this work presents the most recent research in Intelligent Intervals, which combines modern information technology and advanced robotics. Researchers use robots outfitted with various sensors and instruments on the su...
详细信息
We share the common hypothesis/belief that the more aggregated good quality training data, the better the performance that can be attained by the resulting Artificial Intelligence (AI) model. However, this common beli...
详细信息
ISBN:
(纸本)9781665474061
We share the common hypothesis/belief that the more aggregated good quality training data, the better the performance that can be attained by the resulting Artificial Intelligence (AI) model. However, this common belief, in general, is not true in the medical area, since healthcare data sets sourced from different hospitals are often not identically distributed (NonIID). this imposes severe technical challenges for effectively aggregating the individual hospital data sets together. In this vision paper, instead of offering complete solutions, we will discuss some questions and food for thought withthe goal of aiding effective data aggregation and improving federated learning (FL) AI model performance: (1) benchmark and measure the Non-IID degree of medical data sets. (2) include the Non-IID degree metrics in the FL data aggregation mechanism. (3) search for the optimal global model creation strategy among a group of many medical data sets. (4) investigate FL performance better than the centralized learning. this paper will discuss these questions by outlining a visionary approach for exploring a medical blockchain FL mechanism to effectively aggregate medical data across multiple healthcare systems to serve large populations with broad demographics.
this study describes a method for identifying human behavior based on depth motion maps. A depth video array projects each depth outline onto three symmetric Cartesian planes. A comprehensive depth video group forming...
详细信息
this paper concerns the secure fusion filtering under multiple false data injection attack scenarios. A hierarchical clustering based secure fusion filtering approach is proposed for the remote-measuring system with a...
详细信息
ISBN:
(纸本)9781728162072
this paper concerns the secure fusion filtering under multiple false data injection attack scenarios. A hierarchical clustering based secure fusion filtering approach is proposed for the remote-measuring system with a known secure node. the fusion filtering approach includes two parts. In the local filtering part, the remote measurement is utilized to estimate the system sate locally, after detected by Chi-square detector. In the distributed fusion part, a novel hierarchical clustering detection based distributed fusion method is provided to obtain the final fusion filtering results. the simulation results are presented to illustrate the effectiveness of the proposed approach.
In this paper, a distributed sample-based event-triggered method is proposed to coordinate the thermostatically controlled loads (TCLs) such that the photovoltaic and load variations can be alleviated from demand side...
详细信息
ISBN:
(纸本)9781665490283
In this paper, a distributed sample-based event-triggered method is proposed to coordinate the thermostatically controlled loads (TCLs) such that the photovoltaic and load variations can be alleviated from demand side. Firstly, a sample-based event-triggered control scheme, where each TCL communicates with its neighbor TCLs only when the event-triggered condition is satisfied, and thus reducing redundant communication to save the limited communication network resources. then, an initial power state updating scheme of each TCL is designed based on the output of PVs and loads such that the supply and demand balance can be satisfied from demand side. Under the designed control scheme, the resident's comfort temperature range requirement can be met. Furthermore, the challenge problem Zeno behavior that often occurs in event-triggered control is automatically excluded. Finally, by employing Lyapunov stability theory, the sufficient criteria is rigidly derived.
the multi-energy management framework of industrial parks advocates energy conversion and scheduling, which takes full advantage of the compensation and temporal availability of multiple energy. However, how to exploi...
详细信息
ISBN:
(纸本)9781728162072
the multi-energy management framework of industrial parks advocates energy conversion and scheduling, which takes full advantage of the compensation and temporal availability of multiple energy. However, how to exploit elastic loads and compensate inelastic loads to match multiple generators and storage is still a key problem under the uncertainty of demand and supply. To solve the issue, the energy management problem is constructed as a stochastic optimization problem. the optimization aims are to minimize the time-averaged energy cost and improve the energy efficiency while respecting the energy constraints. To achieve the distributed implementation in real time without knowing any priori knowledge of underlying stochastic process, a distributed stochastic gradient algorithm based on dual decomposition and a fast scheme are proposed. the numerical results based on real data show that the industrial park, by adopting the proposed algorithm, can achieve social welfare maximization asymptotically.
Background: the insurance industry faces substantial challenges in retaining customers because insurance contracts renew once a year but need accurate churn risk evaluation and customer loss prediction. Predictions of...
详细信息
ISBN:
(数字)9798331533663
ISBN:
(纸本)9798331533670
Background: the insurance industry faces substantial challenges in retaining customers because insurance contracts renew once a year but need accurate churn risk evaluation and customer loss prediction. Predictions of insurance premiums hold a crucial position for maximizing customer satisfaction while optimizing retention. Methods: To improve premium price prediction results, the research utilizes machine learning (ML) models between Random Forest (RF) and Gradient Boosting Regression (GBR) against baseline models consisting of Support Vector Regression (SVR) and XGB. Results: Results from experimental analyses demonstrate how GBR surpasses both RF and SVR with R²=0.8652 and RMSE=0.3839 but XGB achieves the lowest RMSE value of 0.2231. Conclusion: the outcomes suggest that advanced techniques of ML are more capable of enhancing the premium forecast, thereby enhancing the understanding of risk and setting cost-effective strategies. the following highlights help to increase customer loyalty and satisfaction for insurance companies and policyholders in the insurance landscape.
the conservation and presentation of intangible cultural heritage (ICH) by traditional means are sometimes confronted withthe setbacks of restricted interactivity, non-immersive experiences, and static presentations ...
详细信息
ISBN:
(数字)9798331533663
ISBN:
(纸本)9798331533670
the conservation and presentation of intangible cultural heritage (ICH) by traditional means are sometimes confronted withthe setbacks of restricted interactivity, non-immersive experiences, and static presentations that cannot catch the interests of contemporary audiences. Such setbacks, however, impede the proper communication of ICH, most especially in presenting it as it is in its dynamic, experiential aspect. In response to such setbacks, this study suggests a digital exhibition system of ICH using Augmented Reality (AR) technology. AR provides a novel solution by projecting digital content onto the real world, enabling users to engage with and experience cultural aspects in an immersive and interactive manner. the suggested system improves the accessibility and understanding of intangible cultural heritage by integrating interactive elements, including virtual simulations of rituals, performances, and oral traditions. Empirical case studies illustrate the system's capacity to have a substantial impact on user engagement and offer greater understanding of the cultural context and meaning of ICH. the findings emphasize the success of AR in providing an enriched and more meaningful learning experience, making it easier to preserve and share intangible cultural heritage in ways that other methods cannot. Yet, there are still challenges within content generation and technological demands, which are dealt with in the recommendations for improved integration approaches and development workflows. the research helps to improve AR technology in the context of cultural heritage uses and offers a promising path towards future innovation in the conservation of ICH.
Cryptographic techniques combined with Graph labeling make it harder for an opponent to hack the plaintext. Sharing sensitive information without third-party exposure remains a challenge, but cryptography addresses th...
详细信息
ISBN:
(数字)9798331533663
ISBN:
(纸本)9798331533670
Cryptographic techniques combined with Graph labeling make it harder for an opponent to hack the plaintext. Sharing sensitive information without third-party exposure remains a challenge, but cryptography addresses this issue. this study offers brand-new encryption algorithms for protected message transmission using an n-Prism graph and labeling scheme like minimization of even multiplicative labeling and multiplicative lableing. Experimental results confirm the efficiency and security of the proposed Prism Graph-based Encryption Scheme (PGES). the scheme achieves linear time complexity O(n), significantly reducing execution time compared to traditional methods. At n = 40, PGES executes in 0.000208 seconds, while a general graph-based cryptographic system (GCS) requires 0.00740 seconds. Similarly, Cipher graph-based encryption takes 4.0762 seconds at n = 20, making PGES a more efficient alternative for real-time secure communication. Beyond speed, PGES strengthens security against man-in-the-middle and replay attacks, thanks to its structured graph-labeling approach. By integrating multiplicative and minimization of even multiplicative labeling with matrix operations, the scheme provides a lightweight yet powerful encryption framework. these advantages make PGES a practical choice for applications requiring high security and quick processing.
In recent scenarios, the audit risk identification is a critical component of external auditing for the auditors to focus on high-risk areas and ensure accurate financial reporting. However, the existing Risk Assessme...
详细信息
ISBN:
(数字)9798331533663
ISBN:
(纸本)9798331533670
In recent scenarios, the audit risk identification is a critical component of external auditing for the auditors to focus on high-risk areas and ensure accurate financial reporting. However, the existing Risk Assessment Framework (RAF) faced challenges in identifying audit risks due to imbalanced audit risks. Hence, this research proposes a Synthetic Minority Oversampling Technique with Back Propagation Neural Network (SMOTE-BPNN) to balance the audit risks. the proposed SMOTE-BPNN balances the audit risks by oversampling high-risk audits as well as identify them by learning patterns and relationships among the risks. Initially, the input data is collected from Audit dataset and then fed into processing. Here, the data is preprocessed with data cleaning to eliminate irrelevant attributes and min-max normalization to scale feature values into a specific range. After that, Mutual Information (MI) technique is employed to measure the dependency among variables for the selection of optimal features. then, SMOTE balances the data by oversampling them and finally BPNN is introduced to identify the audit risks efficiently. From the results, the proposed SMOTE-BPNN achieved better results in terms of Accuracy (96.57%), specificity (94.05%), and sensitivity (93.62%) when compared to existing Bi-directional Long Short-Term Memory with Attention Mechanism (BiLSTM-AM) respectively.
暂无评论