In this work, a Non-Intrusive Load Monitoring (NILM) system is designed for smart homes based on smart energy meters. The proposed solution simplifies the monitoring process by using a single set of sensors, in contra...
详细信息
ISBN:
(数字)9798350361025
ISBN:
(纸本)9798350361032
In this work, a Non-Intrusive Load Monitoring (NILM) system is designed for smart homes based on smart energy meters. The proposed solution simplifies the monitoring process by using a single set of sensors, in contrast to conventional systems that call for several sensors. From different appliances and their combinations, crucial electrical information, such as voltage, current, active power, reactive power, apparent power, power factor, and frequency was gathered. Proposed intelligent data analysis employing machine learning methods, particularly Artificial Neural Networks (ANN) and Deep Neural Networks (DNN), is the key innovation. These methods accurately categorize various appliance kinds, with DNN performing best in real-time circumstances. Additionally, there is a built-in email alert system that activates whenever there are odd electrical surges. The streamlined user interface, offers accurate identification of individual appliances and combinations in real-time forecasts based on past data. Future developments include a larger appliance data-set, improved categorization methods, load forecasting, and the creation of a smartphone app for real-time energy consumption data and automatic control, among other things. In a net-shell, this study offers an effective, single-sensorbased solution for load monitoring in smart homes, representing a substantial development in NILM technology. This technology claims to improve resource utilization and energy management in both domestic and commercial settings.
This work presents the results of the examination of the HeLa cell line exposure on the ELF-EMF (extremely low-frequency electromagnetic field). In particular, the relationship between ELF-EMF exposition time and cell...
详细信息
ISBN:
(数字)9798350372359
ISBN:
(纸本)9798350372366
This work presents the results of the examination of the HeLa cell line exposure on the ELF-EMF (extremely low-frequency electromagnetic field). In particular, the relationship between ELF-EMF exposition time and cell death. The examination of cell death hallmarks were examined by estimation levels of selected proteins - FACL4 (a protein that is a part of the ferroptosis pathway) and CK18 (Cytokeratin related to necrosis and apoptosis pathways) in the proposed model of workers exposed to ELF-EMF week.
Spatial frequency (SF) is a characteristic of an image that could dissociate course and fine shape information. Physiological and psychophysical studies widely investigated the role of various SF contents in image pro...
详细信息
Spatial frequency (SF) is a characteristic of an image that could dissociate course and fine shape information. Physiological and psychophysical studies widely investigated the role of various SF contents in image processing. Inspired by the primate brain structure, deep neural networks improved various computer vision tasks such as image classification. Physiological studies show that low SF (LSF) contents of an image could be processed faster to provide feedback to facilitate object recognition. However, this knowledge has not been considered in designing neural network structures. This study introduces SFNet, a new neural network structure that employs an LSF-based feedback mechanism. SFNet is a two-stream structure where one stream is used for LSF processing to provide feedback for image classification. The other stream combines the LSF-based feedback and the HSF processing to form the final decision. The role of the proposed LSF-based feedback in image classification is investigated utilizing the CIFAR100 dataset. The results show that SFNet improves the performance in the presence of SF filtering compared to the equivalent structures.
The rapid development of the Internet of Medical Things (IoMT) has brought about an enormous amount of healthcare data. Effectively and securely processing this sensitive data has become a significant challenge for gr...
详细信息
ISBN:
(数字)9781728190549
ISBN:
(纸本)9781728190556
The rapid development of the Internet of Medical Things (IoMT) has brought about an enormous amount of healthcare data. Effectively and securely processing this sensitive data has become a significant challenge for green communication and privacy protection of the IoMT. As a decentralized learning framework, Federate learning (FL) enables model training without directly aggregating users' raw data, thus ensuring user privacy protection. Moreover, numerous studies have put forth various approaches to enhance the efficiency of FL by minimizing communication costs, yet they may not fully account for the unique characteristics of IoMT. Specifically, the efficiency and performance of model training are closely related to patient life and health. Meanwhile, existing research has indicated that reducing communication costs can result in a decline in training accuracy, which may be critical to patient health. Therefore, aimed at green communication and ensuring the model accuracy, we design a communication-efficient personalized federated learning framework, namely pFedCAS. Specifically, we introduce a control unit, which enables adaptive sparsity of local models, to reduce training costs. Furthermore, a selection unit based on communication quality is added into the global aggregation, which can select suitable clients for model updating. Simulation results validate that the proposed method can significantly reduce communication costs while ensuring the model accuracy. Additionally, The simulation results also validate the excellent robustness of our method to non-iid healthcare data.
Humans have the ability to deviate from their natural behavior when necessary, which is a cognitive process called response inhibition. Similar approaches have independently received increasing attention in recent yea...
详细信息
Iris segmentation and localization in unconstrained environments is challenging due to long distances, illumination variations, limited user cooperation, and moving subjects. Some existing methods in the literat...
详细信息
This demonstration shows live operation of of PDAVIS polarization event camera reconstruction by the E2P DNN reported in the main CVPR conference paper Deep Polarization Reconstruction with PDAVIS Events (paper 9149 [...
详细信息
Fuzzy utility mining considers high-utility fuzzy itemsets as valuable knowledge by integrating quantities of items, their profits, and meaningful fuzzy terms derived by quantities according to membership functions. I...
Fuzzy utility mining considers high-utility fuzzy itemsets as valuable knowledge by integrating quantities of items, their profits, and meaningful fuzzy terms derived by quantities according to membership functions. In fuzzy utility mining, the utility value of a fuzzy itemset in a transaction will always be greater than or equal to those of its subsets, so the measurement of fuzzy utility is an unfair evaluation method. Therefore, the fuzzy average-utility mining problem was issued in 2020, and three solutions were proposed to solve fuzzy average-utility itemsets as two-phase fuzzy average-utility algorithm (TPFAU), two-phase method with tree-based structure (HFAUIM) and one-phase approach with tree-based structure (FHFAUIM), respectively. The second and third methods decrease the candidates generated compared to the first. However, the sorting strategy for mining steps for the last two approaches is based on the frequencies of items in a database and then inserting items of a transaction into a tree in descending order of their frequencies, thus spending more computing time on deriving the actual fuzzy utility value of itemsets. To overcome the above-mentioned problem, this paper adopts a different sorting strategy with a tree-based structure and then by using it to design an algorithm named IFHFAUIM to mine high fuzzy average-utility itemsets. It reduces the storage of required fuzzy utility values in tree nodes and recovers them through tree traversal. computational experiments show that the proposed method could make a good trade-off between execution time and memory usage.
Utility mining is a popular research field in data mining. It uses item utilities and quantities to fit more into real applications. Fuzzy utility mining has also been proposed to reflect the linguistics of human perc...
Utility mining is a popular research field in data mining. It uses item utilities and quantities to fit more into real applications. Fuzzy utility mining has also been proposed to reflect the linguistics of human perceptron for item association. In the past, we proposed a fast-up date-based (FUP-based) approach to maintain high fuzzy utility itemsets for continuously coming transaction data. This paper proposes an algorithm that applies the pre-large strategy on fuzzy utility mining to raise the maintenance performance. Nine cases are considered to maintain the current high fuzzy utility itemsets based on the fuzzy upper-bound utility. The results of the numerical experiments show that our proposed algorithm has better efficiency than the batch and the FUP-based approach in the execution time.
Electro-optic phase modulators are commonly used for polarization and phase encoding in quantum key distribution. Here, a novel state preparation flaw which arises during high speed electro-optic phase modulation is i...
详细信息
ISBN:
(纸本)9781957171258
Electro-optic phase modulators are commonly used for polarization and phase encoding in quantum key distribution. Here, a novel state preparation flaw which arises during high speed electro-optic phase modulation is identified and characterized. The impact of this state preparation flaw on the secure key rate is quantified.
暂无评论