Search

Automatic differentiation is a popular technique for computing derivatives of computer programs. While automatic differentiation has been successfully used in countless engineering, science, and machine learning applications, it can sometimes nevertheless produce surprising results. In this paper, we categorize problematic usages of automatic differentiation, and illustrate each category with examples such as chaos, time‐averages, discretizations, fixed‐point loops, lookup tables, linear solvers, and probabilistic programs, in the hope that readers may more easily avoid or detect such pitfalls. We also review debugging techniques and their effectiveness in these situations. This article is categorized under:Technologies > Machine Learning [ABSTRACT FROM AUTHOR]

ABSTRACT Automatic modulation classification (AMC) is explained as accurately identifying a modulation of a received signal. AMC systems are a significant component of cognitive radio network (CRN) systems. It is difficult to perform modulation classification on an unsettled radio signal without any previous knowledge of the signal's properties. In this work, the deep learning‐aided AMC is suggested to solve the difficulties of the existing models. In the proposed approach, the modulation classification is attained by performing two steps: (a) data collection and (b) classification. Initially, the required data related to the cognitive environment is collected from online resources. Later, the garnered data are passed to the classification phase. The AMC is performed by the adaptive and dilated hybrid network (ADHN), which is the combination of a temporal convolution network (TCN) and a gated recurrent unit (GRU). The ADHN accurately classifies the modulation even in a noisy environment. The classification performance of the ADHN is further boosted by tuning the parameters of this network via the enriched remora optimization algorithm (EROA). This proposed modulation classification model is suitable for various channels. The comparative validation is performed to ensure the usefulness of the designed system via several measures. By experimental analysis, the proposed system acquires the high value of accuracy, precision, and f1‐score by 94.2, 80.2, and 86.7, respectively, when compared with classical approaches. In addition to this, other metrics are considered and obtained with more true value and less false value. Thus, it ensures the effectiveness of classifying the modulation types in CRNs. [ABSTRACT FROM AUTHOR]

The surge in text data has driven extensive research into developing diverse automatic summarization approaches to effectively handle vast textual information. There are several reviews on this topic, yet no large‐scale analysis based on quantitative approaches has been conducted. To provide a comprehensive overview of the field, this study conducted a bibliometric analysis of 3108 papers published from 2010 to 2022, focusing on automatic summarization research regarding topics and trends, top sources, countries/regions, institutions, researchers, and scientific collaborations. We have identified the following trends. First, the number of papers has experienced 65% growth, with the majority being published in computer science conferences. Second, Asian countries and institutions, notably China and India, actively engage in this field and demonstrate a strong inclination toward inter‐regional international collaboration, contributing to more than 24% and 20% of the output, respectively. Third, researchers show a high level of interest in multihead and attention mechanisms, graph‐based semantic analysis, and topic modeling and clustering techniques, with each topic having a prevalence of over 10%. Finally, scholars have been increasingly interested in self‐supervised and zero/few‐shot learning, multihead and attention mechanisms, and temporal analysis and event detection. This study is valuable when it comes to enhancing scholars' and practitioners' understanding of the current hotspots and future directions in automatic summarization. This article is categorized under:Algorithmic Development > Text Mining [ABSTRACT FROM AUTHOR]

Background: Automatic speech recognition (ASR) can potentially help older adults and people with disabilities reduce their dependence on others and increase their participation in society. However, maxillectomy patients with reduced speech intelligibility may encounter some problems using such technologies. Objectives: To investigate the accuracy of three commonly used ASR platforms when used by Japanese maxillectomy patients with and without their obturator placed. Methods: Speech samples were obtained from 29 maxillectomy patients with and without their obturator and 17 healthy volunteers. The samples were input into three speaker‐independent speech recognition platforms and the transcribed text was compared with the original text to calculate the syllable error rate (SER). All participants also completed a conventional speech intelligibility test to grade their speech using Taguchi's method. A comprehensive articulation assessment of patients without their obturator was also performed. Results: Significant differences in SER were observed between healthy and maxillectomy groups. Maxillectomy patients with an obturator showed a significant negative correlation between speech intelligibility scores and SER. However, for those without an obturator, no significant correlations were observed. Furthermore, for maxillectomy patients without an obturator, significant differences were found between syllables grouped by vowels. Syllables containing /i/, /u/ and /e/ exhibited higher error rates compared to those containing /a/ and /o/. Additionally, significant differences were observed when syllables were grouped by consonant place of articulation and manner of articulation. Conclusion: The three platforms performed well for healthy volunteers and maxillectomy patients with their obturator, but the SER for maxillectomy patients without their obturator was high, rendering the platforms unusable. System improvement is needed to increase accuracy for maxillectomy patients. [ABSTRACT FROM AUTHOR]

In the 1960s, meteorological measurements worldwide were still being made at traditional ‘met sites’, many of which are still in use today. This article describes the development at the Institute of Hydrology of what were to become among the first modern automatic weather stations. In this sense, they are of historic interest. [ABSTRACT FROM AUTHOR]

Shape optimization approaches to inverse design offer low‐dimensional, physically‐guided parameterizations of structures by representing them as combinations of primitives. However, on fixed grids, computing the gradient of a user objective via the adjoint variables method requires a product of forward/adjoint field solutions and the Jacobian of the simulation material distribution with respect to the structural shape parameters. Shape parameters often perturb global parts of the simulation grid resulting in many non‐zero Jacobian entries. These are often computed by finite‐difference (FD) in practice, and hence can be non‐trivial. In this work, the gradient calculation is accelerated by invoking automatic differentiation (AD) in instantiations of structural material distributions, enabled by the development of extensible differentiable feature‐mappings from parameters to primitives and differentiable effective logic operations (denoted AutoDiffGeo or ADG). ADG can also be used to accelerate FD‐based shape optimization by efficient boundary selection. AD‐enhanced shape optimization is demonstrated using three integrated photonic examples: a blazed grating coupler, a waveguide transition taper, and a polarization‐splitting grating coupler. The accelerations of the gradient calculation by AD relative to FD with boundary selection exceed 10×$\times$, resulting in total optimization wall time accelerations of 1.4×$1.4\times$–3.8×$3.8\times$ on the same hardware with no compromise to device figure‐of‐merit. [ABSTRACT FROM AUTHOR]

Disturbances and uncertainties, ubiquitous in real‐world systems, complicate model‐based control design. A key challenge is developing a precise control strategy that takes all disturbances into account. The automatic dry‐type clutch is a nonlinear, uncertain, and continuous system, where influencing factors are regarded as total disturbances. An active disturbance rejection control (ADRC) framework with an adaptive extended state observer (AESO) is proposed. The AESO's key strength is its adaptability, adjusting gains over time to minimize state estimation errors and noise impacts. This optimizes disturbance estimation, enhancing closed‐loop system performance. Furthermore, we prove the stability of the AESO through the Lyapunov method and, based on this, set the controller parameters as a Hurwitz matrix to ensure the stability of the closed‐loop system. Experimental data from clutch control demonstrates the efficacy of this controller. It ensures clutch position accuracy with a mean value of 13.5255 mm and a root mean square error of 28.7368 mm. Notably, the AESO's observation errors are minimal, averaging at 0.4365 mm with a root mean square error of 0.7068 mm, even under conditions of uncertain dynamics and measurement noise. This performance surpasses traditional ADRC methods relying on linear extended state observers (ESO) and PI control, thereby advancing the practical applicability of ADRC. Finally, through simulations comparing with fuzzy ESO and nonlinear ESO, the results show that the proposed AESO can achieve the same effect as them. [ABSTRACT FROM AUTHOR]

Automatic modulation classification models based on deep learning models are at risk of being interfered by adversarial attacks. In an adversarial attack, the attacker causes the classification model to misclassify the received signal by adding carefully crafted adversarial interference to the transmitted signal. Based on the requirements of efficient computing and edge deployment, a lightweight automatic modulation classification model is proposed. Considering that the lightweight automatic modulation classification model is more susceptible to interference from adversarial attacks and that adversarial training of the lightweight auto‐modulation classification model fails to achieve the desired results, an adversarial attack defense system for the lightweight automatic modulation classification model is further proposed, which can enhance the robustness when subjected to adversarial attacks. The defense method aims to transfer the adversarial robustness from a trained large automatic modulation classification model to a lightweight model through the technique of adversarial robust distillation. The proposed method exhibits better adversarial robustness than current defense techniques in feature fusion based automatic modulation classification models in white box attack scenarios. [ABSTRACT FROM AUTHOR]

This paper positions possibilities for human geographies of the sea. The growing volume of work under this banner has been largely qualitative in its approach, reflecting, in turn, the questions posed by oceanic scholars. These questions necessitate corresponding methods. Whilst this is not necessarily a problem, and the current corpus of work has offered many significant contributions, in making sense of the human dimensions of maritime worlds, other questions --and methods--may generate knowledge that is useful within this remit of work. This paper considers the place of quantitative approaches in posing lines of enquiry about shipping, one of the prominent areas of concern under the banner of 'human geographies of the seas'. There is longstanding work in transport geographies concerned with shipping, logistics, freight movement and global connections, which embraces quantitative methods which could be bridged to ask fresh questions about oceanic spatial phenomena past and present. This paper reviews the state of the art of human geographies of the sea and transport geographies and navigates how the former field may be stimulated by some of the interests of the latter and a broader range of questions about society-sea-space relations. The paper focuses on Automatic Identification Systems (or AIS) as a potentially useful tool for connecting debates, and deepening spatial understandings of the seas and shipping beyond current scholarship. To advance the argument the example of shipping layups is used to illustrate or rather, position, the point. [ABSTRACT FROM AUTHOR]

Automatic essay scoring (AES) is an essential educational application in natural language processing. This automated process will alleviate the burden by increasing the reliability and consistency of the assessment. With the advances in text embedding libraries and neural network models, AES systems achieved good results in terms of accuracy. However, the actual goals still need to be attained, like embedding essays into vectors with cohesion and coherence, and providing student feedback is still challenging. In this paper, we proposed coherence‐based embedding of an essay into vectors using sentence‐Bidirectional Encoder Representation for Transformers. We trained these vectors on Long short‐term memory and bidirectional long short‐term memory to capture sentence connectivity with other sentences' semantics. We used two datasets: standard ASAP Kaggle and a domain‐specific dataset with almost 2500 responses from 650 students. Our model performed well on both datasets, with an average quadratic weighted kappa score of 0.76. Furthermore, we achieved good results compared to other prescribed models, and we also tested our model on adversarial responses of both datasets and observed decent outcomes. [ABSTRACT FROM AUTHOR]

This paper presents the development of language tutoring systems for non‐native speakers by leveraging advanced end‐to‐end automatic speech recognition (ASR) and proficiency evaluation. Given the frequent errors in non‐native speech, high‐performance spontaneous speech recognition must be applied. Our systems accurately evaluate pronunciation and speaking fluency and provide feedback on errors by relying on precise transcriptions. End‐to‐end ASR is implemented and enhanced by using diverse non‐native speaker speech data for model training. For performance enhancement, we combine semisupervised and transfer learning techniques using labeled and unlabeled speech data. Automatic proficiency evaluation is performed by a model trained to maximize the statistical correlation between the fluency score manually determined by a human expert and a calculated fluency score. We developed an English tutoring system for Korean elementary students called EBS AI PengTalk and a Korean tutoring system for foreigners called KSI Korean AI Tutor. Both systems were deployed by South Korean government agencies. [ABSTRACT FROM AUTHOR]

Third‐party automatic weather stations (TPAWS) provide a compelling data source for scientists and practitioners to observe and estimate more accurate fine‐scale atmospheric conditions, including daily maximum and minimum temperature (denoted as Tmax and Tmin, respectively), than the current primary weather observation network can offer. Several uncertainties and errors arise in data from TPAWS as the quality control applied to these stations may be inadequate or ad hoc. In this study, we develop a statistical approach to evaluate the quality of daily Tmax and Tmin observations collected from TPAWS in Australia. Our approach compares a target observation with multiple types of reliable reference data, including neighbouring primary weather observations from the official Bureau of Meteorology of Australia stations, Australian Gridded Climate Data, and numerical weather prediction data. Guided by the operational requirements in terms of automation, interpretability, and simplicity as well as expandability, a separate test is formed for each type of reference data and then all the individual tests are merged to generate a single result based on a Gaussian mixture model that is used to provide the final overall assessment for each TPAWS observation. The overall assessment is made in the form of a p‐value‐based confidence score that measures the difference between the target observation and trusted reference data. Our method is validated by synthetic datasets based on high‐quality observations and is also applied to daily Tmax and Tmin observations from 184 TPAWS owned by the Department of Primary Industries and Regional Development of Western Australia. The framework can be readily applied to different regions with different reliable or trusted data sources. [ABSTRACT FROM AUTHOR]

Spherical micro/nanorobots are reported as attractive candidates in nano‐surgery, contamination degradation, analytical chemistry, medical engineering, etc. Unlike macroscopic robots, the standard fabrication and inspection strategy to control the high quality of microrobots are rarely explored before. Overcoming the geometrical discrepancy is now essential to keep an identical locomotion behavior for spherical microrobot individuals for complex usages. Herein, acoustic‐based microbubble grippers are proposed controlled by a machine vision system to realize agile recognition and sorting of unqualified spherical microrobot models. Theoretical analysis and numerical simulation reveal the basic grabbing mechanisms via acoustic stimuli. The acoustic resonation of microbubbles can generate a locally enhanced acoustic field, attracting microrobots toward the bubble surface by the acoustic forces. The viscosity of microfluid makes it possible to instantaneously grab or release just by controlling the microbubble activation. Further, a machine vision‐based monitor and control system is proposed to enable automatic control for the entire process. Based on extracted characteristic parameters, target microrobot models are quickly selected and grabbed out. It is expected that such a combination of microgrippers with an advanced control system will pave the way for high‐qualified inspection for microrobots and improve their unique versatility in myriad micromanipulation scenarios. [ABSTRACT FROM AUTHOR]

The wireless Internet of Things (IoT) is widely used for data transmission in power systems. Wireless communication is an important part of the IoT. The existing modulation classification algorithms have low classification accuracy when facing strong electromagnetic interference, which causes decoding error link interruption and wastes wireless channel resources. Therefore, it is necessary to study signal modulation classification methods in a low signal‐to‐noise ratio (SNR) environment. In this paper, a lightweight Deep Neural Networks (DNNs) modulation classification method based on the Informer architecture classifier and two‐dimensional (2‐D) curves input of the spectral correlation function (SCF) is proposed, which uses in‐phase and quadrature (I/Q) signals to generate 2‐D cross‐section SCF curve first and then feeds the feature curve into the Informer network to classify the modulation method. This model can better learn the robustness characteristics in a long sequence. Through testing, the classification accuracy of the modulation signal is not much lower than that of the current good classification method when the SNR is 10 dB, and this method can still show higher accuracy when hardware resources are limited. It is a compact design of a modulation classification model and easy to deploy on low‐cost embedded platforms. [ABSTRACT FROM AUTHOR]

Automatic first‐break picking is a basic step in seismic data processing, so much so that the quality of the picking largely determines the effect of subsequent processing. To a certain extent, artificial intelligence technology has solved the shortcomings of traditional first‐break picking algorithms, such as poor applicability and low efficiency. However, some problems still remain for seismic data, with a low signal‐to‐noise ratio and large first‐break change leading to inaccurate picking and poor generalization of the network. In order to improve the accuracy of the automatic first‐break picking results of the above seismic data, we propose a multi‐view automatic first‐break picking method driven by multi‐network. First, we analysed the single‐trace boundary characteristics and the two‐dimensional boundary characteristics of the first break. Based on these two characteristics of the first break, we used the Long Short‐Term Memory and the ResNet attention gate UNet (resudual attention gate UNet) networks to extract the characteristics of the first arrival and its location from the seismic data, respectively. Then, we introduced the idea of multi‐network learning in the first‐break picking work and designed a feature fusion network. Finally, the multi‐view first‐break features extracted by the Long Short‐Term Memory and resudual attention gate UNet networks are fused, which effectively improves the picking accuracy. The results obtained after applying the method to field seismic data show that the accuracy of the first break detected by a feature fusion network is higher than that given by the above two networks alone and has good applicability and resistance to noise. [ABSTRACT FROM AUTHOR]

This study introduces new insights into the climatology of South Atlantic (SAt) cyclones by employing a novel cyclone life cycle detection method, the CycloPhaser. Utilizing the minimum relative vorticity series and its derivative at the cyclone centre, the program effectively identifies distinct phases in the cyclone life cycle. Cyclone tracks are obtained through the analysis of relative vorticity at 850 hPa, using the ERA5 dataset. The study identified six main cyclone life cycle patterns from the analysis of 28,458 systems. The predominant cyclone type, accounting for approximately 60% of the analysed systems, exhibited a four‐phase configuration: incipient, intensification, mature and decay. Detailed statistics for each developmental phase and the overall life cycle are presented, offering valuable comparisons and new insights while corroborating previous research findings. Key genesis regions in the SAt are identified, along with track density maps that reveal distinct preferences in cyclone developmental cycle. The main outcome of this study is the demonstration that the automated classification procedure enables the analysis of cyclones' life cycles to be conducted promptly and with low computing costs, facilitating the comprehensive study of cyclone behaviour with high efficiency. [ABSTRACT FROM AUTHOR]

In human conversations, listeners often utilize brief backchannels such as "uh‐huh" or "yeah." Timely backchannels are crucial to understanding and increasing trust among conversational partners. In human–machine conversation systems, users can engage in natural conversations when a conversational agent generates backchannels like a human listener. We propose a method that simultaneously predicts backchannels and recognizes speech in real time. We use a streaming transformer and adopt multitask learning for concurrent backchannel prediction and speech recognition. The experimental results demonstrate the superior performance of our method compared with previous works while maintaining a similar single‐task speech recognition performance. Owing to the extremely imbalanced training data distribution, the single‐task backchannel prediction model fails to predict any of the backchannel categories, and the proposed multitask approach substantially enhances the backchannel prediction performance. Notably, in the streaming prediction scenario, the performance of backchannel prediction improves by up to 18.7% compared with existing methods. [ABSTRACT FROM AUTHOR]

As a new software design paradigm, microservices structure an application as a collection of services that are independently deployable and loosely coupled. A key step of migrating non‐microservices‐based systems to microservices‐based systems is the identification of microservices in the target application. Traditional approaches to identify microservices, however, usually suffer from lack of full automation and low effectiveness. This paper puts forward an expert system to identify microservices automatically from legacy systems by leveraging the similarity of RESTful APIs. The system consists of three major parts. The first part calculates the candidate topic similarity and the response message similarity of APIs, and the overall similarity is obtained through their combination. Afterwards, the second part constructs a graph of API similarities with API as the node and the overall similarity as the weight. The third part employs a graph‐based clustering algorithm to identify candidate microservices from the API similarity graph. Experiments conducted on open‐source projects demonstrate the effectiveness of our system. [ABSTRACT FROM AUTHOR]

Introduction: Dynamic hyperinflation in chronic obstructive pulmonary disease (COPD) results in intrinsic positive end‐expiratory pressure (auto‐PEEP). Automatic tube compensation (ATC) is used to increase airway pressure in COPD and overcome endotracheal tube (ETT)–imposed respiratory workload. We aim to investigate effects of ATC activation on auto‐PEEP decrease in COPD. Methods: ATC was activated three times a day (1 min duration) in the morning, evening, and night shift. Auto‐PEEP was measured for the 1 min period (every 6 s) following ATC activation. Linear mixed model (LMM) was used to measure changes in auto‐PEEP and compare with baseline value. Age, gender, and COPD types were inserted in model as covariates and analyzed using SPSS. Results: A total of 60 patients including COPD (n = 40) and COPD with exacerbation (n = 20) were included. Compared with exacerbated COPD, baseline auto‐PEEP in COPD was significantly lower in morning (p = 0.011), evening (p = 0.043), and night shift (p = 0.007). After ATC activation, auto‐PEEP decreased significantly in COPD in morning, evening, and night (p = 0.001), but magnitude of this decrease was notably larger in COPD than in exacerbated COPD (p = 0.001). Moreover, there was a significant relationship between COPD exacerbation and changes in auto‐PEEP in morning (β = −0.27, p = 0.001), evening (β = −0.16, p = 0.001), and night (β = −0.26, p = 0.001). Conclusion: The activation of ATC mode in COPD patients under mechanical ventilation could decrease the value of auto‐PEEP. Nevertheless, COPD patients with an exacerbation appear to benefit less from ATC activation. [ABSTRACT FROM AUTHOR]

Efficient and accurate extraction of discontinuity geometric parameters is significant for evaluating the stability and seepage characteristics of a rock mass. Traditional means of rock discontinuity measurement are susceptible to the influence of terrain and have issues such as high operational workload and low efficiency. An approach was proposed to comprehensively and efficiently obtain the geometric parameter information of the discontinuity, using an Unmanned Aerial Vehicle (UAV), which consists of the following five procedures: (1) measurement of a rock slope with UAV, (2) creation of three‐dimensional (3D) point cloud model for the slope, (3) voxel filtering of point cloud data, (4) planar segmentation based on modified region growing (MRG) algorithm, and (5) acquisition of parameter set of the discontinuity (orientation, trace length, and spacing). A new code, FacetDetect, has been developed based on this method to identify discontinuity from a 3D point cloud. Meanwhile, the trace length and spacing are calculated by the code written in Python. A comparison with the three‐point method reveals that most errors are less than 3° for dip angles and dip directions. These deviations are reasonable and confirm the reliability of the method. Overall, this method is a valuable reference for automatic discontinuity interpretation and related fields. [ABSTRACT FROM AUTHOR]

Objective: Modic changes (MCs) are the most prevalent classification system for describing intravertebral MRI signal intensity changes. However, interpreting these intricate MRI images is a complex and time‐consuming process. This study investigates the performance of single shot multibox detector (SSD) and ResNet18 network‐based automatic detection and classification of MCs. Additionally, it compares the inter‐observer agreement and observer‐classifier agreement in MCs diagnosis to validate the feasibility of deep learning network‐assisted detection of classified MCs. Method: A retrospective analysis of 140 patients with MCs who underwent MRI diagnosis and met the inclusion and exclusion criteria in Tianjin Hospital from June 2020 to June 2021 was used as the internal dataset. This group consisted of 55 males and 85 females, aged 25 to 89 years, with a mean age of (59.0 ± 13.7) years. An external test dataset of 28 patients, who met the same criteria and were assessed using different MRI equipment at Tianjin Hospital, was also gathered, including 11 males and 17 females, aged 31 to 84 years, with a mean age of 62.7 ± 10.9 years. After Physician 1 (with 15 years of experience) annotated all MRI images, the internal dataset was imported into the deep learning model for training. The model comprises an SSD network for lesion localization and a ResNet18 network for lesion classification. Performance metrics, including accuracy, recall, precision, F1 score, confusion matrix, and inter‐observer agreement parameter Kappa value, were used to evaluate the model's performance on the internal and external datasets. Physician 2 (with 1 year of experience) re‐labeled the internal and external test datasets to compare the inter‐observer agreement and observer‐classifier agreement. Results: In the internal dataset, when models were utilized for the detection and classification of MCs, the accuracy, recall, precision and F1 score reached 86.25%, 87.77%, 84.92% and 85.60%, respectively. The Kappa value of the inter‐observer agreement was 0.768 (95% CI: 0.656, 0.847),while observer‐classifier agreement was 0.717 (95% CI: 0.589, 0.809).In the external test dataset, the model's the accuracy, recall, precision and F1 scores for diagnosing MCs reached 75%, 77.08%, 77.80% and 74.97%, respectively. The inter‐observer agreement was 0.681 (95% CI: 0.512, 0.677), and observer‐classifier agreement was 0.519 (95% CI: 0.290, 0.690). Conclusion: The model demonstrated strong performance in detecting and classifying MCs, achieving high agreement with physicians in MCs diagnosis. These results suggest that deep learning models have the potential to facilitate the application of intelligent assisted diagnosis techniques in the field of spine research. [ABSTRACT FROM AUTHOR]

Sulfides with different distribution states may have different effects on steel properties. How to separately count each kind of sulfide remains a question. In the current study, sulfides in 1215 free‐cutting and 416 free‐cutting stainless steel are counted by Image‐Pro Plus image‐processing software. The sulfides can be divided into three categories, that is, cluster‐like sulfides, chain‐like sulfides, and individual sulfides. The features of each kind of sulfide are summarized and an automatic sulfide classification method is proposed. By using this method, sulfides in a metallographic photograph of 1215 steel are successfully classified into three types and counted separately. The quantity percentage of chain‐like, cluster‐like, and individual sulfides is 24.65%, 56.79%, and 18.56%, respectively, while the area percentage of different types of sulfides is 34.33%, 52.80%, and 12.87%. Individual sulfides have the highest‐quantity percentage of sulfides with a diameter smaller than 3 μm and with an area smaller than 10 μm2. Through this method, different types of sulfides can be deeply analyzed. It offers reliable data to evaluate whether the sulfides are well controlled or not, providing a guideline for the improvement of sulfide control methods. [ABSTRACT FROM AUTHOR]

In liberalized power system, the distribution companies are free to choose the contracts with all available generating companies (GENCOs), while the independent system operator acting as regulatory authority. In this article, the liberalized automatic generation control problem is studied for a two‐area interconnected power system. The studies are divided into two parts. In first part, the investigations are carried out with only thermal generations in each area. In second part, the multi‐diverse sourced thermal‐hydro‐gas GENCOs are assumed in each control area. For damping out the system frequency and tie‐line power dynamics, the popularly known PI and PID controllers are employed considering poolco, bilateral and contract violation transactions. In both the parts, the comparative performance between PI/PID controllers is made. Studies reveal that PID outperforms PI controller. A case study with introduction of time delay in the system is performed as the open communication infrastructure introduces inherent time delay in the smart grid scenario. To understand the impact of frequency sensitive loads on system dynamics, the effect of variation in damping coefficient (D) is studied and it is shown how the D is influencing the dynamics. The effect of double reheat turbines is also studied and found that they deteriorate the dynamics when compared to single reheat turbines. In all the above studies, the powerful nature inspired firefly algorithm is employed to optimize the parameters of controllers using the integral squared error method. [ABSTRACT FROM AUTHOR]

INTRODUCTION: Screening for Alzheimer's disease neuropathologic change (ADNC) in individuals with atypical presentations is challenging but essential for clinical management. We trained automatic speech‐based classifiers to distinguish frontotemporal dementia (FTD) patients with ADNC from those with frontotemporal lobar degeneration (FTLD). METHODS: We trained automatic classifiers with 99 speech features from 1 minute speech samples of 179 participants (ADNC = 36, FTLD = 60, healthy controls [HC] = 89). Patients' pathology was assigned based on autopsy or cerebrospinal fluid analytes. Structural network‐based magnetic resonance imaging analyses identified anatomical correlates of distinct speech features. RESULTS: Our classifier showed 0.88 ±$ \pm $ 0.03 area under the curve (AUC) for ADNC versus FTLD and 0.93 ±$ \pm $ 0.04 AUC for patients versus HC. Noun frequency and pause rate correlated with gray matter volume loss in the limbic and salience networks, respectively. DISCUSSION: Brief naturalistic speech samples can be used for screening FTD patients for underlying ADNC in vivo. This work supports the future development of digital assessment tools for FTD. Highlights: We trained machine learning classifiers for frontotemporal dementia patients using natural speech.We grouped participants by neuropathological diagnosis (autopsy) or cerebrospinal fluid biomarkers.Classifiers well distinguished underlying pathology (Alzheimer's disease vs. frontotemporal lobar degeneration) in patients.We identified important features through an explainable artificial intelligence approach.This work lays the groundwork for a speech‐based neuropathology screening tool. [ABSTRACT FROM AUTHOR]

In this paper, we describe a neural network‐based application that recommends multiple items using dialog context input and simultaneously outputs a response sentence. Further, we describe a multi‐item recommendation by specifying it as a set of clothing recommendations. For this, a multimodal fusion approach that can process both cloth‐related text and images is required. We also examine achieving the requirements of downstream models using a pretrained language model. Moreover, we propose a gate‐based multimodal fusion and multiprompt learning based on a pretrained language model. Specifically, we propose an automatic evaluation technique to solve the one‐to‐many mapping problem of multi‐item recommendations. A fashion‐domain multimodal dataset based on Koreans is constructed and tested. Various experimental environment settings are verified using an automatic evaluation method. The results show that our proposed method can be used to obtain confidence scores for multi‐item recommendation results, which is different from traditional accuracy evaluation. [ABSTRACT FROM AUTHOR]

In military contexts, synthetic aperture radar (SAR) automatic target recognition (ATR) models frequently encounter the challenge of imbalanced data, resulting in a noticeable degradation in the recognition performance. Therefore, the authors propose a cost‐sensitive awareness generative adversarial network (CAGAN) model, aiming to improve the robustness of ATR models under imbalanced data. Firstly, the authors introduce a convolutional neural network (DCNN) to extract features. Then, the synthetic minority over‐sampling technique (SMOTE) is applied to achieve feature‐level balancing for the minority category. Finally, a CAGAN model is designed to perform the final classification task. In this process, the GAN‐based adversarial training mechanism enriches the diversity of training samples, making the ATR model more comprehensive in understanding different categories. In addition, the cost matrix increases the penalty for misclassification results and further improves the classification accuracy. Simultaneously, the cost‐sensitive awareness can accurately adjust the cost matrix through training data, thus reducing dependence on expert knowledge and improving the generalisation performance of the ATR model. This model is an end‐to‐end ATR scheme, which has been experimentally validated on the MSTAR and OpenSARship datasets. Compared to other methods, the proposed method exhibits strong robustness in dealing with various imbalanced scenarios and significant generalisation capability across different datasets. [ABSTRACT FROM AUTHOR]

Aiming at the problem that the current arc suppression method of coil cannot achieve full compensation. First, the calculation model of the full compensation parameters of the controllable voltage source is established by analyzing the grounding fault arc suppression principle of the independent controllable voltage source and the parallel arc suppression coil. Second, by analyzing the arc suppression characteristics of controllable voltage source, a PI automatic regulation method based on phase deviation‐fault residual voltage control is proposed. The method uses fault residual voltage and the change of output voltage amplitude of controllable voltage source to control the adjustment direction and fault residual voltage to control the output voltage amplitude of controllable voltage source. The simulation results show that when the capacitive current of the distribution network is 24.47 A, the fault residual voltage is 2.5 V and the residual current is 446 mA after compensation by the independent controllable voltage source. When the capacitive current is 40.8 A and the deharmonic degree of arc suppression coil is −9%, the fault residual voltage and residual current are 2.2 V and 60 mA after compensated by the parallel arc suppression coil of the controlled voltage source. The proposed PI control method exhibits good stability, resulting in low fault residual voltage, and outperforms traditional control methods, enhancing the arc extinction effect of ground faults. [ABSTRACT FROM AUTHOR]

Decoding gene regulatory networks is essential for understanding the mechanisms underlying many complex diseases. GENET is developed, an automated system designed to extract and visualize extensive molecular relationships from published biomedical literature. Using natural language processing, entities and relations are identified from a randomly selected set of 1788 scientific articles, and visualized in a filterable knowledge graph. The performance of GENET is evaluated and compared with existing methods. The named entity recognition model has achieved an overall precision of 94.23% (4835/5131; 93.56–94.84%), recall of 97.72% (4835/4948; 97.27–98.10%), and an F1 score of 95.94%. The relation extraction model has demonstrated an overall precision of 91.63% (2593/2830; 90.55–92.59%), recall of 89.17% (2593/2908; 87.99–90.25%), and an F1 score of 90.38%. GENET significantly outperforms existing methods in extracting molecular relationships (P < 0.001). Additionally, GENET has successfully predicted WNT family member 4 regulates insulin‐like growth factor 2 via signal transducer and activator of transcription 3 in colon cancer. With RNA sequencing data and multiple immunofluorescence, the authenticity of this prediction is validated, supporting the promising feasibility of GENET. [ABSTRACT FROM AUTHOR]

ABSTRACT Recent years have seen a dramatic rise in the use of passive acoustic monitoring (PAM) for biological and ecological applications, and a corresponding increase in the volume of data generated. However, data sets are often becoming so sizable that analysing them manually is increasingly burdensome and unrealistic. Fortunately, we have also seen a corresponding rise in computing power and the capability of machine learning algorithms, which offer the possibility of performing some of the analysis required for PAM automatically. Nonetheless, the field of automatic detection of acoustic events is still in its infancy in biology and ecology. In this review, we examine the trends in bioacoustic PAM applications, and their implications for the burgeoning amount of data that needs to be analysed. We explore the different methods of machine learning and other tools for scanning, analysing, and extracting acoustic events automatically from large volumes of recordings. We then provide a step‐by‐step practical guide for using automatic detection in bioacoustics. One of the biggest challenges for the greater use of automatic detection in bioacoustics is that there is often a gulf in expertise between the biological sciences and the field of machine learning and computer science. Therefore, this review first presents an overview of the requirements for automatic detection in bioacoustics, intended to familiarise those from a computer science background with the needs of the bioacoustics community, followed by an introduction to the key elements of machine learning and artificial intelligence that a biologist needs to understand to incorporate automatic detection into their research. We then provide a practical guide to building an automatic detection pipeline for bioacoustic data, and conclude with a discussion of possible future directions in this field. [ABSTRACT FROM AUTHOR]

Bird‐related outages greatly threaten the safety of overhead transmission and distribution lines, while electrocution and collisions of birds with power lines, especially endangered species, are significant environmental concerns. Automatic bird recognition can be helpful to mitigate this contradiction. This paper proposes a method for automatic classification of bird species related to power line faults combining deep convolution features with error‐correcting output codes support vector machine (ECOC‐SVM). An image dataset of about 20 high‐risk and 20 low‐risk bird species was constructed, and the feed‐forward denoising convolutional neural network was used for image preprocessing. The deep convolution features of bird images were extracted by DarkNet‐53, and taken as inputs of the ECOC‐SVM for model training and bird species classification. The gradient‐weighted class activation mapping was used for visual explanations of the model decision region. The experimental results indicate that the average accuracy of the proposed method can reach 94.39%, and its performance was better than other models using different feature extraction networks and classification algorithms. [ABSTRACT FROM AUTHOR]

Automatic segmentation methods for in vivo magnetic resonance imaging are increasing in popularity because of their high efficiency and reproducibility. However, automatic methods can be perfectly reliable and consistently wrong, and the validity of automatic segmentation methods cannot be taken for granted. Quality control (QC) by trained and reliable human raters is necessary to ensure the validity of automatic measurements. Yet QC practices for applied neuroimaging research are underdeveloped. We report a detailed QC and correction procedure to accompany our validated atlas for hippocampal subfield segmentation. We document a two‐step QC procedure for identifying segmentation errors, along with a taxonomy of errors and an error severity rating scale. This detailed procedure has high between‐rater reliability for error identification and manual correction. The latter introduces at maximum 3% error variance in volume measurement. All procedures were cross‐validated on an independent sample collected at a second site with different imaging parameters. The analysis of error frequency revealed no evidence of bias. An independent rater with a third sample replicated procedures with high within‐rater reliability for error identification and correction. We provide recommendations for implementing the described method along with hypothesis testing strategies. In sum, we present a detailed QC procedure that is optimized for efficiency while prioritizing measurement validity and suits any automatic atlas. [ABSTRACT FROM AUTHOR]

Objective: To create a deep‐learning automatic segmentation model for esophageal cancer (EC), metastatic lymph nodes (MLNs) and their adjacent structures using the UperNet Swin network and computed tomography angiography (CTA) images and to improve the effectiveness and precision of EC automatic segmentation and TN stage diagnosis. Methods: Attention U‐Net, UperNet Swin, UNet++ and UNet were used to train the EC segmentation model to automatically segment the EC, esophagus, pericardium, aorta and MLN from CTA images of 182 patients with postoperative pathologically proven EC. The Dice similarity coefficient (DSC), sensitivity, and positive predictive value (PPV) were used to assess their segmentation effectiveness. The volume of EC was calculated using the segmentation results, and the outcomes and times of automatic and human segmentation were compared. All statistical analyses were completed using SPSS 25.0 software. Results: Among the four EC autosegmentation models, the UperNet Swin had the best autosegmentation results with a DSC of 0.7820 and the highest values of EC sensitivity and PPV. The esophagus, pericardium, aorta and MLN had DSCs of 0.7298, 0.9664, 0.9496 and 0.5091. The DSCs of the UperNet Swin were 0.6164, 0.7842, 0.8190, and 0.7259 for T1‐4 EC. The volume of EC and its adjacent structures between the ground truth and UperNet Swin model were not significantly different. Conclusions: The UperNet Swin showed excellent efficiency in autosegmentation and volume measurement of EC, MLN and its adjacent structures in different T stage, which can help to T and N stage diagnose EC and will save clinicians time and energy. [ABSTRACT FROM AUTHOR]

Glioblastoma multiforme (GBM) is the most prevalent and aggressive primary brain tumour that has the worst prognosis in adults. Currently, the automatic segmentation of this kind of tumour is being intensively studied. Here, the automatic three‐dimensional segmentation of the GBM is achieved with its related subzones (active tumour, inner necrosis, and peripheral oedema). Preliminary segmentations were first defined based on the four basic magnetic resonance imaging modalities and classic image processing methods (multithreshold Otsu, Chan–Vese active contours, and morphological erosion). After an automatic gap‐filling post processing step, these preliminary segmentations were combined and corrected by a supervised artificial neural network of multilayer perceptron type with a hidden layer of 80 neurons, fed by 30 selected radiomic features of gray intensity and texture. Network classification has an overall accuracy of 83.9%, while the complete combined algorithm achieves average Dice similarity coefficients of 89.3%, 80.7%, 79.7%, and 66.4% for the entire region of interest, active tumour, oedema, and necrosis segmentations, respectively. These values are in the range of the best reported in the present bibliography, but even with better Hausdorff distances and lower computational costs. Results presented here evidence that it is possible to achieve the automatic segmentation of this kind of tumour by traditional radiomics. This has relevant clinical potential at the time of diagnosis, precision radiotherapy planning, or post‐treatment response evaluation. [ABSTRACT FROM AUTHOR]

Aim: We conducted a meta‐analysis comparing the invasiveness of automatic lancet devices, which can collect adequate amount of blood at shallow puncture depths, with conventional manual lance devices (lancet or needle) to statistically identify less invasive instruments for neonatal heel lance. Methods: We searched PubMed, Cochrane Central Register of Controlled Trials (CENTRAL), CINAHL, and Ichushi databases for studies comparing the invasiveness between automatic lancet and manual lancet or needle in term and preterm neonates in neonatal intensive care unit. Results: This review included 9 out of 449 searched articles, with 673 neonates. Automatic lancet had significantly lower pain scores (standardised mean difference: −2.0, 95% confidence interval: −3.3 to −0.7), heart rate (mean difference: −8.0, 95% confidence interval: −13.8 to −2.1), cry duration (mean difference: −21.5, 95% confidence interval: −32.5 to −10.4), number of punctures (mean difference: −0.6, 95% confidence interval: −1.1 to −0.2), and duration of procedures (mean difference: −37.7, 95% confidence interval: −75.2 to −0.2) than manual lancet or needle. Furthermore, peripheral oxygen saturation was significantly higher in automatic lancet than in manual lancet or needle (mean difference: 4.5, 95% confidence interval: 0.5–8.5). Conclusion: Automatic heel lancet devices were less invasive than manual heel lance devices (lancet or needle). [ABSTRACT FROM AUTHOR]

To accurately and timely evaluate the long‐term performance of cables in cable‐stayed bridges, an automatic perception technology scheme by on‐line monitoring of cable vibrations is proposed for the fatigue damage evaluation of in‐service cables. In the fatigue‐stress amplitude of cables, the stress produced by tension changes caused by external actions like traffic, wind, and temperature is the main component. When cables vibrate significantly, the stress caused by changes in cable vibration‐induced additional stress should not be neglected. Besides axial stress, bending stress is also significant in cable fatigue damage analysis. To make cable fatigue life prediction closer to real engineering scenarios, this factor should be considered. First, based on the cable dynamic stiffness theory, a method is proposed for the automatic gathering of the actual full‐stress time history of a cable by on‐line vibration monitoring. Furthermore, based on Miner's linear fatigue damage accumulation theory, an automatic fatigue life assessment method is proposed and applied to the vibration monitoring data of cables on an operational bridge. The results indicate that the proposed technology realizes automatic on‐line monitoring of cable forces and fatigue assessment of cables. Through statistical analysis of cable fatigue stress amplitude, it was determined that in cable‐stayed bridges, compared to long cables, short cables are more sensitive to external variable loads, typically experiencing larger and more frequent tension changes, and are more prone to fatigue. Therefore, short cables should be given more attention when analyzing cable fatigue in cable‐stayed bridges. [ABSTRACT FROM AUTHOR]

Background: Perceptual measures such as speech intelligibility are known to be biased, variant and subjective, to which an automatic approach has been seen as a more reliable alternative. On the other hand, automatic approaches tend to lack explainability, an aspect that can prevent the widespread usage of these technologies clinically. Aims: In the present work, we aim to study the relationship between four perceptual parameters and speech intelligibility by automatically modelling the behaviour of six perceptual judges, in the context of head and neck cancer. From this evaluation we want to assess the different levels of relevance of each parameter as well as the different judge profiles that arise, both perceptually and automatically. Methods and Procedures: Based on a passage reading task from the Carcinologic Speech Severity Index (C2SI) corpus, six expert listeners assessed the voice quality, resonance, prosody and phonemic distortions, as well as the speech intelligibility of patients treated for oral or oropharyngeal cancer. A statistical analysis and an ensemble of automatic systems, one per judge, were devised, where speech intelligibility is predicted as a function of the four aforementioned perceptual parameters of voice quality, resonance, prosody and phonemic distortions. Outcomes and Results: The results suggest that we can automatically predict speech intelligibility as a function of the four aforementioned perceptual parameters, achieving a high correlation of 0.775 (Spearman's ρ). Furthermore, different judge profiles were found perceptually that were successfully modelled automatically. Conclusions and Implications: The four investigated perceptual parameters influence the global rating of speech intelligibility, showing that different judge profiles emerge. The proposed automatic approach displayed a more uniform profile across all judges, displaying a more reliable, unbiased and objective prediction. The system also adds an extra layer of interpretability, since speech intelligibility is regressed as a direct function of the individual prediction of the four perceptual parameters, an improvement over more black box approaches. WHAT THIS PAPER ADDS: What is already known on this subject: Speech intelligibility is a clinical measure typically used in the post‐treatment assessment of speech affecting disorders, such as head and neck cancer. Their perceptual assessment is currently the main method of evaluation; however, it is known to be quite subjective since intelligibility can be seen as a combination of other perceptual parameters (voice quality, resonance, etc.). Given this, automatic approaches have been seen as a more viable alternative to the traditionally used perceptual assessments. What this study adds to existing knowledge: The present work introduces a study based on the relationship between four perceptual parameters (voice quality, resonance, prosody and phonemic distortions) and speech intelligibility, by automatically modelling the behaviour of six perceptual judges. The results suggest that different judge profiles arise, both in the perceptual case as well as in the automatic models. These different profiles found showcase the different schools of thought that perceptual judges have, in comparison to the automatic judges, that display more uniform levels of relevance across all the four perceptual parameters. This aspect shows that an automatic approach promotes unbiased, reliable and more objective predictions. What are the clinical implications of this work?: The automatic prediction of speech intelligibility, using a combination of four perceptual parameters, show that these approaches can achieve high correlations with the reference scores while maintaining a certain degree of explainability. The more uniform judge profiles found on the automatic case also display less biased results towards the four perceptual parameters. This aspect facilitates the clinical implementation of this class of systems, as opposed to the more subjective and harder to reproduce perceptual assessments. [ABSTRACT FROM AUTHOR]

Mixed‐metal nanoparticles present a challenging task for synthesis with high precision and reproducibility due to the complex interplay of compositional and reaction condition factors. The present study demonstrates a highly precise and automated flow chemistry technique for synthesizing AgAu alloy nanoboxes with tailored optical properties. The synthesis process involves a proportional–integral (PI) feedback control mechanism that enables accurate regulation of reaction parameters, such as the flow rate, to achieve the target AgAu nanoboxes having a desired UV–vis absorbance wavelength. The PI control algorithm is built on the first‐order plus dead‐time model, which correlates the flow rate of the precursors with the maximum absorbance peaks of the resultant nanoalloy products. Based on the difference between the real‐time measured UV–vis absorbance wavelength and the target wavelength, the flow rate of the precursor (i.e., reagent concentration) is tuned via an iterative process until the real‐time absorbance wavelength of the AgAu alloy nanoboxes is matched with the target setpoint. The implementation of a PI feedback control mechanism in a flow chemistry system can offer a highly versatile and universal strategy for generating on‐demand complex nanomaterials with significantly enhanced consistency and reliability by mitigating concentration variations and minimizing the need for human intervention. [ABSTRACT FROM AUTHOR]

Bullying victimization is widely accepted to be associated with aggression. However, the mechanisms underlying this relationship remain unknown. To examine the long‐term impact of bullying victimization on aggression, the present study tested the potential mediating effects of both anger rumination and hostile automatic thoughts. A total of 809 undergraduates from four universities across China (74.80% female; Mage = 19.63 years, SD = 0.82 years) completed the survey on three occasions, with a 6‐month delay between Time 1 and Time 2 and a 1‐year interval between Time 2 and Time 3. A cross‐lagged model of anger rumination and hostile automatic thoughts was developed to test whether they predicted one another, and two structural models were constructed to test their mediating roles in bullying victimization and aggression. Findings indicated that anger rumination and hostile automatic thoughts are mutually predictable; the correlation between bullying victimization and aggression is mediated independently by anger rumination and hostile automatic thoughts, and the chain mediation of bullying victimization predicting aggression first through anger rumination and then through hostile automatic thinking was established. In addition, an alternative mediation model is also significant, with hostile automatic thoughts as the primary mediator and anger rumination as the secondary mediator. These results highlight the significance of anger rumination and hostile automatic thoughts in the long‐term effects of bullying victimization on aggression. Interventions designed to reduce undergraduate students' anger rumination and hostile automatic thoughts may help reduce their aggression. [ABSTRACT FROM AUTHOR]

Summary: This paper proposes an IoT‐enabled soil monitoring system using wireless sensor network for automatic irrigation in agricultural applications, especially for lemongrass plants, where an automated control system is required for irrigation applications. This can solve the problem of the water crisis, which is faced by the farmers during the cultivation of the crop in the field. This controls the water supply in the irrigation process using an IoT communication system. A system architecture for soil monitoring and controlling irrigation using IoT technique is designed where the different sensors and actuators like humidity, soil moisture, temperature, pump, and so forth are connected with a node microcontrol unit and message queuing telemetry transport (MQTT) protocol for enhancing communication capabilities. This wireless sensor network gives feedback to the system. This provides automation by the on/off pump system during drip irrigation. The sensor data are displayed on a PC or mobile phone through wireless communication and an IoT cloud platform. An experimental testing setup is developed and the experimental performance of a soil monitoring system using IoT technique for automatic drip irrigation has been carried out and soil moisture data are also stored in a cloud server for analytics. The performance shows that the MQTT protocol sends data within 48 s to the IoT cloud so that the data can be acquired in a faster manner. This shows that this kind of soil monitoring system is suitable for automatic drip irrigation, which enhances the farming process and overcomes the water crises in the agricultural system by reducing the wastage of water. [ABSTRACT FROM AUTHOR]

The properties of steels are often closely related to the category and distribution of their microstructures. However, the classification and quantitative analysis of multiphase steel are mostly performed manually, which is time‐consuming and laborious. Moreover, due to the variant experience of experts, the classification results of one image will be different. In this article, an automatic classification model is proposed to identify the multiphase microstructures of steels by means of semantic segmentation, which realizes the automatic statistics of the relative content of each crystalline phase. Semantic segmentation can assign each pixel in an image to one of a set of predefined categories, which can accomplish two tasks concurrently: phase identification and segmentation. We propose an improved fully convolutional network ASPP‐FCN, and carry out comparative experiments with different networks, including FCN, DeepLab v3+, Unet, Enet and PSPnet. The final pixel accuracy of ASPP‐FCN in each category is more than 95%; and the mean intersection over union is over 80%, the results demonstrate that ASPP‐FCN has better segmentation effect in the automatic recognition of the multiphase microstructures of steels. [ABSTRACT FROM AUTHOR]

Many important chemical kinetic systems require detailed chemical kinetic models to resolve. These detailed kinetic models can involve thousands of species and hundreds of thousands of chemical reactions, making them difficult to construct by hand. Modern automatic mechanism generation algorithms can mostly be divided into two classes: rule and rate based. Rule‐based generators choose species based on user defined constraints on species and reaction classes. Rate‐based generators generate a much larger set of potentially important species and reactions and then choose which ones to add based on running simulations of species and reactions deemed important and calculating the flux to potentially important species. In principle, the latter is preferable, as it requires the user to make far fewer assumptions about what is important in the system. However, while the effectiveness of the rate‐based approach has been demonstrated in a wide variety of systems, it has also been demonstrated to have difficulty picking up important low‐flux chemistries. Here we present a discussion of the challenges associated with rate‐based mechanism generation and new algorithms that are able to efficiently mitigate these challenges improving species selection during mechanism generation in a set of case studies. [ABSTRACT FROM AUTHOR]

Background: The reaserch of artificial intelligence (AI) model for predicting spinal refracture is limited to bone mineral density, X‐ray and some conventional laboratory indicators, which has its own limitations. Besides, it lacks specific indicators related to osteoporosis and imaging factors that can better reflect bone quality, such as computed tomography (CT). Objective: To construct a novel predicting model based on bone turn‐over markers and CT to identify patients who were more inclined to suffer spine refracture. Methods: CT images and clinical information of 383 patients (training set = 240 cases of osteoporotic vertebral compression fractures (OVCF), validation set = 63, test set = 80) were retrospectively collected from January 2015 to October 2022 at three medical centers. The U‐net model was adopted to automatically segment ROI. Three‐dimensional (3D) cropping of all spine regions was used to achieve the final ROI regions including 3D_Full and 3D_RoiOnly. We used the Densenet 121‐3D model to model the cropped region and simultaneously build a T‐NIPT prediction model. Diagnostics of deep learning models were assessed by constructing ROC curves. We generated calibration curves to assess the calibration performance. Additionally, decision curve analysis (DCA) was used to assess the clinical utility of the predictive models. Results: The performance of the test model is comparable to its performance on the training set (dice coefficients of 0.798, an mIOU of 0.755, an SA of 0.767, and an OS of 0.017). Univariable and multivariable analysis indicate that T_P1NT was an independent risk factor for refracture. The performance of predicting refractures in different ROI regions showed that 3D_Full model exhibits the highest calibration performance, with a Hosmer–Lemeshow goodness‐of‐fit (HL) test statistic exceeding 0.05. The analysis of the training and test sets showed that the 3D_Full model, which integrates clinical and deep learning results, demonstrated superior performance with significant improvement (p‐value < 0.05) compared to using clinical features independently or using only 3D_RoiOnly. Conclusion: T_P1NT was an independent risk factor of refracture. Our 3D‐FULL model showed better performance in predicting high‐risk population of spine refracture than other models and junior doctors do. This model can be applicable to real‐world translation due to its automatic segmentation and detection. [ABSTRACT FROM AUTHOR]

The development of the Internet of Things (IoT) and machine learning (ML) technologies has triggered smart agricultural systems. In smart agriculture, irrigation management plays a major role to reduce water waste. The monitoring settings, hardware modules, communication technology, and storage systems used in smart irrigation systems were analyzed to determine the optimal nature of water flow. This assessment aims to give an overview of the current state of the irrigation system by taking into account weather and soil moisture. This paper provides a comprehensive review of the utilization of various hardware modules in smart irrigation systems. Moreover, various communication technologies that aid in data transfer for efficient smart irrigation are reviewed. The ML method used for prediction is also evaluated, as well as based storage technologies like the cloud and databases used to store data for predictive irrigation systems. As a result, the paper provides an overview of all the factors that contribute to irrigation systems' smart operation as well as potential future paths for improving agricultural systems through IoT. Core Ideas: Irrigation management is crucial in smart agriculture for minimizing water waste.This apper presents the ideal type of water flow that was determined by smart irrigation systems.Monitoring configurations, hardware modules, communication technology, and storage systems were analyzed in the smart irrigation system. [ABSTRACT FROM AUTHOR]

Braking system is a crucial component of tractors as it ensures safe operation and control of the vehicle. The limited space availability in the workspace of a small tractor exposes the operator to undesirable posture and a maximum level of vibration during operation. The primary cause of road accidents, particularly collisions, is attributed to the tractor operator's insufficient capacity to provide the necessary pedal power for engaging the brake pedal. During the process of engaging the brake pedal, the operator adjusts the backrest support to facilitate access to the brake pedal while operating under stressed conditions. In the present study, a linear actuator‐assisted automatic braking system was developed for the small tractors. An integrated artificial neural network proportional–integral–derivative (ANN‐PID) controller‐based algorithm was developed to control the position of the brake pedal based on the input parameters like terrain condition, obstacle distance, and forward speed of the tractor. The tractor was operated at four different speeds (i.e., 10, 15, 20, and 25 km/h) in different terrain conditions (i.e., dry compacted soil, tilled soil, and asphalt road). The performance parameters like sensor digital output (SDO), force applied on the brake pedal (Fb ), and deceleration were considered as dependent parameters. The SDO was found to good approximation for sensing the position of the brake pedal during braking. The optimized network topology of the developed multilayer perceptron neural network (MLPNN) was 3‐6‐2 for predicting SDO and deceleration of the tractor with a coefficient of determination (R2 ) for the training and testing datasets of the SDO and deceleration were obtained as 0.9953 and 0.9854, and 0.9254 and 0.9096, respectively. The Ziegler–Nichols (Z‐N method) method was adopted to determine the initial optimal gains of the PID controller and later these coefficients were optimized using response surface methodology. The optimized proportional (Kp ), integral (Ki ), and derivative (Kd ) coefficient values were 4.8, 6.782, and 3.15, respectively. The developed integrated ANN, that is, MLPNN and PID‐based algorithm could successfully control the position of the brake pedal during braking. The stopping distance and slip of the tractor during automatic braking increased with an increase in the forward speed for the tractor from 10 to 25 km/h in all the selected terrain conditions. [ABSTRACT FROM AUTHOR]

The article presents a semi‐automatic approach to generating structured hexahedral meshes of patient‐specific aortas ailed by aortic dissection. The condition manifests itself as a formation of two blood flow channels in the aorta, as a result of a tear in the inner layers of the aortic wall. Subsequently, the morphology of the aorta is greatly impacted, making the task of domain discretization highly challenging. The meshing algorithm presented herein is automatic for the individual lumina, whereas the tears require user interaction. Starting from an input (triangle) surface mesh, we construct an implicit surface representation as well as a topological skeleton, which provides a basis for the generation of a block‐structure. Thereafter, the mesh generation is performed via transfinite maps. The meshes are structured and fully hexahedral, exhibit good quality and reliably match the original surface. As they are generated with computational fluid dynamics in mind, a fluid flow simulation is performed to verify their usefulness. Moreover, since the approach is based on valid block‐structures, the meshes can be made very coarse (around 1000 elements for an entire aortic dissection domain), and thus promote using solvers based on the geometric multigrid method, which is typically reliant on the presence of a hierarchy of coarser meshes. [ABSTRACT FROM AUTHOR]

Background: In MR‐guided in‐bore percutaneous needle interventions, typically 2D interactive real‐time imaging is used for navigating the needle into the target. Misaligned 2D imaging planes can result in losing visibility of the needle in the 2D images, which impedes successful targeting. Necessary iterative manual slice adjustment can prolong interventional workflows. Therefore, rapid automatic alignment of the imaging planes with the needle would be preferable to improve such workflows. Purpose: To investigate rapid 3D localization of needles in MR‐guided interventions via a convolutional neural network (CNN)‐based localization algorithm using an undersampled white‐marker contrast acquisition for the purpose of automatic imaging slice alignment. Methods: A radial 3D rf‐spoiled gradient echo MR pulse sequence with white‐marker encoding was implemented and a CNN‐based localization algorithm was employed to extract position and orientation of an aspiration needle from the undersampled white‐marker images. The CNN was trained using porcine tissue phantoms (257 needle trajectories, four‐fold data augmentation, 90%/10% split into training and validation dataset). Achievable localization times and accuracy were evaluated retrospectively in an ex vivo study (109 needle trajectories) for a range of needle orientations between 78° and 90° relative to the B0 field. A proof‐of‐concept in vivo experiment was performed in two porcine animal models and feasibility of automatic imaging slice alignment was evaluated retrospectively. Results: Ex vivo needle localization was achieved with a median localization accuracy of 1.9 mm (distance needle tip to detected needle axis) and a median angular deviation of 2.6° for needle orientations between 86° and 90° to the B0 field from fully sampled WM images (resolution of (4 mm)3, 6434 acquired radial k‐space spokes, acquisition time of 80.4 s) in a field‐of‐view of (256 mm)3. Localization accuracy decreased with increasing undersampling and needle trajectory increasingly aligned with B0. For needle orientations between 86° and 90° to the B0 field, a highly accelerated acquisition of only 32 k‐space spokes (acquisition time of 0.4 s) yielded a median localization accuracy of 3.1 mm and a median angular deviation of 4.7°. For needle orientations between 78° and 82° to the B0 field, a median accuracy and angular deviation of 3.5 mm and 6.8° could still be achieved with 64 sampled spokes (acquisition time of 0.8 s). In vivo, a localization accuracy of 1.4 mm and angular deviation of 3.4° was achieved sampling 32 k‐space spokes (acquisition time of 0.48 s) with the needle oriented at 87.7° to the B0 field. For a needle oriented at 77.6° to the B0 field, localization accuracy of 5.3 mm and angular deviation of 6.8° were still achieved sampling 128 k‐space spokes (acquisition time of 1.92 s), allowing for retrospective slice alignment. Conclusion: The investigated approach enables passive biopsy needle localization in 3D. Acceleration of the localization to real‐time applicability is feasible for needle orientations approximately perpendicular to B0. The method can potentially facilitate MR‐guided needle interventions by enabling automatic imaging slice alignment with the needle. [ABSTRACT FROM AUTHOR]

Background: Patients with respiratory disease often need oxygen supplements through a High‐flow nasal cannula (HFNC), both hypoxia and hyperoxia can be harmful. Proper oxygen therapy requires careful monitoring of oxygen levels and adjustments to oxygen levels. A new automated system called Targeted SpO2 Feedback (TSF) improved the oxygen delivery system compared to manual adjustments. [Correction added on 25 October 2024, after first online publication: Background subsection in Abstract has been added on this version.] Aim: To test whether targeted SpO2 feedback (TSF), an automatic control system for fraction of inspired oxygen (FiO2), achieves more time in the optimal SpO2 range and/or reduces the frequency of manual adjustments to administered FiO2 compared with conventional manual titration in patients with hypoxia on high‐flow nasal cannula (HFNC) therapy. Study Design: Twenty‐two patients were recruited from two hospitals. For each, two sessions of manual mode and two sessions of TSF were applied in a random order, each session lasting 2 h. The target SpO2 on TSF was 95%. Oxygen monitoring levels were classified into four SpO2 ranges: hypoxia (≤ 89%), borderline (90%–93%), optimal (94%–96%) and hyperoxia (≥ 97%). The two modes were compared based on the proportion of time spent in each SpO2 range and the number of manual FiO2 adjustments. Results: The proportion of time in the optimal SpO2 range was 20.5% under manual titration mode and 65.4% under TSF (p <.01). The proportions of time in the hypoxia range were 1.1% and 0.4%, respectively (p =.31), in the borderline range 4.7% and 3.5%, respectively (p =.54), and in the hyperoxia range 73.7% and 30.7%, respectively (p <.01). There were statistical differences only in the optimal and hyperoxia SpO2 ranges. During the 8 h, the frequency of manual FiO2 adjustment was 0.7 times for the manual mode and 0.2 times for TSF, showing no statistically significant difference (p = 0.076). Conclusion: Compared with manual titration, TSF achieved greater time of the optimal SpO2 and less time of hyperoxia during HFNC. The frequency of manual adjustments on TSF tended to be less than on manual titration mode. Relevance to Clinical Practice: Automatic closed‐loop algorithm FiO2 monitoring systems can achieve better oxygen treatments than conventional monitoring and may reduce nurse workloads. In the era of pandemic respiratory diseases, this system can also facilitate contactless SpO2 monitoring during HFNC therapy. [ABSTRACT FROM AUTHOR]

Summary State‐of‐the‐art automatic sleep staging methods have demonstrated comparable reliability and superior time efficiency to manual sleep staging. However, fully automatic black‐box solutions are difficult to adapt into clinical workflow due to the lack of transparency in decision‐making processes. Transparency would be crucial for interaction between automatic methods and the work of sleep experts, i.e., in human‐in‐the‐loop applications. To address these challenges, we propose an automatic sleep staging model (aSAGA) that effectively utilises both electroencephalography and electro‐oculography channels while incorporating transparency of uncertainty in the decision‐making process. We validated the model through extensive retrospective testing using a range of datasets, including open‐access, clinical, and research‐driven sources. Our channel‐wise ensemble model, trained on both electroencephalography and electro‐oculography signals, demonstrated robustness and the ability to generalise across various types of sleep recordings, including novel self‐applied home polysomnography. Additionally, we compared model uncertainty with human uncertainty in sleep staging and studied various uncertainty mapping metrics to identify ambiguous regions, or “grey areas”, that may require manual re‐evaluation. The validation of this grey area concept revealed its potential to enhance sleep staging accuracy and to highlight regions in the recordings where sleep experts may struggle to reach a consensus. In conclusion, this study provides a technical basis and understanding of automatic sleep staging uncertainty. Our approach has the potential to improve the integration of automatic sleep staging into clinical practice; however, further studies are needed to test the model prospectively in real‐world clinical settings and human‐in‐the‐loop scoring applications. [ABSTRACT FROM AUTHOR]

Detailed chemical kinetic mechanisms are necessary for resolving many important chemical processes. As the chemistry of smaller molecules has become better grounded and quantum chemistry calculations have become cheaper, kineticists have become interested in constructing progressively larger kinetic mechanisms to model increasingly complex chemical processes. These large kinetic mechanisms prove incredibly difficult to refine and time‐consuming to interpret. Traditional sensitivity analysis on a large mechanism can range from inconvenient to practically impossible without special techniques to reduce the computational cost. We first present a new time‐local sensitivity analysis we term transitory sensitivity analysis. Transitory sensitivity analysis is demonstrated in an example to accurately identify traditionally sensitive reactions at an 18,000x speed up over traditional sensitivities. By fusing transitory sensitivity analysis with more traditional time‐local branching, pathway, and cluster analyses, we develop an algorithm for efficient automatic mechanism analysis. This automatic mechanism analysis at a time point is able to identify the reactions a target is most sensitive to using transitory sensitivity analysis and then propose hypotheses why the reaction might be sensitive using branching, pathway, and cluster analyses. We implement these algorithms within the reaction mechanism simulator (RMS) package, which enables us to report the automatic mechanism analysis results in highly readable text formats and in molecular flux diagrams. [ABSTRACT FROM AUTHOR]

Population pharmacokinetic (PK) models are widely used to inform drug development by pharmaceutical companies and facilitate drug evaluation by regulatory agencies. Developing a population PK model is a multi‐step, challenging, and time‐consuming process involving iterative manual model fitting and evaluation. A tool for fully automatic model development (AMD) of common population PK models is presented here. The AMD tool is implemented in Pharmpy, a versatile open‐source library for pharmacometrics. It consists of different modules responsible for developing the different components of population PK models, including the structural model, the inter‐individual variability (IIV) model, the inter‐occasional variability (IOV) model, the residual unexplained variability (RUV) model, the covariate model, and the allometry model. The AMD tool was evaluated using 10 real PK datasets involving the structural, IIV, and RUV modules in three sequences. The different sequences yielded generally consistent structural models; however, there were variations in the results of the IIV and RUV models. The final models of the AMD tool showed lower Bayesian Information Criterion (BIC) values and similar visual predictive check plots compared with the available published models, indicating reasonable quality, in addition to reasonable run time. A similar conclusion was also drawn in a simulation study. The developed AMD tool serves as a promising tool for fast and fully automatic population PK model building with the potential to facilitate the use of modeling and simulation in drug development. [ABSTRACT FROM AUTHOR]