Search

This paper investigates the challenge of finding and analyzing security vulnerabilities among widely available low-budget Internet of Things smart home appliances. It considers the identification of security vulnerabilities within the appliances' embedded software and connectivity functions over wired and wireless channels in local networks and external communications with manufacturers' cloud services. To analyze the security of these appliances, a universal laboratory test bench is proposed and a set of methodologies for testing the security of smart home devices is described. The proposed testing platform offers a practical solution for security analysis of Internet of Things smart home devices and it can serve as a reference approach for future research. The results from the research indicated varying levels of susceptibility across different types of devices. A list of recommendations for manufacturers and others to improve the security level of these appliances is provided. The findings emphasize the need for regular security assessments of smart home devices, to maintain the protection of personal and sensitive information. [ABSTRACT FROM AUTHOR]

To support the 2021 Manufacturing & Service Operations Management (M&SOM) Data-Driven Research Challenge, RiRiShun Logistics (a Haier group subsidiary focusing on logistics service for home appliances) provides MSOM members with logistics operational-level data for data-driven research. This paper provides a detailed description of the data associated with over 14 million orders from 149 clients (the consigners) associated with 4.2 million end consumers (the recipients and end users of the appliances) in China, involving 18,000 stock keeping units operated at 103 warehouses. Researchers are welcomed to develop econometric models, data-driven optimization techniques, analytical models, and algorithm designs by using this data set to address questions suggested by company managers. History: This paper has been accepted as part of the 2021 M&SOM Data-Driven Research Challenge. Funding: This work was supported by the National Natural Science Foundation of China [Grants 72091215/72091210, 71871207, 71991464/71991460, and 71921001]. Supplemental Material: Data and the online appendix are is available at https://doi.org/10.1287/msom.2021.0994. [ABSTRACT FROM AUTHOR]

Copyright of Revista Foco (Interdisciplinary Studies Journal) is the property of Revista Foco and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Home appliances connected to Internet-of-Things (IoT) platforms have been extensively installed in smart homes. In this context, home energy management systems (HEMSs) have emerged as a viable solution for reducing energy costs. Although several studies have analyzed the implementation of HEMSs, a majority of these studies were based on the installation of numerous sensors. Owing to the complexity and costs associated with the installation of multiple sensors, implementation of HEMSs in smart homes is challenging. This paper presents an energy management scheme for an HEMS that minimizes the energy cost in a smart home with data obtained from IoT-based appliances typically used in a smart home. Case studies were conducted to demonstrate the effectiveness of the proposed method. Prototype software (version 11) based on the proposed method for a HEMS and a test house with IoT-based appliances were also implemented in the case studies. [ABSTRACT FROM AUTHOR]

A novel ensemble machine learning approach for predicting energy consumption in smart appliances is presented in this paper. The main objective is minimizing the number of necessary sensors and improving the prediction accuracy at the same time. The proposed method combines the Fuzzy C-Means method with a multi-stream deep neural network to achieve this goal. The method focuses on prediction accuracy and aims to extract the minimum number of essential features from the dataset corresponding to the required sensors. These selected features are then scatter-reduced and homogenized into subsets. Each subset is used to train a cluster-specific deep neural network designed exclusively for that subset. The final prediction is obtained by computing the fuzzy-weighted sum of these cluster-specific network outputs. Numerical results show that the proposed prediction method outperforms conventional methods in terms of root mean square error and mean absolute percentage error criteria, despite using fewer sensors. This improvement can be attributed to the reduced dataset scatter, which improves the learning speed and model performance. Furthermore, the fuzzy combination of the outputs improves the final prediction accuracy. Overall, the proposed approach provides a more cost-effective and accurate solution for predicting the energy consumed by smart appliances. [ABSTRACT FROM AUTHOR]

With the development of Non-Intrusive Load Monitoring (NILM), it has become feasible to perform device identification, energy consumption decomposition, and load switching detection using Deep Learning (DL) methods. Similar to other machine learning problems, the research and validation of NILM necessitate substantial data support. Moreover, different regions exhibit distinct characteristics in their electricity environments. Therefore, there is a need to provide open datasets tailored to different regions. In this paper, we introduce the Transient Dataset of Household Appliances with Intensive Switching Events (TDHA25). This dataset comprises switch instantaneous data from 10 typical household appliances in China. The TDHA dataset features a high sampling rate, accurate labelling, and realistic representation of actual appliance start-up waveforms. Additionally, appliance switching is achieved through precise control of relay switches, thus mitigating interference caused by mechanical switches. By furnishing such a dataset, we aim not only to enhance the recognition accuracy of existing NILM algorithms but also to facilitate the application of NILM algorithms in regions sharing similar electricity consumption characteristics to those of China. [ABSTRACT FROM AUTHOR]

Purpose: Considering the problems faced by the home appliance industry in Iran, such as the increase in waste, lack of information transparency and lack of traceability of manufactured products, etc. the companies in the home appliance industry are moving toward Industry 4.0 and have been prompted to use it. On the other hand, the adoption of Industry 4.0 is associated with challenges that may lead to the failure of the adoption project and the bankruptcy of home appliance manufacturers. This study identified the challenges in the implementation of Industry 4.0 on current status and provided suitable solutions to overcome the identified challenges. Design/methodology/approach: In this study, a review of the literature and background of Industry 4.0 identified the challenges that influence the adoption of Industry 4.0. To measure the current status of the identified challenges, the opinions of experts in the Iranian home appliance industry were used. To find solutions to the challenges in the adoption of Industry 4.0 in the Iranian home appliance industry, a fuzzy cognitive mapping and scenario design were used. Findings: The results of this study show that to face the challenge of data sharing, skilled personnel should be effectively promoted among workers in the home appliance industry. The results of this study also show that the barriers to cooperation should be removed to reduce the impact of the IT Security Concerns challenge. Originality/value: This paper is the first article that identifies the challenges and effective solutions for implementing Industry 4.0 in the home appliance industry. [ABSTRACT FROM AUTHOR]

Brain-computer interfaces (BCIs) have a potential to revolutionize humancomputer interaction by enabling direct links between the brain and computer systems. Recent studies are increasingly focusing on practical applications of BCIs--e.g., home appliance control just by thoughts. One of the non-invasive BCIs using electroencephalography (EEG) capitalizes on event-related potentials (ERPs) in response to target stimuli and have shown promise in controlling home appliance. In this paper, we present a comprehensive dataset of online ERP-based BCIs for controlling various home appliances in diverse stimulus presentation environments. We collected online BCI data from a total of 84 subjects among whom 60 subjects controlled three types of appliances (TV: 30, door lock: 15, and electric light: 15) with 4 functions per appliance, 14 subjects controlled a Bluetooth speaker with 6 functions via an LCD monitor, and 10 subjects controlled air conditioner with 4 functions via augmented reality (AR). Using the dataset, we aimed to address the issue of inter-subject variability in ERPs by employing the transfer learning in two different approaches. The first approach, "within-paradigm transfer learning," aimed to generalize the model within the same paradigm of stimulus presentation. The second approach, "cross-paradigm transfer learning," involved extending the model from a 4-class LCD environment to different paradigms. The results demonstrated that transfer learning can effectively enhance the generalizability of BCIs based on ERP across different subjects and environments. [ABSTRACT FROM AUTHOR]

This paper introduces the first completely unsupervised methodology for non-intrusive load monitoring that does not rely on any additional data, making it suitable for real-life applications. The methodology includes an algorithm to efficiently decompose the aggregated energy load from households in events and algorithms based on expert knowledge to assign each of these events to four types of appliances: fridge, dishwasher, microwave, and washer/dryer. The methodology was developed to work with smart meters that have a granularity of 1 min and was evaluated using the Reference Energy Disaggregation Dataset. The results show that the algorithm can disaggregate the refrigerator with high accuracy and the usefulness of the proposed methodology to extract relevant features from other appliances, such as the power use and duration from the heating cycles of a dishwasher. [ABSTRACT FROM AUTHOR]

Non-intrusive load monitoring (NILM) technology, crucial for intelligent electricity management, has gained considerable attention in residential electricity usage studies. NILM enables monitoring of total electrical current and voltage in homes, offering insights vital for enhancing safety and preventing domestic electrical accidents. Despite its importance, accurately discerning the operational status of appliances using non-intrusive methods remains a challenging area within this field. This paper presents a novel methodology that integrates an advanced clustering algorithm with a Bayesian network for the identification of appliance operational states. The approach involves capturing the electrical current signals during appliance operation via NILM, followed by their decomposition into odd harmonics. An enhanced clustering algorithm is then employed to ascertain the central coordinates of the signal clusters. Building upon this, a three-layer Bayesian network inference model, incorporating leak nodes, is developed. Within this model, harmonic signals are used as conditions for node activation. The operational states of the appliances are subsequently determined through probabilistic reasoning. The proposed method's effectiveness is validated through a series of simulation experiments conducted in a laboratory environment. The results of these experiments (low mode 89.1%, medium mode 94.4%, high mode 92.0%, and 98.4% for combination) provide strong evidence of the method's accuracy in inferring the operational status of household electrical appliances based on NILM technology. [ABSTRACT FROM AUTHOR]

Deep drawing is an operation to transform flat or hollow blanks to create hollow parts of the required shape and size. Deep drawing is an essential operation in sheet-forming technology to manufacture hollow parts. These parts are commonly used in the automobile, aviation, and household appliances industries. To prevent wrinkles on the rim part, a blank holder will be used to compress and flatten the workpiece before the metal is pulled into the die by the punch. Deep drawing without using workpiece holding force is applied to form hollow parts with low depth. In this case, the mould has a simple structure, helping to reduce manufacturing time and costs and making it easier to maintain and repair. The radius of the die is an essential parameter in deep drawing; it greatly affects the quality of products (making wrinkles and tears). However, this study has shown that, in deep drawing without using a blank holder, the cone angle of the die α has a major influence on the quality of the body and rim of the products, such as the products may or may not have wrinkles, either being thinned or thickened. This cone angle also affects the drawing force. This study has determined that, with α>120°, wrinkling begins to appear in the part wall, and wrinkling tends to increase as the angle α increases. The cone angle of the die for quality products is in the range of 100° < α ≤ 120°. The taper angle smaller than 120° simultaneously increases the quality of the products and the cost of manufacturing die, so the most optimal value is determined by simulation and experimental verification as α = 120°. The results of this study can be applied to fabricate hollow cylindrical parts with similar shapes when using the deep drawing method without using the blank holder. [ABSTRACT FROM AUTHOR]

Whereas the literature on rebates has focused on single-product firms, this paper analyses the role of rebates offered by a multiproduct firm Rebates have long been recognized as a price discrimination mechanism. When firms offer an extensive product line, an important managerial question concerns the choice of which products to promote. This paper finds that a multiproduct firm leverages rebates to screen consumers on the basis of their redemption costs, which enables it to exercise price discrimination via the product line more effectively. In particular, because consumers who use rebates tend to have lower valuations, the classic cannibalization concern is less severe in the product line offered to rebate users. Therefore, the lowest-quality product that is promoted with a rebate is of higher quality than the lowest-quality product that is offered without rebate. Hence, the firm does not promote its lowest-quality products. Instead, by promoting some products with rebates, the firm drives some low-valuation consumers to trade up to higher-quality products. Notably, it is found that, contrary to the commonly held view, rebates can serve a price discrimination role even when redeemed by all consumers. Therefore, this paper proposes a novel price discrimination explanation for large rebates, sometimes in the order of several hundreds of dollars, that are frequently used in industries such as consumer electronics and household appliances. History: Yuxin Chen served as the senior editor for this article. Supplemental Material: The e-companion is available at https://doi.org/10.1287/mksc.2023.1430. [ABSTRACT FROM AUTHOR]

Life cycle assessment (LCA) is widely used to evaluate product's life cycle environmental impact and identify the environmental weaknesses. However, it is difficult for existing LCA software to perform flexible LCA analysis based on the product life cycle characteristics and industry background. Meanwhile, under the existing LCA research model, product designers and manufacturers are usually not LCA evaluators, resulting in a certain time gap between the evaluation results and product improvement. Designers with less experience in green design often find it difficult to identify high environmental impact links in products at different life cycle stages and product levels, and updated products are challenging to meet various environmental restrictions. This paper establishes a multi-module product life cycle analysis model that combines product industry background that includes basic information, assessment information, structural information, and restriction information to achieve the multi-scenario of product LCA in different dimensions in a typical domain. The calculated mechanism of the dynamic power emission factor is built according to the service time and space dimensions. The proposed method forms an integrated environmental performance evaluation of household appliance (EPEHA) system. A software assessment and an optimization method are proposed to improve the EPEHA system. The results of this study show that these proposed methods can improve the timeliness and diversity of results analysis of product LCA in the field of household appliances in China. The universal data exchange format and simple operation interface of the EPEHA system enable people related to the product to quickly understand the environmental impact of the product in different scenarios, even if they lack green design knowledge and professional software training. [ABSTRACT FROM AUTHOR]

Multi-label classification is an advantageous technique for managing uncertainty in classification problems where each data instance is associated with several labels simultaneously. Such situations are frequent in real-world scenarios, where decisions rely on imprecise or noisy data and adaptable classification methods are preferred. However, the problem of class imbalance represents a common characteristic of several multi-label datasets, in which the distribution of samples and their corresponding labels is non-uniform across the data space. In this paper, we propose a multi-label classification approach utilizing fuzzy logic in order to deal with the class imbalance problem. To eliminate the need for an expert to determine the logical rules of inference, deep neural networks are adopted, which have proven to be exceptionally effective for such problems. By combining both fuzzy inference systems and deep neural networks, the strengths and weaknesses of each approach can be mitigated. As a further development, a symbolic representation of time series is put in place to reduce data dimensionality and speed up the training procedure. This allows for more flexibility in model application, in particular with respect to time constraints arising from the causality of observed time series. Tests carried out on a multi-label classification dataset related to the current and voltage profiles of several household appliances show that the proposed model outperforms four baseline models for time series classification. [ABSTRACT FROM AUTHOR]

The aim of this experimental research is to confirm the correctness of the proposed methodology for optimizing atmospheric gas burners. Also, the burner was tested in actual conditions. The object of this experimental optimization is a typical modern atmospheric gas burner for households (required heat output for average households ranges from 8-12 kW) to which the proposed methodology will be applied in order to optimize its design characteristics and performance to obtain energy efficient and an environmentally friendly device. [ABSTRACT FROM AUTHOR]

In this paper, a method to analyse load features utilising sample shifting technique (SST) for non-intrusive load identification (NILI) is presented and discussed. Fuzzy rules are used as the foundation for the identification logic. Voltage and current signals for electrical home appliances are acquired in order to develop their respective features. Two features like reactive power and total harmonic distortion for current (THD I), are created with the necessary computations of the samples using SST. A method based on fuzzy rules is created in order to identify different electrical equipment both for their individual as well as simultaneous running. Again, the performance of the proposed system is tested under the noisy environment while the accuracy of the system is found satisfactory. By utilising SST, the burden of computation is reduced in comparison to the other methods which are justified with the experimental results. • Only voltage and current information are used for load identification. • Sample Shifting Technique is used to extract load features. • Reactive power and THD for current are used as load features. • Fuzzy logic-based rules are applied for non-intrusive load identification. • The use of of SST assists in the extraction of load features and reduces the complexity of the hardware by eliminating the need for filters or ZCDs. • Individual load can be identified during practical multiple loads are working parallelly. • System shows robustness under noisy environment. [ABSTRACT FROM AUTHOR]

Non invasive load monitoring (NILM) is beneficial for enhancing the monitoring capability of the distribution network and is crucial for improving the safety of smart grid operation. However, household appliances involve a variety of devices and a large amount of data, making it difficult to achieve high-precision load identification. Especially when a large amount of loads are running simultaneously, problems such as feature overlap and reduced distinguish ability may occur, and thus increasing the difficulty of load identification. To solve these problems, this paper proposes a new NILM method based on dynamic time warping (DTW) optimization and event detection. Firstly, a feature extraction algorithm of STFT-SSAE is constructed by using short-time Fourier transform (STFT) to extract time–frequency features from the load, and then by sparse stack autoencoder (SSAE) to extract important features from time–frequency information. Secondly, the above features are input into Bi-LSTM and DTW models respectively, and a new probabilistic model is established. A Bi-LSTM-DTW load recognition architecture is built by combining the two models. Finally, the load identification model of SSAE-Bi-LSTM based on DTW optimization (DOSL) is trained by the preset combined data, which ensures the high confidence of the DOSL model in various complex operating scenarios. This paper introduces the public data set PLAID for experimental verification. The results show that the selected load features has good discrimination, and the proposed algorithm has the best identification effect with the accuracy rate of 0.9412. The proposed algorithm is also validated for generalization ability on the public dataset UK-DALE, with a identification accuracy rate of 0.9306, and the error of different datasets is only about 1%. • A complete multiple house-hold appliances NILM framework. • A novel STFT-SSAE algorithm for load feature extraction. • Bi-LSTM-DTW load identification architecture combined with output probability vector. [ABSTRACT FROM AUTHOR]

With the popularization of Internet of Things applications, trillions of new devices with different application requirements, such as smart wearables and smart home appliances, will be connected to the network. Hence, it is crucial to ensure the data transmission security of these low-power and multifunctional sensor nodes. In this paper, a novel lightweight block cipher, GFSPX, is proposed for resource-constrained microdevices. The proposed algorithm combines a generalized Feistel structure with the substitution permutation networks structure to design the round function, which effectively addresses the inherent problem of slow diffusion in the traditional Feistel structure. Furthermore, the introduction of Addition or AND, Rotation, XOR operations in the round function to process part of the plaintext reduces the demand for hardware resource of the algorithm. The avalanche test results indicate that the GFSPX algorithm has strong diffusion and can satisfy the avalanche effect in just six rounds. The security analysis results verify the security of the GFSPX algorithm against differential and linear cryptanalysis attacks, algebraic attacks, structural attacks and key scheduling attacks. Finally, the performance analysis results indicate that the hardware implementation cost of GFSPX algorithm is relatively low, requiring only 1715 GE based on 0.13 micron logic process. In addition, the software implementation of this algorithm works well at an encryption rate of 12.31 Mb/s. [ABSTRACT FROM AUTHOR]

The operational behavior of modern active distribution networks differs greatly from their passive predecessors. Active network management schemes, such as Conservation Voltage Reduction (CVR), are being widely explored to enhance energy conservation and network resiliency. CVR can potentially decrease energy consumption in distribution networks by reducing the voltage at load terminals. However, accurately assessing CVR suitability for distribution feeders is paramount, as it exploits the voltage dependency of load. Most CVR assessment schemes require extensive data from smart meters, micro-pmus, and detailed network topology information. This paper presents a novel synthetic data-based approach for probabilistic CVR assessment, which uses customer categorization to generate realistic synthetic data for probabilistic assessment, taking into account the voltage dependency of common household appliances. Additionally, an extended version of the probabilistic synthetic-data-based approach is introduced to enhance the accuracy of CVR assessment using limited distribution network information. MATLAB was used for data handling and customer categorization, while OpenDSS was used for power flow analysis to evaluate CVR effectiveness. The proposed CVR assessment methodologies are tested and validated in detail for the TOPI distribution network in KPK, Pakistan. The study’s findings shows that CVR can significantly reduce energy and cost, with a 10.13% reduction in energy use and approximately 4 million PKR in cost [ABSTRACT FROM AUTHOR]

• Consumers are not well informed on how to perform product life extension behaviours. • Consumer education motivates consumers to perform product life extension behaviours. • Credible, actionable guidance motivates adoption of product life extension behaviours. • Diverse communication channels ensure wider groups of consumers can be educated. This paper investigates consumer education as an effective intervention for adoption of product life extension behaviours by consumers of domestic appliances in the UK. Product life extension behaviours, including maintenance and repair, keep electrical appliances in use for as long as possible, ultimately supporting a circular economy by slowing the flow of materials. The study aims to demonstrate the influence communication-based interventions can have on consumer behaviour. The study was carried out in three phases over a 3-month period with seven households in Southwark Borough in London, forming an in-depth understanding of daily routines involving domestic appliance interactions. The results of the study suggest that consumer adoption of product life extension behaviours can be influenced by education. The study proposes that industry addresses the intention-action gap with improved and targeted design and delivery of education that motivates and empowers consumers to perform product life extension behaviours on their domestic appliances. [ABSTRACT FROM AUTHOR]

The objective of this study is to optimize a linear objective function that pertains to the obsolescence of home appliances in a household. The approach introduced is an ILP-based method that is both simple and adaptable. This optimization guarantees that the total energy consumption remains below a predetermined energy threshold, while also adhering to an inequality constraint. The proposed methodology was effectively tested using a household containing four home appliances: a washing machine, a dishwasher, a refrigerator, and an oven. The findings indicate that the refrigerator is the most hazardous and inexpensive home appliance. The current formulation aims to optimize the device's lifespan considering the customer's financial constraints and the expenses associated with repairing and replacing its parts. This study centers on the maintenance of printed circuit boards (PCBs) and considers the effects of degradation-related malfunctions, as assessed through testing. Moreover, we employ an additional ILP approach to assess the vulnerability of refrigerator's PCB components by determining which ones should be replaced when a customer has limited financial resources. [ABSTRACT FROM AUTHOR]

Deep learning (DL) has been widely applied to forecast the sales volume of household appliances with high accuracy. Unfortunately, in small towns, due to the limited amount of historical sales data, it is difficult to forecast household appliance sales accurately. To overcome the above-mentioned challenge, we propose a novel household appliance sales forecasting algorithm based on transfer learning, temporal convolutional network (TCN), long short-term memory (LSTM), and attention mechanism (called "TransTLA"). Firstly, we combine TCN and LSTM to exploit the spatiotemporal correlation of sales data. Secondly, we utilize the attention mechanism to make full use of the features of sales data. Finally, in order to mitigate the impact of data scarcity and regional differences, a transfer learning technique is used to improve the predictive performance in small towns, with the help of the learning experience from the megacity. The experimental outcomes reveal that the proposed TransTLA model significantly outperforms traditional forecasting methods in predicting small town household appliance sales volumes. Specifically, TransTLA achieves an average mean absolute error (MAE) improvement of 27.60% over LSTM, 9.23% over convolutional neural networks (CNN), and 11.00% over the CNN-LSTM-Attention model across one to four step-ahead predictions. This study addresses the data scarcity problem in small town sales forecasting, helping businesses improve inventory management, enhance customer satisfaction, and contribute to a more efficient supply chain, benefiting the overall economy. [ABSTRACT FROM AUTHOR]

Event detection is a prerequisite and key component of NILM (Non-Intrusive Load Monitoring) by monitoring transient changes in residential loads to discern whether a transient event has occurred in an appliance. However, the event detection performance of existing algorithms is affected by the operating environment, and it isn't easy to maintain high accuracy. For this reason, this paper proposes an adaptive event detection method based on the PCW (power change-point weights) model. Specifically, the DACUSUM (Dynamic Adaptive Cumulative Sum) algorithm with dynamic updating of parameters is first proposed, which effectively avoids the miss and false detection of CUSUM in the process of event detection. Secondly, the PCW model is proposed, which is capable of evaluating the effect of event detection of thresholds through the transient information entropy without prior knowledge. Lastly, based on the DACUSUM and PCW model, the threshold-adaptive event detection method is proposed, which takes the transient information entropy as the objective function and utilizes the genetic algorithm to dynamically adjust the thresholds to improve the performance of event detection under different operating environments. Taking eight typical appliances as an example, on the one hand, the proposed DACUSUM reduces the leakage and false detection phenomena compared with CUSUM and improves the event detection performance. On the other hand, the PCW model-based event detection strategy doesn't need human intervention or prior knowledge and is adaptable to different operating environments. The experimental results show that the proposed strategy achieves F1 scores of over 90% for the event detection of eight types of home appliances. • A Dynamic Adaptive CUSUM (DACUSUM) algorithm based on dynamic parameters and correction window is proposed. • The power change-point weight (PCW) model is established on the basis of change point detection. • An adaptive event detection method for different operating environments is proposed. [ABSTRACT FROM AUTHOR]

• A novel model leveraging distributionally robust deep learning (DRDN) is introduced to disaggregate load for the first time in NILM. • Six feasible ϕ -divergence functions are adopted to construct the DRDN model, the improvements across these functions showing the universality of the method. • DRDN excels in extracting features from intricate-group samples, combining convolutional neural networks' strengths in power feature extraction with DRO's proficiency in handling complex samples. Non-Intrusive Load Monitoring (NILM) is a crucial technique for energy conservation as it provides detailed energy consumption data for individual household appliances, leading to targeted energy saving strategies. In practice, the startup phase of appliances is more significant than the shutdown phase, especially when predicting appliance-level consumption. When implementing Sequence-to-Point (S2P) based network models, where each appliance is trained separately, the primary source of training error comes from state transitions during startup, particularly those involving other appliances. These transitions can be mistakenly learned by the network as spurious correlations. This paper presents a method for effectively filtering such samples, and extracting features that are more resistant to spurious correlation confusion. We propose a Distributionally Robust Deep Network (DRDN) model grounded in ϕ -divergence, to address the NILM disaggregation problem. Our model incorporates an adaptive loss-scaled robust parameter to enable sample selection and improve decision-making. Our experimental results on the REDD and UK-DALE datasets demonstrate that DRDN models exhibit superior transferability and effectiveness in solving domain generalization problem compared to traditional deep learning approaches across different buildings. [ABSTRACT FROM AUTHOR]

The increasing global population and reliance on electrical devices for daily life resulted in sharply rising energy consumption. Also, this leads to higher household electricity bills. As a result, there is a growing demand for energy monitoring systems that can accurately estimate energy usage to help save power, especially for older home appliances that are difficult or expensive to update with monitoring sensors. However, current energy monitoring systems have some drawbacks, such as the inability to detect different types of appliances and the deployment complexity. Moreover, such systems are too costly to use in older power infrastructures. To address this issue, we proposed a centralized smart energy monitoring system designed for legacy home appliances, aiming to address the limitations of current energy monitoring systems by avoiding costly infrastructure upgrades to calculate the power consumption of legacy home appliances. The proposed system employs a two-layered architecture comprising hardware (Emontx device, Analog-to-Digital Converters (ADC), and Current Transformer (CT) sensors) and a software layer that includes Artificial Intelligence (AI) predictors using a pre-defined set of rules and K Nearest Neighbours (KNN) algorithms. We conducted three experiments on real home appliances to evaluate the proposed work. The accuracy of the proposed system showed positive results after several modifications and hard tuning of several parameters in devices, specifically for Jordanian power plants. [ABSTRACT FROM AUTHOR]

Efficient energy management in residential environments is a constant challenge, in which Home Energy Management Systems (HEMS) play an essential role in optimizing consumption. Load recognition allows the identification of active appliances, providing robustness to the HEMS. The precise identification of household appliances is an area not completely explored. Gaps like improving classification performance through techniques dedicated to separability between classes and models that achieve enhanced reliability remain open. This work improves several aspects of load recognition in HEMS applications. In this research, we adopt Neighborhood Component Analysis (NCA) to extract relevant characteristics from the data, seeking the separability between classes. We also employ the Regularized Extreme Learning Machine (RELM) to identify household appliances. This pioneering approach achieves performance improvements, presenting higher accuracy and weighted F1-Score values—97.24% and 97.14%, respectively—surpassing state-of-the-art methods and enhanced reliability according to the Kappa index, i.e., 0.9388, outperforming competing classifiers. Such evidence highlights the promising potential of Machine Learning (ML) techniques, specifically NCA and RELM, to contribute to load recognition and energy management in residential environments. [ABSTRACT FROM AUTHOR]

Population expansion and improving living standards, particularly in developed nations, have led to an increase in the usage of domestic electrical equipment, worldwide energy consumption, and CO2 emissions per capita. To limit the usage of non-reusable components and the amount of garbage that must be transferred at the end of a product's life cycle, longer-lasting electrical domestic appliances are a pillar of the circular economy. In recent years, the complexity of printed circuit boards (PCBs) used in the manufacture of modern electrical devices has increased, leading to an increase in device failures. This study focuses on the maintenance and recycling of domestic electrical appliance components and printed circuit boards. The proposed methodology for PCB repair is defined as a sequential quadratic programming (SQP) problem implemented in MATLAB environment and successfully tested to a variety of domestic appliances such as refrigerator, dishwasher and washing machine. The possibility of recycling metal parts of electronic components, which were replaced after PCBs' repair was also studied. Metals' percentage concentration of PCB electronic components for three customer's budgets considering metals and valuable metals recovery as given from the corresponding average metal recovery and calculated from different recycling procedures presented in the literature. The results of the proposed procedure in terms of valuable metals gave 38.4078 ppm of silver. We also compared the suggested procedure with other works in terms of environmental perspective considering four measures, namely the gross energy requirement (GER), the global warming potential (GWP), the acidification potential (AP), and the solid waste burden (SWB). In terms of economic perspective and considering the existence of silver (Ag) in the electronic components, the recommended method gave comparable amount of money. Finally, a comparison of different recycling works from a technical viewpoint is also conducted. Moreover, a reparability index of domestic electrical appliances is introduced to further quantify the results of the proposed algorithm. [ABSTRACT FROM AUTHOR]

DC-DC converters are circuits that are widely used in energy distribution systems, in industry and technology applications, as well as in household appliances such as computers and televisions, and in uninterruptible power supplies used to feed all these systems. For the design and optimization of DC-DC converter circuits, it is important to create and analyze mathematical models according to the load it is connected to. Simple load structures and circuit structures have been examined and control units have been designed in studies carried out to date. In this study, while the DC-DC converter with a more complex load structure is discussed, mathematical analysis and PID control of DCDC converters with Buck-Boost feature are performed with the same modulation index in different time periods. In the results obtained, it is shown how to create the mathematical models of a system that provides DC-DC energy conversion with a complex load structure and how to formulate the PID control in a system with this complex load structure. [ABSTRACT FROM AUTHOR]

In the context of increasingly necessary energy transition, the precise modeling of profiles for low-voltage (LV) network consumers is crucial to enhance hosting capacity. Typically, load curves for these consumers are estimated through measurement campaigns conducted by Distribution System Operators (DSOs) for a representative subset of customers or through the aggregation of load curves from household appliances within a residence. With the instrumentation of smart meters becoming more common, a new approach to modeling profiles for residential customers is proposed to make the most of the measurements from these meters. The disaggregation model estimates the load profile of customers on a low-voltage network by disaggregating the load curve measured at the secondary substation level. By utilizing only the maximum power measured by Linky smart meters, along with the load curve of the secondary substation, this model can estimate the daily profile of customers. For 48 secondary substations in our dataset, the model obtained an average symmetric mean average percentage error (SMAPE) error of 4.91% in reconstructing the load curve of the secondary substation from the curves disaggregated by the model. This methodology can allow for an estimation of the daily consumption behaviors of the low-voltage customers. In this way, we can safely envision solutions that enhance the grid hosting capacity. [ABSTRACT FROM AUTHOR]

Energy management systems (EMS), as enablers of more efficient energy consumption, monitor and manage appliances to help residents be more energy efficient and thus more frugal. Recent appliance detection and identification techniques for such systems rely on machine learning. However, machine learning solutions for appliance classification on existing low-frequency household metering have not yet been thoroughly investigated. In this paper, we propose CARMEL, a new approach for identifying home appliances from load monitoring in building EMS based on a new data representation technique and a new model that leverages spatio-temporal correlations in the new representation. The proposed data representation technique performs dimensionality expansion of time series that scales linearly, rather than quadratically and, together with the proposed model, outperform the state of the art image transformation models by 5 percentage points. Evaluation on 5 different low-frequency household metering datasets, considering 29 appliances in total, shows that the proposed representation and the corresponding resource-aware deep learning architecture (1) achieve an average weighted F1 score of 0.92 and (2) require only 230 labeled samples and 3x fewer epochs to transfer to new households. • A new, expressive and more efficient transformation of time series signal through sub-window imaging. • A new model that captures spatio-temporal correlations within the appliance traces. • Appliance detection improvement over the state of the art models by 5 percentage points on 5 open-source datasets. • Lower adoption barrier of such data hungry AI technologies by transferring the classification model. [ABSTRACT FROM AUTHOR]

Classifiers are used for categorising nouns according to animacy, form, shape, and size. As one of the Austronesian languages, Malay is said to have an extensive numeral classifier system. Past studies have classified these two classifiers as general classifiers; however, an extensive study comparing the use of these two classifiers have not been attempted. This study aims to highlight the similarities and differences by comparing the Chinese classifier “个 (gè)” and the Malay “buah” using evidence from reference classifier dictionaries of the two languages. The findings show that while some similarities exist and both classifiers can be used interchangeably with some nouns, these classifiers are unique and have distinctive semantic usage. Both 个 (gè) and buah are used for organisation, products of nature, buildings and places, and artifacts (things created by humans). However, only 个 (gè) can be used for organs or body parts, humans, fruits and food, time, directions, and thought and intellectual products. In contrast, only buah is used for transportation, accessories, home furniture and appliances, publications, musical instruments, and performances. [ABSTRACT FROM AUTHOR]

With the rapid development of the internet of things (IoT), hundreds of millions of IoT devices, such as smart home appliances, intelligent-connected vehicles, and wearable devices, have been connected to the network. The open nature of IoT makes it vulnerable to cybersecurity threats. Traditional cryptography-based encryption methods are not suitable for IoT due to their complexity and high communication overhead requirements. By contrast, RF-fingerprint-based recognition is promising because it is rooted in the inherent non-reproducible hardware defects of the transmitter. However, it still faces the challenges of low inter-class variation and large intra-class variation among RF fingerprints. Inspired by fine-grained recognition in computer vision, we propose a fine-grained RF fingerprint recognition network (FGRFNet) in this article. The network consists of a top-down feature pathway hierarchy to generate pyramidal features, attention modules to locate discriminative regions, and a fusion module to adaptively integrate features from different scales. Experiments demonstrate that the proposed FGRFNet achieves recognition accuracies of 89.8% on 100 ADS-B devices, 99.5% on 54 Zigbee devices, and 83.0% on 25 LoRa devices. [ABSTRACT FROM AUTHOR]