Preset Threshold Research Articles

Impact of immigration background on feasibility of electronic patient-reported outcomes in advanced urothelial cancer patients

BackgroundElectronic patient-reported outcomes (ePROs) have been shown to enhance healthcare quality by improving patient symptom management or quality of life (QoL). However, ePROs data for urothelial cancer (UC) patients receiving systemic therapies are scarce, and the application of ePROs in this patient cohort may need specific setups. This study tested the feasibility of ePROs for UC patients receiving systemic therapies in the outpatient clinic of a tertiary care center.Patients and MethodsFrom January 2022 to April 2023, 30 UC patients receiving systemic cancer therapies received ePROs based on the Common Terminology Criteria for Adverse Events (CTCAE) and European Organization for Research and Treatment of Cancer Core Quality of Life questionnaires (EORTC QLQ-30) to report their symptoms and QoL during systemic therapy, in total, 125 questions for every therapy cycle. The proportion of patients adherent to the ePROs was assessed to evaluate feasibility, with a preset threshold of 50%. At least half of all treatment cycles with a minimum of two consecutive ePROs (corresponding to two successive therapy cycles) had to be completed to be counted as adherent, and a maximum of six successive therapy cycles was followed by ePROs. Descriptive statistics were calculated for clinical and demographic patient characteristics. T-test and chi-square-test analyses were performed to study the association between ePROs adherence and clinical or demographic factors. The digital process was closely monitored for procedural impediments that could occur.Results21 (70%) of the included 30 patients adhered to the provided ePROs, significantly higher than the predetermined threshold of 50%. Adherence remained above 70% until the end of the observation period. A significant negative effect of immigration background on ePROs compliance was observed (p = 0.006). No other variables were significantly associated with ePROs compliance.ConclusionsIn this study, ePROs were a feasible method to assess symptoms and QoL during the systemic cancer therapy of UC patients at our center. The compliance of patients with immigration backgrounds was the most significant barrier to using ePROs in this setting. However, the study is limited by the exclusion of patients without email access and the lack of assessment of physician compliance with the ePROs data, which may affect the generalizability and implementation of the findings.

Short Circuit Indicator

This application introduces the short-circuit indicator, an important protection against electrical hazards in residential, commercial and industrial environments. This device continuously monitors the voltage in the circuit and acts as an alert sentry against dangerous surges. By using a preset threshold, the signal can distinguish between normal voltage fluctuations and short-circuit characteristic spikes. By detecting a jump, the register takes immediate action to prevent losses. It disconnects the circuit quickly, efficiently disconnecting abnormal electrical currents, and protects the connected devices from potential damage. In addition, the device comes with an easy-to-use information system that includes an integrated LED and buzzer. This immediate warning brings the user’s attention to the issue, allowing them to take appropriate steps to address the shortcuts and restore safety.

The immune cells causative role in lung cancer: Mendelian randomization study

BackgroundsLung cancer (LC) is the leading cause of cancer-related deaths in China, with its incidence and mortality rates rising annually. Various studies have demonstrated disparities in immune cell counts and profiles between LC patients and healthy individuals. However, the existence of a causal link remains largely uncertain. To explore the potential causal association between immune cells and LC risk, a Mendelian randomization (MR) approach was employed.MethodsEmploying immune cell genome-wide association study (GWAS) data from a public database (n = 731 subjects) and Lung Cancer Genome Research Consortium's GWAS dataset (n = 492,803 participants), unconventional genetic loci remarkably associated with the significant abundance of 731 types of immune cells were extracted according to preset threshold points as instrumental variables. The primarily analytical strategy involved the inverse variance weighting (IVW) method, with the effect size estimates expressed as odds ratio (OR) and 95% CI. The robustness of the findings was assessed through a leave-one-out sensitivity analysis, heterogeneity test, horizontal gene pleiotropy test, MR-PRESSO and MR-Egger.ResultsThe MR analysis identified a significant association between 18 distinct immune cell types and lung cancer risk. MR analysis revealed that 7 types of immune cells, including CD20 on IgD − CD38 − B cell, CD20 on switched memory B cell, IgD on IgD + CD24 + B cell, BAFF − R on IgD − CD38 + B cell, CD39 + resting CD4 regulatory T cell Absolute Count, CD127 on CD45RA + CD4 + T cell, CD8 on Effector Memory CD8 + T cell, displayed a protective effect against lung cancer development. Conversely, 11 other immune cells populations were positive associated with an increased lung cancer risk. In contrast, reverse MR analysis indicated that the lung cancer risk was linked to 11 immune cells, with 2 types of immune cells (CD25 on IgD − CD27 − B cell, CD4 + T cell %leukocyte) showing a are positive correlation with cancer development, whereas 9 types of immune cells appeared to be inversely regulated. These findings collectively imply that specific immune cell populations may play critical roles in either promoting or suppressing the initiation and progression of lung cancer.ConclusionThe findings of this study offer fresh insights into the underlying biological mechanisms governing lung cancer development, thereby opening new avenues for future research in the domain of LC. The identification of specific immune cell subsets with protective or promoting roles provides crucial leads for preventive and therapeutic strategies. These insights have the potential to enhance early detection methods and inform the development of more effective treatment approaches, ultimately benefiting patient outcomes and improving the overall management of lung cancer.

Deployment of intelligent irrigation monitoring system with Android app for machine learning prediction.

Water is a fundamental necessity for humans and a critical resource in agriculture. However, water scarcity poses a significant challenge, especially considering that agriculture accounts for a substantial portion of freshwater usage. The inadequate monitoring resources in agriculture lead to unnecessary wastage of water, affecting crop growth and the water supply. This challenge has spurred us to focus on the agricultural domain, aiming to conserve water by imparting intelligence into irrigation systems by converging IoT and machine learning technologies. Our study has proposed a Smart Irrigation System (SIS), designed to operate remotely, leveraging open-source IoT platforms. Utilizing IoT and machine learning methodologies can effectively optimize water usage in irrigation practices. The designed system comprises hardware and software tools, where comprehensive data is monitored through an application interface. The sensor's interface with a 32-bit microcontroller is used to gather data such as environmental temperature, humidity, and soil moisture and temperature. The user (farmer) continuously receives real-time updates about the condition of the farmland through the Blynk app. The app triggers a notification advising the user to start or stop watering based on pre-set threshold values of soil moisture. Additionally, users can control the water pump remotely through the app. The data collected from the deployed smart irrigation system was used to train a machine learning algorithm incorporating weather parameters and soil temperature to predict soil moisture content. This trained model aims to offer guidance for future assessments of unknown soil samples based on the weather conditions.

Deep Learning Algorithms for Breast Cancer Detection in a UK Screening Cohort: As Stand-alone Readers and Combined with Human Readers.

Background Deep learning (DL) algorithms have shown promising results in mammographic screening either compared to a single reader or, when deployed in conjunction with a human reader, compared with double reading. Purpose To externally validate the performance of three DL algorithms as mammographic screen readers in an independent UK data set. Materials and Methods Three commercial DL algorithms (DL-1, DL-2, and DL-3) were retrospectively investigated from January 2022 to June 2022 using consecutive full-field digital mammograms collected at two UK sites during 1 year (2017). Normal cases with 3-year follow-up and histopathologically proven cancer cases detected either at screening (that round or next) or within the 3-year interval were included. A preset specificity threshold equivalent to a single reader was applied. Performance was evaluated for stand-alone DL reading compared with single human reading, and for DL reading combined with human reading compared with double reading, using sensitivity and specificity as the primary metrics. P < .025 was considered to indicate statistical significance for noninferiority testing. Results A total of 26 722 cases (median patient age, 59.0 years [IQR, 54.0-63.0 years]) with mammograms acquired using machines from two vendors were included. Cases included 332 screen-detected, 174 interval, and 254 next-round cancers. Two of three stand-alone DL algorithms achieved noninferior sensitivity (DL-1: 64.8%, P < .001; DL-2: 56.7%, P = .03; DL-3: 58.9%, P < .001) compared with the single first reader (62.8%), and specificity was noninferior for DL-1 (92.8%; P < .001) and DL-2 (96.8%; P < .001) and superior for DL-3 (97.9%; P < .001) compared with the single first reader (96.5%). Combining the DL algorithms with human readers achieved noninferior sensitivity (67.0%, 65.6%, and 65.4% for DL-1, DL-2, and DL-3, respectively; P < .001 for all) compared with double reading (67.4%), and superior specificity (97.4%, 97.6%, and 97.6%; P < .001 for all) compared with double reading (97.1%). Conclusion Use of stand-alone DL algorithms in combination with a human reader could maintain screening accuracy while reducing workload. Published under a CC BY 4.0 license. Supplemental material is available for this article.

A Method for Predicting the Remaining Service Life of Finite Data Products Based on Gaussian Stochastic Processes

There is a problem of poor predictive performance when predicting the remaining service life of products. Therefore, this paper proposes a finite data product remaining service life prediction method based on Gaussian stochastic processes. Analyze the types of product failure and degradation under limited data, and determine the factors affecting the degradation performance of product life through constant stress accelerated degradation tests, step stress accelerated degradation tests, and sequential stress accelerated aging tests; using the Wiener process to analyze the performance degradation characteristics of products, setting product failure thresholds, defining the remaining life of the product based on the degradation process, and using equal interval partitioning methods to determine the product health index, and clarifying the product failure process under limited data; by calculating the mathematical expected value, the numerical characteristics of the remaining life of the product are defined. Variance and moments are used to determine the predicted second-order central moment and origin moment. Based on the monotonic increasing characteristics of the inverse Gaussian process, the probability distribution of the random variable of product failure is determined after the Gaussian process. Under limited data, the actual working time of the product and the degradation amount at the time scale are clarified, and a preset threshold is set for the degradation amount. Build a residual life prediction model for product degradation and output the prediction results. The experimental results show that this method can accurately predict the remaining service life of the product and has good predictive performance.

Accuracy of Non-Invasive Imaging Techniques for the Diagnosis of MASH in Patients With MASLD: A Systematic Review.

Metabolic dysfunction-associated steatotic liver disease (MASLD) is a growing public health problem. The secondary stage in MASLD is steatohepatitis (MASH), the co-existence of steatosis and inflammation, a leading cause of progression to fibrosis and mortality. MASH resolution alone improves survival. Currently, MASH diagnosis is via liver biopsy. This study sought to evaluate the accuracy of imaging-based tests for MASH diagnosis, which offer a non-invasive method of diagnosis. Eight academic literature databases were searched and references of previous systematic reviews and included papers were checked for additional papers. Liver biopsy was used for reference standard. We report on 69 imaging-based studies. There were 31 studies on MRI, 27 on ultrasound, five on CT, 13 on transient elastography, eight on controlled attenuation parameter (CAP) and two on scintigraphy. The pathological definition of MASH was inconsistent, making it difficult to compare studies. 55/69 studies (79.71%) were deemed high-risk of bias as they had no preset thresholds and no validation. The two largest groups of imaging papers were on MRI and ultrasound. AUROCs were up to 0.93 for MRE, 0.90 for MRI, 1.0 for magnetic resonance spectroscopy (MRS) and 0.94 for ultrasound-based studies. Our study found that the most promising imaging tools are MRI techniques or ultrasound-based scores and confirmed there is potential to utilise these for MASH diagnosis. However, many publications are single studies without independent prospective validation. Without this, there is no clear imaging tool or score currently available that is reliably tested to diagnose MASH.

RGB‐based indices for estimating cover crop biomass, nitrogen content, and carbon:nitrogen ratio

AbstractPlant cover and biochemical composition are essential parameters for evaluating cover crop management. Destructive sampling or estimates with aerial imagery require substantial labor, time, expertise, or instrumentation cost. Using low‐cost consumer and mobile phone cameras to estimate plant canopy coverage and biochemical composition could broaden the use of high‐throughput technologies in research and crop management. Here, we estimated canopy development, tissue nitrogen, and biomass of medium red clover (Trifolium pratense L.), a perennial forage legume and common cover crop, using red‐green‐blue (RGB) indices collected with standard settings in non‐standardized field conditions. Pixels were classified as plant or background using combinations of four RGB indices with both unsupervised machine learning and preset thresholds. The excess green minus red (ExGR) index with a preset threshold of zero was the best index and threshold combination. It correctly identified pixels as plant or background 86.25% of the time. This combination also provided accurate estimates of crop growth and quality: Canopy coverage correlated with red clover biomass (R2 = 0.554, root mean square error [RMSE] = 219.29 kg ha−1), and ExGR index values of vegetation pixels were highly correlated with clover nitrogen content (R2 = 0.573, RMSE = 3.5 g kg−1) and carbon:nitrogen ratio (R2 = 0.574, RMSE = 1.29 g g−1). Data collection were simple to implement and stable across imaging conditions. Pending testing across different sensors, sites, and crop species, this method contributes to a growing and open set of decision support tools for agricultural research and management.

Polymyalgia rheumatica and giant cell arteritis: A bidirectional Mendelian randomization study.

Polymyalgia rheumatica (PMR) and giant cell arteritis (GCA) as 2 types of autoimmune diseases are frequently concomitant, and Mendelian randomization (MR) was applied in this study to assess the causal relationship between them. In this study, single-nucleotide polymorphism (SNP) was used as the instrumental variable for Mendelian analysis, and the SNP data of GCA and PMR were obtained from the FinnGen Biobank databases. SNPs are significantly correlated with GCA and PMR and were screened based on preset thresholds. Inverse variance weighted analysis was used as the main analysis, supplemented with MR-Egger and weighted median. The evidence of the impact of GCA on PMR risk was found in inverse variance weighted results (odds ratio, 1.22 [95% confidence interval, 1.11-1.34]; P < .01), and the evidence of the impact of PMR on GCA risk has also been found (odds ratio, 1.58 [95% confidence interval, 1.28-1.96]; P < .01). Finally, the stability and reliability of the results were tested using the retention method, heterogeneity test, and horizontal gene pleiotropy test. MR analysis indicates that GCA increases the risk of PMR and PMR is an important risk factor for GCA, with a causal relationship. The potential value of reasonable management of PMR in patients with GCA has received high attention. In addition, novel GCA therapeutics may be indicated for PMR, and it is a potential for further investigation.

Big Data-Based Optimized Deep Learning Model for Improving Performance of Electronics Health Care Data

Bigdata analytics is a new area of supervised analytics that healthcare analytics has moved into. Healthcare data is transmissive, incremental, and substantial, and it has pre-set thresholds for classifying patient conditions and diseases. The necessary understanding of disease occurrences is applied to the analysis of this data. The research project introduces healthcare data analytics with a novel framework that leverages unstructured data for the classification of healthy and unhealthy samples in order to understand the nature of healthy and unhealthy labelled classes. This is motivated by the fact that healthcare data is informative and voluminous in nature. Additionally, the unknown samples' health status is predicted using the supervised knowledge. Each model presented in this work is supported by accuracy and a computational complexity model.

A Mumford-Shah Model-based Method for Inpainting Markers in Ultrasound Images

Abstract During ultrasound diagnosis in clinics, clinicians often mark the lesion area, resulting in the presence of unnecessary objects in the collected ultrasound images. These markers potentially affect subsequent image analysis. To address this problem, we proposed an image inpainting method that combines image processing with Mumford-Shah algorithm to remove markers from ultrasound images. The proposed method consists of two parts. First, the input ultrasound images were processed by several image processing algorithms, including contrast enhancement, image binarization, edge detection, hole filling, and connected domain marking. These algorithms were combined to extract the mask of the manual marker in the ultrasound images. Second, the original ultrasound images and mask images were put into the Mumford-Shah model to implement ultrasound image inpainting by minimizing the following energy functional. The continuous iteration of Euler-Lagrange equation was employed to update the iteration item. If the difference between the two output results was less than the pre-set threshold, the output result could be regarded as the repaired ultrasound image. Experimental results show that the designed image processing method accurately extracted the binary mask, whether they are colourful or binary, number or line in ultrasound images. Meanwhile, the improved Mumford-Shah model effectively implemented the ultrasound image inpainting, with the accuracy of 96.55%. Therefore, the proposed method can be used to remove unnecessary objects in ultrasound images, which is beneficial to improve the accuracy of the artificial intelligence model.

A Real-Time Intelligent Valve Monitoring Approach through Cameras Based on Computer Vision Methods.

Abnormal valve positions can lead to fluctuations in the process industry, potentially triggering serious accidents. For processes that frequently require operational switching, such as green chemical processes based on renewable energy or biotechnological fermentation processes, this issue becomes even more severe. Despite this risk, many plants still rely on manual inspections to check valve status. The widespread use of cameras in large plants now makes it feasible to monitor valve positions through computer vision technology. This paper proposes a novel real-time valve monitoring approach based on computer vision to detect abnormalities in valve positions. Utilizing an improved network architecture based on YOLO V8, the method performs valve detection and feature recognition. To address the challenge of small, relatively fixed-position valves in the images, a coord attention module is introduced, embedding position information into the feature channels and enhancing the accuracy of valve rotation feature extraction. The valve position is then calculated using a rotation algorithm with the valve's center point and bounding box coordinates, triggering an alarm for valves that exceed a pre-set threshold. The accuracy and generalization ability of the proposed approach are evaluated through experiments on three different types of valves in two industrial scenarios. The results demonstrate that the method meets the accuracy and robustness standards required for real-time valve monitoring in industrial applications.

A Shared-Road-Rights Driving Strategy Based on Resolution Guidance for Right-of-Way Conflicts

In addressing the critical issue of right-of-way conflicts in mixed-traffic environments, this paper introduces a novel shared right-of-way driving strategy that encompasses two guiding frameworks for resolution. The first framework applies to active lane changing. Before lane changing occurs, this framework allocates the right of way for autonomous vehicles (AVs). Based on the allocated right of way, the AVs decide whether to send a request for a shared right of way to relevant vehicles. To enhance lane-changing comfort, the vehicle assesses whether the variance of roll and lateral acceleration exceeds a preset threshold, ultimately deciding whether to proceed with the lane change. The second framework pertains to passive lane changing. After detecting an obstacle, this framework allocates the right of way. The AVs calculate acceleration based on their speed and distance from the obstacle, using this information to determine whether to change lanes or decelerate in order to avoid the obstacle. If lane changing is chosen, further evaluation is necessary. Based on the allocated right of way, the AVs decide whether to request a shared right of way from relevant vehicles. To improve lane-changing comfort, the AVs compare the variance of roll and lateral acceleration with that of pitch and longitudinal acceleration, and then they decide whether to proceed with the lane change. The proposed strategy has been validated in various scenarios, including high-speed (105 km/h), low speed (13 km/h), and general scenarios with AVs and obstacles at a distance of 125 m. The results show that the strategy effectively functions in both high-speed and low-speed scenarios.

Research on Sintering Machine Axle Fault Detection Based on Wheel Swing Characteristics

During the sintering process in iron production, wheel swing is a sign of sintering machine trolley axle faults, which may lead to the wheel falling off and affect the production operation of the sintering machine system in serious cases. To solve this problem, this paper proposes a fault detection and localization method based on the You Only Look Once version 9 (YOLOv9) object detection algorithm and frame difference method for detecting sintering machine trolley wheel swing. The wheel images transmitted from the camera were sent to a trolley wheel and side panel number detection model that was trained on YOLOv9 for recognition. The wheel recognition boxes of the previous and subsequent frames were fused into the wheel region of interest. In the wheel region of interest, the difference operation was carried out. The result of the difference operation was compared with the preset threshold to determine whether the trolley wheel swings. When a wheel swing fault occurs, the image of the side plate at the time of the fault is collected, and the number on the side plate is identified so as to accurately locate the faulty trolley and to assist the field personnel in troubleshooting the fault. The experimental results show that this method can detect wheel swing faults in the industrial field, and the detection accuracy of wheel swing faults was 93.33%. The trolley side plate numbers’ average precision was 99.2% in fault localization. Utilizing the aforementioned method to construct a system for detecting wheel swing can provide technical support for fault detection of the trolley axle on the sintering machine.

Intelligent recognition of structural health state of EV lithium-ion Battery using transfer learning based on X-ray computed tomography

The lithium-ion battery (LIB) achieves wide applications on electric vehicles (EVs). The morphology of LIB electrode is highly correlated to the performance and safety of EV. Therefore, it is significant to monitor the structural health state of LIB to guarantee a reliable operation of EV. Currently, few research focused on the intelligent recognition of LIB structural health state. To bridge the gap, this paper proposes an image-based method to conduct structural health state recognition of LIB. The geometric deformation of LIB electrode is recorded by X-ray computed tomography (CT) images under different structure health state. Then a novel transfer learning network is incorporated to enhance the generalization ability of model. In the network, prior knowledge is first acquired from source domain data to initialize a convolutional autoencoder (CAE). Then the CAE is fine-tuned on CT images (target domain data), and a structural deviation index is established to reflect the structure health condition. Once the index exceeds the pre-set threshold, the alarm is triggered. The performance of the proposed method was evaluated on experimental data, and the results proved that the proposed method can perform structural health state monitoring effectively, and transfer learning can improve the generalization ability of detection model significantly.

BC-GAN: A threshold-free framework for unsupervised early fault detection in rotating machinery

Early fault detection (EFD) is a crucial component of proactive maintenance that can prevent expensive downtime, enhance safety, and optimize equipment performance and longevity. Existing limitations of the contemporary EFD approaches frequently include: (1) manually designed features relying on expert skills and knowledge, (2) the vaguely determined pre-set thresholds to distinguish between the faulty and healthy state of the testing object (however, the threshold value can vary notably from task to task), and (3) most methods, which have been originally designed for vibration data, cannot be generalised to other techniques, for example acoustic emission (AE) signals. To address these issues, a novel binary-classification generative adversarial network (BC-GAN) is designed for general EFD problems and applied to several specific datasets acquired from different run-to-failure tests of rotating components. Compared with conventional methods, unsupervised BC-GAN directly outputs the probability that an input belongs to either the “health” or “fault” state of the rotating machine without a priory threshold setting. Experimental results demonstrate the high versatility of the proposed network, which can be applied in various laboratory and industrial settings to both vibration and AE signals.

Design and Simulation of Intra-Row Obstacle Avoidance Shovel-Type Weeding Machine in Orchard

This paper presents the design of an intra-row obstacle avoidance shovel-type weeding machine. Theoretical analysis of intra-row weeding components guided the determination of the structures and parameters for key parts, including the signal acquisition mechanism, automatic obstacle avoidance mechanism, and weeding shovel. Furthermore, a hydraulic system was designed to support these functions. The design aims to optimize intra-row weeding operations, reduce labor costs, enhance weed control effectiveness, and prevent collisions between weeding equipment and grapevines. Through the construction of a mathematical model, the analysis determined the necessary minimum return speed of the hydraulic cylinder for the intra-row weeding shovel to avoid grapevines. We also established a reasonable range for the extension speed of the hydraulic cylinder to minimize areas missed during weeding. Further analysis showed that using the minimum return speed of the hydraulic cylinder effectively reduced missed weeding areas. A virtual prototype model of the weeding machine was created in ADAMS. Using the coverage rate of weeding operation as the evaluation index, single-factor simulation tests determined that the extension speed of the piston rod in the obstacle avoidance hydraulic cylinder and the forward speed of the weeding machine are the main influencing factors. The preset threshold of the control system, which triggered the automatic obstacle avoidance mechanism when the obstacle avoidance rod reached a specific angle (the “Angle Threshold”), was identified as a secondary influencing factor. Other factors were considered irrelevant. Hydraulic cylinder extension speed, weeding machine forward speed, and angle threshold were chosen as the influencing factors. Following the principles of a Box–Behnken experimental design, a quadratic regression combination experiment was designed using a three-factor, three-level response surface analysis method. The evaluation criterion focused on the coverage rate of weeding operation. A regression model was developed to determine the coverage rate of the weeding operation, identifying the optimal parameters as follows: obstacle avoidance hydraulic cylinder extension speed of 120 mm/s, forward speed of the weeding machine at 0.6 m/s, and an angle threshold of 18°. The optimized coverage rate of the weeding operation achieved 86.1%. This study serves as a reference for further optimization of intra-row weeding machines in vineyards and for other crops.

Research on fault line selection method based on steady state variables

When a single-phase ground fault occurs, the transient zero sequence current will significantly increase. So, it is possible to detect whether a single-phase grounding fault has occurred in the transmission line by calculating and comparing the amplitude of transient zero sequence current. Only when the amplitude of the zero sequence voltage under the steady-state power frequency is greater than the preset threshold can the line selection device be effectively and reliably started. The instantaneous value protection device can also be used to start first, and then, the steady-state amplitude of the power frequency can be compared as the verification object.

Satellite Image Cloud Automatic Annotator with Uncertainty Estimation

In satellite imagery, clouds obstruct the ground information, directly impacting various downstream applications. Thus, cloud annotation/cloud detection serves as the initial preprocessing step in remote sensing image analysis. Recently, deep learning methods have significantly improved in the field of cloud detection, but training these methods necessitates abundant annotated data, which requires experts with professional domain knowledge. Moreover, the influx of remote sensing data from new satellites has further led to an increase in the cost of cloud annotation. To address the dependence on labeled datasets and professional domain knowledge, this paper proposes an automatic cloud annotation method for satellite remote sensing images, CloudAUE. Unlike traditional approaches, CloudAUE does not rely on labeled training datasets and can be operated by users without domain expertise. To handle the irregular shapes of clouds, CloudAUE firstly employs a convex hull algorithm for selecting cloud and non-cloud regions by polygons. When selecting convex hulls, the cloud region is first selected, and points at the edges of the cloud region are sequentially selected as polygon vertices to form a polygon that includes the cloud region. Then, the same selection is performed on non-cloud regions. Subsequently, the fast KD-Tree algorithm is used for pixel classification. Finally, an uncertainty method is proposed to evaluate the quality of annotation. When the confidence value of the image exceeds a preset threshold, the annotation process terminates and achieves satisfactory results. When the value falls below the threshold, the image needs to undergo a subsequent round of annotation. Through experiments on two labeled datasets, HRC and Landsat 8, CloudAUE demonstrates comparable or superior accuracy to deep learning algorithms, and requires only one to two annotations to obtain ideal results. An unlabeled self-built Google Earth dataset is utilized to validate the effectiveness and generalizability of CloudAUE. To show the extension capabilities in various fields, CloudAUE also achieves desirable results on a forest fire dataset. Finally, some suggestions are provided to improve annotation performance and reduce the number of annotations.

Multiple time servers timed-release encryption based on Shamir secret sharing for EHR cloud system

Electronic health record (EHR) cloud system, as a primary tool driving the informatization of medical data, have positively impacted both doctors and patients by providing accurate and complete patient information. However, ensuring the security of EHR cloud system remains a critical issue. Some patients require regular remote medical services, and controlling access to medical data involving patient privacy during specific times is essential. Timed-release encryption (TRE) technology enables the sender to preset a future time T at which the data can be decrypted and accessed. It is a cryptographic primitive with time-dependent properties. Currently, mainstream TRE schemes are based on non-interactive single time server methods. However, if the single time server is attacked or corrupted, it is easy to directly threaten the security applications of TRE. Although some research schemes “distribute” the single time server into multiple ones, they still cannot resist the single point of failure problem. To address this issue, we propose a multiple time servers TRE scheme based on Shamir secret sharing and another variant derived from it. In our proposed schemes, the data receiver does not need to interact with the time servers; instead, they only need to obtain the time trapdoors that exceed or equal the preset threshold value for decryption, which ensures the identity privacy of the data sender and tolerates partial downtime or other failures of some time servers, significantly improving TRE reliability. Security analysis indicates that our proposed schemes demonstrate data confidentiality, verifiability, anti-advance decryption, and robust decryption with multiple time trapdoors, making them more practical. Efficiency analysis indicates that although our schemes have slightly higher computational costs than most efficient existing TRE schemes, such differences are insignificant from a practical application perspective.