Entropy-Based Approach to Remove Redundant Monitoring Wells from Regional-Scale Groundwater Network

An entropy based approach is applied to identify redundant wells in the network. In the process of this research, groundwater monitoring network is considered as a communication system with a capability to transfer information, and monitoring wells are taken as information receivers. The concepts of entropy and mutual information are then applied to measure the information content of individual monitoring well and information relationship between monitoring well pairs. The efficiency of information transfer among monitoring wells is the basis to judge the redundancy in the network. And the capacity of the monitoring wells to provide information on groundwater is the point of evaluation to identify redundant monitoring wells. This approach is demonstrated using the data from a regional scale groundwater network in Hebei plain, China. The result shows that the entropy based method is recommendable in optimizing groundwater networks, especially for those within media of higher heterogeneities and anisotropies.

Application of GNSS-PPP on Dynamic Deformation Monitoring of Offshore Platforms

The real-time dynamic deformation monitoring of offshore platforms under environmental excitation is crucial to their safe operation.Although Global Navigation Satellite System-Precise Point Positioning(GNSS-PPP)has been considered for this purpose,its monitoring accuracy is relatively low.Moreover,the influence of background noise on the dynamic monitoring accuracy of GNSS-PPP remains unclear.Hence,it is imperative to further validate the feasibility of GNSS-PPP for deformation monitoring of offshore platforms.To address these concerns,vibration table tests with different amplitudes and frequencies are conducted.The results demonstrate that GNSS-PPP can effectively monitor horizontal vibration displacement as low as±30 mm,which is consistent with GNSS-RTK.Furthermore,the spectral characteristic of background noise in GNSS-PPP is similar to that of GNSS-RTK(Real Time Kinematic).Building on this observation,an improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise(CEEMDAN)has been proposed to de-noise the data and enhance the dynamic monitoring accuracy of GNSS-PPP.Field monitoring application research is also undertaken,successfully extracting and analyzing the dynamic deformation of an offshore platform structure under environmental excitation using GNSS-PPP monitoring in conjunction with improved CEEMDAN de-noising.By comparing the de-noised dynamic deformation trajectories of the offshore platform during different periods,it is observed that the platform exhibits reversible alternating vibration responses under environmental excitation,with more pronounced displacement deformation in the direction of load action.The research results confirm the feasibility and potential of GNSS-PPP for dynamic deformation monitoring of offshore platforms.

An Auxiliary Monitoring Method for Well Killing Based on Statistical Data

In the present study,a large set of data related to well killing is considered.Through a complete exploration of the whole process leading to well-killing,various factors affecting such a process are screened and sorted,and a correlation model is built accordingly in order to introduce an auxiliary method for well-killing monitoring based on statistical information.The available data show obvious differences due to the diverse control parameters related to different well-killing methods.Nevertheless,it is shown that a precise three-fold relationship exists between the reservoir parameters,the elapsed time and the effectiveness of the considered well-killing strategy.The proposed monitoring auxiliary method is intended to support risk assessment and optimization in the context of typical well-killing applications.

Push forward LC-MS-based therapeutic drug monitoring and pharmacometabolomics for anti-tuberculosis precision dosing and comprehensive clinical management

The spread of tuberculosis(TB),especially multidrug-resistant TB and extensively drug-resistant TB,has strongly motivated the research and development of new anti-TB drugs.New strategies to facilitate drug combinations,including pharmacokinetics-guided dose optimization and toxicology studies of first-and second-line anti-TB drugs have also been introduced and recommended.Liquid chromatography-mass spectrometry(LC-MS)has arguably become the gold standard in the analysis of both endo-and exo-genous compounds.This technique has been applied successfully not only for therapeutic drug monitoring(TDM)but also for pharmacometabolomics analysis.TDM improves the effectiveness of treatment,reduces adverse drug reactions,and the likelihood of drug resistance development in TB patients by determining dosage regimens that produce concentrations within the therapeutic target window.Based on TDM,the dose would be optimized individually to achieve favorable outcomes.Pharmacometabolomics is essential in generating and validating hypotheses regarding the metabolism of anti-TB drugs,aiding in the discovery of potential biomarkers for TB diagnostics,treatment monitoring,and outcome evaluation.This article highlighted the current progresses in TDM of anti-TB drugs based on LC-MS bioassay in the last two decades.Besides,we discussed the advantages and disadvantages of this technique in practical use.The pressing need for non-invasive sampling approaches and stability studies of anti-TB drugs was highlighted.Lastly,we provided perspectives on the prospects of combining LC-MS-based TDM and pharmacometabolomics with other advanced strategies(pharmacometrics,drug and vaccine developments,machine learning/artificial intelligence,among others)to encapsulate in an all-inclusive approach to improve treatment outcomes of TB patients.

Long-term hydrochemical monitoring and geothermometry:understanding groundwater salinization and thermal fluid contamination in Mila’s basin,Northeastern Algeria

The regular hydrochemical monitoring of groundwater in the Mila basin over an extended period has provided valuable insights into the origin of dissolved salts and the hydrogeochemical processes controlling water salinization.The data reveals that the shallow Karst aquifer shows an increase in TDS of 162 mg L^(-1) while the ther-mal carbonate aquifer that is also used for drinking water supply exhibits an increase of 178 mg L^(-1).Additionally,significant temperature variations are recorded at the sur-face in the shallow aquifers and the waters are carbo-gaseous.Analysis of dissolved major and minor elements has identified several processes influencing the chemical composition namely:dissolution of evaporitic minerals,reduction of sulphates,congruent and incongruent car-bonates’dissolution,dedolomitization and silicates’weathering.The hydrogeochemical and geothermometric results show a mixing of saline thermal water with recharge water of meteoric origin.Two main geothermalfields have been identified,a partially evolved water reservoir and a water reservoir whosefluid interacts with sulphuric acid(H_(2)S)of magmatic origin.These hot waters that are char-acterized by a strong hydrothermal alteration do ascend through faults and fractures and contribute to the contamination of shallower aquifers.Understanding the geothermometry and the hydrogeochemistry of waters is crucial for managing and protecting the quality of groundwater resources in the Mila basin,in order to ensure sustainable water supply for the region.A conceptual model for groundwater circulation and mineralization acquisition has been established to further enhance under-standing in this regard.

An improved typhoon monitoring model based on precipitable water vapor and pressure

The potential of monitoring the movement of typhoons using the precipitable water vapor(PWV) has been confirmed. However, monitoring the movement of typhoon is focused on PWV, making it difficult to describe the movement of a typhoon in detail minutely and resulting in insufficient accuracy. Hence,based on PWV and meteorological data, we propose an improved typhoon monitoring mode. First, the European Centre for Medium-Range Weather Forecasts Reanalysis 5-derived PWV(ERA5-PWV) and the Global Navigation Satellite System-derived PWV(GNSS-PWV) were compared with the reference radiosonde PWV(RS-PWV). Then, using the PWV and atmospheric parameters derived from ERA5, we discussed the anomalous variations of PWV, pressure(P), precipitation, and wind speed during different typhoons. Finally, we compiled a list of critical factors related to typhoon movement, PWV and P. We developed an improved multi-factor typhoon monitoring mode(IMTM) with different models(i.e.,IMTM-I and IMTM-II) in different cases with a higher density of GNSS observation or only Numerical Weather Prediction(NWP) data. The IMTM was evaluated through the reference movement speeds of HATO and Mangkhut from the China Meteorological Observatory Typhoon Network(CMOTN). The results show that the root mean square(RMS) of the IMTM-I is 1.26 km/h based on ERA5-P and ERA5-PWV,and the absolute bias values are mostly within 2 km/h. Compared with the models considering the single factor ERA5-P/ERA5-PWV, the RMS of the IMTM-I is improved by 26.3% and 38.5%, respectively. The IMTM-II model manifests a residual of only 0.35 km/h. Compared with the single-factor model based on GNSS-PWV/P, the residual of the IMTM-II model is reduced by 90.8% and 84.1%, respectively. These results propose that the typhoon movement monitoring approach combining PWV and P has evident advantages over the single-factor model and is expected to supplement traditional typhoon monitoring.

A Fuzzy Trust Management Mechanism with Dynamic Behavior Monitoring for Wireless Sensor Networks

Traditional wireless sensor networks(WSNs)are typically deployed in remote and hostile environments for information collection.The wireless communication methods adopted by sensor nodes may make the network highly vulnerable to various attacks.Traditional encryption and authentication mechanisms cannot prevent attacks launched by internal malicious nodes.The trust-based security mechanism is usually adopted to solve this problem in WSNs.However,the behavioral evidence used for trust estimation presents some uncertainties due to the open wireless medium and the inexpensive sensor nodes.Moreover,how to efficiently collect behavioral evidences are rarely discussed.To address these issues,in this paper,we present a trust management mechanism based on fuzzy logic and a cloud model.First,a type-II fuzzy logic system is used to preprocess the behavioral evidences and alleviate uncertainty.Then,the cloud model is introduced to estimate the trust values for sensor nodes.Finally,a dynamic behavior monitoring protocol is proposed to provide a balance between energy conservation and safety assurance.Simulation results demonstrate that our trust management mechanism can effectively protect the network from internal malicious attacks while enhancing the energy efficiency of behavior monitoring.

Irregular initial solidification by mold thermal monitoring in the continuous casting of steels:A review

Occasional irregular initial solidification phenomena,including stickers,deep oscillation marks,depressions,and surface cracks of strand shells in continuous casting molds,are important limitations for developing the high-efficiency continuous casting of steels.The application of mold thermal monitoring(MTM) systems,which use thermocouples to detect and respond to temperature variations in molds,has become an effective method to address irregular initial solidification phenomena.Such systems are widely applied in numerous steel companies for sticker breakout prediction.However,monitoring the surface defects of strands remains immature.Hence,indepth research is necessary to utilize the potential advantages and comprehensive monitoring of MTM systems.This paper summarizes what is included in the irregular initial solidification phenomena and systematically reviews the current state of research on these phenomena by the MTM systems.Furthermore,the influences of mold slag behavior on monitoring these phenomena are analyzed.Finally,the remaining problems of the formation mechanisms and investigations of irregular initial solidification phenomena are discussed,and future research directions are proposed.

Nanomaterial-assisted wearable glucose biosensors for noninvasive real-time monitoring:Pioneering point-of-care and beyond

This review explores glucose monitoring and management strategies,emphasizing the need for reliable and userfriendly wearable sensors that are the next generation of sensors for continuous glucose detection.In addition,examines key strategies for designing glucose sensors that are multi-functional,reliable,and cost-effective in a variety of contexts.The unique features of effective diabetes management technology are highlighted,with a focus on using nano/biosensor devices that can quickly and accurately detect glucose levels in the blood,improving patient treatment and control of potential diabetes-related infections.The potential of next-generation wearable and touch-sensitive nano biomedical sensor engineering designs for providing full control in assessing implantable,continuous glucose monitoring is also explored.The challenges of standardizing drug or insulin delivery doses,low-cost,real-time detection of increased blood sugar levels in diabetics,and early digital health awareness controls for the adverse effects of injectable medication are identified as unmet needs.Also,the market for biosensors is expected to expand significantly due to the rising need for portable diagnostic equipment and an ever-increasing diabetic population.The paper concludes by emphasizing the need for further research and development of glucose biosensors to meet the stringent requirements for sensitivity and specificity imposed by clinical diagnostics while being cost-effective,stable,and durable.

Advances in Wireless,Batteryless,Implantable Electronics for Real‑Time,Continuous Physiological Monitoring

This review summarizes recent progress in developing wireless,batteryless,fully implantable biomedical devices for real-time continuous physiological signal monitoring,focusing on advancing human health care.Design considerations,such as biological constraints,energy sourcing,and wireless communication,are discussed in achieving the desired performance of the devices and enhanced interface with human tissues.In addition,we review the recent achievements in materials used for developing implantable systems,emphasizing their importance in achieving multi-functionalities,biocompatibility,and hemocompatibility.The wireless,batteryless devices offer minimally invasive device insertion to the body,enabling portable health monitoring and advanced disease diagnosis.Lastly,we summarize the most recent practical applications of advanced implantable devices for human health care,highlighting their potential for immediate commercialization and clinical uses.

Fiber optic monitoring of an anti-slide pile in a retrogressive landslide

Anti-slide piles are one of the most important reinforcement structures against landslides,and evalu-ating the working conditions is of great significance for landslide mitigation.The widely adopted analytical methods of pile internal forces include cantilever beam method and elastic foundation beam method.However,due to many assumptions involved in calculation,the analytical models cannot be fully applicable to complex site situations,e.g.landslides with multi-sliding surfaces and pile-soil interface separation as discussed herein.In view of this,the combination of distributed fiber optic sensing(DFOS)and strain-internal force conversion methods was proposed to evaluate the working conditions of an anti-sliding pile in a typical retrogressive landslide in the Three Gorges reservoir area,China.Brillouin optical time domain reflectometry(BOTDR)was utilized to monitor the strain distri-bution along the pile.Next,by analyzing the relative deformation between the pile and its adjacent inclinometer,the pile-soil interface separation was profiled.Finally,the internal forces of the anti-slide pile were derived based on the strain-internal force conversion method.According to the ratio of calculated internal forces to the design values,the working conditions of the anti-slide pile could be evaluated.The results demonstrated that the proposed method could reveal the deformation pattern of the anti-slide pile system,and can quantitatively evaluate its working conditions.

Deformation monitoring of long-span railway bridges based on SBAS-InSAR technology

The deformation monitoring of long-span railway bridges is significant to ensure the safety of human life and property.The interferometric synthetic aperture radar(In SAR)technology has the advantage of high accuracy in bridge deformation monitoring.This study monitored the deformation of the Ganjiang Super Bridge based on the small baseline subsets(SBAS)In SAR technology and Sentinel-1A data.We analyzed the deformation results combined with bridge structure,temperature,and riverbed sediment scouring.The results are as follows:(1)The Ganjiang Super Bridge area is stable overall,with deformation rates ranging from-15.6 mm/yr to 10.7 mm/yr(2)The settlement of the Ganjiang Super Bridge deck gradually increases from the bridge tower toward the main span,which conforms to the typical deformation pattern of a cable-stayed bridge.(3)The sediment scouring from the riverbed cause the serious settlement on the bridge’s east side compared with that on the west side.(4)The bridge deformation negatively correlates with temperature,with a faster settlement at a higher temperature and a slow rebound trend at a lower temperature.The study findings can provide scientific data support for the health monitoring of long-span railway bridges.

Energy evolution and structural health monitoring of coal under different failure modes:An experimental study

Structural instability in underground engineering,especially in coal-rock structures,poses significant safety risks.Thus,the development of an accurate monitoring method for the health of coal-rock bodies is crucial.The focus of this work is on understanding energy evolution patterns in coal-rock bodies under complex conditions by using shear,splitting,and uniaxial compression tests.We examine the changes in energy parameters during various loading stages and the effects of various failure modes,resulting in an innovative energy dissipation-based health evaluation technique for coal.Key results show that coal bodies go through transitions between strain hardening and softening mechanisms during loading,indicated by fluctuations in elastic energy and dissipation energy density.For tensile failure,the energy profile of coal shows a pattern of “high dissipation and low accumulation” before peak stress.On the other hand,shear failure is described by “high accumulation and low dissipation” in energy trends.Different failure modes correlate with an accelerated increase in the dissipation energy before destabilization,and a significant positive correlation is present between the energy dissipation rate and the stress state of the coal samples.A novel mathematical and statistical approach is developed,establishing a dissipation energy anomaly index,W,which categorizes the structural health of coal into different danger levels.This method provides a quantitative standard for early warning systems and is adaptable for monitoring structural health in complex underground engineering environments,contributing to the development of structural health monitoring technology.

Comparative Analysis of ARIMA and LSTM Model-Based Anomaly Detection for Unannotated Structural Health Monitoring Data in an Immersed Tunnel

Structural Health Monitoring(SHM)systems have become a crucial tool for the operational management of long tunnels.For immersed tunnels exposed to both traffic loads and the effects of the marine environment,efficiently identifying abnormal conditions from the extensive unannotated SHM data presents a significant challenge.This study proposed amodel-based approach for anomaly detection and conducted validation and comparative analysis of two distinct temporal predictive models using SHM data from a real immersed tunnel.Firstly,a dynamic predictive model-based anomaly detectionmethod is proposed,which utilizes a rolling time window for modeling to achieve dynamic prediction.Leveraging the assumption of temporal data similarity,an interval prediction value deviation was employed to determine the abnormality of the data.Subsequently,dynamic predictive models were constructed based on the Autoregressive Integrated Moving Average(ARIMA)and Long Short-Term Memory(LSTM)models.The hyperparameters of these models were optimized and selected using monitoring data from the immersed tunnel,yielding viable static and dynamic predictive models.Finally,the models were applied within the same segment of SHM data,to validate the effectiveness of the anomaly detection approach based on dynamic predictive modeling.A detailed comparative analysis discusses the discrepancies in temporal anomaly detection between the ARIMA-and LSTM-based models.The results demonstrated that the dynamic predictive modelbased anomaly detection approach was effective for dealing with unannotated SHM data.In a comparison between ARIMA and LSTM,it was found that ARIMA demonstrated higher modeling efficiency,rendering it suitable for short-term predictions.In contrast,the LSTM model exhibited greater capacity to capture long-term performance trends and enhanced early warning capabilities,thereby resulting in superior overall performance.

Comparison of CWSI and T_(s)-T_(a)-VIs in moisture monitoring of dryland crops(sorghum and maize)based on UAV remote sensing

Monitoring agricultural drought using remote sensing data is crucial for precision irrigation in modern agriculture.Utilizing unmanned aerial vehicle(UAV)remote sensing,we explored the applicability of an empirical crop water stress index(CWSI)based on canopy temperature and three-dimensional drought indices(TDDI)constructed from surface temperature(T_(s)),air temperature(T_(a))and five vegetation indices(VIs)for monitoring the moisture status of dryland crops.Three machine learning algorithms(random forest regression(RFR),support vector regression,and partial least squares regression)were used to compare the performance of the drought indices for vegetation moisture content(VMC)estimation in sorghum and maize.The main results of the study were as follows:(1)Comparative analysis of the drought indices revealed that T_(s)-T_(a)-normalized difference vegetation index(TDDIn)and T_(s)-T_(a)-enhanced vegetation index(TDDIe)were more strongly correlated with VMC compared with the other indices.The indices exhibited varying sensitivities to VMC under different irrigation regimes;the strongest correlation observed was for the TDDIe index with maize under the fully irrigated treatment(r=-0.93).(2)Regarding spatial and temporal characteristics,the TDDIn,TDDIe and CWSI indices showed minimal differences Over the experimental period,with coefficients of variation were 0.25,0.18 and 0.24,respectively.All three indices were capable of effectively characterizing the moisture distribution in dryland maize and sorghum crops,but the TDDI indices more accurately monitored the spatial distribution of crop moisture after a rainfall or irrigation event.(3)For prediction of the moisture content of single crops,RFR models based on TDDIn and TDDIe estimated VMC most accurately(R^(2)>0.7),and the TDDIn-based model predicted VMC with the highest accuracy when considering multiple-crop samples,with R^(2)and RMSE of 0.62 and 14.26%,respectively.Thus,TDDI proved more effective than the CWSI in estimating crop water content.

Microarrow sensor array with enhanced skin adhesion for transdermal continuous monitoring of glucose and reactive oxygen species

Conventional blood sampling for glucose detection is prone to cause pain and fails to continuously record glucose fluctuations in vivo.Continuous glucose monitoring based on implantable electrodes could induce pain and potential tissue inflammation,and the presence of reactive oxygen species(ROS)due to inflammationmay affect glucose detection.Microneedle technology is less invasive,yet microneedle adhesion with skin tissue is limited.In this work,we developed a microarrow sensor array(MASA),which provided enhanced skin surface adhesion and enabled simultaneous detection of glucose and H_(2)O_(2)(representative of ROS)in interstitial fluid in vivo.The microarrows fabricated via laser micromachining were modified with functional coating and integrated into a patch of a three-dimensional(3D)microneedle array.Due to the arrow tip mechanically interlocking with the tissue,the microarrow array could better adhere to the skin surface after penetration into skin.The MASA was demonstrated to provide continuous in vivo monitoring of glucose and H_(2)O_(2) concentrations,with the detection of H_(2)O_(2) providing a valuable reference for assessing the inflammation state.Finally,the MASA was integrated into a monitoring system using custom circuitry.This work provides a promising tool for the stable and reliable monitoring of blood glucose in diabetic patients.

Implantable Electrochemical Microsensors for In Vivo Monitoring of Animal Physiological Information

In vivo monitoring of animal physiological information plays a crucial role in promptly alerting humans to potential diseases in animals and aiding in the exploration of mechanisms underlying human diseases.Currently,implantable electrochemical microsensors have emerged as a prominent area of research.These microsensors not only fulfill the technical requirements for monitoring animal physiological information but also offer an ideal platform for integration.They have been extensively studied for their ability to monitor animal physiological information in a minimally invasive manner,characterized by their bloodless,painless features,and exceptional performance.The development of implantable electrochemical microsensors for in vivo monitoring of animal physiological information has witnessed significant scientific and technological advancements through dedicated efforts.This review commenced with a comprehensive discussion of the construction of microsensors,including the materials utilized and the methods employed for fabrication.Following this,we proceeded to explore the various implantation technologies employed for electrochemical microsensors.In addition,a comprehensive overview was provided of the various applications of implantable electrochemical microsensors,specifically in the monitoring of diseases and the investigation of disease mechanisms.Lastly,a concise conclusion was conducted on the recent advancements and significant obstacles pertaining to the practical implementation of implantable electrochemical microsensors.

Short-term displacement prediction for newly established monitoring slopes based on transfer learning

This study makes a significant progress in addressing the challenges of short-term slope displacement prediction in the Universal Landslide Monitoring Program,an unprecedented disaster mitigation program in China,where lots of newly established monitoring slopes lack sufficient historical deformation data,making it difficult to extract deformation patterns and provide effective predictions which plays a crucial role in the early warning and forecasting of landslide hazards.A slope displacement prediction method based on transfer learning is therefore proposed.Initially,the method transfers the deformation patterns learned from slopes with relatively rich deformation data by a pre-trained model based on a multi-slope integrated dataset to newly established monitoring slopes with limited or even no useful data,thus enabling rapid and efficient predictions for these slopes.Subsequently,as time goes on and monitoring data accumulates,fine-tuning of the pre-trained model for individual slopes can further improve prediction accuracy,enabling continuous optimization of prediction results.A case study indicates that,after being trained on a multi-slope integrated dataset,the TCN-Transformer model can efficiently serve as a pretrained model for displacement prediction at newly established monitoring slopes.The three-day average RMSE is significantly reduced by 34.6%compared to models trained only on individual slope data,and it also successfully predicts the majority of deformation peaks.The fine-tuned model based on accumulated data on the target newly established monitoring slope further reduced the three-day RMSE by 37.2%,demonstrating a considerable predictive accuracy.In conclusion,taking advantage of transfer learning,the proposed slope displacement prediction method effectively utilizes the available data,which enables the rapid deployment and continual refinement of displacement predictions on newly established monitoring slopes.

Interplay of laser power and pore characteristics in selective laser melting of ZK60 magnesium alloys:A study based on in-situ monitoring and image analysis

This study offers significant insights into the multi-physics phenomena of the SLM process and the subsequent porosity characteristics of ZK60 Magnesium(Mg)alloys.High-speed in-situ monitoring was employed to visualise process signals in real-time,elucidating the dynamics of melt pools and vapour plumes under varying laser power conditions specifically between 40 W and 60 W.Detailed morphological analysis was performed using Scanning-Electron Microscopy(SEM),demonstrating a critical correlation between laser power and pore formation.Lower laser power led to increased pore coverage,whereas a denser structure was observed at higher laser power.This laser power influence on porosity was further confirmed via Optical Microscopy(OM)conducted on both top and cross-sectional surfaces of the samples.An increase in laser power resulted in a decrease in pore coverage and pore size,potentially leading to a denser printed part of Mg alloy.X-ray Computed Tomography(XCT)augmented these findings by providing a 3D volumetric representation of the sample internal structure,revealing an inverse relationship between laser power and overall pore volume.Lower laser power appeared to favour the formation of interconnected pores,while a reduction in interconnected pores and an increase in isolated pores were observed at higher power.The interplay between melt pool size,vapour plume effects,and laser power was found to significantly influence the resulting porosity,indicating a need for effective management of these factors to optimise the SLM process of Mg alloys.

Novel Fractal-Based Features for Low-Power Appliances in Non-Intrusive Load Monitoring

Non-intrusive load monitoring is a method that disaggregates the overall energy consumption of a building to estimate the electric power usage and operating status of each appliance individually.Prior studies have mostly concentrated on the identification of high-power appliances like HVAC systems while overlooking the existence of low-power appliances.Low-power consumer appliances have comparable power consumption patterns,which can complicate the detection task and can be mistaken as noise.This research tackles the problem of classification of low-power appliances and uses turn-on current transients to extract novel features and develop unique appliance signatures.A hybrid feature extraction method based on mono-fractal and multi-fractal analysis is proposed for identifying low-power appliances.Fractal dimension,Hurst exponent,multifractal spectrum and the Hölder exponents of switching current transient signals are extracted to develop various‘turn-on’appliance signatures for classification.Four classifiers,i.e.,deep neural network,support vector machine,decision trees,and K-nearest neighbours have been optimized using Bayesian optimization and trained using the extracted features.The simulated results showed that the proposed method consistently outperforms state-of-the-art feature extraction methods across all optimized classifiers,achieving an accuracy of up to 96%in classifying low-power appliances.