RESUMEN

In the realm of cloud computing, ensuring the dependability and robustness of software systems is paramount. The intricate and evolving nature of cloud infrastructures, however, presents substantial obstacles in the pre-emptive identification and rectification of software anomalies. This study introduces an innovative methodology that amalgamates hybrid optimization algorithms with Neural Networks (NN) to refine the prediction of software malfunctions. The core objective is to augment the purity metric of our method across diverse operational conditions. This is accomplished through the utilization of two distinct optimization algorithms: the Yellow Saddle Goat Fish Algorithm (YSGA), which is instrumental in the discernment of pivotal features linked to software failures, and the Grasshopper Optimization Algorithm (GOA), which further polishes the feature compilation. These features are then processed by Neural Networks (NN), capitalizing on their proficiency in deciphering intricate data patterns and interconnections. The NNs are integral to the classification of instances predicated on the ascertained features. Our evaluation, conducted using the Failure-Dataset-OpenStack database and MATLAB Software, demonstrates that the hybrid optimization strategy employed for feature selection significantly curtails complexity and expedites processing.

RESUMEN

Background and Purpose: Automatic segmentation methods have greatly changed the RadioTherapy (RT) workflow, but still need to be extended to target volumes. In this paper, Deep Learning (DL) models were compared for Gross Tumor Volume (GTV) segmentation in locally advanced cervical cancer, and a novel investigation into failure detection was introduced by utilizing radiomic features. Methods and materials: We trained eight DL models (UNet, VNet, SegResNet, SegResNetVAE) for 2D and 3D segmentation. Ensembling individually trained models during cross-validation generated the final segmentation. To detect failures, binary classifiers were trained using radiomic features extracted from segmented GTVs as inputs, aiming to classify contours based on whether their Dice Similarity Coefficient ( DSC ) < T and DSC ⩾ T . Two distinct cohorts of T2-Weighted (T2W) pre-RT MR images captured in 2D sequences were used: one retrospective cohort consisting of 115 LACC patients from 30 scanners, and the other prospective cohort, comprising 51 patients from 7 scanners, used for testing. Results: Segmentation by 2D-SegResNet achieved the best DSC, Surface DSC ( SDSC 3 mm ), and 95th Hausdorff Distance (95HD): DSC = 0.72 ± 0.16, SDSC 3 mm =0.66 ± 0.17, and 95HD = 14.6 ± 9.0 mm without missing segmentation ( M =0) on the test cohort. Failure detection could generate precision ( P = 0.88 ), recall ( R = 0.75 ), F1-score ( F = 0.81 ), and accuracy ( A = 0.86 ) using Logistic Regression (LR) classifier on the test cohort with a threshold T = 0.67 on DSC values. Conclusions: Our study revealed that segmentation accuracy varies slightly among different DL methods, with 2D networks outperforming 3D networks in 2D MRI sequences. Doctors found the time-saving aspect advantageous. The proposed failure detection could guide doctors in sensitive cases.

RESUMEN

In this paper, we propose a Transformer-based encoder architecture integrated with an unsupervised denoising method to learn meaningful and sparse representations of vibration signals without the need for data transformation or pre-trained data. Existing Transformer models often require transformed data or extensive computational resources, limiting their practical adoption. We propose a simple yet competitive modification of the Transformer model, integrating a trainable noise reduction method specifically tailored for failure mode classification using vibration data directly in the time domain without converting them into other domains or images. Furthermore, we present the key architectural components and algorithms underlying our model, emphasizing interpretability and trustworthiness. Our model is trained and validated using two benchmark datasets: the IMS dataset (four failure modes) and the CWRU dataset (four and ten failure modes). Notably, our model performs competitively, especially when using an unbalanced test set and a lightweight architecture.

RESUMEN

Studies analyzing indoor thermal environments comprising temperature and humidity may be insufficient when obtaining data from sensors, which may be susceptible to inaccurate or failed information from internal and external factors. Therefore, this study proposes an intelligent climate monitoring using a supervised learning method for virtual hygrothermal measurement in enclosed buildings used to predict temperature and relative humidity when a sensor failure is detected. The methodology comprises the data collection from a wireless sensor network, the building of the learning model for predicting the dynamics of environmental variables, and the implementation of a sensor failure detection model. We use an artificial hydrocarbon network as the learning model for their simplicity and effectiveness under uncertain and noisy data. The experiments use data acquired in two settings: (1) a laboratory office and (2) a museum storage room. The first scenario has multiple workstations, and the staff turns on or off the air conditioning depending on the feeling of comfort, generating an uncontrolled environment for the variables of interest. The second scenario has controlled temperature and humidity to ensure the conservation conditions of the museum pieces. Both scenarios used 12 sensors that acquired data for one month, providing an average of 58,300 values for each variable. Results of the proposed methodology provide 95% of accuracy in terms of sensor failure detection and identification, and less than 0.22% of tolerance variability in temperature and humidity after sensor accommodation in both scenarios.

RESUMEN

Medical image segmentation is crucial for clinical applications, but challenges persist due to noise and variability. In particular, accurate glottis segmentation from high-speed videos is vital for voice research and diagnostics. Manual searching for failed segmentations is labor-intensive, prompting interest in automated methods. This paper proposes the first deep learning approach for detecting faulty glottis segmentations. For this purpose, faulty segmentations are generated by applying both a poorly performing neural network and perturbation procedures to three public datasets. Heavy data augmentations are added to the input until the neural network's performance decreases to the desired mean intersection over union (IoU). Likewise, the perturbation procedure involves a series of image transformations to the original ground truth segmentations in a randomized manner. These data are then used to train a ResNet18 neural network with custom loss functions to predict the IoU scores of faulty segmentations. This value is then thresholded with a fixed IoU of 0.6 for classification, thereby achieving 88.27% classification accuracy with 91.54% specificity. Experimental results demonstrate the effectiveness of the presented approach. Contributions include: (i) a knowledge-driven perturbation procedure, (ii) a deep learning framework for scoring and detecting faulty glottis segmentations, and (iii) an evaluation of custom loss functions.

RESUMEN

In challenging environments, feature-based visual SLAM encounters frequent failures in frame tracking, introducing unknown poses to robotic applications. This paper introduces an immediate approach for recovering untracked camera poses. Through the retrieval of key information from elapsed untracked frames, lost poses are efficiently restored with a short time consumption. Taking account of reconstructed poses and map points during local optimizing, a denser local map is constructed around ambiguous frames to enhance the further SLAM procedure. The proposed method is implemented in a SLAM system, and monocular experiments are conducted on datasets. The experimental results demonstrate that our method can reconstruct the untracked frames in nearly real time, effectively complementing missing segments of the trajectory. Concurrently, the accuracy and robustness for subsequent tracking are improved through the integration of recovered poses and map points.

RESUMEN

Inertial Measurement Units are present in several applications in aerospace, unmanned vehicle navigation, legged robots, and human motion tracking systems, due to their ability to estimate a body's acceleration, orientation and angular rate. In contrast to rovers and drones, legged locomotion involves repeated impacts between the feet and the ground, and rapid locomotion (e.g., running) involves alternating stance and flight phases, resulting in substantial oscillations in vertical acceleration. The aim of this research is to investigate the effects of periodic low-acceleration impacts (4 g, 8 g and 16 g), which imitate the vertical motion of a running robot, on the attitude estimation of multiple Micro-Electromechanical Systems IMUs. The results reveal the presence of a significant drift in the attitude estimation of the sensors, which can provide important information during the design process of a robot (sensor selection), or during the control phase (e.g., the system will know that after a series of impacts the attitude estimations will be inaccurate).

RESUMEN

Introduction: In Interactive Task Learning (ITL), an agent learns a new task through natural interaction with a human instructor. Behavior Trees (BTs) offer a reactive, modular, and interpretable way of encoding task descriptions but have not yet been applied a lot in robotic ITL settings. Most existing approaches that learn a BT from human demonstrations require the user to specify each action step-by-step or do not allow for adapting a learned BT without the need to repeat the entire teaching process from scratch. Method: We propose a new framework to directly learn a BT from only a few human task demonstrations recorded as RGB-D video streams. We automatically extract continuous pre- and post-conditions for BT action nodes from visual features and use a Backchaining approach to build a reactive BT. In a user study on how non-experts provide and vary demonstrations, we identify three common failure cases of an BT learned from potentially imperfect initial human demonstrations. We offer a way to interactively resolve these failure cases by refining the existing BT through interaction with a user over a web-interface. Specifically, failure cases or unknown states are detected automatically during the execution of a learned BT and the initial BT is adjusted or extended according to the provided user input. Evaluation and results: We evaluate our approach on a robotic trash disposal task with 20 human participants and demonstrate that our method is capable of learning reactive BTs from only a few human demonstrations and interactively resolving possible failure cases at runtime.

RESUMEN

OBJECTIVE: We investigated the extent to which a voluntary-use range and bearing line (RBL) tool improves return-to-manual performance when supervising high-degree conflict detection automation in simulated air traffic control. BACKGROUND: High-degree automation typically benefits routine performance and reduces workload, but can degrade return-to-manual performance if automation fails. We reasoned that providing a voluntary checking tool (RBL) would support automation failure detection, but also that automation induced complacency could extend to nonoptimal use of such tools. METHOD: Participants were assigned to one of three conditions, where conflict detection was either performed: manually, with RBLs available to use (Manual + RBL), automatically with RBLs (Auto + RBL), or automatically without RBLs (Auto). Voluntary-use RBLs allowed participants to reliably check aircraft conflict status. Automation failed once. RESULTS: RBLs improved automation failure detection - with participants intervening faster and making fewer false alarms when provided RBLs compared to not (Auto + RBL vs Auto). However, a cost of high-degree automation remained, with participants slower to intervene to the automation failure than to an identical manual conflict event (Auto + RBL vs Manual + RBL). There was no difference in RBL engagement time between Auto + RBL and Manual + RBL conditions, suggesting participants noticed the conflict event at the same time. CONCLUSIONS: The cost of automation may have arisen from participants' reconciling which information to trust: the automation (which indicated no conflict and had been perfectly reliable prior to failing) or the RBL (which indicated a conflict). APPLICATIONS: Providing a mechanism for checking the validity of high-degree automation may facilitate human supervision of automation.

RESUMEN

Data reliability is of paramount importance for decision-making processes in the industry, and for this, having quality links for wireless sensor networks plays a vital role. Process and machine monitoring can be carried out through ANDON towers with wireless transmission and machine learning algorithms that predict link quality (LQE) to save time, hence reducing expenses by early failure detection and problem prevention. Indeed, alarm signals used in conjunction with LQE classification models represent a novel paradigm for ANDON towers, allowing low-cost remote sensing within industrial environments. In this research, we propose a deep learning model, suitable for implementation in small workshops with limited computational resources. As part of our work, we collected a novel dataset from a realistic experimental scenario with actual industrial machinery, similar to that commonly found in industrial applications. Then, we carried out extensive data analyses using a variety of machine learning models, each with a methodical search process to adjust hyper-parameters, achieving results from common features such as payload, distance, power, and bit error rate not previously reported in the state of the art. We achieved an accuracy of 99.3% on the test dataset with very little use of computational resources.

Asunto(s)

RESUMEN

Deep neural networks (DNNs) have started to find their role in the modern healthcare system. DNNs are being developed for diagnosis, prognosis, treatment planning, and outcome prediction for various diseases. With the increasing number of applications of DNNs in modern healthcare, their trustworthiness and reliability are becoming increasingly important. An essential aspect of trustworthiness is detecting the performance degradation and failure of deployed DNNs in medical settings. The softmax output values produced by DNNs are not a calibrated measure of model confidence. Softmax probability numbers are generally higher than the actual model confidence. The model confidence-accuracy gap further increases for wrong predictions and noisy inputs. We employ recently proposed Bayesian deep neural networks (BDNNs) to learn uncertainty in the model parameters. These models simultaneously output the predictions and a measure of confidence in the predictions. By testing these models under various noisy conditions, we show that the (learned) predictive confidence is well calibrated. We use these reliable confidence values for monitoring performance degradation and failure detection in DNNs. We propose two different failure detection methods. In the first method, we define a fixed threshold value based on the behavior of the predictive confidence with changing signal-to-noise ratio (SNR) of the test dataset. The second method learns the threshold value with a neural network. The proposed failure detection mechanisms seamlessly abstain from making decisions when the confidence of the BDNN is below the defined threshold and hold the decision for manual review. Resultantly, the accuracy of the models improves on the unseen test samples. We tested our proposed approach on three medical imaging datasets: PathMNIST, DermaMNIST, and OrganAMNIST, under different levels and types of noise. An increase in the noise of the test images increases the number of abstained samples. BDNNs are inherently robust and show more than 10% accuracy improvement with the proposed failure detection methods. The increased number of abstained samples or an abrupt increase in the predictive variance indicates model performance degradation or possible failure. Our work has the potential to improve the trustworthiness of DNNs and enhance user confidence in the model predictions.

RESUMEN

We propose an unmanned aerial vehicle (UAV) failure detection system as the first step of a three-step autonomous emergency landing safety framework for UAVs. We showed the effectiveness and feasibility of using vibration data with the k-means clustering algorithm in detecting mid-flight UAV failures for that purpose. Specifically, we measured vibration signals for different faulty propeller cases during several test flights, utilizing a custom-made hardware system. After we made the vibration graphs and extracted the data, we investigated to determine the combination of acceleration and gyroscope parameters that results in the best accuracy of failure detection in quadcopter UAVs. Our investigations show that considering the gyroscope parameter in the vertical direction (gZ) along with the accelerometer parameter in the same direction (aZ) results in the highest accuracy of failure detection for the purpose of emergency landing of faulty UAVs, while ensuring a quick detection and timely engagement of the safety framework. Based on the parameter set (gZ-aZ), we then created scatter plots and confusion matrices, and applied the k-means clustering algorithm to the vibration dataset to classify the data into three health state clusters-normal, faulty, and failure. We confirm the effectiveness of the proposed system with flight experiments, in which we were able to detect faults and failures utilizing the aforementioned clusters in real time.

Asunto(s)

RESUMEN

Multiple sensors are often mounted in a complex manufacturing process to detect failures. Due to the high reliability of modern manufacturing processes, failures only happen occasionally. Therefore, data collected in practical manufacturing processes are extremely imbalanced, which often brings about bias of supervised learning models. Data collected by the multiple sensors can be regarded as multivariate time series or multi-sensor stream data. The high dimension of multi-sensor stream data makes building models even more challenging. In this study, a new and easy-to-apply data augmentation approach, namely, imbalanced multi-sensor stream data augmentation (IMSDA), is proposed for imbalanced learning. IMSDA can generate high quality of failure data for all dimensions. The generated data can keep the similar temporal property of the original multivariate time series. Both raw data and generated data are used to train the failure detection models, but the models are tested by the same real dataset. The proposed method is applied to a real-world industry case. Results show that IMSDA can not only obtain good quality failure data to reduce the imbalance level but also significantly improve the performance of supervised failure detection models.

RESUMEN

Photovoltaic panels exposed to harsh environments such as mountains and deserts (e.g., the Gobi desert) for a long time are prone to hot-spot failures, which can affect power generation efficiency and even cause fires. The existing hot-spot fault detection methods of photovoltaic panels cannot adequately complete the real-time detection task; hence, a detection model considering both detection accuracy and speed is proposed. In this paper, the feature extraction part of YOLOv5 is replaced by the more lightweight Focus structure and the basic unit of ShuffleNetv2, and then the original feature fusion method is simplified. Considering that there is no publicly available infrared photovoltaic panel image dataset, this paper generates an infrared photovoltaic image dataset through frame extraction processing and manual annotation of a publicly available video. Consequently, the number of parameters of the model was 3.71 M, mAP was 98.1%, and detection speed was 49 f/s. A comprehensive comparison of the accuracy, detection speed, and model parameters of each model showed that the indicators of the new model are superior to other detection models; thus, the new model is more suitable to be deployed on the UAV platform for real-time photovoltaic panel hot-spot fault detection.

RESUMEN

Autonomous flights are the major industry contributors towards next-generation developments in pervasive and ubiquitous computing. Modern aerial vehicles are designed to receive actuator commands from the primary autopilot software as input to regulate their servos for adjusting control surfaces. Due to real-time interaction with the actual physical environment, there exists a high risk of control surface failures for engine, rudder, elevators, and ailerons etc. If not anticipated and then timely controlled, failures occurring during the flight can have severe and cataclysmic consequences, which may result in mid-air collision or ultimate crash. Humongous amount of sensory data being generated throughout mission-critical flights, makes it an ideal candidate for applying advanced data-driven machine learning techniques to identify intelligent insights related to failures for instant recovery from emergencies. In this paper, we present a novel framework based on machine learning techniques for failure prediction, detection, and classification for autonomous aerial vehicles. The proposed framework utilizes long short-term memory recurrent neural network architecture to analyze time series data and has been applied at the AirLab Failure and Anomaly flight dataset, which is a comprehensive publicly available dataset of various fault types in fixed-wing autonomous aerial vehicles' control surfaces. The proposed framework is able to predict failure with an average accuracy of 93% and the average time-to-predict a failure is 19 s before the actual occurrence of the failure, which is 10 s better than current state-of-the-art. Failure detection accuracy is 100% and average detection time is 0.74 s after happening of failure, which is 1.28 s better than current state-of-the-art. Failure classification accuracy of proposed framework is 100%. The performance analysis shows the strength of the proposed methodology to be used as a real-time failure prediction and a pseudo-real-time failure detection along with a failure classification framework for eventual deployment with actual mission-critical autonomous flights.

RESUMEN

The physical interactions between wearable lower limb robots and humans have been investigated to inform effective robot design for walking augmentation. However, human-robot interactions when internal faults occur within robots have not been systematically reported, but it is essential to improve the robustness of robotic devices and ensure the user's safety. This paper aims to (1) present a methodology to characterize the behavior of the robotic transfemoral prosthesis as an effective wearable robot platform while interacting with the users in the presence of internal faults, and (2) identify the potential data sources for accurate detection of the prosthesis fault. We first obtained the human perceived response in terms of their walking stability when the prosthesis control fault (inappropriate intrinsic control output/command) was emulated/applied in level-ground walking. Then the measurements and their features, obtained from the transfemoral prosthesis, were examined for the emulated faults that elicited a sense of instability in human users. The optimal features that contributed the most in separating faulty interaction from the normal walking condition were determined using two machine-learning-based approaches: One-Class Support Vector Machine (OCSVM) and Mahalanobis Distance (MD) classifier. The OCSVM anomaly detector could achieve an average sensitivity of 85.7 % and an average false alarm rate of 1.7 % with a reasonable detecting time of 147.6 ms for detecting emulated control errors among all subjects. The result demonstrates the potential of using machine-learning-based schemes in identifying prosthesis control faults based on intrinsic sensors on the prosthesis. This study presents a procedure to study human-robot fault tolerance and inform the future design of robust prosthesis control.

RESUMEN

A SiC ceramic coating was prepared on carbon/carbon composites by pack cementation. The phase composition and microstructure of the coated specimens were characterized using X-ray diffraction instrument and scanning electron microscope. The results showed that the mass-loss percentage of the coated specimen was 9.5% after being oxidized for 20 h. The oxidation failure of the SiC ceramic coating at 1773 K was analysed by non-destructive X-ray computed tomography. The effective self-healing of cracks with widths below 12.7 µm introduced during the coating preparation process and generated while the specimens cooled down from the high oxidation temperature prevented the oxidation of carbon/carbon composites. X-ray computed tomography was used to obtain three-dimensional images revealing internal damage caused by spallation and open holes on the coating. Stress induced by heating and cooling caused the formation, growth and coalescence of cracks, which in turn led to exfoliation of the coating and subsequent failure of oxidation protection.

RESUMEN

This manuscript deals with the detection of internal cracks and defects in aeronautical fibreglass structures. In technical practice, it is problematic to accurately determine the service life or MTBF (Mean Time Between Failure) of composite materials by the methods used in metallic materials. The problem is mainly the inhomogeneous and anisotropic structure of composites, possibly due to the differences in the macrostructure during production, production processes, etc. Diagnostic methods for detecting internal cracks and damage are slightly different, and in practice, it is more difficult to detect defects using non-destructive testing (NDT). The article deals with the use of Radio frequency identification (RFID) technology integrated in the fibreglass laminates of aircraft structures to detect internal defects based on deformation behaviour of passive RFID tag antenna. The experiments proved the potential of using RFID technology in fibreglass composite laminates when using tensile tests applied on specimens with different structural properties. Therefore, the implementation of passive RFID tags into fibreglass composite structures presents the possibilities of detecting internal cracks and structural health monitoring. The result and conclusion of the basic research is determination of the application conditions for our proposed technology in practice. Moreover, the basic research provides recommendations for the applied research in terms of the use in real composite airframe structures.

Asunto(s)

RESUMEN

This article presents the research and results of field tests and simulations regarding an autonomous/robotic railway vehicle, designed to collect multiple information on safety and functional parameters of a surface railway and/or subway section, based on data fusion and machine learning. The maintenance of complex railways, or subway networks with long operating times is a difficult process and intensive resources consuming. The proposed solution delivers human operators in the fault management service and operations from the time-consuming task of railway inspection and measurements, by integrating several sensors and collecting most relevant information on railway, associated automation equipment and infrastructure on a single intelligent platform. The robotic cart integrates autonomy, remote sensing, artificial intelligence, and ability to detect even infrastructural anomalies. Moreover, via a future process of complex statistical filtering of data, it is foreseen that the solution might be configured to offer second-order information about infrastructure changes, such as land sliding, water flooding, or similar modifications. Results of simulations and field tests show the ability of the platform to integrate several fault management operations in a single process, useful in increasing railway capacity and resilience.

Asunto(s)

RESUMEN

Many environmental monitoring applications that are based on the Internet of Things (IoT) require robust and available systems. These systems must be able to tolerate the hardware or software failure of nodes and communication failure between nodes. However, node failure is inevitable due to environmental and human factors, and battery depletion in particular is a major contributor to node failure. The existing failure detection algorithms seldom consider the problem of node battery consumption. In order to rectify this, we propose a low-power failure detector (LP-FD) that can provide an acceptable failure detection service and can save on the battery consumption of nodes. From simulation experiments, results show that the LP-FD can provide better detection speed, accuracy, overhead and battery consumption than other failure detection algorithms.

Asunto(s)