RTAIAED: A Real-Time Ambulance in an Emergency Detector with a Pyramidal Part-Based Model Composed of MFCCs and YOLOv8.

In emergency situations, every second counts for an ambulance navigating through traffic. Efficient use of traffic light systems can play a crucial role in minimizing response time. This paper introduces a novel automated Real-Time Ambulance in an Emergency Detector (RTAIAED). The proposed system uses special Lookout Stations (LSs) suitably positioned at a certain distance from each involved traffic light (TL), to obtain timely and safe transitions to green lights as the Ambulance in an Emergency (AIAE) approaches. The foundation of the proposed system is built on the simultaneous processing of video and audio data. The video analysis is inspired by the Part-Based Model theory integrating tailored video detectors that leverage a custom YOLOv8 model for enhanced precision. Concurrently the audio analysis component employs a neural network designed to analyze Mel Frequency Cepstral Coefficients (MFCCs) providing an accurate classification of auditory information. This dual-faceted approach facilitates a cohesive and synergistic analysis of sensory inputs. It incorporates a logic-based component to integrate and interpret the detections from each sensory channel, thereby ensuring the precise identification of an AIAE as it approaches a traffic light. Extensive experiments confirm the robustness of the approach and its reliable application in real-world scenarios thanks to its predictions in real time (reaching an fps of 11.8 on a Jetson Nano and a response time up to 0.25 s), showcasing the ability to detect AIAEs even in challenging conditions, such as noisy environments, nighttime, or adverse weather conditions, provided a suitable-quality camera is appropriately positioned. The RTAIAED is particularly effective on one-way roads, addressing the challenge of regulating the sequence of traffic light signals so as to ensure a green signal to the AIAE when arriving in front of the TL, despite the presence of the "double red" periods in which the one-way traffic is cleared of vehicles coming from one direction before allowing those coming from the other side. Also, it is suitable for managing temporary situations, like in the case of roadworks.

A Multi-Layer LoRaWAN Infrastructure for Smart Waste Management.

Long Range Wide Area Network (LoRaWAN) has rapidly become one of the key enabling technologies for the development of Internet of Things (IoT) architectures. A wide range of different solutions relying on this communication technology can be found in the literature: nevertheless, the most part of these architectures focus on single task systems. Conversely, the aim of this paper is to present the architecture of a LoRaWAN infrastructure gathering under the same network different typologies of services within one of the most significant sub-systems of the Smart City ecosystem (i.e., the Smart Waste Management). The proposed architecture exploits the whole range of different LoRaWAN classes, integrating nodes of growing complexity according to the different functions. The lowest level of this architecture is occupied by smart bins that simply collect data about their status. Moving on to upper levels, smart drop-off containers allow the interaction with users as well as the implementation of asynchronous downlink queries. At the top level, Video Surveillance Units (VSUs) are provided with machine learning capabilities for the detection of the presence of fire nearby bins or drop-off containers, thus fully implementing the Edge Computing paradigm. The proposed network infrastructure and its subsystems have been tested in a laboratory and in the field. This study has enhanced the readiness level of the proposed technology to Technology Readiness Level (TRL) 3.

A new deep learning approach integrated with clinical data for the dermoscopic differentiation of early melanomas from atypical nevi.

BACKGROUND: Timely recognition of malignant melanoma (MM) is challenging for dermatologists worldwide and represents the main determinant for mortality. Dermoscopic examination is influenced by dermatologists' experience and fails to achieve adequate accuracy and reproducibility in discriminating atypical nevi (AN) from early melanomas (EM). OBJECTIVE: We aimed to develop a Deep Convolutional Neural Network (DCNN) model able to support dermatologists in the classification and management of atypical melanocytic skin lesions (aMSL). METHODS: A training set (630 images), a validation set (135) and a testing set (214) were derived from the idScore dataset of 979 challenging aMSL cases in which the dermoscopic image is integrated with clinical data (age, sex, body site and diameter) and associated with histological data. A DCNN_aMSL architecture was designed and then trained on both dermoscopic images of aMSL and the clinical/anamnestic data, resulting in the integrated "iDCNN_aMSL" model. Responses of 111 dermatologists with different experience levels on both aMSL classification (intuitive diagnosis) and management decisions (no/long follow-up; short follow-up; excision/preventive excision) were compared with the DCNNs models. RESULTS: In the lesion classification study, the iDCNN_aMSL achieved the best accuracy, reaching an AUC = 90.3 %, SE = 86.5 % and SP = 73.6 %, compared to DCNN_aMSL (SE = 89.2 %, SP = 65.7 %) and intuitive diagnosis of dermatologists (SE = 77.0 %; SP = 61.4 %). CONCLUSIONS: The iDCNN_aMSL proved to be the best support tool for management decisions reducing the ratio of inappropriate excision. The proposed iDCNN_aMSL model can represent a valid support for dermatologists in discriminating AN from EM with high accuracy and for medical decision making by reducing their rates of inappropriate excisions.

Image generation by GAN and style transfer for agar plate image segmentation.

BACKGROUND AND OBJECTIVES: Deep learning models and specifically Convolutional Neural Networks (CNNs) are becoming the leading approach in many computer vision tasks, including medical image analysis. Nevertheless, the CNN training usually requires large sets of supervised data, which are often difficult and expensive to obtain in the medical field. To address the lack of annotated images, image generation is a promising method, which is becoming increasingly popular in the computer vision community. In this paper, we present a new approach to the semantic segmentation of bacterial colonies in agar plate images, based on deep learning and synthetic image generation, to increase the training set size. Indeed, semantic segmentation of bacterial colony is the basis for infection recognition and bacterial counting in Petri plate analysis. METHODS: A convolutional neural network (CNN) is used to separate the bacterial colonies from the background. To face the lack of annotated images, a novel engine is designed - which exploits a generative adversarial network to capture the typical distribution of the bacterial colonies on agar plates - to generate synthetic data. Then, bacterial colony patches are superimposed on existing background images, taking into account both the local appearance of the background and the intrinsic opacity of the bacterial colonies, and a style transfer algorithm is used for further improve visual realism. RESULTS: The proposed deep learning approach has been tested on the only public dataset available with pixel-level annotations for bacterial colony semantic segmentation in agar plates. The role of including synthetic data in the training of a segmentation CNN has been evaluated, showing how comparable performances can be obtained with respect to the use of real images. Qualitative results are also reported for a second public dataset in which the segmentation annotations are not provided. CONCLUSIONS: The use of a small set of real data, together with synthetic images, allows obtaining comparable results with respect to using a complete set of real images. Therefore, the proposed synthetic data generator is able to address the scarcity of biomedical data and provides a scalable and cheap alternative to human ground-truth supervision.

A Low Power IoT Sensor Node Architecture for Waste Management Within Smart Cities Context.

This paper focuses on the realization of an Internet of Things (IoT) architecture to optimize waste management in the context of Smart Cities. In particular, a novel typology of sensor node based on the use of low cost and low power components is described. This node is provided with a single-chip microcontroller, a sensor able to measure the filling level of trash bins using ultrasounds and a data transmission module based on the LoRa LPWAN (Low Power Wide Area Network) technology. Together with the node, a minimal network architecture was designed, based on a LoRa gateway, with the purpose of testing the IoT node performances. Especially, the paper analyzes in detail the node architecture, focusing on the energy saving technologies and policies, with the purpose of extending the batteries lifetime by reducing power consumption, through hardware and software optimization. Tests on sensor and radio module effectiveness are also presented.

A Wireless Sensor Network for the Real-Time Remote Measurement of Aeolian Sand Transport on Sandy Beaches and Dunes.

Direct measurements of aeolian sand transport on coastal dunes and beaches is of paramount importance to make correct decisions about coast management. As most of the existing studies are mainly based on a statistical approach, the solution presented in this paper proposes a sensing structure able to orient itself according to wind direction and directly calculate the amount of wind-transported sand by collecting it and by measuring its weight. Measurements are performed remotely without requiring human action because the structure is equipped with a ZigBee radio module, which periodically sends readings to a local gateway. Here data are processed by a microcontroller and then transferred to a remote data collection centre, through GSM technology. The ease of installation, the reduced power consumption and the low maintenance required, make the proposed solution able to work independently, limiting human intervention, for all the duration of the expected experimental campaign. In order to analyze the cause-effect relationship between the transported sand and the wind, the sensing structure is integrated with a multi-layer anemoscope-anemometer structure. The overall sensor network has been developed and tested in the laboratory, and its operation has been validated in field through a 48 h measurement campaign.

COMPUTER ASSISTED RETINAL VESSEL TORTUOSITY EVALUATION IN NOVEL MUTATION FABRY DISEASE: Towards New Prognostic Markers.

PURPOSE: Fabry disease is a rare lysosomal storage disorder with systemic involvement. The authors report on a large Fabry family with GLA p.M187R mutation and exhaustive ophthalmologic assessment. METHODS: Comprehensive systemic evaluation and genetic diagnosis were performed. Ophthalmologic evaluation included intraocular pressure/visual acuity measurement, refractometry, slit lamp examination, retinography, and optical coherence tomography. Three parameters quantified retinal vessel tortuosity: sum of angle metrics, product of angle distance, and triangular index. Calculations were semiautomatized using dedicated software. RESULTS: Ten individuals (2 males and 8 females) were described. Seventy-five percent had retinal vessel tortuosity. One hundred percent had cornea verticillata. Perimacular vessels were predominantly involved. The correlation between the right and left eye tortuosity measurements was very tight. A significant correlation between retinal vessel tortuosity and systemic severity measured by general Mainz Severity Score Index (MSSI), renal MSSI, and neurological MSSI but no cardiac MSSI was observed. Right sum of angle metrics value was an independent statistical predictor of the general-MSSI score in presence of age. CONCLUSION: p.M187R mutation causes a severe systemic and ophthalmologic phenotype, in both male and female patients. Semiautomatic assessment of retinal vessel tortuosity is an objective and reproducible tool. All three parameters of tortuosity are closely associated with Fabry severity scores. Studies of larger series are being awaited to establish the role of retinal vessel tortuosity as a noninvasive marker of disease progression.

Computer-Assisted Evaluation of Retinal Vessel Diameter in Retinitis Pigmentosa.

PURPOSE: The evaluation of retinal vessel attenuation is very subjective and not sufficiently reliable in patients with retinitis pigmentosa (RP). We tested semiautomatic software capable of obtaining real-time measurements of vessel diameter. METHODS: Retinal vessel diameter was calculated in 25 RP subjects and in 20 healthy controls. The Mann-Whitney test was used to compare the average values of RP patients with those of controls and subgroups of RP patients with different clinical features. RESULTS: The retinal vessel diameter was significantly smaller in RP patients than in controls (p < 0.001). In particular, vessel diameters were smaller in older subjects, in patients with worse ERG responses, and in patients with more severe visual field loss. CONCLUSIONS: Computer-assisted analysis of retinal fundus pictures may be helpful in the diagnosis of RP and in monitoring disease progression.

Automatic image classification for the urinoculture screening.

Urinary tract infections (UTIs) are considered to be the most common bacterial infection and, actually, it is estimated that about 150 million UTIs occur world wide yearly, giving rise to roughly $6 billion in healthcare expenditures and resulting in 100,000 hospitalizations. Nevertheless, it is difficult to carefully assess the incidence of UTIs, since an accurate diagnosis depends both on the presence of symptoms and on a positive urinoculture, whereas in most outpatient settings this diagnosis is made without an ad hoc analysis protocol. On the other hand, in the traditional urinoculture test, a sample of midstream urine is put onto a Petri dish, where a growth medium favors the proliferation of germ colonies. Then, the infection severity is evaluated by a visual inspection of a human expert, an error prone and lengthy process. In this paper, we propose a fully automated system for the urinoculture screening that can provide quick and easily traceable results for UTIs. Based on advanced image processing and machine learning tools, the infection type recognition, together with the estimation of the bacterial load, can be automatically carried out, yielding accurate diagnoses. The proposed AID (Automatic Infection Detector) system provides support during the whole analysis process: first, digital color images of Petri dishes are automatically captured, then specific preprocessing and spatial clustering algorithms are applied to isolate the colonies from the culture ground and, finally, an accurate classification of the infections and their severity evaluation are performed. The AID system speeds up the analysis, contributes to the standardization of the process, allows result repeatability, and reduces the costs. Moreover, the continuous transition between sterile and external environments (typical of the standard analysis procedure) is completely avoided.

Leveraging Multiscale Hessian-Based Enhancement With a Novel Exudate Inpainting Technique for Retinal Vessel Segmentation.

Accurate vessel detection in retinal images is an important and difficult task. Detection is made more challenging in pathological images with the presence of exudates and other abnormalities. In this paper, we present a new unsupervised vessel segmentation approach to address this problem. A novel inpainting filter, called neighborhood estimator before filling, is proposed to inpaint exudates in a way that nearby false positives are significantly reduced during vessel enhancement. Retinal vascular enhancement is achieved with a multiple-scale Hessian approach. Experimental results show that the proposed vessel segmentation method outperforms state-of-the-art algorithms reported in the recent literature, both visually and in terms of quantitative measurements, with overall mean accuracy of 95.62% on the STARE dataset and 95.81% on the HRF dataset.

Monitoring architectural heritage by wireless sensors networks: San Gimignano--a case study.

This paper describes a wireless sensor network (WSN) used to monitor the health state of architectural heritage in real-time. The WSN has been deployed and tested on the "Rognosa" tower in the medieval village of San Gimignano, Tuscany, Italy. This technology, being non-invasive, mimetic, and long lasting, is particularly well suited for long term monitoring and on-line diagnosis of the conservation state of heritage buildings. The proposed monitoring system comprises radio-equipped nodes linked to suitable sensors capable of monitoring crucial parameters like: temperature, humidity, masonry cracks, pouring rain, and visual light. The access to data is granted by a user interface for remote control. The WSN can autonomously send remote alarms when predefined thresholds are reached.

Computer assisted evaluation of retinal vessels tortuosity in Fabry disease.

PURPOSE: Fabry Disease (FD) is a rare X-linked metabolic disorder characterized by diffuse deposition of sphingolipids in many tissues. Retinal vessel tortuosity is a common ocular manifestation in FD and may represent a useful marker for the disease. Unfortunately its clinical evaluation is poorly reproducibile and alternative means of evaluation may be of interest. We tested a new semi-automatic software measuring retinal vessel tortuosity from eye fundus digital images in a group of FD patients. METHODS: Observational case-control study evaluating four mathematical parameters describing tortuosity (relative length, sum of angle metric [SOAM], product of angle distance [PAD], triangular index) obtained from fundus pictures of 35 FD patients and 35 age-matched controls. Only the right eye was considered in order to reduce bias. Mann-Whitney test was used to compare the FD group versus the control group, males versus females and patients with versus without clinically identified retinal vessels tortuosity in the FD group. Linear regression analysis was performed on a subgroup of patients to evaluate the possible association of retinal vessels tortuosity parameters with age and with markers of systemic disease's progression. RESULTS: Three parameters (SOAM, PAD and triangular index) were significantly higher in FD patients in comparison with the controls (p < 0.0001, p = 0.001, p = 0.002 respectively). In the FD group the same three parameters showed higher values in hemizygous males than in heterozygous females ((p < 0.0001, p = 0.002, p < 0.0001 respectively). CONCLUSION: A computer assisted analysis of retinal vasculature demonstrated an increased vessels tortuosity in FD patients. The technique might be useful to establish disease severity and monitor its progression.