Characteristics Of Series Research Articles

Around the EQUATOR With Clin-STAR: AI-Based Randomized Controlled Trial Challenges and Opportunities in Aging Research.

The CONSORT 2010 statement is a guideline that provides an evidence-based checklist of minimum reporting standards for randomized trials. With the rapid growth of Artificial Intelligence (AI) based interventions in the past 10 years, the CONSORT-AI extension was created in 2020 to provide guidelines for AI-based randomized controlled trials (RCT). The Clin-STAR "Around the EQUATOR" series features existing reported standards while also highlighting the inherent complexities of research involving research of older participants. In this work, we propose that when designing AI-based RCTs involving older adults, researchers adopt a conceptual framework (CONSORT-AI-5Ms) designed around the 5Ms (Mind, Mobility, Medications, Matters most, and Multi-complexity) of Age-Friendly Healthcare Systems. Employing the 5Ms in this context, we provide a detailed rationale and include specific examples of challenges and potential solutions to maximize the impact and value of AI RCTs in an older adult population. By combining the original intent of CONSORT-AI with the 5Ms framework, CONSORT-AI-5Ms provides a patient-centered and equitable perspective to consider when designing AI-based RCTs to address the diverse needs and challenges associated with geriatric care.

Ship Anomalous Behavior Detection Based on BPEF Mining and Text Similarity

Maritime behavior detection is vital for maritime surveillance and management, ensuring safe ship navigation, normal port operations, marine environmental protection, and the prevention of illegal activities on water. Current methods for detecting anomalous vessel behaviors primarily rely on single time series data or feature point analysis, which struggle to capture the relationships between vessel behaviors, limiting anomaly identification accuracy. To address this challenge, we proposed a novel vessel anomaly detection framework, which is called the BPEF-TSD framework. It integrates a ship behavior pattern recognition algorithm, Smith–Waterman, and text similarity measurement methods. Specifically, we first introduced the BPEF mining framework to extract vessel behavior events from AIS data, then generated complete vessel behavior sequence chains through temporal combinations. Simultaneously, we employed the Smith–Waterman algorithm to achieve local alignment between the test vessel and known anomalous vessel behavior sequences. Finally, we evaluated the overall similarity between behavior chains based on the text similarity measure strategy, with vessels exceeding a predefined threshold being flagged as anomalous. The results demonstrate that the BPEF-TSD framework achieves over 90% accuracy in detecting abnormal trajectories in the waters of Xiamen Port, outperforming alternative methods such as LSTM, iForest, and HDBSCAN. This study contributes valuable insights for enhancing maritime safety and advancing intelligent supervision while introducing a novel research perspective on detecting anomalous vessel behavior through maritime big data mining.

CLTNet: A Hybrid Deep Learning Model for Motor Imagery Classification

Background: Brain–computer interface (BCI) technology opens up new avenues for human–machine interaction and rehabilitation by connecting the brain to machines. Electroencephalography (EEG)-based motor imagery (MI) classification is a key component of BCI technology, which is capable of translating neural activity in the brain into commands for controlling external devices. Despite the great potential of BCI technology, the challenges of extracting and decoding brain signals limit its wide application. Methods: To address this challenge, this study proposes a novel hybrid deep learning model, CLTNet, which focuses on solving the feature extraction problem to improve the classification of MI-EEG signals. In the preliminary feature extraction stage, CLTNet uses a convolutional neural network (CNN) to extract time series, channel, and spatial features of EEG signals to obtain important local information. In the deep feature extraction stage, the model combines the long short-term memory (LSTM) network and the Transformer module to capture time-series data and global dependencies in the EEG. The LSTM explains the dynamics of the brain activity, while the Transformer’s self-attention mechanism reveals the global features of the time series. Ultimately, the CLTNet model classifies motor imagery EEG signals through a fully connected layer. Results: The model achieved an average accuracy of 83.02% and a Kappa value of 0.77 on the BCI IV 2a dataset, and 87.11% and a Kappa value of 0.74 on the BCI IV 2b dataset, both of which outperformed the traditional methods. Conclusions: The innovation of the CLTNet model is that it integrates multiple network architectures, which offers a more comprehensive understanding of the characteristics of the EEG signals during motor imagery, providing a more comprehensive perspective and establishing a new benchmark for future research in this area.

Fault diagnostic method based on transfer dynamic deep learning for few shot temporal–spatial correlation industry process

AbstractData‐based fault diagnosis plays a crucial role in ensuring the safety of industrial processes. However, the complex industry process often has temporal–spatial correlation with insufficient labelled fault data. To settle these problems, a new transfer dynamic deep learning strategy that combines autoencoder (AE) with gate recurrent unit (GRU) is proposed. First, dynamic AE networks are introduced to extract the single‐attribute time series features, and the dynamic GRU is employed to extract the spatial correlation features among multiple feature dimensions and temporal correlation among samples. Then, to solve the problem of insufficiently labelled industrial data, the model‐based transfer learning between the sufficient laboratory data and insufficient labelled industrial data is executed. Experimental results based on the Tennessee Eastman (TE) process and the benchmark simulation model 1 (BSM1) process show that the proposed approach has excellent performance.

Claudin 18.2 Expression in 1,404 Digestive Tract Adenocarcinomas including 1,175 Colorectal Carcinomas: Distinct Colorectal Carcinoma Subtypes are Claudin 18.2 Positive.

Claudin 18.2 (CLDN18.2) immunohistochemical expression can be used to select patients with gastric/gastroesophageal junction adenocarcinomas for zolbetuximab (IMAB362) therapy, a monoclonal antibody targeting CLDN18.2. The aim of this study was to correlate immunohistochemical expression of CLDN18.2 with clinicopathologic and molecular features in a large series of digestive tract cancers. Immunohistochemistry (IHC) for CLDN18.2 was performed on tissue microarrays from 1404 adenocarcinomas including 155 gastric/gastroesophageal, 74 pancreatic ductal, 1175 colorectal (576 in initial test cohort; 599 in subsequent validation cohort), and correlated with HER2 and mismatch repair (MMR) status. Cases were scored as CLDN18.2 positive or negative, with positivity defined as moderate to strong membranous staining in >75% of tumor cells. CLDN18.2 expression was correlated with clinicopathologic and molecular features for all colorectal adenocarcinomas. CLDN18.2 was positive in 39% (61/155) of gastric/gastroesophageal adenocarcinomas, 38% (28/74) of pancreatic ductal adenocarcinomas, and 3.4% (40/1175) of colorectal adenocarcinomas (p<0.001). For gastric/gastroesophageal and pancreatic ductal adenocarcinoma, there was no correlation between CLDN18.2 expression and either HER2 or MMR status. In contrast, CLDN18.2-positive colorectal adenocarcinomas had distinct clinicopathologic and molecular features. CLDN18.2-positive colorectal adenocarcinomas were more frequently proximally located and were more often MMR deficient and BRAF V600E positive (all with p<0.05). Quantitative pathologic analysis using the digital pathology biomarker QuantCRC demonstrated marked differences in histologic features between CLDN18.2-positive and negative colorectal adenocarcinomas, with CLDN18.2-positive tumors having increased tumor:stroma ratio and %mucin but decreased %immature stroma in both the test and validation cohorts (all with p<0.05). In conclusion, CLDN18.2-positive colorectal adenocarcinomas are frequently MMR deficient, BRAF V600E mutated, and demonstrate distinct histologic features. Future studies addressing the efficacy of zolbetuximab therapy in this subset of colorectal cancers are needed.

Plankton Concentration Model Consistent with Natural Events and Monitoring Series of Holographic Measurements

This paper considers the features of a time series of plankton concentrations, which are further compared with such phenomena as the alteration of day and night and tidal processes. The analysis of experimental data recorded as a result of long-term monitoring measurements under field conditions showed that the diurnal variability in plankton concentrations can be described using a model harmonic function. At the same time, based on the parameters of the diurnal variability model, it is possible to build a bioindication system to detect the influence of estimated abnormal environmental factors, such as pollution. This study discusses the ideology of building such a system based on regular observations of the behavior of autochthonous plankton using a submersible digital holographic camera.

TTSNet: Transformer-Temporal Convolutional Network-Self-Attention with Feature Fusion for Prediction of Remaining Useful Life of Aircraft Engines.

Accurately predicting the remaining useful life (RUL) is crucial for ensuring the safety and reliability of aircraft engine operation. However, aircraft engines operate in harsh conditions, with the characteristics of high speed, high temperature, and high load, resulting in high-dimensional and noisy data. This makes feature extraction inadequate, leading to low accuracy in the prediction of the RUL of aircraft engines. To address this issue, Transformer-TCN-Self-attention network (TTSNet) with feature fusion, as a parallel three-branch network, is proposed for predicting the RUL of aircraft engines. The model first applies exponential smoothing to smooth the data and suppress noise to the original signal, followed by normalization. Then, it uses a parallel transformer encoder, temporal convolutional network (TCN), and multi-head attention three-branch network to capture both global and local features of the time series. The model further completes feature dimension weight allocation and fusion through a multi-head self-attention mechanism, emphasizing the contribution of different features to the model. Subsequently, it fuses the three parts of features through a linear layer and concatenation. Finally, a fully connected layer is used to establish the mapping relationship between the feature matrix and the RUL label, obtaining the RUL prediction value. The model was validated on the C-MAPSS aircraft engine dataset. Experimental results show that compared to other related RUL models, the RMSE and Score reached 11.02 and 194.6 on dataset FD001, respectively; on dataset FD002, the RMSE and Score reached 13.25 and 874.1, respectively. On dataset FD003, the RMSE and Score reached 11.06 and 200.1 and on dataset FD004, the RMSE and Score reached 18.26 and 1968.5, respectively, demonstrating better performance of RUL prediction.

Enhancing the Transformer Model with a Convolutional Feature Extractor Block and Vector-Based Relative Position Embedding for Human Activity Recognition.

The Transformer model has received significant attention in Human Activity Recognition (HAR) due to its self-attention mechanism that captures long dependencies in time series. However, for Inertial Measurement Unit (IMU) sensor time-series signals, the Transformer model does not effectively utilize the a priori information of strong complex temporal correlations. Therefore, we proposed using multi-layer convolutional layers as a Convolutional Feature Extractor Block (CFEB). CFEB enables the Transformer model to leverage both local and global time series features for activity classification. Meanwhile, the absolute position embedding (APE) in existing Transformer models cannot accurately represent the distance relationship between individuals at different time points. To further explore positional correlations in temporal signals, this paper introduces the Vector-based Relative Position Embedding (vRPE), aiming to provide more relative temporal position information within sensor signals for the Transformer model. Combining these innovations, we conduct extensive experiments on three HAR benchmark datasets: KU-HAR, UniMiB SHAR, and USC-HAD. Experimental results demonstrate that our proposed enhancement scheme substantially elevates the performance of the Transformer model in HAR.

EfficientDense-ViT: APT Detection via Hybrid Deep Learning Framework with Hybrid Dipper Throated Sine Cosine Optimization Algorithm (HDT-SCO)

Advanced Persistent Threats (APT) are intelligent, sophisticated cyberattacks that frequently evade detection by gradually interfering with vital systems or focusing on sensitive data. It is proposed herein the new approach of the Hybrid Dipper Throated Sine Cosine Optimization Algorithm (HDT-SCO) for APT detection in association with the EfficientDense-ViT model. It handles the class imbalance issue with advanced processing Adaptive Synthetic Minority Oversampling Technique (ADASYN), including min-max scaling for normalization, and median imputation for missing values. In terms of feature engineering, ResNet-152 and Symbolic Aggregate Approximation (SAX) are adopted for statistical, deep, and time series feature extraction. HDT-SCO optimizes the selection of relevant features to refine by integrating into it the three approaches: PCA, RFE, RF Feature Importance, and L1 Regularization (Lasso). Compared to current detection techniques, the best detection model shows high performance and efficiency through the hybrid deep learning model known as EfficientDense-ViT, which is a combination of EfficientNet, DenseNet, and Vision Transformers (ViT) that can detect APTs reliably. This method shows considerable improvement in both accuracy (0.98741 for the 7030 split and 0.99143 for the 8020 split) and efficiency as compared to existing models in the detection of APTs in cybersecurity.

Aggregated Time Series Features in a Voxel-Based Network Architecture

Aggregated Time Series Features in a Voxel-Based Network Architecture

Subduction-collision and rapid uplift of the NW Yangtze Block during the Ediacaran-Cambrian transition: new evidence from the shoshonite series

ABSTRACT The NW Yangtze Block has long been regarded as a passive continental margin during Ediacaran and Cambrian. However, with the deepening of the regional geological survey and deep oil and gas exploration, the depositional sequence and palaeogeographic patterns of Ediacaran and Cambrian in the Sichuan basin are not consistent with the general sedimentary evolution process of passive margin more and more. To fully understand the tectonic property and palaeogeography of the NW Yangtze Block, a comprehensive study of the whole rock geochemistry, zircon U-Pb chronology and Hf isotopic composition analysis were carried out on the Weimen volcanic rocks, which mainly consist of trachyte, trachy-andesite, andesite, dacite, and rhyodacite in Maoxian area. They have high light rare earth element (LREE) and large ion lithophile element (LILE) concentrations, but are depleted in high field strength elements (HFSE). They are characterized by having high K2O+Na2O (5.60–9.48%), MgO (1.47–4.58%), Ce/Yb (11.67–25.79), and normalized hypersthene (Hy = 2.14–14.17), indicate an unambiguous feature of the shoshonite series. LA-ICP-MS zircon U-Pb dating results show that the volcanic rocks have crystallization ages ranging from 528 Ma to 523 Ma, with positive zircon εHf (t) ranging from + 1.31 to + 5.26. In combination with previous studies, the early Cambrian shoshonite series in Maoxian area are interpreted to be formed in a continental collision setting. Therefore, the discovery of the shoshonite series suggests that the NW Yangtze Block has experienced an important process of continental subduction and collisional orogeny in response to the Gondwana assembly, and consequently provided a large amount of terrigenous sources to rapidly fill into the early Cambrian foreland basin.

Multi-modal prediction of extracorporeal support-a resource intensive therapy, utilizing a large national database.

Extracorporeal membrane oxygenation (ECMO) is among the most resource-intensive therapies in critical care. The COVID-19 pandemic highlighted the lack of ECMO resource allocation tools. We aimed to develop a continuous ECMO risk prediction model to enhance patient triage and resource allocation. We leveraged multimodal data from the National COVID Cohort Collaborative (N3C) to develop a hierarchical deep learning model, labeled "PreEMPT-ECMO" (Prediction, Early Monitoring, and Proactive Triage for ECMO) which integrates static and multi-granularity time series features to generate continuous predictions of ECMO utilization. Model performance was assessed across time points ranging from 0 to 96hours prior to ECMO initiation, using both accuracy and precision metrics. Between January 2020 and May 2023, 101400 patients were included, with 1298 (1.28%) supported on ECMO. PreEMPT-ECMO outperformed established predictive models, including Logistic Regression, Support Vector Machine, Random Forest, and Extreme Gradient Boosting Tree, in both accuracy and precision at all time points. Model interpretation analysis also highlighted variations in feature contributions through each patient's clinical course. We developed a hierarchical model for continuous ECMO use prediction, utilizing a large multicenter dataset incorporating both static and time series variables of various granularities. This novel approach reflects the nuanced decision-making process inherent in ECMO initiation and has the potential to be used as an early alert tool to guide patient triage and ECMO resource allocation. Future directions include prospective validation and generalizability on non-COVID-19 refractory respiratory failure, aiming to improve patient outcomes.

Developing an Annual Review of the Literature.

Many national meetings and speaker series feature an "Annual Review of the Literature" (ARL) session in which an individual or team presents a sampling of articles, selected and prepared because they represent important current topics or new ideas in the discipline of interest. Despite this, there is little in the medical literature describing how to thoughtfully and systematically develop these sessions. We identify best practices that we have developed and used in the United States Clerkship Directors of Internal Medicine (CDIM) over many years. These include identification of a theme, team assembly, timeline development, search strategy and rubric development and employment, and presentation planning strategies. Employing the steps described can help facilitate this otherwise arduous process.

30 m 5-yearly land cover maps of Qilian Mountain Area (QMA_LC30) from 1990 to 2020

The Qilian Mountain Area (QMA) serves as a crucial ecological barrier and strategic water conservation zone in China. Recent years have seen heightened social attention to environmental issues within the QMA, underscoring the need for accurate and continuous land cover maps to support ecological monitoring, analysis, and forecasting. This paper presents the QMA_LC30 dataset, which includes 9 land cover categories and spans the period from 1990 to 2020, with updates every 5 years. The dataset primarily utilizes 30 m Landsat series data and features: 1) High precision, achieved through a geographical division and hierarchical classification decision tree approach, complemented by visual interpretation. 2) Robust consistency, ensured by a change detection method based on a benchmark map. The QMA_LC30 dataset undergoes rigorous accuracy validation, achieving an overall accuracy of over 0.92 for all 7 periods of land cover maps. Compared to GlobeLand30, ESA WorldCover, ESRI 2020 Land Cover, FROM_GLC30, and GLC_FCS30, QMA_LC30 demonstrates the highest consistency with remote sensing images.

MasterPlan: A Reinforcement Learning Based Scheduler for Archive Storage

With the sheer volume of data in today’s world, archive storage systems play a significant role in persisting the cold data. Due to stringent cost concerns, one popular design is to organize disks into groups and periodically switch them to be powered on for serving user requests. Scheduling thus becomes critical for both CapEx and performance. Unfortunately, field results indicate that existing schedulers can be often suboptimal. Our further analysis suggests that the main reason is the mismatch between the ever-changing workloads and the fixed set of coarsely-configured parameters in current heuristic-based schedulers. In this paper, we propose MasterPlan , a reinforcement learning (RL) based scheduler for archive storage systems. By identifying the unique characteristics of archive storage service, we design a state space and reward function for the RL agent. MasterPlan includes a continuous action encoding approach to guarantee efficient exploration, and a meta adaptation module to extract features of workload series. Experiments show that MasterPlan can achieve 1.25 × throughput, 2.16 × 99 th latency and 1.47 × power draw improvement compared to existing solutions.

Characteristics of strong earthquake preparation in main-seismic type and multi-seismic type earthquake segments in the North China tectonic region

The North China Tectonic Zone (NCTZ) is the most seismically active area in eastern China, where a large number of strong earthquakes, especially M8 or so, had occurred. In order to study the risk of future strong earthquakes in the NCTZ, we study tectonic features of strong earthquakes and the time series features of Ms ≥ 5 earthquakes since the year 1484 (MT). The results show that the 14 seismic segments of faults are classified into Main-seismic types and multi-seismic types. The characteristics of the main seismic segment include: NNE dextral strike-slip faults, only one prominent around M8 main shock has occurred since the year 1484, most of the deep and large faults cutting the Moho surface below the main earthquakes with high angles, the flower structures of tectonics. The characteristics of multi-seismic type include: NWW left-lateral strike-slip faults, NEE oriented tensional faults, convergence areas of several sets of faults since the year 1484, and the magnitude of most of them was not greater than M7.0. Finally, we analyze the strong-earthquake-generating characteristics of the similar seismic segments and discuss their strong-earthquake-generating patterns based on the relationship between the rupture zone and the main compressive stress field.

Online Purchase Behavior Prediction Model Based on Recurrent Neural Network and Naive Bayes

In the current competition process of e-commerce platforms, the technical and algorithmic wars that can quickly grasp user needs and accurately recommend target commodities are the core tools of platform competition. At the same time, the existing online purchase behavior prediction models lack consideration of time series features. This paper combines the Recurrent Neural Network, which is more suitable for the commodity recommendation scenario of the e-commerce platform, with Naive Bayes, which is simple in logic and efficient in operation and constructs the online purchase behavior prediction model RNN-NB, which can consider the features of time series. The RNN-NB model is trained and tested using 3 million time series data with purchase behavior provided by the Ali Tianchi big data platform. The prediction effect of the RNN-NB model and Naive Bayes model is evaluated and compared respectively under the same experimental conditions. The results show that the overall prediction effect of the RNN-NB model is better and more stable. In addition, through the analysis of user time series features, it can be found that the possibility of user purchase is negatively correlated with the length of time series, and merchants should pay more attention to those users with shorter time series in commodity recommendation and targeted offers. The contributions of this paper are as follows: (1) By constructing an online purchasing behavior model RNN-NB, which integrates the N vs 1 structure Recurrent Neural Network and naive Bayesian model, the validity limitations of some single-architecture recommendation algorithms are solved. (2) Based on the existing naive Bayesian model, the prediction accuracy of online purchasing behavior is further improved. (3) The analysis based on the features of the time series provides new ideas for the research of later scholars and new guidance for the marketing of platform merchants.

Modeling nonlinear behavior of piezoelectric actuators using improved WT-GRU neural network

The coupling of hysteresis and low damping vibration in a piezoelectric actuator results in low modeling accuracy and adversely affects output motion precision. To mitigate this problem, this paper proposes an improved wavelet transform gated recurrent unit (WT-GRU) model. This model integrates a convolutional layer with WT-GRU to enhance its capability to express complex relationships. Firstly, the input voltage sequence undergoes wavelet transform to decompose it into a set of frequency subsequences. Then, using the feature extraction and representation ability of the convolutional layer, significant features are extracted from subsequences to construct a time series feature vector. Finally, a gated recurrent unit is trained to predict the output displacement sequence accurately. Statistical metrics such as mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination ( R2) were utilized to evaluate the model performance. Additionally, experimental tests were conducted with frequency excitation signals at 80–120 Hz. Experimental results show that the proposed model achieves a MAE of 0.0102 mm, an RMSE of 0.0148 mm, and an R2 value of 0.9478. This model exhibits a significant advantage in accurately predicting the output displacement of piezoelectric actuators, thereby providing a reliable foundation for designing piezoelectric actuator control systems.

ST-Tree with interpretability for multivariate time series classification

Multivariate time series classification is of great importance in practical applications and is a challenging task. However, deep neural network models such as Transformers exhibit high accuracy in multivariate time series classification but lack interpretability and fail to provide insights into the decision-making process. On the other hand, traditional approaches based on decision tree classifiers offer clear decision processes but relatively lower accuracy. Swin Transformer (ST) addresses these issues by leveraging self-attention mechanisms to capture both fine-grained local patterns and global patterns. It can also model multi-scale feature representation learning, thereby providing a more comprehensive representation of time series features. To tackle the aforementioned challenges, we propose ST-Tree with interpretability for multivariate time series classification. Specifically, the ST-Tree model combines ST as the backbone network with an additional neural tree model. This integration allows us to fully leverage the advantages of ST in learning time series context while providing interpretable decision processes through the neural tree. This enables researchers to gain clear insights into the model’s decision-making process and extract meaningful interpretations. Through experimental evaluations on 10 UEA datasets, we demonstrate that the ST-Tree model improves accuracy in multivariate time series classification tasks and provides interpretability through visualizing the decision-making process across different datasets.

A residual GRU method with deep cross fusion for Alzheimer’s disease progression prediction using missing variable-length time series data

Alzheimer’s disease (AD) is a neurodegenerative disorder with a long prodromal phase. Early prediction of AD progression is crucial for improving clinical diagnosis. However, missing data and variable-length of time series data make it difficult to predict the progression of AD in clinical practice. Regarding this problem, existing researches mainly employed LSTM (Long Short-Term Memory) networks to impute missing data and make predictions, but those methods only encoded fixed-length time series data and suffered from the error accumulation, resulting in relatively unsatisfactory prediction results. To address this issue, this paper develops a novel method, named residual sharing GRU (Gated Recurrent Unit) with enhanced deep cross fusion module (RGRU-EDCF), to perform AD progression prediction. Specifically, we first design an enhanced cross deep module to impute missing data and learn complementary information. Moreover, we design a residual sharing GRU model to realize the input of variable-length time series data, thus, enhancing flexibility of model. Besides, the residual structure in the residual sharing GRU model is used for reducing error accumulation. We also add a local multi-head attention mechanism for specific time series features learning for classification and regression prediction. Finally, we use specific time series features to realize prediction of classification and regression tasks. Unlike existing methods that trained the missing data imputation and prediction model separately, our method considers an end-to-end training strategy to train both enhanced cross deep module and the residual sharing GRU model to further promote the performance of AD progression prediction. The proposed method is validated using time series data from the ADNI dataset. The accuracy can reach 95.17% in the prediction task, MAE can reach 2.64 in cognitive score prediction, and 4.04 in MRI biomarkers prediction, it is competitive and superior over other state-of-the-art methods. We also validate our proposed method on MIMIC-III dataset.