Search

When constructing an investment portfolio, it is important to maximize returns while minimizing risks. This portfolio optimization can be considered as a multi-objective optimization problem that is solved by means of multi-objective evolutionary algorithms. The use of multi-objective evolutionary algorithms (MOEAs) provides an effective approach for dealing with the complex data involved in multi-objective optimization problems. However, current MOEAs often rely on a single strategy to obtain optimal solutions, leading to premature convergence and an insufficient population diversity. In this paper, a new MOEA called the Synergistic MOEA with Diffusion Population Generation (DPG-SMOEA) is proposed to address these limitations by integrating MOEAs with diffusion models. To train the diffusion model, a mixed memory pool strategy is optimized, which collects improved solutions from the MOEA/D-AEE, an optimized MOEA, as training samples. The trained model is then used to generate offspring. Considering the cold-start mechanism of the diffusion model, particularly during the training phase where it is not suitable for generating initial offspring, this paper adjusts and optimizes the collaborative strategy to enhance the synergy between the diffusion model and MOEA/D-AEE. Experimental validation of the DPG-SMOEA demonstrates the advantages of using diffusion models in low-dimensional and relatively continuous data analysis. The results show that the DPG-SMOEA performs well on the low-dimensional Hang Seng Index test dataset, while achieving average performance on other high-dimensional datasets, consistent with theoretical predictions. Overall, the DPG-SMOEA achieves better results compared to MOEA/D-AEE and other multi-objective optimization algorithms. [ABSTRACT FROM AUTHOR]

Wireless sensing techniques for Human Activity Recognition (HAR) have been widely studied in recent years. At present, research on HAR based on Radio Frequency Identification (RFID) is changing from the tag attachment method to the tag non-attachment method. Affected by multipath, the current solutions in tag non-attachment scenarios mainly focus on single-object activity recognition, which is not suitable for multi-object scenarios. To address these issues, we propose STMultiple, a novel tag non-attachment activity recognition model for multi-object. The model first preprocesses the raw signal with filter and phase calibration, then it applies dilated convolution in the frequency domain to extract multi-object activity features, finally the feature pyramid structure and ProbSparse are used to optimize the vanilla Transformer-Encoder to enhance the activity recognition ability. Extensive experiments show that STMultiple can achieve recognition accuracy of up to 97.93% and down to about 90% in challenging environments ranging from two to five users, which has excellent performance compared to several state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Comprehensive Summary: Metal organic frameworks have been employed as high‐performance layered double hydroxide (LDH) composite supercapacitor electrode materials but have shown unsatisfactory redox ability and stability. Herein, a host‐guest CuMo‐based polyoxometalate‐based metal organic framework (POMOF) with copious electrochemically active sites and strong electrochemical redox activities has been effectively coupled with POM‐incorporated CoNi‐LDH to develop a nanocomposite (NENU‐5@CoNi‐LDH) by a simple solvothermal method. The designed electrode shows a high specific capacity of 333.61 mAh·g–1 at 1 A·g–1. In addition, the novel hybrid symmetric supercapacitor NENU‐5@CoNi‐LDH/active carbon (AC) demonstrated a high energy density of 80.8 Wh·kg–1 at a power density of 750.7 W·kg–1. Interestingly, the nanocomposite of NENU‐5@CoNi‐LDH exhibits an outstanding capacitance retention of 79% after 5000 charge‐discharge cycles at 10 A·g–1. This work provides a new strategy and will be the backbone for future energy storage research. [ABSTRACT FROM AUTHOR]

Comprehensive Summary: Metal organic frameworks have been employed as high‐performance layered double hydroxide (LDH) composite supercapacitor electrode materials but have shown unsatisfactory redox ability and stability. Herein, a host‐guest CuMo‐based polyoxometalate‐based metal organic framework (POMOF) with copious electrochemically active sites and strong electrochemical redox activities has been effectively coupled with POM‐incorporated CoNi‐LDH to develop a nanocomposite (NENU‐5@CoNi‐LDH) by a simple solvothermal method. The designed electrode shows a high specific capacity of 333.61 mAh·g–1 at 1 A·g–1. In addition, the novel hybrid symmetric supercapacitor NENU‐5@CoNi‐LDH/active carbon (AC) demonstrated a high energy density of 80.8 Wh·kg–1 at a power density of 750.7 W·kg–1. Interestingly, the nanocomposite of NENU‐5@CoNi‐LDH exhibits an outstanding capacitance retention of 79% after 5000 charge‐discharge cycles at 10 A·g–1. This work provides a new strategy and will be the backbone for future energy storage research. [ABSTRACT FROM AUTHOR]

C57BL/6J mice have long been studied as a model of age-related hearing loss (ARHL). In C57BL/6J mice, ARHL begins in the high-frequency range at 3 months of age and spreads toward low frequencies by 10 months of age. We previously confirmed that c.753A>G genome editing of an ahl allele (c.753A) in the cadherin 23 gene (Cdh23) suppressed the onset of ARHL until 12 months of age. We further investigated the hearing phenotypes of the original and genome-edited C57BL/6J-Cdh23 +/+ (c.753G/G) mice until 24 months of age. The hearing tests revealed that most of the C57BL/6J mice maintained good hearing levels until 14 months of age following genome editing of a Cdh23 ahl allele. However, the hearing levels of the C57BL/6J-Cdh23 +/+ mice gradually declined, and severe ARHL developed with increasing age. ARHL in the C57BL/6J mice was correlated with degeneration of the stereocilia in cochlear hair cells. The stereocilia degeneration was rescued in the C57BL/6J-Cdh23 +/+ mice at 12 months of age, but the stereocilia bundles exhibited abnormal phenotypes similar to those of the original C57BL/6J mice at more advanced ages. Therefore, genome editing of Cdh23 ahl did not completely suppress ARHL in C57BL/6J mice. We also compared the hearing levels of C57BL/6J-Cdh23 +/+ mice with those of C3H/HeN and MSM/Ms mice, which carry the Cdh23 + allele. The severity and onset patterns of ARHL in the C57BL/6J-Cdh23 +/+ mice differed from those observed in other Cdh23 +/+ mice. Therefore, we hypothesize that other susceptible and/or resistant alleles of ARHL exist in the genetic backgrounds of these mice., Competing Interests: Declaration of competing interest None., (Copyright © 2020 Elsevier B.V. All rights reserved.)