Sampling Rate Research Articles

STUDY OF THE EFFECTIVENESS OF THE APPLICATION OF COMPLEX GEOLOGICAL AND TECHNOLOGICAL MEASURES ON THE EXAMPLE OF GAS-CONDENSATE GENERATION IN THE CENTRAL PART OF THE PRIAXIAL ZONE OF THE DNIPROV-DNETZ BASIN

The field development system is the basis of hydrocarbon production, as it ensures the achievement of the necessary technical and economic indicators. Therefore, a high-perfor- mance development system is necessary to ensure maximum profit in the shortest possible time. Empirical studies, analysis and assessment of the effect of implementing a complex of geological and technological measures on the operational facility of a gas condensate field in the central part of the peri-axial zone of the Dnieper-Donets Basin were carried out in order to find methods for improving the existing gas and gas condensate field development systems and increasing gas extraction rates. It is shown that due to hydraulic fracturing, drilling and transfer of wells to the production facility during the five years of production of the produced gas, it is 7.8 % more than in the previous 21 hours, the rate of development of the field from 2015 to 2019 increased from 2.52 %. to 7.9 %, the average well yield increased by 83 % with an increase in the operational fund by 55 %. The results of studies of the effect of the application of geo- logical-technological measures are shown in the form of graphical dependences of the change in the rate of sampling on the number of production wells over time, the rate of daily gas sampling on the number of conducted geological-technological measures on the researched operational object over time. It has been determined that the main driver of the increase in gas production is the hydraulic fracturing of the formation in most of the operational wells, thanks to which the average increase in the output of the wells is 425 %. According to the results of geological and industrial data processing and analysis of changes in the rate of daily gas extraction over time, the effect of the performed operations is divided into three time segments lasting 15–18 months. The decrease in the duration of the effect from the increase in the fund of production wells and the conduct of hydraulic fracturing of the reservoir is due to the decrease in the volume of reservoir energy, therefore the investigated complex of measures will have the greatest effect when implemented at the initial stage of the development of a reservoir with similar geological parameters.

Automobile Maintenance Prediction Using Integrated Deep Learning and Geographical Information System

In the industry, predictive maintenance, or PdM, has gained popularity as a means of lowering maintenance costs and achieving efficient operational oversight. The essence of PdM is to anticipate the occurrence of the next breakdown, allowing for the timely scheduling of maintenance activities prior to its actual manifestation. The objective of this work is to develop a Time-Between-Failure (TBF) forecasting framework using a data-driven methodology. Forecasting the Remaining Usable Life (RUL) is a vital issue in PdM. The objective of the current research is to include Geographic Information Systems (GIS) data into TBF (Time Between Failures) modeling and investigate their influence on automotive TBF via the use of deep learning techniques. Initially, an information fusion technique has been investigated to address the disparity in information category and sample rate between the maintenance information and GIS information. The Cox Proportional Hazard Model (Cox PHM) has been employed using the combined information to create the Health Index (HI). This research introduces an Integrated Deep Learning (IDL) architecture that aims to provide a unique perspective on PdM. This design consists of an input layer, a Long-Short Term Memory (LSTM) layer, a Dropout layer (DO) followed by another LSTM layer, a hidden layer, and an output layer. The Genetic Algorithm (GA) has been employed to discover the optimal number of periods and batch size for the design. The activation function is utilized after the output level and the DO ratio, and the optimization method enhances the loss function established using Grid Searching (GS). Research utilizing an extensive record of vehicle upkeep from a fleet firm demonstrated the efficiency of the suggested method and the influence of GIS parameters on the investigated automobiles.

Genetic and molecular characterization of H9N2 avian influenza viruses in Yunnan Province, Southwestern China

The H9N2 subtype of the avian influenza virus (AIV) is widely prevalent in birds, threatening the poultry industry and providing genetic material for emerging human pathogens. The prevalence and genetic characteristics of H9N2 in Yunnan Province, China, are largely unknown. Samples were collected from live poultry markets (LPMs) and breeding farms in Yunnan Province. H9N2-positive samples were identified by polymerase chain reaction (PCR), with a high positivity rate of 42.86% in tissue samples. The positivity rate of swab samples in the LPMs in Kunming was 3.97% (17/564), but no AIV was detected in samples from poultry farms in Lijiang, Wenshan, and Yuxi. Evolutionary analysis and genotyping were performed for the 17 strains of isolated H9N2 virus. Phylogenetic analysis revealed that all H9N2 viral genes had 91.6%-100% nucleotide homology, belonged to the G57 genotype, and had high homology with H9N2 viruses isolated from Guangdong and Guangxi, suggesting that the H9N2 viruses in Yunnan Province may have been imported by chicks. Using a nucleotide divergence cutoff of 95%, we identified ten distinct H9N2 genotypes that continued to evolve. The surface genes of the H9N2 isolates displayed substantial genetic diversity, highlighting the genetic diversity and complexity of the H9N2-subtype AIVs in Yunnan. Molecular analysis demonstrated that all 17 strains of H9N2 isolates had mutations at H183N, Q226L, L31P, and I268V in hemagglutinin; S31N in matrix protein 2; and no replacements at positions 274 and 292 of the neuraminidase protein. Sixteen strains had the A558V mutation and one strain had the E627V mutation in polymerase basic protein 2. Analysis of these amino acid sites suggests that H9N2 influenza viruses in Yunnan continue to mutate and adapt to mammals and are sensitive to neuraminidase inhibitors but resistant to adamantanes. It is necessary to strengthen surveillance of AIV H9N2 subtypes in poultry and LPMs in Yunnan to further understand their genetic diversity.

Expected Values in Complex Networks Constructed Using a Compression Algorithm to Time Series

This paper introduces a methodology for computing expected values associated with compression networks resulting from the application of compression algorithms to independent and identically distributed random time series. Our analysis establishes a robust correspondence between the calculated expected values and empirically derived results obtained from constructing networks using nondeterministic time series. Notably, the ratio of the average indegree of a network to the computed expected indegree for stochastic time series serves as a versatile metric. It enables the assessment of inherent randomness in time series and facilitates the distinction between nondeterministic and chaotic systems. The metric demonstrates high sensitivity to nondeterminism in both synthetic and real-world datasets, highlighting its capacity to detect subtle disturbances and high-frequency noise, even in series characterized by a deficient sample rate. Our results extend and confirm previous findings in the field.

Multi-Tracking Sensor Architectures for Reconstructing Autonomous Vehicle Crashes: An Exploratory Study.

With the continuous development of new sensor features and tracking algorithms for object tracking, researchers have opportunities to experiment using different combinations. However, there is no standard or agreed method for selecting an appropriate architecture for autonomous vehicle (AV) crash reconstruction using multi-sensor-based sensor fusion. This study proposes a novel simulation method for tracking performance evaluation (SMTPE) to solve this problem. The SMTPE helps select the best tracking architecture for AV crash reconstruction. This study reveals that a radar-camera-based centralized tracking architecture of multi-sensor fusion performed the best among three different architectures tested with varying sensor setups, sampling rates, and vehicle crash scenarios. We provide a brief guideline for the best practices in selecting appropriate sensor fusion and tracking architecture arrangements, which can be helpful for future vehicle crash reconstruction and other AV improvement research.

Pathlength-selective, interferometric diffuse correlation spectroscopy (PaLS-iDCS).

Diffuse correlation spectroscopy (DCS) is an optical method that offers non-invasive assessment of blood flow in tissue through the analysis of intensity fluctuations in diffusely backscattered coherent light. The non-invasive nature of the technique has enabled several clinical applications for deep tissue blood flow measurements, including cerebral blood flow monitoring as well as tumor blood flow mapping. While a promising technique, in measurement configurations targeting deep tissue hemodynamics, the standard DCS implementations suffer from insufficient signal-to-noise ratio (SNR), depth sensitivity, and sampling rate, limiting their utility. In this work, we present an enhanced DCS method called pathlength-selective, interferometric DCS (PaLS-iDCS), which improves upon both the sensitivity of the measurement to deep tissue hemodynamics and the SNR of the measurement using pathlength-specific coherent gain. Through interferometric detection, PaLS-iDCS can provide time-of-flight (ToF) specific blood flow information without the use of expensive time-tagging electronics and low-jitter detectors. The new technique is compared to time-domain DCS (TD-DCS), another enhanced DCS method able to resolve photon ToF in tissue, through Monte Carlo simulation, phantom experiments, and human subject measurements. PaLS-iDCS consistently demonstrates improvements in SNR (>2x) for similar measurement conditions (same photon ToF), and the SNR improvements allow for measurements at extended photon ToFs, which have increased sensitivity to deep tissue hemodynamics (~50% increase). Further, like TD-DCS, PaLS-iDCS allows direct estimation of tissue optical properties from the sampled ToF distribution without the need for a separate spectroscopic measurement. This method offers a relatively straightforward way to allow DCS systems to make robust measurements of blood flow with greatly enhanced sensitivity to deep tissue hemodynamics, enabling further applications of this non-invasive technology.

Analysis of Postoperative Complication and Revision Rates and Mid- to Long-Term Implant Survival in Primary Short-Stem Total Hip Arthroplasty.

Background/Objectives: Short-stem prostheses were introduced as an alternative to conventional straight-stem prostheses. Despite their benefits, including minimally invasive approaches, soft-tissue- and bone-sparing implantation, and physiological load transfer to the metaphysis, data on postoperative complication and revision rates as well as on implant survival are scarce. Methods: A retrospective analysis of 1327 patients who underwent primary total hip arthroplasty (THA) using the Metha® short stem between 2006 and 2023 was conducted. Complication and revision rates were analysed for the intraoperative, direct postoperative, and follow-up episodes. Implant survival was analysed with the endpoint of all-cause stem revision. Results: Intraoperative complications were observed in 3.77% of the cases and included 44 hairline cracks and 6 fractures. In 15 cases (30.0%), conversion to a straight-stem or revision implant was necessary. The direct postoperative complication rate was 2.44%, and 11 revision procedures were performed during inpatient stay (0.84%). Mean follow-up was 7 years (range 1-17). During follow-up, femoral component revision was performed in 60 cases. Aseptic loosening and stem subsidence accounted for a combined percentage of 80% of all indications. Implant survival rate was 95.66% after 5 years, 95.58% after 10 years, and 95.50% after 15 years. Conclusions: Our study provides a comprehensive analysis of postoperative complication and revision rates in a large sample undergoing primary short-stem THA. Postoperative complication rates were favourable, and the long-term implant survival rates were comparable to conventional straight-stem prostheses. Therefore, short-stem THA may be considered an alternative for younger patients.

Dual-template magnetic molecularly imprinted polymers for selective extraction and sensitive detection of aflatoxin B1 and benzo(α)pyrene in environmental water and edible oil

The coexistence of multiple contaminates in the environment and food is of growing concern due to their extremely hazard as a well-known class I carcinogen, like aflatoxin B1 (AFB1) and benzo(α)pyrene (BaP). AFB1 and BaP are susceptible to coexistence in environmental water and edible oil, posing a significant potential risk to environmental monitoring and food safety. The remaining challenges in detecting multiple contaminates include unsatisfied sensitivity, insufficient targets selectivity, and interferences in complex matrices. Here, we developed dual-template magnetic molecularly imprinted polymers (DMMIPs) for selective extraction of dual targets in complex matrices from the environment and food. The DMMIPs were fabricated by surface imprinting with vinyl-functionalized Fe3O4 as carrier, 5,7-dimethoxycoumarin and pyrene as dummy templates, and methacrylamide as functional monomer. The DMMIPs showed excellent adsorption ability (12.73–15.80 mg/g), imprinting factors (2.01–2.58), and reusability of three adsorption-desorption cycles for AFB1 and BaP. The adsorption mechanism including hydrogen bond, electrostatic interaction and van der Waals force was confirmed by physical characterization and DFT calculation. Applying DMMIPs in magnetic solid phase extraction (MSPE) followed by high-performance liquid chromatography (HPLC) analysis enabled detection limits of 0.134 μg/L for AFB1 and 0.107 μg/L for BaP. Recovery rates for water and edible oil samples were recorded as 86.2%–110.3% with RSDs of 4.1%–11.9%. This approach demonstrates potential for simultaneous identification and extraction of multiple contaminants in environmental and food.

Viewing preferences of ASD children on paintings

The eye movement patterns of children with autism spectrum disorder (ASD) based on high-precision, high-sampling-rate professional eye trackers have been widely studied. Still, the equipment used in these studies is expensive and requires skilled operators, and the stimuli are focused on pictures or videos created out of ASD group. We utilized a previously developed eye-tracking device using a tablet, and the double-column paintings with one column from children with ASD, and the other from typically developing (TD) children as stimuli, to investigate the preference of ASD children for the paintings created within their group. This study collected eye movement data from 82 children with ASD and 102 TD children, and an adaptive eye movement classification algorithm was applied to the data aligned by the sampling rate, followed by feature extraction and statistical analysis from the aspects of time, frequency, range, and clustering. Statistical tests indicate that apart from displaying more pronounced non-compliance during the experiment, resulting in a higher data loss rate, children with ASD did not show significant preferences in viewing the two types of paintings compared to TD children. Therefore, we tend to believe that there is no significant difference in preference for ASD and TD paintings showcasing as diptych from the two groups of children using our eye tracking device, and their feature values indicate that they do not have a viewing preference for the paintings.

A Vehicle Passive Entry Passive Start System with the Intelligent Internet of Things

With the development of sensor and communication technologies, the Internet of Things (IoT) subsystem is gradually becoming a crucial part in vehicles. It can effectively enhance functionalities of vehicles. However, new attack types are also emerging. For example, a driver with the smart key in their pocket can push the start button to start a car. At the same time, security issues in the push-to-start scenario are pervasive, such as smart key forgery. In this study, we propose a vehicle Passive Entry Passive Start (PEPS) system that adopts deep learning algorithms to recognize the driver using the electrocardiogram (ECG) signals measured on the driver’s smart watch. ECG signals are used for personal identification. Smart watches, serving as new smart keys of the PEPS system, can improve convenience and security. In the experiment, we consider commercial smart watches capable of sensing ECG signals. The sample rate and precision are typically lower than those of a 12-lead ECG used in hospitals. The experimental results show that Long Short-Term Memory (LSTM) models achieve the best accuracy score for identity recognition (91%) when a single ECG cycle is used. However, it takes at least 30 min for training. The training of a personalized Auto Encoder model takes only 5 min for each subject. When 15 continuous ECG cycles are sensed and used, this can achieve 100% identity accuracy. As the personalized Auto Encoder model is an unsupervised learning one-class recognizer, it can be trained using only the driver’s ECG signal. This will simplify the management of ECG recordings extremely, as well as the integration of the proposed technology into PEPS vehicles. A FIDO (Fast Identify Online)-like environment for the proposed PEPS system is discussed. Public key cryptography is adopted for communication between the smart watch and the PEPS car. The driver is first verified on the smart watch via local ECG biometric authentication, and then identified by the PEPS car. Phishing attacks, MITM (man in the middle) attacks, and replay attacks can be effectively prevented.

Microbiological screening of corneas stored in organ culture medium at Lions Eye Bank of Western Australia from 2011 to 2022.

The purpose of this study was to analyse the contamination rate of corneal samples stored in OCM at Lions Eye Bank of Western Australia over a 12-year period. All OCM samples used to preserve corneas from 2011 to 2022 (inclusive) underwent microbiological testing. Samples were collected into aerobic and anaerobic culture bottles on day 3-5 of corneal preservation and 24h after transfer to thinning medium. Samples were tested for 7days using the BACTEC FX system. Corneas remained in quarantine until clearance was obtained. From 2011 to 2022, 3009 corneas were retrieved and 2756 corneas were stored in OCM. Thirty one (1.1%) positive samples were reported, with 20 growths of bacterial origin and 11 fungal. Microbial contamination was mostly identified on day 1 of culture (77.5%). Donors of contaminated samples had a mean age of 55years, with 17 male and 14 female donors. The highest incidence of contamination came from donors whose cause of death was cancer. Death to enucleation times of contaminated samples ranged from 3.5 to 25.5h (mean = 13.5 ± 7.3) and death to preservation time ranged from 4.1 to 27.5h (mean = 14.8 ± 7.2). These did not significantly differ from the average time from death to enucleation (mean = 13.9 ± 3) and death to preservation (mean = 16.3 ± 4.2) of non-contaminated samples. Microbiological screening of corneas stored in OCM at LEBWA showed a very low rate of positive cultures with no predictive donor characteristics.

Research on the flow characteristics of blasthole stemming slurry in open-pit mining

The flow characteristics of blasthole stemming slurry (BSS), predominantly comprising yellow mud (YM), tail mud (TM), or drilling cuttings (DC), were systematically investigated. Various influencing factors, including slurry mass concentration, the addition of TM or DC, and the mass ratio of TM to YM (TM/YM) and DC to YM (DC/YM), were meticulously examined. Experiments were conducted to assess the fluidity, rheological properties, and bleeding rate of BSS samples, which were prepared by manipulating slurry mass concentration and the proportions of TM or DC. The results indicate that the rheological properties of BSS are suitably described by the Herschel-Bulkley model. A critical mass concentration was identified, beyond which the flowability of BSS rapidly deteriorates. Replacing YM with an equivalent amount of TM at a mass concentration of 59% increased the yield stress by 167.30%, while reducing the bleeding rate to 0 within the 53%–59% mass concentration range. Conversely, replacing YM with DC at a mass concentration of 62% reduced the yield stress by 63.96%, while increasing the 60-minute bleeding rate from 0% to 1.44%. Increasing the TM/YM ratio resulted in reduced fluidity, elevated yield stress, and a variable degree of shear thickening. The degree of shear thickening was highest when the TM/YM ratio was 1, with significant impacts on differential viscosity at higher shear rates. On the other hand, increasing the DC/YM ratio enhanced fluidity, decreased yield stress, and influenced the degree of shear thickening and differential viscosity, with the highest shear thickening and lowest differential viscosity observed at a DC/YM ratio of 3. The bleeding rate of BSS consistently rose with the increase in the DC/YM ratio.

Adaptive Joint Carrier and DOA Estimations of FHSS Signals Based on Knowledge-Enhanced Compressed Measurements and Deep Learning.

As one of the most widely used spread spectrum techniques, the frequency-hopping spread spectrum (FHSS) has been widely adopted in both civilian and military secure communications. In this technique, the carrier frequency of the signal hops pseudo-randomly over a large range, compared to the baseband. To capture an FHSS signal, conventional non-cooperative receivers without knowledge of the carrier have to operate at a high sampling rate covering the entire FHSS hopping range, according to the Nyquist sampling theorem. In this paper, we propose an adaptive compressed method for joint carrier and direction of arrival (DOA) estimations of FHSS signals, enabling subsequent non-cooperative processing. The compressed measurement kernels (i.e., non-zero entries in the sensing matrix) have been adaptively designed based on the posterior knowledge of the signal and task-specific information optimization. Moreover, a deep neural network has been designed to ensure the efficiency of the measurement kernel design process. Finally, the signal carrier and DOA are estimated based on the measurement data. Through simulations, the performance of the adaptively designed measurement kernels is proved to be improved over the random measurement kernels. In addition, the proposed method is shown to outperform the compressed methods in the literature.

Design, Development and Application of a Modular Electromagnetic Induction (EMI) Sensor for Near-Surface Geophysical Surveys.

Low-frequency electromagnetic induction (EMI) is a non-invasive geophysical method that is based on the induction of electromagnetic (EM) waves into the subsurface to quantify changes in electrical conductivity. In this study, we present an open (design details and software are accessible) and modular system for the collection of EMI data. The instrument proposed allows for the separations between the transmitter to be adjusted and up to four receiving antennas as well as the acquisition frequency (in the range between 3 and 50 kHz) to permit measurements with variable depth of investigation. The sensor provides access to raw data and the software described in this study allows control of the signal processing chain. The design specifications permit apparent conductivity measurements in the range of between 1 mS/m and 1000 mS/m, with a resolution of 1.0 mS/m and with a sampling rate of up to 10 samples per second. The sensor allows for a synchronous acquisition of a time stamp and a location stamp for each data sample. The sensor has a mass of less than 5 kg, is portable and suitable for one-person operation, provides 4 h of operation time on one battery charge, and provides sufficient rigidity for practical field operations.

Two‐dimensional adaptive Whittaker–Shannon Sinc‐based zooming

AbstractIn this work, we introduce a novel image zooming methodology that transitions from a nonadaptive Sin‐based approach to an adaptive Sinc‐based zooming technique. The two techniques base their theoretical foundation on the Whittaker–Shannon interpolation formula and the Nyquist theorem. The evolution into adaptive Sinc‐based zoom is accomplished through the use of two novel concepts: (1) the pixel‐local scaled k‐space and (2) the k‐space filtering sigmoidal function. The pixel‐local scaled k‐space is the standardized and scaled k‐space magnitude of the image to zoom. The k‐space filtering sigmoidal function scales the pixel‐local scaled k‐space values into the numerical interval [0, 1]. Using these two novel concepts, the Whittaker–Shannon interpolation formula is elaborated and used to zoom images. Zooming is determined by the shape of the Sinc functions in the Whittaker–Shannon interpolation formula, which, in turn, depends on the combined effect of the pixel‐local scaled k‐space, the sampling rate, and the k‐space filtering sigmoidal function. The primary outcome of this research demonstrates that the Whittaker–Shannon interpolation formula can achieve successful zooms for values of the sampling rate significantly greater than the bandwidth. Conversely, when the sampling rate is much greater than the bandwidth, the nonadaptive technique fails to perform the zoom correctly. The conclusion is that the k‐space filtering sigmoidal function is identified as the crucial parameter in the adaptive Sinc‐based zoom technique. The implications of this research extend to Sinc‐based image zooming applications.

Ultrasensitive detection of CEA in human serum using label-free electrochemical biosensor with magnetic self-assembly based on α-Fe2O3/Fe3O4 nanorods

Early-stage colorectal cancer (CRC) is often asymptomatic, leading to late diagnoses and impacting treatment outcomes. Timely detection and diagnosis are crucial, with serum carcinoembryonic antigen (CEA) levels playing a key role in CRC diagnosis and prognosis. To enhance precision, a label-free electrochemical nano-biosensor utilizing magnetic self-assembly (MSA) technology was developed for sensitive CEA detection. The biosensor's core was the α-Fe2O3/Fe3O4 nanorods prepared by the hydrolysis-calcination reduction process. Its unique magnetism was the cornerstone of MSA technology. The biosensor exhibited excellent mechanical strength, ensuring stability during storage at 4 °C for at least one month. The aptamer probe (CEAA) self-assembled on the nanorods' surface via an Au–S bond, creating the magnetic probe (CEAA/α-Fe2O3/Fe3O4@Au). Upon capturing CEA, the current response decreased, indicating a “turn-off" nano-biosensor type as observed through differential pulse voltammetry (DPV) monitoring. In this research, the biosensor not only exhibited robust specificity and superior anti-interference ability but also demonstrated successful regeneration. The limit of detection (LOD) was 0.197 pg/mL, the recovery rate for real serum samples was between 94.15 % and 105.08 %, and the relative standard deviation (RSD) ranged from 1.40 % to 2.09 %. This biosensor showed promise in enhancing the accuracy and effectiveness of CRC diagnostic and prognostic protocols, offering a new direction for point-of-care testing.

Graph-Based Electroencephalography Analysis in Tinnitus Therapy.

Tinnitus is the perception of sounds like ringing or buzzing in the ears without any external source, varying in intensity and potentially becoming chronic. This study aims to enhance the understanding and treatment of tinnitus by analyzing a dataset related to tinnitus therapy, focusing on electroencephalography (EEG) signals from patients undergoing treatment. The objectives of the study include applying various preprocessing techniques to ensure data quality, such as noise elimination and standardization of sampling rates, and extracting essential features from EEG signals, including power spectral density and statistical measures. The novelty of this research lies in its innovative approach to representing different channels of EEG signals as new graph network representations without losing any information. This transformation allows for the use of Graph Neural Networks (GNNs), specifically Graph Convolutional Networks (GCNs) combined with Long Short-Term Memory (LSTM) networks, to model intricate relationships and temporal dependencies within the EEG data. This method enables a comprehensive analysis of the complex interactions between EEG channels. The study reports an impressive accuracy rate of 99.41%, demonstrating the potential of this novel approach. By integrating graph representation and deep learning, this research introduces a new methodology for analyzing tinnitus therapy data, aiming to contribute to more effective treatment strategies for tinnitus sufferers.

Unmanned Ground Vehicle Path Planning Based on Improved DRL Algorithm

Path planning and obstacle avoidance are fundamental problems in unmanned ground vehicle path planning. Aiming at the limitations of Deep Reinforcement Learning (DRL) algorithms in unmanned ground vehicle path planning, such as low sampling rate, insufficient exploration, and unstable training, this paper proposes an improved algorithm called Dual Priority Experience and Ornstein–Uhlenbeck Soft Actor-Critic (DPEOU-SAC) based on Ornstein–Uhlenbeck (OU noise) and double-factor prioritized sampling experience replay (DPE) with the introduction of expert experience, which is used to help the agent achieve faster and better path planning and obstacle avoidance. Firstly, OU noise enhances the agent’s action selection quality through temporal correlation, thereby improving the agent’s detection performance in complex unknown environments. Meanwhile, the experience replay is based on double-factor preferential sampling, which has better sample continuity and sample utilization. Then, the introduced expert experience can help the agent to find the optimal path with faster training speed and avoid falling into a local optimum, thus achieving stable training. Finally, the proposed DPEOU-SAC algorithm is tested against other deep reinforcement learning algorithms in four different simulation environments. The experimental results show that the convergence speed of DPEOU-SAC is 88.99% higher than the traditional SAC algorithm, and the shortest path length of DPEOU-SAC is 27.24, which is shorter than that of SAC.

AI-Based Anomaly Detection Techniques for Structural Fault Diagnosis Using Low-Sampling-Rate Vibration Data

Rotorcrafts experience severe vibrations during operation. To ensure the safety of rotorcrafts, it is necessary to perform anomaly detection to detect small-scale structural faults in major components. To accurately detect small-scale faults before they grow to a fatal size, HR (high sampling rate) vibration data are required. However, to increase the efficiency of data storage media, only LR (low sampling rate) vibration data are generally collected during actual flight operation. Anomaly detection using only LR data can detect faults above a certain size, but may fail to detect small-scale faults. To address this problem, we propose an anomaly detection technique using the SR3 (Super-Resolution via Repeated Refinement) algorithm to upscale LR data to HR data, and then applying the LSTM-AE model. This technique is validated for two datasets (drone arm data, CWRU bearing data). First, the necessity for HR data is illustrated by showing that anomaly detection using LR data fails, and the upscaling performance of the SR3 algorithm is validated in the frequency and time domain. Finally, the anomaly detection for a structural fault diagnosis is performed for the upscaled data and the HR data using the LSTM-AE model. The quantitative evaluation of the Min–Max normalized reconstruction error distribution is performed through the MSE (Mean Square Error) value of the anomaly detection results. As a result, it is confirmed that the anomaly detection using upscaled test data can be performed as successfully as the anomaly detection using HR test data for both datasets by the proposed technique.

Multi-Objective Region Encryption Algorithm Based on Adaptive Mechanism

The advancement of information technology has led to the widespread application of remote measurement systems, where information in the form of images or videos, serving as measurement results, is transmitted over networks. However, this transmission is highly susceptible to attacks, tampering, and disputes, posing significant risks to the trustworthy transmission of measurement results from instruments and devices. In recent years, many encryption algorithms proposed for images have focused on encrypting the entire image, resulting in resource waste. Additionally, most encryption algorithms are designed only for single-object-type images. Addressing these issues, this paper proposes a multi-object region encryption algorithm based on an adaptive mechanism. Firstly, an adaptive mechanism is employed to determine the strategy for adjusting the sampling rate of encryption objects, achieved through an encryption resource allocation algorithm. Secondly, an improved polygon segmentation algorithm is utilized to separate single-object regions from multi-object images, dynamically adjusting the sequence of encryption objects based on the adaptive mechanism. Finally, encryption is achieved using a chaos fusion XOR encryption algorithm. Experimental validation using instrument images demonstrates that the proposed algorithm offers high efficiency and security advantages compared to other mainstream image encryption algorithms.