RESUMEN
Accurate prognosis and diagnosis are crucial for selecting and planning lung cancer treatments. As a result of the rapid development of medical imaging technology, the use of computed tomography (CT) scans in pathology is becoming standard practice. An intricate interplay of requirements and obstacles characterizes computer-assisted diagnosis, which relies on the precise and effective analysis of pathology images. In recent years, pathology image analysis tasks such as tumor region identification, prognosis prediction, tumor microenvironment characterization, and metastasis detection have witnessed the considerable potential of artificial intelligence, especially deep learning techniques. In this context, an artificial intelligence (AI)-based methodology for lung cancer diagnosis is proposed in this research work. As a first processing step, filtering using the Butterworth smooth filter algorithm was applied to the input images from the LUNA 16 lung cancer dataset to remove noise without significantly degrading the image quality. Next, we performed the bi-level feature selection step using the Chaotic Crow Search Algorithm and Random Forest (CCSA-RF) approach to select features such as diameter, margin, spiculation, lobulation, subtlety, and malignancy. Next, the Feature Extraction step was performed using the Multi-space Image Reconstruction (MIR) method with Grey Level Co-occurrence Matrix (GLCM). Next, the Lung Tumor Severity Classification (LTSC) was implemented by using the Sparse Convolutional Neural Network (SCNN) approach with a Probabilistic Neural Network (PNN). The developed method can detect benign, normal, and malignant lung cancer images using the PNN algorithm, which reduces complexity and efficiently provides classification results. Performance parameters, namely accuracy, precision, F-score, sensitivity, and specificity, were determined to evaluate the effectiveness of the implemented hybrid method and compare it with other solutions already present in the literature.
RESUMEN
The phonocardiogram (PCG) can be used as an affordable way to monitor heart conditions. This study proposes the training and testing of several classifiers based on SVMs (support vector machines), k-NN (k-Nearest Neighbor), and NNs (neural networks) to perform binary ("Normal"/"Pathologic") and multiclass ("Normal", "CAD" (coronary artery disease), "MVP" (mitral valve prolapse), and "Benign" (benign murmurs)) classification of PCG signals, without heart sound segmentation algorithms. Two datasets of 482 and 826 PCG signals from the Physionet/CinC 2016 dataset are used to train the binary and multiclass classifiers, respectively. Each PCG signal is pre-processed, with spike removal, denoising, filtering, and normalization; afterward, it is divided into 5 s frames with a 1 s shift. Subsequently, a feature set is extracted from each frame to train and test the binary and multiclass classifiers. Concerning the binary classification, the trained classifiers yielded accuracies ranging from 92.4 to 98.7% on the test set, with memory occupations from 92.7 kB to 11.1 MB. Regarding the multiclass classification, the trained classifiers achieved accuracies spanning from 95.3 to 98.6% on the test set, occupying a memory portion from 233 kB to 14.1 MB. The NNs trained and tested in this work offer the best trade-off between performance and memory occupation, whereas the trained k-NN models obtained the best performance at the cost of large memory occupation (up to 14.1 MB). The classifiers' performance slightly depends on the signal quality, since a denoising step is performed during pre-processing. To this end, the signal-to-noise ratio (SNR) was acquired before and after the denoising, indicating an improvement between 15 and 30 dB. The trained and tested models occupy relatively little memory, enabling their implementation in resource-limited systems.
Asunto(s)
Algoritmos , Aprendizaje Automático , Redes Neurales de la Computación , Procesamiento de Señales Asistido por Computador , Máquina de Vectores de Soporte , Dispositivos Electrónicos Vestibles , Humanos , Fonocardiografía/métodosRESUMEN
A global health emergency resulted from the COVID-19 epidemic. Image recognition techniques are a useful tool for limiting the spread of the pandemic; indeed, the World Health Organization (WHO) recommends the use of face masks in public places as a form of protection against contagion. Hence, innovative systems and algorithms were deployed to rapidly screen a large number of people with faces covered by masks. In this article, we analyze the current state of research and future directions in algorithms and systems for masked-face recognition. First, the paper discusses the importance and applications of facial and face mask recognition, introducing the main approaches. Afterward, we review the recent facial recognition frameworks and systems based on Convolution Neural Networks, deep learning, machine learning, and MobilNet techniques. In detail, we analyze and critically discuss recent scientific works and systems which employ machine learning (ML) and deep learning tools for promptly recognizing masked faces. Also, Internet of Things (IoT)-based sensors, implementing ML and DL algorithms, were described to keep track of the number of persons donning face masks and notify the proper authorities. Afterward, the main challenges and open issues that should be solved in future studies and systems are discussed. Finally, comparative analysis and discussion are reported, providing useful insights for outlining the next generation of face recognition systems.
Asunto(s)
COVID-19 , Reconocimiento Facial , Internet de las Cosas , Humanos , Pandemias/prevención & control , AlgoritmosRESUMEN
A quantitative evaluation of kinetic parameters, the joint's range of motion, heart rate, and breathing rate, can be employed in sports performance tracking and rehabilitation monitoring following injuries or surgical operations. However, many of the current detection systems are expensive and designed for clinical use, requiring the presence of a physician and medical staff to assist users in the device's positioning and measurements. The goal of wearable sensors is to overcome the limitations of current devices, enabling the acquisition of a user's vital signs directly from the body in an accurate and non-invasive way. In sports activities, wearable sensors allow athletes to monitor performance and body movements objectively, going beyond the coach's subjective evaluation limits. The main goal of this review paper is to provide a comprehensive overview of wearable technologies and sensing systems to detect and monitor the physiological parameters of patients during post-operative rehabilitation and athletes' training, and to present evidence that supports the efficacy of this technology for healthcare applications. First, a classification of the human physiological parameters acquired from the human body by sensors attached to sensitive skin locations or worn as a part of garments is introduced, carrying important feedback on the user's health status. Then, a detailed description of the electromechanical transduction mechanisms allows a comparison of the technologies used in wearable applications to monitor sports and rehabilitation activities. This paves the way for an analysis of wearable technologies, providing a comprehensive comparison of the current state of the art of available sensors and systems. Comparative and statistical analyses are provided to point out useful insights for defining the best technologies and solutions for monitoring body movements. Lastly, the presented review is compared with similar ones reported in the literature to highlight its strengths and novelties.
Asunto(s)
Atletas , Rendimiento Atlético , Humanos , Estado de Salud , Frecuencia Cardíaca , CinéticaRESUMEN
The prevalence of neck pain, a chronic musculoskeletal disease, has significantly increased due to the uncontrollable use of social media (SM) devices. The use of SM devices by younger generations increased enormously during the COVID-19 pandemic, being-in some cases-the only possibility for maintaining interpersonal, social, and friendship relationships. This study aimed to predict the occurrence of neck pain and its correlation with the intensive use of SM devices. It is based on nine quantitative parameters extracted from the retrospective X-ray images. The three parameters related to angle_1 (i.e., the angle between the global horizontal and the vector pointing from C7 vertebra to the occipito-cervical joint), angle_2 (i.e., the angle between the global horizontal and the vector pointing from C1 vertebra to the occipito-cervical joint), and the area between them were measured from the shape of the neck vertebrae, while the rest of the parameters were extracted from the images using the gray-level co-occurrence matrix (GLCM). In addition, the users' ages and the duration of the SM usage (H.mean) were also considered. The decision tree (DT) machine-learning algorithm was employed to predict the abnormal cases (painful subjects) against the normal ones (no pain). The results showed that angle_1, area, and the image contrast significantly increased statistically with the time of SM-device usage, precisely in the range of 2 to 9 h. The DT showed a promising result demonstrated by classification accuracy and F1-scores of 94% and 0.95, respectively. Our findings confirmed that the objectively detected parameters, which elucidate the negative impacts of SM-device usage on neck pain, can be predicted by DT machine learning.
RESUMEN
Breathing monitoring is crucial for evaluating a patient's health status. The technologies commonly used to monitor respiration are costly, bulky, obtrusive, and inaccurate, mainly when the user moves. Consequently, efforts have been devoted to providing new solutions and methodologies to overcome these limitations. These methods have several uses, including healthcare monitoring, measuring athletic performance, and aiding patients with respiratory diseases, such as COPD (chronic obtrusive pulmonary disease), sleep apnea, etc. Breathing-induced chest movements can be measured noninvasively and discreetly using inertial sensors. This research work presents the development and testing of an inertia-based chest band for breathing monitoring through a differential approach. The device comprises two IMUs (inertial measurement units) placed on the patient's chest and back to determine the differential inertial signal, carrying out information detection about the breathing activity. The chest band includes a low-power microcontroller section to acquire inertial data from the two IMUs and process them to extract the breathing parameters (i.e., RR-respiration rate; TI/TE-inhalation/exhalation time; IER-inhalation-to-exhalation time; V-flow rate), using the back IMU as a reference. A BLE transceiver wirelessly transmits the acquired breathing parameters to a mobile application. Finally, the test results demonstrate the effectiveness of the used dual-inertia solution; correlation and Bland-Altman analyses were performed on the RR measurements from the chest band and the reference, demonstrating a high correlation (r¯ = 0.92) and low mean difference (MD¯ = -0.27 BrPM (breaths per minute)), limits of agreement (LoA¯ = +1.16/-1.75 BrPM), and mean absolute error (MAE¯ = 1.15%). Additionally, the experimental results demonstrated that the developed device correctly measured the other breathing parameters (TI, TE, IER, and V), keeping an MAE of ≤5%. The obtained results indicated that the developed chest band is a viable solution for long-term breathing monitoring, both in stationary and moving users.
Asunto(s)
Síndromes de la Apnea del Sueño , Dispositivos Electrónicos Vestibles , Humanos , Respiración , Frecuencia Respiratoria , EspiraciónRESUMEN
Sleep is crucial for human health from metabolic, mental, emotional, and social points of view; obtaining good sleep in terms of quality and duration is fundamental for maintaining a good life quality. Over the years, several systems have been proposed in the scientific literature and on the market to derive metrics used to quantify sleep quality as well as detect sleep disturbances and disorders. In this field, wearable systems have an important role in the discreet, accurate, and long-term detection of biophysical markers useful to determine sleep quality. This paper presents the current state-of-the-art wearable systems and software tools for sleep staging and detecting sleep disorders and dysfunctions. At first, the paper discusses sleep's functions and the importance of monitoring sleep to detect eventual sleep disturbance and disorders. Afterward, an overview of prototype and commercial headband-like wearable devices to monitor sleep is presented, both reported in the scientific literature and on the market, allowing unobtrusive and accurate detection of sleep quality markers. Furthermore, a survey of scientific works related the effect of the COVID-19 pandemic on sleep functions, attributable to both infection and lifestyle changes. In addition, a survey of algorithms for sleep staging and detecting sleep disorders is introduced based on an analysis of single or multiple biosignals (EEG-electroencephalography, ECG-electrocardiography, EMG-electromyography, EOG-electrooculography, etc.). Lastly, comparative analyses and insights are provided to determine the future trends related to sleep monitoring systems.
RESUMEN
This study addresses sensor allocation by analyzing exponential stability for discrete-time teleoperation systems. Previous studies mostly concentrate on the continuous-time teleoperation systems and neglect the management of significant practical phenomena, such as data-swap, the effect of sampling rates of samplers, and refresh rates of actuators on the system's stability. A multi-rate sampling approach is proposed in this study, given the isolation of the master and slave robots in teleoperation systems which may have different hardware restrictions. This architecture collects data through numerous sensors with various sampling rates, assuming that a continuous-time controller stabilizes a linear teleoperation system. The aim is to assign each position and velocity signals to sensors with different sampling rates and divide the state vector between sensors to guarantee the stability of the resulting multi-rate sampled-data teleoperation system. Sufficient Krasovskii-based conditions will be provided to preserve the exponential stability of the system. This problem will be transformed into a mixed-integer program with LMIs (linear matrix inequalities). These conditions are also used to design the observers for the multi-rate teleoperation systems whose estimation errors converge exponentially to the origin. The results are validated by numerical simulations which are useful in designing sensor networks for teleoperation systems.
RESUMEN
This paper reports on the progress of a wearable assistive technology (AT) device designed to enhance the independent, safe, and efficient mobility of blind and visually impaired pedestrians in outdoor environments. Such device exploits the smartphone's positioning and computing capabilities to locate and guide users along urban settings. The necessary navigation instructions to reach a destination are encoded as vibrating patterns which are conveyed to the user via a foot-placed tactile interface. To determine the performance of the proposed AT device, two user experiments were conducted. The first one requested a group of 20 voluntary normally sighted subjects to recognize the feedback provided by the tactile-foot interface. The results showed recognition rates over 93%. The second experiment involved two blind voluntary subjects which were assisted to find target destinations along public urban pathways. Results show that the subjects successfully accomplished the task and suggest that blind and visually impaired pedestrians might find the AT device and its concept approach useful, friendly, fast to master, and easy to use.
Asunto(s)
Peatones , Dispositivos de Autoayuda , Personas con Daño Visual , Dispositivos Electrónicos Vestibles , Humanos , Teléfono InteligenteRESUMEN
The evolution of low power electronics and the availability of new smart materials are opening new frontiers to develop wearable systems for medical applications, lifestyle monitoring, and performance detection. This paper presents the development and realization of a novel smart insole for monitoring the plantar pressure distribution and gait parameters; indeed, it includes a piezoresistive sensing matrix based on a Velostat layer for transducing applied pressure into an electric signal. At first, an accurate and complete characterization of Velostat-based pressure sensors is reported as a function of sizes, support material, and pressure trend. The realization and testing of a low-cost and reliable piezoresistive sensing matrix based on a sandwich structure are discussed. This last is interfaced with a low power conditioning and processing section based on an Arduino Lilypad board and an analog multiplexer for acquiring the pressure data. The insole includes a 3-axis capacitive accelerometer for detecting the gait parameters (swing time and stance phase time) featuring the walking. A Bluetooth Low Energy (BLE) 5.0 module is included for transmitting in real-time the acquired data toward a PC, tablet or smartphone, for displaying and processing them using a custom Processing® application. Moreover, the smart insole is equipped with a piezoelectric harvesting section for scavenging energy from walking. The onfield tests indicate that for a walking speed higher than 1 ms-1, the device's power requirements (i.e., P¯=5.84 mW) was fulfilled. However, more than 9 days of autonomy are guaranteed by the integrated 380-mAh Lipo battery in the total absence of energy contributions from the harvesting section.
Asunto(s)
Análisis de la Marcha , Zapatos , Suministros de Energía Eléctrica , Marcha , CaminataRESUMEN
The huge spreading of Internet of things (IoT)-oriented modern technologies is revolutionizing all fields of human activities, leading several benefits and allowing to strongly optimize classic productive processes. The agriculture field is also affected by these technological advances, resulting in better water and fertilizers' usage and so huge improvements of both quality and yield of the crops. In this manuscript, the development of an IoT-based smart traceability and farm management system is described, which calibrates the irrigations and fertigation operations as a function of crop typology, growth phase, soil and environment parameters and weather information; a suitable software architecture was developed to support the system decision-making process, also based on data collected on-field by a properly designed solar-powered wireless sensor network (WSN). The WSN nodes were realized by using the ESP8266 NodeMCU module exploiting its microcontroller functionalities and Wi-Fi connectivity. Thanks to a properly sized solar power supply system and an optimized scheduling scheme, a long node autonomy was guaranteed, as experimentally verified by its power consumption measures, thus reducing WSN maintenance. In addition, a literature analysis on the most used wireless technologies for agri-food products' traceability is reported, together with the design and testing of a Bluetooth low energy (BLE) low-cost sensor tag to be applied into the containers of agri-food products, just collected from the fields or already processed, to monitor the main parameters indicative of any failure or spoiling over time along the supply chain. A mobile application was developed for monitoring the tracking information and storing conditions of the agri-food products. Test results in real-operative scenarios demonstrate the proper operation of the BLE smart tag prototype and tracking system.
RESUMEN
The aim of this work is to investigate and characterize the photo-ignition process of dry multi-walled carbon nanotubes (MWCNTs) mixed with ferrocene (FeCp2) powder, using an LED (light-emitting diode) as the light source, a combination that has never been used, to the best of our knowledge. The ignition process was improved by adding a lipophilic porphyrin (H2Pp) in powder to the MWCNTs/FeCp2 mixtures-thus, a lower ignition threshold was obtained. The ignition tests were carried out by employing a continuous emission and a pulsed white LED in two test campaigns. In the first, two MWCNT typologies, high purity (HP) and industrial grade (IG), were used without porphyrin, obtaining, for both, similar ignition thresholds. Furthermore, comparing ignition thresholds obtained with the LED source with those previously obtained with a Xenon (Xe) lamp, a significant reduction was observed. In the second test campaign, ignition tests were carried out by means of a properly driven and controlled pulsed XHP70 LED source. The minimum ignition energy (MIE) of IG-MWCNTs/FeCp2 samples was determined by varying the duration of the light pulse. Experimental results show that ignition is obtained with a pulse duration of 110 ms and a MIE density of 266 mJ/cm². The significant reduction of the MIE value (10-40%), observed when H2Pp in powder form was added to the MWCNTs/FeCp2 mixtures, was ascribed to the improved photoexcitation and charge transfer properties of the lipophilic porphyrin molecules.