Search

Lithium-ion (Li-ion) batteries are crucial in numerous applications, including portable electronics, electric vehicles, and energy storage systems. Electrochemical Impedance Spectroscopy (EIS) is a powerful technique for characterizing batteries, providing valuable insights into charge transfer kinetics like ion diffusion and interfacial reactions. However, obtaining comprehensive and diverse datasets for battery State of Charge (SoC) studies remains challenging due to the complex nature of battery operations and the time-intensive testing process. This paper presents a novel and original EIS dataset specifically designed for 600 mAh capacity Lithium Iron Phosphate (LFP) batteries at various SoC levels. The dataset includes repeated EIS measurements using different battery discharging cycles, allowing researchers to examine the frequency domain properties and develop data-driven algorithms for assessing battery SoC and predicting performance. The data acquisition system employs a battery specific impedance meter and an electronic load, ensuring accurate and controlled measurements. The dataset, comprising EIS measurements from multiple LFP batteries, serves as a valuable resource for researchers in the fields of battery technology, electrochemistry, power sources, and energy storage. Moreover, industries such as consumer electronics, power systems, and electric transportation can benefit from the dataset's insights for effectively managing rechargeable battery devices. The presented dataset expands the scope of impedance spectroscopy measurements and holds significant potential for future applications and advancements in Li-ion battery technologies.

In the field of cybersecurity, the ability to gather detailed information about target systems is a critical component of the reconnaissance phase of cyber attacks. This phase, known as cybersecurity reconnaissance, involves techniques that adversaries use to collect information vital for the success of subsequent attack stages. Traditionally, reconnaissance activities include network scanning, sniffing, and social engineering, which allow attackers to map the network, identify vulnerabilities, and plan their exploits. In this paper, we explore a novel application of side-channel analysis within system-based reconnaissance. Side-channel attacks, typically used to extract cryptographic keys or sensitive data through indirect observations such as power consumption or electromagnetic emissions, are here repurposed for a different kind of system intrusion. Specifically, we demonstrate how side-channel analysis and machine learning techniques can classify running processes on a target system that are very popular in common IoT applications. This approach is particularly concerning for IoT environments where devices often control critical infrastructure or handle sensitive data. The ability to identify active applications can reveal operation patterns, system behaviors, and potential vulnerabilities that traditional security measures may not protect against. Moreover, in IoT scenarios, this information can be leveraged to orchestrate sophisticated attacks targeting specific services or to exploit timing-based vulnerabilities when certain critical applications are running. By categorizing this approach as a form of local system-based reconnaissance, we highlight its potential to silently gather critical information about a system’s state. Such capabilities represent a significant breach of privacy and provide attackers with the intelligence needed to carry out more targeted and effective attacks. This research also underscores the evolving nature of reconnaissance techniques and the growing risks of advanced side-channel cybersecurity methods.

This paper presents an innovative approach for detecting illegal microdumps using very high-resolution optical satellite imagery, addressing a significant environmental monitoring challenge in Campania, Italy. Due to the regional vulnerability to illegal dumping, exacerbated by the waste management crisis, there is a pressing need for enhanced surveillance and accurate identification of microdump locations. This paper uses deep learning techniques to introduce an effective technology for detecting microdumps in high-resolution optical satellite images from Pleiades and GeoEye-1 satellites in an end-to-end solution, from images to detection. Its primary aim is to preliminarily assess dumping sites within specific target areas of interest (patrolling cells) for subsequent on-ground confirmation and characterization. The proposed system comprises two neural networks: the first, based on RetinaNet, identifies regions containing microdumps, while the second, utilizing InceptionV3, enhances the detection through pixel-wise classification. A fusion rule is then applied to combine the decisions of these networks. This technology addresses an environmental issue and is part of a progressive monitoring process. Validation was performed through a significant case study focusing on an extensive area between Naples and Caserta in the Campania region in Italy, particularly affected by illegal microdumps. A model was trained and validated using the pansharpened version of Pleiades multispectral images. This model exhibits potential for detecting microdumps in images from other satellite missions, as confirmed by validating it with GeoEye-1 imagery without further fine-tuning or training. The performance of the proposed detection system, evaluated for the reference application, achieves a detection rate of approximately 90% and a false discovery rate of about 40%. Notably, this is attained using a fully automatic processing chain without geospatial integration with additional information sources. In conclusion, despite satellite images having limited ground sampling distance and subsequent lower accuracy of image understanding algorithms, they remain suitable for environmental monitoring applications from an end-user perspective.

Gait analysis (GAn) is crucial for assessing human biomechanics, aiding rehabilitation, and informing health diagnostics. Traditional optoelectronic systems represent the gold standard for determining joint kinematics, but they present challenges due to high costs and technical demands in offering precise 3D marker-based GAn. Inertial measurement units (IMUs) provide a portable, cost-effective alternative but face data volume, setup time, and calibration challenges. Thanks to recent advancements in computer vision, markerless video-based solutions have become increasingly popular as they have the potential to overcome the limitations of marker-based systems and IMUs. In this study, we developed and validated a novel sensorless method for estimating knee flexion and ankle dorsiflexion angles using a single-camera setup integrated with the OpenPose (OP) open-source library. Thirty-one healthy subjects (20 females, 11 males) were recorded walking on a sensorised treadmill with lower-body IMUs at a natural pace, using a synchronised webcam. Results showed that the markerless software demonstrated significant accuracy in estimating the angles of knee flexion and ankle dorsiflexion compared to IMU-based measurements. By applying a universal compensation algorithm, we demonstrated that the method is subject-independent, ensuring its robustness and generalisability across different populations. Results showed that the markerless software demonstrated significant accuracy in estimating the angles of knee flexion and ankle dorsiflexion compared to IMU-based measurements. After compensation, the method achieved a compatibility of over 93% for knee joint angles and significant improvements for ankle dorsiflexion, indicating its potential to complement or substitute traditional IMU systems in biomechanical assessments. This validation suggests that our cost-effective, markerless approach can complement or substitute traditional IMUs systems in biomechanical assessments.

The problem of detecting illegal pollutants in wastewater is of fundamental importance for public health and security. The availability of distributed, low–cost and low–power monitoring systems, particularly enforced by IoT communication mechanisms and low-complexity machine learning algorithms, would make it feasible and easy to manage in a widespread manner. Accordingly, an End-to-End IoT-ready node for the sensing, local processing, and transmission of the data collected on the pollutants in the wastewater is presented here. The proposed system, organized in sensing and data processing modules, can recognize and distinguish contaminants from unknown substances typically present in wastewater. This is particularly important in the classification stage since distinguishing between background (not of interest) and foreground (of interest) substances drastically improves the classification performance, especially in terms of false positive rates. The measurement system, i.e., the sensing part, is represented by the so-called Smart Cable Water based on the SENSIPLUS chip, which integrates an array of sensors detecting various water-soluble substances through impedance spectroscopy. The data processing is based on a commercial Micro Control Unit (MCU), including an anomaly detection module, a classification module, and a false positive reduction module, all based on machine learning algorithms that have a computational complexity suitable for low-cost hardware implementation.An extensive experimental campaign on different contaminants has been carried out to train machine-learning algorithms suitable for low-cost and low-power MCU. The corresponding dataset has been made publicly available for download. The obtained results demonstrate an excellent classification ability, achieving an accuracy of more than 95% on average, and are a reliable “proof of concept” of a pervasive IoT system for distributed monitoring.

The detection of contaminants in several environments (e.g., air, water, sewage systems) is of paramount importance to protect people and predict possible dangerous circumstances. Most works do this using classical Machine Learning tools that act on the acquired measurement data. This paper introduces two main elements: a low-cost platform to acquire, pre-process, and transmit data to classify contaminants in wastewater; and a novel classification approach to classify contaminants in wastewater, based on deep learning and the transformation of raw sensor data into natural language metadata. The proposed solution presents clear advantages against state-of-the-art systems in terms of higher effectiveness and reasonable efficiency. The main disadvantage of the proposed approach is that it relies on knowing the injection time, i.e., the instant in time when the contaminant is injected into the wastewater. For this reason, the developed system also includes a finite state machine tool able to infer the exact time instant when the substance is injected. The entire system is presented and discussed in detail. Furthermore, several variants of the proposed processing technique are also presented to assess the sensitivity to the number of used samples and the corresponding promptness/computational burden of the system. The lowest accuracy obtained by our technique is 91.4%, which is significantly higher than the 81.0% accuracy reached by the best baseline method.

The paper proposes a new experimental measurement method for State of Charge (SoC) estimation able to optimize between measurement time and target Accuracy adoptable in Battery Management System (BMS) design where both these parameters are key parameters for the overall management performance. The method is applicable when the SoC is estimated in classes through Electrochemical Impedance Spectroscopy (EIS) and is based on two operating stages: i) the experimental characterization of the real behavior of the considered batteries, ii) a time–Accuracy optimization based on suitable feature selection and Machine Learning approaches. In detail, as for the ii) phase, fixed the number of classes in which the SoC is estimated, the proposed measurement method finds the minimum number of impedance spectrum frequency measurements useful for SoC estimation. This is a big issue for BMS designers since in SoC estimation performed by EIS the measurement time is typically greater than some minutes if no optimization is considered. A possible strategy to reduce the required time for SoC estimation could be using Feature Selection (FS) techniques. In our method the FS is implemented using different combinations of search algorithms and fitness functions. Since FS strongly depends on the experimental set–up, the uncertainty of the measurement system, and the classifier adopted for the data–driving evaluation model, the proposed method is flexible and customizable depending on the specific applications. For this reason, the method is divided into steps where the BMS designers define the requirements based on their needs and their hardware. Also the output FS could be adapted to the different exigencies because the selected features could be different if more emphasis is on increasing classification Accuracy or decreasing the measurement time. Hence, we suggest two application scenarios: in the first one, the only requirement is increasing the classification Accuracy rather than the measurement time optimization. The second scenario has both a classification Accuracy target and lowering the measurement time. We also noted that the proposed method is useful also for increasing the overall classification Accuracy because naturally excludes the features that deceive the classifiers. As an application for the proposed method, we developed an automatic measurement system and performed an experimental campaign on seven Lithium Iron Phosphate batteries. The experimental results show that the proposed approach, for all the considered combinations, significantly reduces the measurement time required for EIS while maintaining high SoC estimation Accuracy. Furthermore, for all the obtained solutions, the effectiveness of our approach was confirmed by the significant savings in measurement time. In particular, the best solution reduces from 4 minutes when using all features to about 1.5 seconds with the selected features.

The technological step towards sensors’ miniaturization, low-cost platforms, and evolved communication paradigms is rapidly moving the monitoring and computation tasks to the edge, causing the joint use of the Internet of Things (IoT) and machine learning (ML) to be massively employed. Edge devices are often composed of sensors and actuators, and their behavior depends on the relative rapid inference of specific conditions. Therefore, the computation and decision-making processes become obsolete and ineffective by communicating raw data and leaving them to a centralized system. This paper responds to this need by proposing an integrated architecture, able to host both the sensing part and the learning and classifying mechanisms, empowered by ML, directly on board and thus able to overcome some of the limitations presented by off-the-shelf solutions. The presented system is based on a proprietary platform named SENSIPLUS, a multi-sensor device especially devoted to performing electrical impedance spectroscopy (EIS) on a wide frequency interval. The measurement acquisition, data processing, and embedded classification techniques are supported by a system capable of generating and compiling code automatically, which uses a toolchain to run inference routines on the edge. As a case study, the system capabilities of such a platform in this work are exploited for water quality assessment. The joint system, composed of the measurement platform and the developed toolchain, is named SENSIPLUS-LM, standing for SENSIPLUS learning machine. The introduction of the toolchain empowers the SENSIPLUS platform moving the inference phase of the machine learning algorithm to the edge, thus limiting the needs of external computing platforms. The software part, i.e., the developed toolchain, is available for free download from GitLab, as reported in this paper.

In the framework of indoor air monitoring, this paper proposes an Internet of Things ready solution to detect and classify contaminants. It is based on a compact and low-power integrated system including both sensing and processing capabilities. The sensing is composed of a sensor array on which electrical impedance measurements are performed through a microchip, named SENSIPLUS, while the processing phase is mainly based on Machine Learning techniques, embedded in a low power and low resources micro controller unit, for classification purposes. An extensive experimental campaign on different contaminants has been carried out and raw sensor data have been processed through a lightweight Multi Layer Perceptron for embedded implementation. More complex and computationally costly Deep Learning techniques, as Convolutional Neural Network and Long Short Term Memory, have been adopted as a reference for the validation of Multi Layer Perceptron performance. Results prove good classification capabilities, obtaining an accuracy greater than 75% in average. The obtained results, jointly with the reduced computational costs of the solution, highlight that this proposal is a proof of concept for a pervasive IoT air monitoring system.

This paper proposes a deep leaning technique for accurate detection and reliable classification of organic pollutants in water. The pollutants are detected by means of cyclic voltammetry characterizations made by using low-cost disposable screen-printed electrodes. The paper demonstrates the possibility of strongly improving the detection of such platforms by modifying them with nanomaterials. The classification is addressed by using a deep learning approach with convolutional neural networks. To this end, the results of the voltammetry analysis are transformed into equivalent RGB images by means of Gramian angular field transformations. The proposed technique is applied to the detection and classification of hydroquinone and benzoquinone, which are particularly challenging since these two pollutants have a similar electroactivity and thus the voltammetry curves exhibit overlapping peaks. The modification of electrodes by carbon nanotubes improves the sensitivity of a factor of about ×25, whereas the convolution neural network after Gramian transformation correctly classifies 100% of the experiments.

Monitoring of aquatic ecosystems has been historically accomplished by intensive campaigns of direct measurements (by probes and other boat instruments) and indirect extensive methods such as aero-photogrammetry and satellite detection. These measurements characterized the research in the last century, with significant but limited improvements within those technological boundaries. The newest advances in the field of smart devices and increased networking capabilities provided by emerging tools, such as the Internet of Things (IoT), offer increasing opportunities to provide accurate and precise measurements over larger areas. These perspectives also correspond to an increasing need to promptly respond to frequent catastrophic impacts produced by drilling stations and intense transportation activities of dangerous materials over ocean routes. The shape of coastal ecosystems continuously varies due to increasing anthropic activities and climatic changes, aside from touristic activities, industrial impacts, and conservation practices. Smart buoy networks (SBNs), autonomous underwater vehicles (AUVs), and multi-sensor microsystems (MSMs) such as smart cable water (SCW) are able to learn specific patterns of ecological conditions, along with electronic “noses”, permitting them to set innovative low-cost monitoring stations reacting in real time to the signals of marine environments by autonomously adapting their monitoring programs and eventually sending alarm messages to prompt human intervention. These opportunities, according to multimodal scenarios, are dramatically changing both the coastal monitoring operations and the investigations over large oceanic areas by yielding huge amounts of information and partially computing them in order to provide intelligent responses. However, the major effects of these tools on the management of marine environments are still to be realized, and they are likely to become evident in the next decade. In this review, we examined from an ecological perspective the most striking innovations applied by various research groups around the world and analyzed their advantages and limits to depict scenarios of monitoring activities made possible for the next decade.

To better asses the ageing and to reduce the hazards involved in the use of Lithium-Ion Batteries, multi-measurand monitoring units and strategies are urged. In this paper, a Cell Management Unit, based on the SENSIPLUS chip, a recently introduced multichannel, multi-mode sensor interface, is described. SENSIPLUS is a single System on a Chip combined with a reduced number of external components, resulting in a highly miniaturized device, built on 20 × 8 mm2 printed circuit board. Thanks to SENSIPLUS’ versatility, the proposed system is capable of performing direct measurements (EIS, cell voltage) on the cell it is applied to, and reading different kinds of sensors. The SENSIPLUS versatile digital communication interface, combined with a digital isolator, enable connection of several devices to a single bus for parallel monitoring a large number of cells connected in series. Experiments performed by connecting the proposed system to a commercial Lithium-Ion Battery and to capacitive and resistive sensors are described. In particular, the capability of measuring the cell internal impedance with a resolution of 120 μΩ is demonstrated.

In the framework of palaeography, the availability of both effective image analysis algorithms, and high-quality digital images has favored the development of new applications for the study of ancient manuscripts and has provided new tools for decision-making support systems. The quality of the results provided by such applications, however, is strongly influenced by the selection of effective features, which should be able to capture the distinctive aspects to which the paleography expert is interested in. This process is very difficult to generalize due to the enormous variability in the type of ancient documents, produced in different historical periods with different languages and styles. The effect is that it is very difficult to define standard techniques that are general enough to be effectively used in any case, and this is the reason why ad-hoc systems, generally designed according to paleographers’ suggestions, have been designed for the analysis of ancient manuscripts. In recent years, there has been a growing scientific interest in the use of techniques based on deep learning (DL) for the automatic processing of ancient documents. This interest is not only due to their capability of designing high-performance pattern recognition systems, but also to their ability of automatically extracting features from raw data, without using any a priori knowledge. Moving from these considerations, the aim of this study is to verify if DL-based approaches may actually represent a general methodology for automatically designing machine learning systems for palaeography applications. To this purpose, we compared the performance of a DL-based approach with that of a “classical” machine learning one, in a particularly unfavorable case for DL, namely that of highly standardized schools. The rationale of this choice is to compare the obtainable results even when context information is present and discriminating: this information is ignored by DL approaches, while it is used by machine learning methods, making the comparison more significant. The experimental results refer to the use of a large sets of digital images extracted from an entire 12th-century Bibles, the “Avila Bible”. This manuscript, produced by several scribes who worked in different periods and in different places, represents a severe test bed to evaluate the efficiency of scribe identification systems.