Planning,monitoring and replanning techniques for handling abnormity in HTN-based planning and execution

A framework that integrates planning,monitoring and replanning techniques is proposed.It can devise the best solution based on the current state according to specific objectives and properly deal with the influence of abnormity on the plan execution.The framework consists of three parts:the hierarchical task network(HTN)planner based on Monte Carlo tree search(MCTS),hybrid plan monitoring based on forward and backward and norm-based replanning method selection.The HTN planner based on MCTS selects the optimal method for HTN compound task through pre-exploration.Based on specific objectives,it can identify the best solution to the current problem.The hybrid plan monitoring has the capability to detect the influence of abnormity on the effect of an executed action and the premise of an unexecuted action,thus trigger the replanning.The norm-based replanning selection method can measure the difference between the expected state and the actual state,and then select the best replanning algorithm.The experimental results reveal that our method can effectively deal with the influence of abnormity on the implementation of the plan and achieve the target task in an optimal way.

Manganese Abnormity in Holocene Sediments of the Bohai Sea

Manganese abnormity has been observed in the Holocene sediments of the mud area of Bohai Sea. On the basis of grain size, chemical composition, heavy mineral content and accelerator mass spectrometry （AMS） 14C dating of foraminifer, relationships between manganese abnormity and sedimentation rates, material source, hydrodynamic conditions are probed. Manganese abnormity occurred during the Middle Holocene when sea level and sedimentation rates were higher than those at present. Sedimentary hiatus was not observed when material sources and hydrodynamic conditions were quite similar. Compared with the former period, the latter period showed a decrease in reduction environment and an inclination toward oxidation environment with high manganese content, whereas provenance and hydrodynamic conditions showed only a slight change. From the above observations, it can be concluded that correlation among manganese abnormity, material source, and hydrodynamic conditions is not obvious. Redox environment seems to be the key factor for manganese enrichment, which is mainly related to marine authigenic process.

Electromagnetic Abnormity Recorded by Borehole TOA Installment during the Mojiang M_S5. 9 Earthquake on September 8,2018

As an achievement of the cooperation with Japan,TOA electromagnetic observation station was established with an 800 m borehole antenna and put into service in 1992 in Dali,Yunnan province,China.Li Wuxian et al.(2003)summarized main anomalous variation characters by analyzing 23 strong earthquakes with magnitudes more than 5.0 recorded in the first ten years.This work mainly presents the electromagnetic changes prior to the last Mojiang MS5.9 earthquake on September 8,2018.First of all,the initial weak signals appeared in two ULF channels out of three observing channels(CH10.01-0.10 Hz,CH20.1-1.0 Hz and CH31-9 kHz)on May 30,2018 at Dali TOA electromagnetic station.The information recorded was characterized by wave-like changes with magnitudes of ACH1≤0.26 mV in CH1 and pulse-like impulses of ACH2≤0.6 mV in CH2,respectively.Then,abnormal information gradually enhanced either in magnitudes or in occurrence frequency.Pulse-like signals were full of lattices of recording paper for CH2 during June24-25 and slopped over the recording paper during June 28-29,with the magnitudes being greater than or equal to 10 mV.At the same time,the clear wave-like signals also appeared in CH1 with a maximum magnitude of^0.6 mV on June 28 and reached its climax.From then on,the information started to decrease from the end of July and only weak signals occasionally occurred till the end of August 2018,when obvious anomaly was recorded again in two ULF channels with maximum magnitudes of ACH1~0.2 mV and ACH2~0.3 mV respectively.Generally,these signals did not appear continuously but group by group and accumulated intensively only in ULF band instead of VLF band during the total period.10 days later,the Mojiang MS5.9 earthquake occurred on September 8,2018,300 km away from Dali TOA station,and a coseismic response was also recorded at this time.Thus,these ULF electromagnetic abnormities could be probably attributed to the Mojiang event.

Electromagnetic Abnormity Observed at Sujiatun Seismic Station and Its Relation toEarthquake

The Sujiatun seismic station is a local professional seismic observation station in the city of Shenyang, Liaoning province. Electromagnetic radiations observation apparatus, of the type EMAOS-L, are used there. In this paper, four years observation data and observed earthquakes with M_S≥4.0 were collected in the Sujiatun observation station. The characteristics of electromagnetic radiation abnormities and earthquakes are analyzed from such aspects as capabilities of the apparatus used, tectonic structure, origins of electromagnetic radiations and so on. By analysis, precursor abnormities observed at this observation station are remarkable. The electric and magnetic abnormities are with good synchronism and the abnormities can respond better to the earthquakes with the epicenter distance being less than 20km and taking place in the upper crust. At the same time, for earthquakes with large magnitudes, the variation of precursor abnormities shows a periodic diurnal variation.

融合IMR-WGAN的时序数据修复方法

工业数据由于技术故障和人为因素通常导致数据异常,现有基于约束的方法因约束阈值设置的过于宽松或严格会导致修复错误,基于统计的方法因平滑修复机制导致对时间步长较远的异常值修复准确度较低.针对上述问题,提出了基于奖励机制的最小迭代修复和改进WGAN混合模型的时序数据修复方法.首先,在预处理阶段,保留异常数据,进行信息标注等处理,从而充分挖掘异常值与真实值之间的特征约束.其次,在噪声模块提出了近邻参数裁剪规则,用于修正最小迭代修复公式生成的噪声向量.将其传递至模拟分布模块的生成器中,同时设计了一个动态时间注意力网络层,用于提取时序特征权重并与门控循环单元串联组合捕捉不同步长的特征依赖,并引入递归多步预测原理共同提升模型的表达能力;在判别器中设计了Abnormal and Truth奖励机制和Weighted Mean Square Error损失函数共同反向优化生成器修复数据的细节和质量.最后,在公开数据集和真实数据集上的实验结果表明,该方法的修复准确度与模型稳定性显著优于现有方法.

Comparison of efficacy of treating obese patients with endocrine-metabolic abnormity by electroacupuncture of different types of wave modes

Objective To compare the efficacy of treating obese patients with abnormity of lipids and serum leptin by dilatational wave or continuous wave of electroacupuncture combined with thunder-fire moxibustion in order to provide a clinical basis for selecting wave types of electroacupuncture for different patterns of obesity. Methods Sixty obese patients with abnormal lipids and serum leptin were randomly divided into a dilatational wave group and a continuous wave group via random number table, with 30 cases in each group. They were divided by TCM differentiation into three types： stomachintestine excessive heat, weakness of the spleen-stomach and spleen-kidney yang deficiency, treated by electroacupuncture on Tianshu （天枢 ST 25）, Daheng （大横 SP 15）, Zusanli （足三里ST 36）, Shangjuxu （上巨虚 ST 37）, Fanglong （丰隆 ST 40）, Yinlingquan （阴陵泉 SP 9）, Quchi （曲池 LI 11）, Zhigou （支沟 TE 6） and Hegu （合谷 LI 4） along with thunder-fire moxibustion. The frequency of electro-acupuncture in the dilatational wave group and the continuous wave group was 2 Hz/100 Hz and 2 Hz, respectively. Patients in the two groups were treated once a day, six times a week. The treatment lasted for 4 weeks with 3-month follow-up. Body mass and body fat percentage before and after the treatment, as well as during the follow-up, were compared. The effectiveness rates in the two groups were compared, and the efficacy statistics of patients with different TCM patterns in the dilatational wave group were also analyzed. Lipid levels of the patients in two groups before and after the treatment were measured with an automatic biochemical analyzer, and serum leptin levels were detected with flow cytometry system. Results After the treatment, the patients＇ blood lipids, serum leptin levels, body mass and body fat percentage were effectively reduced in the two groups; three months＇ follow-up witnessed continuous decline of obesity indicators （P〈0.01 or P〈0.05）, and patients in the dilatat-ional wave group improved more significantly than those in continuous wave group （P〈0.05 or P〈0.01）. The efficacy in the dilatational wave group was superior to that in the continuous wave group （P〈0.01）. The best efficacy could be found among patients with weakness of the spleen and the stomach in the dilatational wave group. Conclusion Efficacy of treating obese patients with abnormity of lipids and serum leptin by electro-acupuncture combined with thunder-fire moxibustion in the dilatational wave group was significantly better than that of the continuous wave group, and efficacy for obese patients with weakness of the spleen and the stomach was superior to that of those with stomach-intestine excessive heat and spleen-kidney yang deficiency.

Integrated ribosome and proteome analyses reveal insights into sevoflurane-induced long-term social behavior and cognitive dysfunctions through ADNP inhibition in neonatal mice

A growing number of studies have demonstrated that repeated exposure to sevoflurane during development results in persistent social abnormalities and cognitive impairment.Davunetide,an active fragment of the activity-dependent neuroprotective protein(ADNP),has been implicated in social and cognitive protection.However,the potential of davunetide to attenuate social deficits following sevoflurane exposure and the underlying developmental mechanisms remain poorly understood.In this study,ribosome and proteome profiles were analyzed to investigate the molecular basis of sevoflurane-induced social deficits in neonatal mice.The neuropathological basis was also explored using Golgi staining,morphological analysis,western blotting,electrophysiological analysis,and behavioral analysis.Results indicated that ADNP was significantly down-regulated following developmental exposure to sevoflurane.In adulthood,anterior cingulate cortex(ACC)neurons exposed to sevoflurane exhibited a decrease in dendrite number,total dendrite length,and spine density.Furthermore,the expression levels of Homer,PSD95,synaptophysin,and vglut2 were significantly reduced in the sevoflurane group.Patch-clamp recordings indicated reductions in both the frequency and amplitude of miniature excitatory postsynaptic currents(mEPSCs).Notably,davunetide significantly ameliorated the synaptic defects,social behavior deficits,and cognitive impairments induced by sevoflurane.Mechanistic analysis revealed that loss of ADNP led to dysregulation of Ca^(2+)activity via the Wnt/β-catenin signaling,resulting in decreased expression of synaptic proteins.Suppression of Wnt signaling was restored in the davunetide-treated group.Thus,ADNP was identified as a promising therapeutic target for the prevention and treatment of neurodevelopmental toxicity caused by general anesthetics.This study provides important insights into the mechanisms underlying social and cognitive disturbances caused by sevoflurane exposure in neonatal mice and elucidates the regulatory pathways involved.

Improving Federated Learning through Abnormal Client Detection and Incentive

Data sharing and privacy protection are made possible by federated learning,which allows for continuous model parameter sharing between several clients and a central server.Multiple reliable and high-quality clients must participate in practical applications for the federated learning global model to be accurate,but because the clients are independent,the central server cannot fully control their behavior.The central server has no way of knowing the correctness of the model parameters provided by each client in this round,so clients may purposefully or unwittingly submit anomalous data,leading to abnormal behavior,such as becoming malicious attackers or defective clients.To reduce their negative consequences,it is crucial to quickly detect these abnormalities and incentivize them.In this paper,we propose a Federated Learning framework for Detecting and Incentivizing Abnormal Clients(FL-DIAC)to accomplish efficient and security federated learning.We build a detector that introduces an auto-encoder for anomaly detection and use it to perform anomaly identification and prevent the involvement of abnormal clients,in particular for the anomaly client detection problem.Among them,before the model parameters are input to the detector,we propose a Fourier transform-based anomaly data detectionmethod for dimensionality reduction in order to reduce the computational complexity.Additionally,we create a credit scorebased incentive structure to encourage clients to participate in training in order tomake clients actively participate.Three training models(CNN,MLP,and ResNet-18)and three datasets(MNIST,Fashion MNIST,and CIFAR-10)have been used in experiments.According to theoretical analysis and experimental findings,the FL-DIAC is superior to other federated learning schemes of the same type in terms of effectiveness.

Combinatorial reasoning-based abnormal sensor recognition method for subsea production control system

The subsea production system is a vital equipment for offshore oil and gas production.The control system is one of the most important parts of it.Collecting and processing the signals of subsea sensors is the only way to judge whether the subsea production control system is normal.However,subsea sensors degrade rapidly due to harsh working environments and long service time.This leads to frequent false alarm incidents.A combinatorial reasoning-based abnormal sensor recognition method for subsea production control system is proposed.A combinatorial algorithm is proposed to group sensors.The long short-term memory network(LSTM)is used to establish a single inference model.A counting-based judging method is proposed to identify abnormal sensors.Field data from an offshore platform in the South China Sea is used to demonstrate the effect of the proposed method.The results show that the proposed method can identify the abnormal sensors effectively.

Abnormal State Detection in Lithium-ion Battery Using Dynamic Frequency Memory and Correlation Attention LSTM Autoencoder

This paper addresses the challenge of identifying abnormal states in Lithium-ion Battery(LiB)time series data.As the energy sector increasingly focuses on integrating distributed energy resources,Virtual Power Plants(VPP)have become a vital new framework for energy management.LiBs are key in this context,owing to their high-efficiency energy storage capabilities essential for VPP operations.However,LiBs are prone to various abnormal states like overcharging,over-discharging,and internal short circuits,which impede power transmission efficiency.Traditional methods for detecting such abnormalities in LiB are too broad and lack precision for the dynamic and irregular nature of LiB data.In response,we introduce an innovative method:a Long Short-Term Memory(LSTM)autoencoder based on Dynamic Frequency Memory and Correlation Attention(DFMCA-LSTM-AE).This unsupervised,end-to-end approach is specifically designed for dynamically monitoring abnormal states in LiB data.The method starts with a Dynamic Frequency Fourier Transform module,which dynamically captures the frequency characteristics of time series data across three scales,incorporating a memory mechanism to reduce overgeneralization of abnormal frequencies.This is followed by integrating LSTM into both the encoder and decoder,enabling the model to effectively encode and decode the temporal relationships in the time series.Empirical tests on a real-world LiB dataset demonstrate that DFMCA-LSTM-AE outperforms existing models,achieving an average Area Under the Curve(AUC)of 90.73%and an F1 score of 83.83%.These results mark significant improvements over existing models,ranging from 2.4%–45.3%for AUC and 1.6%–28.9%for F1 score,showcasing the model’s enhanced accuracy and reliability in detecting abnormal states in LiB data.

First record of abnormal body coloration in a rockfish Sebastes koreanus(Scorpaenoidei:Sebastidae)from coastal water of China based on morphological characteristics and DNA barcoding

The first record of abnormal body coloration in Sebastes koreanus Kim and Lee,1994,from the Yellow Sea of China,was documented based on morphological characteristics and DNA barcoding.The two rockfish specimens were collected from the coastal waters of Qingdao,China,and the whole body and all fins of them were red.Of the two red-colored rockfish,there were tiny deep red spots on each fin,2 red radial stripes behind and below the eyes and 1 large deep red blotch on the opercula,while the similar stripe and spot patterns are also present in the S.koreanus specimens with normal body coloration.The countable characteristics of the two specimens are in the range of the morphometry of S.koreanus.To further clarify the species identity and taxonomic status of the two specimens,DNA barcode analysis was carried out.The genetic distance between the red-colored rockfish and S.koreanus was 0,and the minimum net genetic distances between the red-colored rockfish and other Sebastes species except for S.koreanus were 3.0%,which exceeds the threshold of species delimitation.The phylogenetic analysis showed that the DNA barcoding sequences of the two red-colored rockfish clustered with the S.koreanus sequences.The above results of DNA barcode analysis also support that the two red-colored rockfish could be identified as the species of S.koreanus.The mechanism of color variation in S.koreanus is desirable for further research and the species could be an ideal model to study the color-driven speciation of the rockfishes.

Abnormal Traffic Detection for Internet of Things Based on an Improved Residual Network

Along with the progression of Internet of Things(IoT)technology,network terminals are becoming continuously more intelligent.IoT has been widely applied in various scenarios,including urban infrastructure,transportation,industry,personal life,and other socio-economic fields.The introduction of deep learning has brought new security challenges,like an increment in abnormal traffic,which threatens network security.Insufficient feature extraction leads to less accurate classification results.In abnormal traffic detection,the data of network traffic is high-dimensional and complex.This data not only increases the computational burden of model training but also makes information extraction more difficult.To address these issues,this paper proposes an MD-MRD-ResNeXt model for abnormal network traffic detection.To fully utilize the multi-scale information in network traffic,a Multi-scale Dilated feature extraction(MD)block is introduced.This module can effectively understand and process information at various scales and uses dilated convolution technology to significantly broaden the model’s receptive field.The proposed Max-feature-map Residual with Dual-channel pooling(MRD)block integrates the maximum feature map with the residual block.This module ensures the model focuses on key information,thereby optimizing computational efficiency and reducing unnecessary information redundancy.Experimental results show that compared to the latest methods,the proposed abnormal traffic detection model improves accuracy by about 2%.

Fortifying Smart Grids: A Holistic Assessment Strategy against Cyber Attacks and Physical Threats for Intelligent Electronic Devices

Intelligent electronic devices(IEDs)are interconnected via communication networks and play pivotal roles in transmitting grid-related operational data and executing control instructions.In the context of the heightened security challenges within smart grids,IEDs pose significant risks due to inherent hardware and software vulner-abilities,as well as the openness and vulnerability of communication protocols.Smart grid security,distinct from traditional internet security,mainly relies on monitoring network security events at the platform layer,lacking an effective assessment mechanism for IEDs.Hence,we incorporate considerations for both cyber-attacks and physical faults,presenting security assessment indicators and methods specifically tailored for IEDs.Initially,we outline the security monitoring technology for IEDs,considering the necessary data sources for their security assessment.Subsequently,we classify IEDs and establish a comprehensive security monitoring index system,incorporating factors such as running states,network traffic,and abnormal behaviors.This index system contains 18 indicators in 3 categories.Additionally,we elucidate quantitative methods for various indicators and propose a hybrid security assessment method known as GRCW-hybrid,combining grey relational analysis(GRA),analytic hierarchy process(AHP),and entropy weight method(EWM).According to the proposed assessment method,the security risk level of IEDs can be graded into 6 levels,namely 0,1,2,3,4,and 5.The higher the level,the greater the security risk.Finally,we assess and simulate 15 scenarios in 3 categories,which are based on monitoring indicators and real-world situations encountered by IEDs.The results show that calculated security risk level based on the proposed assessment method are consistent with actual simulation.Thus,the reasonableness and effectiveness of the proposed index system and assessment method are validated.

Vehicle Abnormal Behavior Detection Based on Dense Block and Soft Thresholding

With the rapid advancement of social economies,intelligent transportation systems are gaining increasing atten-tion.Central to these systems is the detection of abnormal vehicle behavior,which remains a critical challenge due to the complexity of urban roadways and the variability of external conditions.Current research on detecting abnormal traffic behaviors is still nascent,with significant room for improvement in recognition accuracy.To address this,this research has developed a new model for recognizing abnormal traffic behaviors.This model employs the R3D network as its core architecture,incorporating a dense block to facilitate feature reuse.This approach not only enhances performance with fewer parameters and reduced computational demands but also allows for the acquisition of new features while simplifying the overall network structure.Additionally,this research integrates a self-attentive method that dynamically adjusts to the prevailing traffic conditions,optimizing the relevance of features for the task at hand.For temporal analysis,a Bi-LSTM layer is utilized to extract and learn from time-based data nuances.This research conducted a series of comparative experiments using the UCF-Crime dataset,achieving a notable accuracy of 89.30%on our test set.Our results demonstrate that our model not only operates with fewer parameters but also achieves superior recognition accuracy compared to previous models.

Predictors of Adverse Pregnancy Outcomes Following Traumatic Injuries

Objective After traumatic injury in pregnant women,providing timely and appropriate management for high-risk patients is crucial for both pregnant women and fetuses.This study aimed to identify risk factors that predict adverse pregnancy outcomes after traumatic injury.Methods A retrospective cohort study including 317 pregnant patients who experienced trauma was conducted.The collected data included general demographics,injury mechanisms and adverse pregnancy outcomes.Patients were divided into two subgroups based on the absence or presence of trauma-related adverse pregnancy outcomes.Univariate and multivariate logistic regressions were conducted to estimate the associations between clinical variables and adverse pregnancy outcomes.Results A total of 41(12.93%)patients experienced adverse pregnancy outcomes within the first 24 h post-trauma.This study revealed that age>35 years(OR=14.995,95%CI:5.024–44.755,P<0.001),third trimester trauma(OR=3.878,95%CI:1.343–11.204,P=0.012),abdominal pain(OR=3.032,95%CI:1.221–7.527,P=0.017),vaginal bleeding(OR=3.226,95%CI:1.093–9.523,P=0.034),positive scan in focused assessment with sonography for trauma(FAST)positive(OR=8.496,95%CI:2.825–25.555,P<0.001),9≤injury severity score(ISS)<16(OR=3.039,95%CI:1.046–8.835,P=0.041)and ISS≥16(OR=5.553,95%CI:1.387–22.225,P=0.015)increased the probability of posttraumatic adverse pregnancy outcomes.Maternal age,gestational age at delivery,vaginal bleeding and positive FAST results were risk factors for abnormal delivery.Conclusion Advanced maternal age,third trimester,and positive FAST results should alert multidisciplinary trauma teams to closely monitor patients to prevent adverse pregnancy outcomes.

Abnormal Action Detection Based on Parameter-Efficient Transfer Learning in Laboratory Scenarios

Laboratory safety is a critical area of broad societal concern,particularly in the detection of abnormal actions.To enhance the efficiency and accuracy of detecting such actions,this paper introduces a novel method called TubeRAPT(Tubelet Transformer based onAdapter and Prefix TrainingModule).Thismethod primarily comprises three key components:the TubeR network,an adaptive clustering attention mechanism,and a prefix training module.These components work in synergy to address the challenge of knowledge preservation in models pretrained on large datasets while maintaining training efficiency.The TubeR network serves as the backbone for spatio-temporal feature extraction,while the adaptive clustering attention mechanism refines the focus on relevant information.The prefix training module facilitates efficient fine-tuning and knowledge transfer.Experimental results demonstrate the effectiveness of TubeRAPT,achieving a 68.44%mean Average Precision(mAP)on the CLA(Crazy LabActivity)small-scale dataset,marking a significant improvement of 1.53%over the previous TubeR method.This research not only showcases the potential applications of TubeRAPT in the field of abnormal action detection but also offers innovative ideas and technical support for the future development of laboratory safety monitoring technologies.The proposed method has implications for improving safety management systems in various laboratory environments,potentially reducing accidents and enhancing overall workplace safety.

Relationship of Retinal Nerve Fiber Layer Thickness and Retinal Vessel Calibers with Cognitive Impairment in the Asymptomatic Polyvascular Abnormalities Population

Objective Cognitive impairment(CI)in older individuals has a high morbidity rate worldwide,with poor diagnostic methods and susceptible population identification.This study aimed to investigate the relationship between different retinal metrics and CI in a particular population,emphasizing polyvascular status.Methods We collected information from the Asymptomatic Polyvascular Abnormalities Community Study on retinal vessel calibers,retinal nerve fiber layer(RNFL)thickness,and cognitive function of 3,785participants,aged 40 years or older.Logistic regression was used to analyze the relationship between retinal metrics and cognitive function.Subgroups stratified by different vascular statuses were also analyzed.Results RNFL thickness was significantly thinner in the CI group(odds ratio:0.973,95%confidence interval:0.953–0.994).In the subgroup analysis,the difference still existed in the non-intracranial arterial stenosis,non-extracranial carotid arterial stenosis,and peripheral arterial disease subgroups(P<0.05).Conclusion A thin RNFL is associated with CI,especially in people with non-large vessel stenosis.The underlying small vessel change in RNFL and CI should be investigated in the future.

A method for cleaning wind power anomaly data by combining image processing with community detection algorithms

Current methodologies for cleaning wind power anomaly data exhibit limited capabilities in identifying abnormal data within extensive datasets and struggle to accommodate the considerable variability and intricacy of wind farm data.Consequently,a method for cleaning wind power anomaly data by combining image processing with community detection algorithms(CWPAD-IPCDA)is proposed.To precisely identify and initially clean anomalous data,wind power curve(WPC)images are converted into graph structures,which employ the Louvain community recognition algorithm and graph-theoretic methods for community detection and segmentation.Furthermore,the mathematical morphology operation(MMO)determines the main part of the initially cleaned wind power curve images and maps them back to the normal wind power points to complete the final cleaning.The CWPAD-IPCDA method was applied to clean datasets from 25 wind turbines(WTs)in two wind farms in northwest China to validate its feasibility.A comparison was conducted using density-based spatial clustering of applications with noise(DBSCAN)algorithm,an improved isolation forest algorithm,and an image-based(IB)algorithm.The experimental results demonstrate that the CWPAD-IPCDA method surpasses the other three algorithms,achieving an approximately 7.23%higher average data cleaning rate.The mean value of the sum of the squared errors(SSE)of the dataset after cleaning is approximately 6.887 lower than that of the other algorithms.Moreover,the mean of overall accuracy,as measured by the F1-score,exceeds that of the other methods by approximately 10.49%;this indicates that the CWPAD-IPCDA method is more conducive to improving the accuracy and reliability of wind power curve modeling and wind farm power forecasting.

Abnormal Action Recognition with Lightweight Pose Estimation Network in Electric Power Training Scene

Electric power training is essential for ensuring the safety and reliability of the system.In this study,we introduce a novel Abnormal Action Recognition(AAR)system that utilizes a Lightweight Pose Estimation Network(LPEN)to efficiently and effectively detect abnormal fall-down and trespass incidents in electric power training scenarios.The LPEN network,comprising three stages—MobileNet,Initial Stage,and Refinement Stage—is employed to swiftly extract image features,detect human key points,and refine them for accurate analysis.Subsequently,a Pose-aware Action Analysis Module(PAAM)captures the positional coordinates of human skeletal points in each frame.Finally,an Abnormal Action Inference Module(AAIM)evaluates whether abnormal fall-down or unauthorized trespass behavior is occurring.For fall-down recognition,three criteria—falling speed,main angles of skeletal points,and the person’s bounding box—are considered.To identify unauthorized trespass,emphasis is placed on the position of the ankles.Extensive experiments validate the effectiveness and efficiency of the proposed system in ensuring the safety and reliability of electric power training.

Rice AGL1 determines grain size and sterile lemma identity

The grass spikelet is a unique inflorescence structure that determines grain size.Although many genetic factors have been well characterized for grain size and glume development,the underlying molecular mechanisms in rice are far from established.Here,we isolated rice gene,AGL1 that controlled grain size and determines the fate of the sterile lemma.Loss of function of AGL1 produced larger grains and reduced the size of the sterile lemma.Larger grains in the agl1 mutant were caused by a larger number of cells that were longer and wider than in the wild type.The sterile lemma in the mutant spikelet was converted to a rudimentary glume-like organ.Our findings showed that the AGL1(also named LAX1)protein positively regulated G1 expression,and negatively regulated NSG1 expression,thereby affecting the fate of the sterile lemma.Taken together,our results revealed that AGL1 played a key role in negative regulation of grain size by controlling cell proliferation and expansion,and supported the opinion that rudimentary glume and sterile lemma in rice are homologous organs.