the diagnosis of many disorders such as heart diseases, diabetes and hypertension. The imaging of retina using advanced fundus camera has become a standard in computer-assisted diagnosis of opthalmic disorders. Modern cameras produce high quality color digital images, but during the acquisition process the light reflected by the retinal surface generates a luminosity and contrast variation. Irregular illumination can introduce severe distortions in the resulting images, decreasing the visibility of anatomical structures and consequently demoting the performance of the automated segmentation of these structures. In this paper, a novel approach for illumination correction of color fundus images is proposed and applied as preprocessing step for retinal vessel segmentation. Our method builds on the connection between two different phenomena, shadows and haze, and works by removing the haze from the image in the inverted intensity domain. This is shown to be equivalent to correct the nonuniform illumination in the original intensity domain. We tested the proposed method as preprocessing stage of two vessel segmentation methods, one unsupervised based on mathematical morphology, and one supervised based on deep learning Convolutional Neural Networks (CNN). Experiments were performed on the publicly available retinal image database DRIVE. Statistically significantly better vessel segmentation performance was achieved in both test cases when illumination correction was applied.

When mammograms are analyzed through a Computer Aided Diagnosis (CAD) system the presence of the pectoral muscle can affect the results of the automatic detection of breast lesions. This problem is particularly evident in mediolateral oblique (MLO) view where the pectoral muscle appears as a high intensity region across the margin of the mammogram. An automatic identification of the pectoral muscle is an essential step because of its similar characteristics with the abnormal tissue that can interfere with the detection of suspicious regions or bias the estimation of breast tissue density. This paper presents a new approach for the detection of pectoral muscle in MLO view of the mammo-graphic images. It is based on a preprocessing step useful to normalize the image and highlight the boundary between the muscle and the mammary tissue. A subsequent step including edge detection and regression via RANSAC provides the final contour of the muscle area. The experiments performed on a standard data set show very encouraging results.

The presence of clusters of microcalcifications in mammograms is particularly significant for early detection of breast cancer. In this paper a Computer Aided Detection system designed for this task is described. The detection of microcalcifications is performed by means of a segmentation based on a watershed transform and a further analysis based both on heuristic rules and AdaBoost classification. Finally a clustering algorithm is applied to detect those clusters of medical interest. The approach has been successfully tested on a Full Field Digital Mammographic database that has been developed through a strong cooperation between radiologists and computer scientists.

Mammography is a noninvasive diagnostic technique widely used for early cancer detection in women breast. The automatic detection and classification of some abnormalities in mammograms is of challenging scientific and technical interest because of the associated research topics and the potential clinical applications. Therefore, the design of a medical CAD (Computer-Aided Diagnosis or Detection) system for the analysis of mammographies involves a team composed by both medical and technical experts. In this paper we show the interaction that occurs between computer scientists and radiologists in the development and evaluation of a CAD system for the detection of clusters of micro-calcifications.

In this paper, we propose a method for the linear combination of several dichotomizers aimed at maximizing the area under the receiver operating characteristic (ROC) curve of the resulting classification system. This is particularly suited for real applications where it is difficult to exactly determine the key parameters such as costs and priors. In such cases, the accuracy is not adequate in measuring the quality of a classification system, while the ROC analysis provides the right tools for an appropriate assessment of the classification performance. The proposed approach revealed to be particularly effective with respect to other widespread combination rules both on artificial and real applications.

Mammography is a not invasive diagnostic technique widely used for early cancer detection in women breast. A particularly significant clue of such disease is the presence of clusters of microcalcifications. The automatic detection and classification of such clusters is a very difficult task because of the small size of the microcalcifications and of the poor quality of the digital mammograms. In literature, all the proposed methods for the automatic detection focus on the single microcalcification. In this paper, an approach that moves the final decision on the regions identified by the segmentation in the phase of clustering is proposed. To this aim, the output of a classifier on the single microcalcifications is used as input data in a clustering algorithms which produce the detected clusters. As final output the system highlights the suspicious clusters, leaving to the specialist the diagnosis responsibility. The approach has been successfully tested on a standard database of 40 mammographic images, publicly available.

We present a method for segmenting a planar digital curve into line segments and circular arcs. It is based on Dynamic Programming and works in a transformed domain which makes the approximation process simpler and independent from the particular geometrical primitive considered. Experiments performed on some shapes conjirm the effectiveness oj the approach.