Search

Various deep learning methods are employed to detect stress and diseases in market garden crops, as well as to assess their severity. This study aims to comprehensively analyze these techniques and identify potential research avenues. The diversity of deep learning techniques was explored through a literature review based on the PRISMA guidelines. Research equations were defined, resulting in a sample of 1,422 publications, of which 72 were deemed usable and considered in the final analysis. For classification tasks, hybrid CNN models were the most widely used (19.2%). Commonly utilized models included VGG16 (10%), InceptionV3 (6.1%), DCNN (5%), and YoloV5 (5%). In object detection tasks, Fast R-CNN was used six times, followed by YoloV5 (three occurrences) and YoloV3 (two occurrences). In segmentation tasks, Mask R-CNN accounted for 28.67% of the models, while DeepLabV3+ accounted for 24.98%. Assessing disease severity in market garden crops is complex due to the unique criteria for each plant disease and the presence of multiple diseases across different crop types. To address this complexity, establishing a standardized method is crucial. Further research is essential to enhance the application of deep learning techniques in the study of market garden crops. This includes gathering extensive datasets that encompass various scenarios of crop diseases and considering the impact of climate variations on stress manifestation.

Today, Permanent Magnet Synchronous Motors (PMSMs) are a dominant choice in industry applications. During operation, different possible faults in the system can occur, so early and automated fault detection and severity estimation are required to ensure smooth operation and optimal maintenance planning. In this direction, outlier detection methods are employed in this paper. The motor's current signals are used to extract useful indicators of the fault, along with d-q transform. Statistical indicators in both time and frequency domains are selected to describe fault-related patterns. Based on the extracted features, three outlier detection methods are investigated: the Isolation Forest, the One Class Support Vector Machine, and the Robust Covariance Ellipse. Each method is investigated through different model parameters to evaluate fault detection and severity estimation capabilities. Finally, an ensemble approach is proposed based on decisions and outlier score ensemble. The proposed methodology is verified through different operating conditions in a PMSM test bench. [ABSTRACT FROM AUTHOR]

Digital image processing has witnessed a significant transformation, owing to the adoption of deep learning (DL) algorithms, which have proven to be vastly superior to conventional methods for crop detection. These DL algorithms have recently found successful applications across various domains, translating input data, such as images of afflicted plants, into valuable insights, like the identification of specific crop diseases. This innovation has spurred the development of cutting-edge techniques for early detection and diagnosis of crop diseases, leveraging tools such as convolutional neural networks (CNN), K-nearest neighbour (KNN), support vector machines (SVM), and artificial neural networks (ANN). This paper offers an all-encompassing exploration of the contemporary literature on methods for diagnosing, categorizing, and gauging the severity of crop diseases. The review examines the performance analysis of the latest machine learning (ML) and DL techniques outlined in these studies. It also scrutinizes the methodologies and datasets and outlines the prevalent recommendations and identified gaps within different research investigations. As a conclusion, the review offers insights into potential solutions and outlines the direction for future research in this field. The review underscores that while most studies have concentrated on traditional ML algorithms and CNN, there has been a noticeable dearth of focus on emerging DL algorithms like capsule neural networks and vision transformers. Furthermore, it sheds light on the fact that several datasets employed for training and evaluating DL models have been tailored to suit specific crop types, emphasizing the pressing need for a comprehensive and expansive image dataset encompassing a wider array of crop varieties. Moreover, the survey draws attention to the prevailing trend where the majority of research endeavours have concentrated on individual plant diseases, ML, or DL algorithms. In light of this, it advocates for the development of a unified framework that harnesses an ensemble of ML and DL algorithms to address the complexities of multiple plant diseases effectively. [ABSTRACT FROM AUTHOR]

Introduction: In precision agriculture, accurately diagnosing apple frog-eye leaf spot disease is critical for effective disease management. Traditional methods, predominantly relying on labor-intensive and subjective visual evaluations, are often inefficient and unreliable. Methods: To tackle these challenges in complex orchard environments, we develop a specialized deep learning architecture. This architecture consists of a two-stage multi-network model. The first stage features an enhanced Pyramid Scene Parsing Network (L-DPNet) with deformable convolutions for improved apple leaf segmentation. The second stage utilizes an improved U- Net (D-UNet), optimized with bilinear up sampling and batch normalization, for precise disease spot segmentation. Results: Our model sets new benchmarks in performance, achieving a mean Intersection over Union (mIoU) of 91.27% for segmentation of both apple leaves and disease spots, and a mean Pixel Accuracy (mPA) of 94.32%. It also excels in classifying disease severity across five levels, achieving an overall precision of 94.81%. Discussion: This approach represents a significant advancement in automated disease quantification, enhancing disease management in precision agriculture through data-driven decision-making. [ABSTRACT FROM AUTHOR]

Cerebellar ataxia is the poorly coordinated movement that results from injury or disease affecting the cerebellum. The diagnosis and assessment of ataxia are significantly challenging due to dependency on clinicians’ experience and the attendant subjectivity of such a process. In recent years, neuroimaging and sensor-based approaches, supported by effective machine learning techniques have made advances in the pursuit of addressing these clinical challenges. In this work, we present an outline of approaches to applying machine learning to this clinical challenge. We first provide a fundamental clinical overview with practical problems and then from a machine learning perspective, outline possible approaches with which to address these clinical challenges. Also discussed are the limitations in existing methods, the provision of cross disciplinary approaches and the current state-of-the-art as a potential basis for future research.

Agriculture plays the vigorous role in economy as well as it is contemplated to be the mainstay of economic system in emerging countries. Furthermore, it influences the society in huge ways including ancillary livelihoods, anyhow occurring of plant diseases impacts many farmers. Henceforth, erroneous leaf disease identification inclines to menacing effects on plants thereby curtailing product quality, productivity or quantity. To overcome these issues, we have designed Multi-agent DRL and EfficientNet assisted 3D plant leaf disease identification and severity estimation (MULTINET) framework. The main aim of this study is to effectively identify plant leaf diseases and quatify the severity of the disease. The proposed work comprehends of following four consecutive processes. At first, we have performed image pre-treatment for data cleansing using Adaptable LoW Pass Weiner (AWW) filter and then EMbellished Manta-Ray Optimization Algorithm (EMMARO) based data augmentation for enhancing image quality and balance the classes. After that, we have adopted Block Divider Model (BDM) for transfiguring 2D to 3D image which sustenance to navigate the information from multiple perceptive and bargains superior viewpoints from miscellaneous angles. Following that, we have executed dual effective segmentation on 3D image by utilizing Enhanced Deep Q-Network (EnDeep) that embrace of Haar-U-Net (HUNT) Algorithm for appropriate feature extraction and Convolution Feature Attention (CFA) Mechanism for dimensionality reduction. Here, the Multiple Deep Reinforcement Learning (DRL) agents are employed for segmentation and ensuring its accuracy through segmentation reliability checker which accommodates rewards entrenched on its actions. Based on those segmented regions, we have accomplished species detection and disease classification by the proposed Lightweight EfficientNet and Di-attention aided Bilinear-VGG (EBBI) Algorithm. At last, the severity enumeration is performed by contemplating lesions counts and its density. The proposed MULTINET framework is conducted in MATLAB R2020a simulation tool and the performance of proposed work is evaluated in terms of accuracy, precision, sensitivity, F1-score and ROC curve where the proposed work outperforms existing works. The accuracy of the proposed work increases from 19%-29%, precision increases from 19%-28%, sensitivity increases from 31%-38%, F1-score increases from 31%-38%, and ROC curve increases about 0.15–0.22 when compared with the existing works.

Today, Permanent Magnet Synchronous Motors (PMSMs) are a dominant choice in industry applications. During operation, different possible faults in the system can occur, so early and automated fault detection and severity estimation are required to ensure smooth operation and optimal maintenance planning. In this direction, outlier detection methods are employed in this paper. The motor’s current signals are used to extract useful indicators of the fault, along with d-q transform. Statistical indicators in both time and frequency domains are selected to describe fault-related patterns. Based on the extracted features, three outlier detection methods are investigated: the Isolation Forest, the One Class Support Vector Machine, and the Robust Covariance Ellipse. Each method is investigated through different model parameters to evaluate fault detection and severity estimation capabilities. Finally, an ensemble approach is proposed based on decisions and outlier score ensemble. The proposed methodology is verified through different operating conditions in a PMSM test bench.

Obstructive sleep apnea (OSA) severity assessment is based on manually scored respiratory events and their arbitrary definitions. Thus, we present an alternative method to objectively evaluate OSA severity independently of the manual scorings and scoring rules. A retrospective envelope analysis was conducted on 847 suspected OSA patients. Four parameters were calculated from the difference between the nasal pressure signal's upper and lower envelopes: average (AV), median (MD), standard deviation (SD), and coefficient of variation (CoV). We computed the parameters from the entirety of the recorded signals to perform binary classifications of patients using three different apnea–hypopnea index (AHI) thresholds (5-15-30). Additionally, the calculations were undertaken in 30-second epochs to estimate the ability of the parameters to detect manually scored respiratory events. Classification performances were assessed with areas under the curves (AUCs). As a result, the SD (AUCs ≥ 0.86) and CoV (AUCs ≥ 0.82) were the best classifiers for all AHI thresholds. Furthermore, non-OSA and severe OSA patients were separated well with SD (AUC = 0.97) and CoV (AUC = 0.95). Respiratory events within the epochs were identified moderately with MD (AUC = 0.76) and CoV (AUC = 0.82). In conclusion, envelope analysis is a promising alternative method by which to assess OSA severity without relying on manual scoring or the scoring rules of respiratory events. [ABSTRACT FROM AUTHOR]

The pathogens such as fungi and bacteria can lead to rice diseases that can drastically impair crop production. Because the illness is difficult to control on a broad scale, crop field monitoring is one of the most effective methods of control. It allows for early detection of the disease and the implementation of preventative measures. Disease severity estimation based on digital picture analysis, where the pictures are obtained from the rice field using mobile devices, is one of the most effective control strategies. This paper offers a method for quantifying the severity of three rice crop diseases (brown spot, blast, and bacterial blight) that can determine the stage of plant disease. A total of 1200 images of rice illnesses and healthy images make up the input dataset. With the help of agricultural experts, the diseased zone was labeled according to the disease type using the Make Sense tool. More than 75% of the images in the dataset correspond to one disease label, healthy plants represent more than 15%, and multiple diseases represent 5% of the images labeled. This paper proposes a novel artificial intelligence rice grade model that uses an optimized faster-region-based convolutional neural network (FRCNN) approach to calculate the area of leaf instances and the infected regions. EfficientNet-B0 architecture was used as a backbone as the network shows the best accuracy (96.43%). The performance was compared with the CNN architectures: VGG16, ResNet101, and MobileNet. The model evaluation parameters used to measure the accuracy are positive predictive value, sensitivity, and intersection over union. This severity estimation method can be further deployed as a tool that allows farmers to obtain perfect predictions of the disease severity level based on lesions in the field conditions and produce crops more organically. [ABSTRACT FROM AUTHOR]

Ulcerative colitis (UC) is an inflammatory bowel disease characterised by inflammation of the large intestine. UC severity is often represented by the Mayo Endoscopic Subscore (MES) which quantifies disease activity from endoscopy videos. In clinical trials, an endoscopy video is assigned an MES based upon the most severe inflammation observed in the video. For this reason, severe inflammation spread throughout the colon will receive the same MES as an otherwise healthy colon with a small localized inflammation. Therefore, the extent of disease activity throughout the colon may not be completely captured by the MES. In this work, we aim to automatically estimate MES for each frame in an endoscopy video to provide a higher resolution assessment of UC. Because annotating severity at the frame-level is highly expensive and labour-intensive, we propose a novel weakly supervised, ordinal classification method to estimate frame severity from video labels alone. Using clinical trial data, we demonstrate that our models achieve substantial agreement with ground truth labels, comparable to the agreement between expert clinicians. These findings indicate that our framework could serve as a foundation for novel clinical endpoints, based on a more localised scoring system, to better evaluate UC drug efficacy in clinical trials. [ABSTRACT FROM AUTHOR]

This study presents a novel interturn short-circuit fault (ISCF) and demagnetization fault (DF) diagnosis strategy based on a self-attention-based severity estimation network (SASEN). We analyze the effects of the ISCF and DF in a permanent-magnet synchronous machine and select appropriate inputs for estimating the fault severities, i.e., a positive-sequence voltage and current and negative-sequence voltage and current. The chosen inputs are fed into the SASEN to estimate fault indicators for quantifying the fault severities of the ISCF and DF. The SASEN comprises an encoder and decoder based on a self-attention module. The self-attention mechanism enhances the high-dimensional feature extraction and regression ability of the network by concentrating on specific sequence representations, thereby supporting the estimation of the fault severities. The proposed strategy can diagnose a hybrid fault in which the ISCF and DF occur simultaneously and does not require the exact model and parameters essential for the existing method for estimating the fault severity. The effectiveness and feasibility of the proposed fault diagnosis strategy are demonstrated through experimental results based on various fault cases and load torque conditions. [ABSTRACT FROM AUTHOR]

Summary: Structures in real‐life scenarios like industrial robots, spaceships, aircrafts, submarines, bridges, and pressure vessels undergo different loading conditions. These structures are prone to damage due to the risks related to fatigue and aging. Small cracks may appear in these complex structures and prove to be fatal. These cracks may open and close, hence termed as breathing cracks, exhibiting nonlinear behavior under load. Various nonlinear techniques exist for the detection and severity estimation of breathing crack in one‐dimensional structures such as beams. However, in plate‐like (2D) structures these types of cracks are difficult to identify. Moreover, most of the research has been conducted in plate‐like structures with a through crack. However, it becomes a challenge when the breathing crack is not only part‐through but localized in the central region of the plate. This paper presents the Hilbert transform to identify a central part‐through breathing crack in 2D structure. The appearance of nonlinearities in the response spectrum helps in crack detection which depends primarily on the type of excitation. The impulse and harmonic excitation tend to enhance the nonlinearity whereas the random excitation makes the nonlinearity difficult to detect in the response spectrum. This paper presents the numerical and experimental investigations of a plate with part‐through crack under different excitation signals. Furthermore, the proposed techniques have also been applied on random response of plate to achieve identification and severity of the crack. [ABSTRACT FROM AUTHOR]

The pathogens such as fungi and bacteria can lead to rice diseases that can drastically impair crop production. Because the illness is difficult to control on a broad scale, crop field monitoring is one of the most effective methods of control. It allows for early detection of the disease and the implementation of preventative measures. Disease severity estimation based on digital picture analysis, where the pictures are obtained from the rice field using mobile devices, is one of the most effective control strategies. This paper offers a method for quantifying the severity of three rice crop diseases (brown spot, blast, and bacterial blight) that can determine the stage of plant disease. A total of 1200 images of rice illnesses and healthy images make up the input dataset. With the help of agricultural experts, the diseased zone was labeled according to the disease type using the Make Sense tool. More than 75% of the images in the dataset correspond to one disease label, healthy plants represent more than 15%, and multiple diseases represent 5% of the images labeled. This paper proposes a novel artificial intelligence rice grade model that uses an optimized faster-region-based convolutional neural network (FRCNN) approach to calculate the area of leaf instances and the infected regions. EfficientNet-B0 architecture was used as a backbone as the network shows the best accuracy (96.43%). The performance was compared with the CNN architectures: VGG16, ResNet101, and MobileNet. The model evaluation parameters used to measure the accuracy are positive predictive value, sensitivity, and intersection over union. This severity estimation method can be further deployed as a tool that allows farmers to obtain perfect predictions of the disease severity level based on lesions in the field conditions and produce crops more organically.

Tea leaf blight (TLB) is a common tea disease seriously affecting the quality and yield of tea. An accurate estimation of TLB severity can be used to guide tea farmers to reasonably spray pesticides. This study proposes an estimation method for TLB severity in natural scene images and consists of four main steps: segmentation of the diseased leaves, area fitting of the diseased leaves, segmentation of the disease spots, and estimation of disease severity. Target leaves with TLB in the tea images are segmented by combining the U-Net network and fully connected conditional random field to reduce the influence of complex background. An ellipse restoration method is proposed to generate an elliptic mask to fit the full size of the occluded or damaged TLB leaves. The disease spot regions are segmented from the TLB leaves by a support vector machine classifier to calculate the Initial Disease Severity (IDS) index. The IDS index, color features, and texture features of the TLB leaves are inputted into the metric learning model to finally estimated disease severity. Experimental results show that the proposed method has higher estimation accuracy and stronger robustness against occluded and damaged TLB leaves compared with conventional convolution neural network methods and classical machine learning techniques. [ABSTRACT FROM AUTHOR]

Purpose: Obstructive sleep apnea (OSA) is associated with increased risk for stroke, which is known to further impair respiratory functions. However, it is unknown whether the type and severity of respiratory events are linked to stroke or transient ischemic attack (TIA). Thus, we investigate whether the characteristics of individual respiratory events differ between patients experiencing TIA or acute ischemic stroke and matched patients with clinically suspected sleep-disordered breathing. Methods: Polygraphic data of 77 in-patients with acute ischemic stroke (n = 49) or TIA (n = 28) were compared to age, gender, and BMI-matched patients with suspected sleep-disordered breathing and no cerebrovascular disease. Along with conventional diagnostic parameters (e.g., apnea-hypopnea index), durations and severities of individual apneas, hypopneas and desaturations were compared between the groups separately for ischemic stroke and TIA patients. Results: Stroke and TIA patients had significantly shorter apneas and hypopneas (p < 0.001) compared to matched reference patients. Furthermore, stroke patients had more central apnea events (p = 0.007) and a trend for higher apnea/hypopnea number ratios (p = 0.091). The prevalence of OSA (apnea-hypopnea index ≥ 5) was 90% in acute stroke patients and 79% in transient ischemic attack patients. Conclusion: Stroke patients had different characteristics of respiratory events, i.e., their polygraphic phenotype of OSA differs compared to matched reference patients. The observed differences in polygraphic features might indicate that stroke and TIA patients suffer from OSA phenotype recently associated with increased cardiovascular mortality. Therefore, optimal diagnostics and treatment require routine OSA screening in patients with acute cerebrovascular disease, even without previous suspicion of OSA. [ABSTRACT FROM AUTHOR]

In the active magnetic bearings (AMBs) supported rotating machinery, touchdown bearings are considered as safety devices to support the rotor in the deficiency of electromagnetic field. Generally, the industrial AMB machines do not have force sensors for touchdown bearings and the system is only equipped with the position sensors to monitor the rotor displacement that disables the opportunity to measure the forces during dropdown events that might be destructive for the safe operation of the rotor system. This study explores the relative severity of dropdowns that are evaluated from a computational rotor model using the rotor displacement data recorded from the position sensors installed in the machine as an input. The model for double-row angular contact ball bearing type touchdown bearings is integrated with the rotor model. The simulation model is verified by comparing the simulated rotor orbits against measured orbits at four different dropdowns. The Fast Fourier transform (FFT) is used to observe the studied dropdown events in frequency domain revealing from the rotor response the following details: harmonics of the operation speed, rub-impact frequencies, pendulum motion of the rotor and the first two bending frequencies of the rotor settled on the touchdown bearings. The critical speed map also verifies the bending frequencies and identified support properties. The model-based approach can be used to evaluate and compare a single dropdown event with respect to previous events providing an insight for decision making whether touchdown bearing should be replaced. [ABSTRACT FROM AUTHOR]

This study focuses on observing and analyzing the occurrence of a fall for humans during normal gait, which perhaps results in severe injury. Previously, the insufficiency of a recovery step, which diminishes the forward rotation of the body after tripping, was suggested as a factor for the failure of fall avoidance motion. However, although it was identified that a slow and/or short recovery step resulted in the failure of fall prevention, the physical process of tripping and falling during the gait was not analyzed sufficiently. In this study, the subject’s reaction motion and fall process against tripping became clearer because the fall motion, which included the phase closer to the ground contact, could be recorded for a longer time than that in most previous studies. Although the subject attempted to mitigate the forward angular momentum and the descent of body induced by tripping by holding on his recovery foot, it was not effective, especially when the recovery step length was short. Among such trials, the larger forward inclination of the body, the excessive forward movement of the center of mass from the support point, and the smaller ground reaction force of the recovery foot in the normal direction was observed. Because the short recovery step resulted in the limitation of the moment arm, which affected the reaction torque of the recovery foot, it became difficult to decelerate the body rotation and prevent the fall. Furthermore, it was also suggested that the forward lean of the body and the decrease of the ground reaction force increased the impact speed and effective mass, which affected the impact force. The observation of such an advanced fall phase also contributes to a more realistic simulation of the human reaction motion for a more precise estimation of the fall injuries.

• Relationship between relative natural frequency change curves and mode shapes. • A novel strategy for damage localization and severity estimation based on relative natural frequency changes. • Numerical and experimental verification of the proposed method. • Investigation on elimination of temperature effect in damage localization. Concentrated damage such as cracks is one of the most common types of damage in beams. It is essential to detect such damage early to avoid structural failure. Vibration-based damage detection methods that employ changes in structural dynamic parameters such as natural frequencies have been extensively studied, and it is commonly acknowledged that natural frequencies depicting structural global dynamic properties are incompetent to portray local damage. Differing from extant work, this study presents a concept of relative natural frequency change (RNFC) curves for local damage characterization and especially ascertains the relationship between RNFC curves and mode shapes, leading to an explicit equation of RNFC. With RNFC curves and measured values of RNFCs, a two-step method for localizing and quantifying damage is created: a novel probabilistic damage indicator is developed using Bayesian data fusion for localizing single and multiple damage; moreover, a damage severity factor defined as the stiffness reduction ratio of the damaged element is formulated to quantify damage. The proposed method features localization, quantification, and evolution monitoring of damage, relying solely on natural frequencies. The efficacy of the method is verified numerically and then validated experimentally on cracked beams. The numerical and experimental results demonstrate the capability of the method to localize single and multiple damage and to estimate damage severity. This mechanism of characterizing damage relying solely on natural frequencies provides the foundation for developing practical local damage detection and monitoring technologies for beam-type structures. [ABSTRACT FROM AUTHOR]

This paper presents a novel method to estimate the number of shorted turns in a permanent magnet synchronous machine (PMSM) following the detection of interturn short-circuit (ITSC) fault and its location. In this proposed method, PMSM is excited through a low sinusoidal voltage at standstill condition to obtain the winding resistance and synchronous inductance by current response. It is shown that the ITSC fault introduces variation in the current response, which can be used to calculate the number of shorted turns under zero fault resistance assumption. Using this practical procedure, the fault severity can be estimated directly in a straight-forward manner. In other words, the severity estimation for a given machine can be done without complex machine modeling or experiments on ITSC prototype with multiple taps. The findings in this paper are essential for a comprehensive solution including fault mitigation algorithms and postfault operations. In order to verify the findings, a three-phase equivalent circuit model supported by finite element analysis results is used to take saturation and space harmonics into account. In addition, experimental results are presented to demonstrate the validity and practicability of the severity estimation. [ABSTRACT FROM AUTHOR]

• To present a pre-processing approach using Amended Bilateral Filter (ABF) for enhancing the image and suppressing the noise. • Extract features using DenseNet-201, ResNet-152, and VGG-19 ensemble models to minimize model complexity. • To introduce Modified Archer Fish Optimization Algorithm (Mod-AFO) for reducing feature dimensionality issues. COVID-19 is a huge pandemic disease and is gradually growing into our daily lives. It has affected us all in different ways, which the World Health Organization classified as a pandemic in 2020. A number of deep learning methods have been developed to identify COVID-19 in chest X-rays, but very few techniques are used to estimate the severity of COVID-19. Additionally, it is very complex to effectively train the data, resulting in slower convergence and time complexities. Therefore, to overcome these drawbacks, this study proposes a unique model to classify the severity of Covid-19 using a deep learning method. The pre-processing step includes image enhancement and noise reduction using the Amended Bilateral Filter (ABF). The relevant features are then extracted using an ensemble-based deep learning model, which includes the DenseNet-201, ResNet-152 and VGG-19 models, which are integrated via an ensemble average approach. The most optimal features are selected using the Modified Archer Fish Optimization Algorithm (Mod-AFO). The proposed optimization algorithm exhibits high convergence and reduced model complexity. COVID-19 severity classification can be effectively categorized using a Multihead attention-assisted hierarchical deep-maxout network model (Multi-HDM). The proposed classification model is comparatively faster in severity estimation and high in performance. Using Python, the proposed model performances are analyzed and compared with the existing models to demonstrate the superiority of the proposed model. The proposed model achieved 98.2% accuracy, 98.5% sensitivity, 96.4% specificity and 96.4% precision in COVID-19 severity estimation using the COVID-19 Chest X-ray images and Lung masks dataset. [ABSTRACT FROM AUTHOR]

We present in this paper a statistical method to estimate the severity of a transverse crack form the free-end deflections of a cantilever beam. To this aim, we carry out simulations involving the ANSYS software and register the free-end deflections resulted for different crack positions near the fastened end. By involving a statistical method, we find the damage severity which reflects the crack effect on the frequency drop if the crack is located exactly at the fixture. The accuracy of the achieved damage severity values is verified by comparing the calculated frequency drops for several crack locations with those obtained from simulations. We found that the damage severity contrived by involving the statistical method is accurate and can be successfully used to predict the dynamic behavior of a cracked beam. [ABSTRACT FROM AUTHOR]

Purpose: Frequency of apnea and hypopnea events is used to estimate the severity of obstructive sleep apnea (OSA). However, comprehensive information on whether apneas and hypopneas cause an equal biological effect is not available. The purpose of the present work was to evaluate the effect of the breathing cessation event type (i.e., obstructive apnea or hypopnea) and duration on the severity of related SpO desaturation events. Methods: Type 1 polysomnographies of 395 patients (220 males and 175 females) examined for suspected OSA were analyzed. Desaturation severity related to hypopnea and obstructive apnea events were compared and comparison was controlled for gender, sleep stage, sleeping position, age, and body mass index. Hypopneas and obstructive apneas were further divided into eight different durational categories and related desaturation event characteristics were compared between the categories. Results: SpO desaturation events caused by obstructive apneas were statistically significantly ( p ≤ 0.004) longer, greater in area, and deeper compared to the SpO desaturations caused by hypopneas. The increase in the duration of hypopnea and obstructive apnea events led to increase in the duration and area of related SpO desaturations. The increase in the obstructive apnea event duration also led to increase in the depth of related desaturation event. Conclusions: Obstructive apneas led to more severe SpO desaturation compared to hypopneas. Increased event duration led to increase in the severity of the related SpO desaturation. In addition to considering event duration, obstructive apneas should have more weight than hypopneas when estimating severity of OSA and associated long-term cardiovascular risk. [ABSTRACT FROM AUTHOR]

Automated dysarthria severity identification can aid clinicians in monitoring the patient's progress, and can improve the performance of dysarthric speech recognition systems. In this paper, we explore the potency of squeeze-and-excitation (SE) networks for dysarthria severity level classification using mel spectrograms. Deep convolutional neural network (CNN) models built using SE components and residual blocks are analysed in this regard. A comparison of the system performance is done against a shallow CNN and a convolutional recurrent neural network built using a bidirectional long short-term memory network. The models are evaluated on the Universal Access dysarthric speech corpus under speaker-dependent (SD) and speaker-independent (SID) scenarios. The proposed model obtained appreciable results in the SD scenario, and its margin of about 10% over the baselines in the SID scenario promises its applicability in automated dysarthria severity level classification. • Squeeze-and-excitation blocks are introduced for dysarthria severity classification. • Mel spectrograms extracted from the dysarthric speech utterances are used as input. • Squeeze-and-excite operations aid in identifying the pauses, heavy sighs and murmurs. • Based on the degree of occurence of these characteristics, severity is identified. • Speaker and gender dependencies evaluated in seen and unseen speaker scenarios. [ABSTRACT FROM AUTHOR]

The CHRONIOUS system offers an integrated platform aiming at the effective management and real-time assessment of the health status of the patient suffering from chronic obstructive pulmonary disease (COPD). An intelligent system is developed for the analysis and the real-time evaluation of patient's condition. A hybrid classifier has been implemented on a personal digital assistant, combining a support vector machine, a random forest, and a rule-based system to provide a more advanced categorization scheme for the early and in real-time characterization of a COPD episode. This is followed by a severity estimation algorithm which classifies the identified pathological situation in different levels and triggers an alerting mechanism to provide an informative and instructive message/advice to the patient and the clinical supervisor. The system has been validated using data collected from 30 patients that have been annotated by experts indicating 1) the severity level of the current patient's health status, and 2) the COPD disease level of the recruited patients according to the GOLD guidelines. The achieved characterization accuracy has been found 94%. [ABSTRACT FROM PUBLISHER]

SUMMARY The objective of this paper is to evaluate, using field measurements, the performance of the nondestructive evaluation methodology presented in the accompanying paper 'Nondestructive damage detection in Euler-Bernoulli beams using nodal curvatures - Part I: Theory and numerical verification'. Experimental modal data collected from the Interstate 40 bridge are utilized to accomplish the stated objective. Prior to the replacement of the bridge in 1993, researchers from New Mexico State University and Los Alamos National Laboratory introduced incremental levels of damage on the structure and performed experimental modal analyses at each damage stage. The results of the experiments were utilized to evaluate the performance of five previously published nondestructive damage identification methods. Utilizing the measured modal parameters from the Interstate 40 bridge study, structural damage is localized and quantified with the nondestructive evaluation methodology presented in the accompanying paper. The results of this study indicate that the proposed methodology performed equally as well as the damage index method for damage localization and additionally provided realistic estimates of damage severity. Copyright © 2013 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Abstract: In this paper the use of two existing algorithms developed for global nondestructive evaluation to locate and evaluate localised damage in timber beams is investigated using a finite element model. These damage localisation algorithms were found, through this investigation, not to be effective in locating multiple damage scenarios and unable to evaluate the severity of damage. Hence, modifications on damage index algorithms as well as a hybrid algorithm are proposed to overcome the problems. In this study, experimental modal analysis (EMA) was used as a tool to extract mode shapes for calculating the damage index in the proposed method which utilises changes in modal strain energy between the undamaged and the damaged timber beam model. The modified damage index (MDI) method normalises the mode shape curvature and the hybrid algorithm combines the modified damage index and changes in flexibility algorithms which reflect the changes of natural frequency and mode shape. Analytical evaluations were performed to compare and verify the ability of original and modified damage localisation algorithms in locating single and multiple damage in timber beams. The modified damage index (MDI) algorithm and the hybrid damage algorithm are also used in the experimental studies to validate the effectiveness of the methods to locate and evaluate damage within timber beams by laboratory experiments. [Copyright &y& Elsevier]

The objective of this paper is to develop appropriate algorithms to locate and size damage in plate structures. Two methods, one using the changes in the compliance distribution and the other using the changes in the modal strain energy, are presented in this paper. A damage index, used to identify possible locations and corresponding severities of local damage, is defined and expressed in terms of modal displacements that are obtained numerically from mode shapes of the undamaged and the damaged structures. The possible damage locations in the structure are determined by the application of damage indicators according to previously developed decision rules. Each of the two methods is demonstrated using a numerical example of a simply supported plate with simulated damage. [ABSTRACT FROM AUTHOR]

• The shape of leaves alone has predictive power for disease recognition. • A general disease model can be trained to recognize previously unseen tomato leaf diseases. • Automatic disease severity estimation can achieve results comparable to those of human evaluation. The management of plant disease is a significant economic and environmental factor in the production of greenhouse tomato plants. Human expertise for assessing the presence and extent of disease is important in creating and implementing management plans, but it is difficult and expensive to acquire. In this paper, we present a new computer vision system to automatically recognize several diseases, detect previously unseen disease and to estimate per-leaf severity. Training and testing of models used several modified versions of the nine types of tomato disease of the PlantVillage tomato dataset and showed how different leaf properties impact disease detection. [ABSTRACT FROM AUTHOR]

Heart failure is a serious condition with high prevalence (about 2% in the adult population in developed countries, and more than 8% in patients older than 75 years). About 3-5% of hospital admissions are linked with heart failure incidents. Heart failure is the first cause of admission by healthcare professionals in their clinical practice. The costs are very high, reaching up to 2% of the total health costs in the developed countries. Building an effective disease management strategy requires analysis of large amount of data, early detection of the disease, assessment of the severity and early prediction of adverse events. This will inhibit the progression of the disease, will improve the quality of life of the patients and will reduce the associated medical costs. Toward this direction machine learning techniques have been employed. The aim of this paper is to present the state-of-the-art of the machine learning methodologies applied for the assessment of heart failure. More specifically, models predicting the presence, estimating the subtype, assessing the severity of heart failure and predicting the presence of adverse events, such as destabilizations, re-hospitalizations, and mortality are presented. According to the authors' knowledge, it is the first time that such a comprehensive review, focusing on all aspects of the management of heart failure, is presented.