Supervised deep learning (SDL) has shown remarkable success in various financial applications, such as stock prediction and fraud detection. However, SDL’s reliance on class labels renders it unsuitable for portfolio...
详细信息
ISBN:
(数字)9798350370249
ISBN:
(纸本)9798350370270
Supervised deep learning (SDL) has shown remarkable success in various financial applications, such as stock prediction and fraud detection. However, SDL’s reliance on class labels renders it unsuitable for portfolio management (PM) tasks, where such labels are often unavailable. To address this limitation, we propose a novel two-level architecture based on deep reinforcement learning (DRL) for PM, which does not require class labels. Our approach comprises several local agents that provide trading decisions and uncertainty assessments for individual stocks, and a global agent that makes portfolio management decisions based on the outputs of the local agents. Additionally, we incorporate the concept of explainable AI (XAI) into our framework using the SHAP (Shapley additive explanations) method, enhancing the transparency and interpretability of the global agent’s decisions. Our experimental results demonstrate that the proposed architecture consistently yields profitable outcomes in the market.
Background] Emotional Intelligence (EI) can impact Software Engineering (SE) outcomes through improved team communication, conflict resolution, and stress management. SE workers face increasing pressure to develop bot...
详细信息
ISBN:
(数字)9798331538712
ISBN:
(纸本)9798331502539
Background] Emotional Intelligence (EI) can impact Software Engineering (SE) outcomes through improved team communication, conflict resolution, and stress management. SE workers face increasing pressure to develop both technical and interpersonal skills, as modern software development emphasizes collaborative work and complex team interactions. Despite EI's documented importance in professional practice, SE education continues to prioritize technical knowledge over emotional and social competencies. [Objective] This paper analyzes SE students' self-perceptions of their EI after a twomonth cooperative learning project, using Mayer and Salovey's four-ability model to examine how students handle emotions in collaborative development. [Method] We conducted a case study with 29 SE students organized into four squads within a projectbased learning course, collecting data through questionnaires and focus groups that included brainwriting and sharing circles, then analyzing the data using descriptive statistics and open coding. [Results] Students demonstrated stronger abilities in managing their own emotions compared to interpreting others' emotional states. Despite limited formal EI training, they developed informal strategies for emotional management, including structured planning and peer support networks, which they connected to improved productivity and conflict resolution. [Conclusion] This study shows how SE students perceive EI in a collaborative learning context and provides evidence-based insights into the important role of emotional competencies in SE education.
While much CCI research has dealt with the educational challenge of providing children with knowledge and skills for a digital society, little work has dealt with the strategic challenge of developing and implementing...
详细信息
Matrix factorization (MF) technique has been widely utilized in recommendation systems due to the precise prediction of users' interests. Prior MF-based methods adapt the overall rating to make the recommendation ...
详细信息
Reinforcement Learning (RL) is an extraordinarily paradigm that aims to solve a complex problem. This technique leverages the traditional feedforward networks with temporal-difference learning to overcome supervised a...
详细信息
Until recently, Smart Home technologies are still not widely deployed in most peoples living spaces. The main reason is that operations management mechanisms for Smart Home such as remote deployment, monitoring, and m...
详细信息
Matrix factorization (MF) technique has been widely utilized in recommendation systems due to the precise prediction of users' interests. Prior MF-based methods adapt the overall rating to make the recommendation ...
ISBN:
(数字)9781728128207
ISBN:
(纸本)9781728128214
Matrix factorization (MF) technique has been widely utilized in recommendation systems due to the precise prediction of users' interests. Prior MF-based methods adapt the overall rating to make the recommendation by extracting latent factors from users and items. However, in real applications, people's preferences usually vary with time; the traditional MF-based methods could not properly capture the change of users' interests. In this paper, by incorporating the recurrent neural network (RNN) into MF, we develop a novel recommendation system, M-RNN-F, to effectively describe the preference evolution of users over time. A learning model is proposed to capture the evolution pattern and predict the user preference in the future. The experimental results show that M-RNN-F performs better than other state-of-the-art recommendation algorithms. In addition, we conduct the experiments on real world dataset to demonstrate the practicability.
Background: Asthma and atopic dermatitis are common allergic conditions that contribute to substantial health loss, economic burden, and pain across individuals of all ages worldwide. Therefore, as a component of the ...
Background: Asthma and atopic dermatitis are common allergic conditions that contribute to substantial health loss, economic burden, and pain across individuals of all ages worldwide. Therefore, as a component of the Global Burden of Diseases, Injuries, and Risk Factors Study (GBD) 2021, we present updated estimates of the prevalence, disability-adjusted life-years (DALYs), incidence, and deaths due to asthma and atopic dermatitis and the burden attributable to modifiable risk factors, with forecasted prevalence up to 2050. Methods: Asthma and atopic dermatitis prevalence, incidence, DALYs, and mortality, with corresponding 95% uncertainty intervals (UIs), were estimated for 204 countries and territories from 1990 to 2021. A systematic review identified data from 389 sources for asthma and 316 for atopic dermatitis, which were further pooled using the Bayesian meta-regression tool. We also described the age-standardised DALY rates of asthma attributable to four modifiable risk factors: high BMI, occupational asthmagens, smoking, and nitrogen dioxide pollution. Furthermore, as a secondary analysis, prevalence was forecasted to 2050 using the Socio-demographic Index (SDI), air pollution, and smoking as predictors for asthma and atopic dermatitis. To assess trends in the burden of asthma and atopic dermatitis before (2010–19) and during (2019–21) the COVID-19 pandemic, we compared their average annual percentage changes (AAPCs). Findings: In 2021, there were an estimated 260 million (95% UI 227–298) individuals with asthma and 129 million (124–134) individuals with atopic dermatitis worldwide. Asthma cases declined from 287 million (250–331) in 1990 to 238 million (209–272) in 2005 but increased to 260 million in 2021. Atopic dermatitis cases consistently rose from 107 million (103–112) in 1990 to 129 million (124–134) in 2021. However, age-standardised prevalence rates decreased—by 40·0% (from 5568·3 per 100 000 to 3340·1 per 100 000) for asthma and 8·3% (from 1885·4
Reinforcement Learning (RL) is an extraordinarily paradigm that aims to solve a complex problem. This technique leverages the traditional feedforward networks with temporal-difference learning to overcome supervised a...
ISBN:
(数字)9781728128207
ISBN:
(纸本)9781728128214
Reinforcement Learning (RL) is an extraordinarily paradigm that aims to solve a complex problem. This technique leverages the traditional feedforward networks with temporal-difference learning to overcome supervised and unsupervised real-world problems. However, RL is one of state-of-the-art topic due to the opaque aspects in design and implementation. Also, in which situation we will get performance gain from RL is still unclear. Therefore, This study firstly examines the impact of Experience Replay in Deep Q-Learning agent with Self-Driving Car application. Secondly, The impact of Eligibility Trace in RNN A3C agents with Breakout AI game application is studied. Our results indicated that these two techniques enhance RL performance by more than 20 percent as compared with traditional RL methods.
Until recently, Smart Home technologies are still not widely deployed in most peoples living spaces. The main reason is that operations management mechanisms for Smart Home such as remote deployment, monitoring, and m...
详细信息
Until recently, Smart Home technologies are still not widely deployed in most peoples living spaces. The main reason is that operations management mechanisms for Smart Home such as remote deployment, monitoring, and maintenance are not well-studied and only a few attempts have so far been made toward this aspect. CWMP, proposed by Broadband Forum, is a promising standard for realizing a Smart Home operations management platform. Previously, we have investigated real-world operations management issues of Smart Home services, namely, newly installed, module purchasing and download, service start, service update, service diagnosis, failure recovery, usage statistics, and billing. After examining CWMP in detail, several issues of CWMP, namely, poor performance and scalability, poor domain model design and inappropriate web callback architecture, have been identified. The objective of this paper is, therefore, to deal with the issues mentioned above by suggesting a set of RESTful ways to refactor the CWMP-based operations management platform. The overall approach is based on the RESTful architectural style. The proposed architecture has been realized as an operations management platform prototype. Validations and experiments are performed to verify the effectiveness of the proposed architecture.
暂无评论