One of the most notable developments in the asset management industry in recent decades has been the growth of algorithmic trading.At the same time,significant structural changes in the industry have occurred,with pas...One of the most notable developments in the asset management industry in recent decades has been the growth of algorithmic trading.At the same time,significant structural changes in the industry have occurred,with passive investing gaining momentum.The intersection of these two major trends poses special challenges during market downturns,magnifying portfolio losses and leading to significant outflows.Emerging market(EM)investors have seen two major downturn events in the 2020s,namely the COVID-19 pandemic and the Russia-Ukraine conflict,both of which have strongly affected EM portfolios’risk-return profiles and increased their correlations with their developed market counterparts,eliminating much or all of EMs’diversification benefits.This has led to major capital outflows from EM countries,further destabilizing these fragile economies.Against this backdrop,we argue that capital need not exit these riskier markets during periods of turmoil and support this by developing a second-generation Automated Adaptive Trading System(AATS)back-tested on a relevant,diversified EM portfolio that tracks the Morgan Stanley Capital International(MSCI)Emerging Markets Index during a volatile period characterized by negative returns,high risk,and a high correlation with global markets for the buy-and-hold EM portfolio.The system incorporates an Autoregressive Moving Average-Generalized AutoRegressive Conditional Heteroskedasticity model that offers an interpretability advantage over machine-learning methods.The main strength of the AATS is its ability to allow the embedded hybrid forecasting model to adapt to the changing environments that characterize EMs.This is done by implementing a recursive window technique and running a user-specified fitness function to dynamically optimize the mean equation parameters throughout the lead time.Back-testing several configurations of the flexible AATS consistently reveals its superiority while assuring the robustness of the results.We conclude that with the right investment tools,EMs continue to offer compelling opportunities that should not be overlooked.The novel AATS proposed in this study is such a tool,providing active EM investors with substantial value-added through its ability to generate abnormal returns,and can help to enhance the resilience of EMs by mitigating the cost of crises for those countries.展开更多
Regarding the performance of traditional endpoint detection algorithms degrades as the environment noise level increases, a recursive calculating algorithm for higher-order cu- mulants over a sliding window is propose...Regarding the performance of traditional endpoint detection algorithms degrades as the environment noise level increases, a recursive calculating algorithm for higher-order cu- mulants over a sliding window is proposed. Then it is applied to the speech endpoint detection. Furthermore, endpoint detection is carried out with the feature of energy. Experimental results show that both the computational efficiency and the robustness against noise of the proposed algorithm are improved remarkably compared with traditional algorithm. The average prob- ability of correct point detection （Pc-point） of the proposed voice activity detection （VAD） is 6.07% higher than that of G.729b VAD in different noisy at different signal-noise ratios （SNRs） environments.展开更多
Human motion prediction is a critical issue in human-robot collaboration(HRC)tasks.In order to reduce the local error caused by the limitation of the capture range and sampling frequency of the depth sensor,a hybrid h...Human motion prediction is a critical issue in human-robot collaboration(HRC)tasks.In order to reduce the local error caused by the limitation of the capture range and sampling frequency of the depth sensor,a hybrid human motion prediction algorithm,optimized sliding window polynomial fitting and recursive least squares(OSWPF-RLS)was proposed.The OSWPF-RLS algorithm uses the human body joint data obtained under the HRC task as input,and uses recursive least squares(RLS)to predict the human movement trajectories within the time window.Then,the optimized sliding window polynomial fitting(OSWPF)is used to calculate the multi-step prediction value,and the increment of multi-step prediction value was appropriately constrained.Experimental results show that compared with the existing benchmark algorithms,the OSWPF-RLS algorithm improved the multi-step prediction accuracy of human motion and enhanced the ability to respond to different human movements.展开更多
基金funded by the EU’s NextGenerationEU instrument through the National Recovery and Resilience Plan of Romania-Pillar Ⅲ-C9-I8,managed by the Ministry of Research,Innovation and Digitalization,within the project entitled,Non-Gaussian self-similar processes:Enhancing mathematical tools and financial models for capturing complex market dynamics,contract no.760243/28.12.2023,code CF 194/31.07.2023’.
文摘One of the most notable developments in the asset management industry in recent decades has been the growth of algorithmic trading.At the same time,significant structural changes in the industry have occurred,with passive investing gaining momentum.The intersection of these two major trends poses special challenges during market downturns,magnifying portfolio losses and leading to significant outflows.Emerging market(EM)investors have seen two major downturn events in the 2020s,namely the COVID-19 pandemic and the Russia-Ukraine conflict,both of which have strongly affected EM portfolios’risk-return profiles and increased their correlations with their developed market counterparts,eliminating much or all of EMs’diversification benefits.This has led to major capital outflows from EM countries,further destabilizing these fragile economies.Against this backdrop,we argue that capital need not exit these riskier markets during periods of turmoil and support this by developing a second-generation Automated Adaptive Trading System(AATS)back-tested on a relevant,diversified EM portfolio that tracks the Morgan Stanley Capital International(MSCI)Emerging Markets Index during a volatile period characterized by negative returns,high risk,and a high correlation with global markets for the buy-and-hold EM portfolio.The system incorporates an Autoregressive Moving Average-Generalized AutoRegressive Conditional Heteroskedasticity model that offers an interpretability advantage over machine-learning methods.The main strength of the AATS is its ability to allow the embedded hybrid forecasting model to adapt to the changing environments that characterize EMs.This is done by implementing a recursive window technique and running a user-specified fitness function to dynamically optimize the mean equation parameters throughout the lead time.Back-testing several configurations of the flexible AATS consistently reveals its superiority while assuring the robustness of the results.We conclude that with the right investment tools,EMs continue to offer compelling opportunities that should not be overlooked.The novel AATS proposed in this study is such a tool,providing active EM investors with substantial value-added through its ability to generate abnormal returns,and can help to enhance the resilience of EMs by mitigating the cost of crises for those countries.
基金supported by the National Natural Science Eoundation of China(61271352)
文摘Regarding the performance of traditional endpoint detection algorithms degrades as the environment noise level increases, a recursive calculating algorithm for higher-order cu- mulants over a sliding window is proposed. Then it is applied to the speech endpoint detection. Furthermore, endpoint detection is carried out with the feature of energy. Experimental results show that both the computational efficiency and the robustness against noise of the proposed algorithm are improved remarkably compared with traditional algorithm. The average prob- ability of correct point detection （Pc-point） of the proposed voice activity detection （VAD） is 6.07% higher than that of G.729b VAD in different noisy at different signal-noise ratios （SNRs） environments.
基金supported by the National Natural Science Foundation of China(61701270)the Young Doctor Cooperation Foundation of Qilu University of Technology(Shandong Academy of Sciences)(2017BSHZ008)。
文摘Human motion prediction is a critical issue in human-robot collaboration(HRC)tasks.In order to reduce the local error caused by the limitation of the capture range and sampling frequency of the depth sensor,a hybrid human motion prediction algorithm,optimized sliding window polynomial fitting and recursive least squares(OSWPF-RLS)was proposed.The OSWPF-RLS algorithm uses the human body joint data obtained under the HRC task as input,and uses recursive least squares(RLS)to predict the human movement trajectories within the time window.Then,the optimized sliding window polynomial fitting(OSWPF)is used to calculate the multi-step prediction value,and the increment of multi-step prediction value was appropriately constrained.Experimental results show that compared with the existing benchmark algorithms,the OSWPF-RLS algorithm improved the multi-step prediction accuracy of human motion and enhanced the ability to respond to different human movements.
