Bio-inspired Machine Learning for Distributed Confidential Multi-Portfolio Selection Problem

Khan, Ameer Tamoor; Cao, Xinwei; Liao, Bolin; Francis, Adam

doi:10.3390/biomimetics7030124

Cited by 18 publications

(9 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, ML technology [27][28][29][30][31][32][33][34] has developed rapidly and has been widely applied in various fields, such as mechanics [35][36][37][38], medicine [39][40][41][42], and energy [43][44][45][46]. The advantage of ML technology in prediction lies in its ability to handle nonlinear relationships and complex data patterns between input variables and output variables [47].…”

Section: Literature Reviewmentioning

confidence: 99%

Wind Power Forecasting Based on WaveNet and Multitask Learning

et al. 2023

Self Cite

View full text Add to dashboard Cite

Accurately predicting the power output of wind turbines is crucial for ensuring the reliable and efficient operation of large-scale power systems. To address the inherent limitations of physical models, statistical models, and machine learning algorithms, we propose a novel framework for wind turbine power prediction. This framework combines a special type of convolutional neural network, WaveNet, with a multigate mixture-of-experts (MMoE) architecture. The integration aims to overcome the inherent limitations by effectively capturing and utilizing complex patterns and trends in the time series data. First, the maximum information coefficient (MIC) method is applied to handle data features, and the wavelet transform technique is employed to remove noise from the data. Subsequently, WaveNet utilizes its scalable convolutional network to extract representations of wind power data and effectively capture long-range temporal information. These representations are then fed into the MMoE architecture, which treats multistep time series prediction as a set of independent yet interrelated tasks, allowing for information sharing among different tasks to prevent error accumulation and improve prediction accuracy. We conducted predictions for various forecasting horizons and compared the performance of the proposed model against several benchmark models. The experimental results confirm the strong predictive capability of the WaveNet–MMoE framework.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Wind Power Forecasting Based on WaveNet and Multitask Learning

et al. 2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…The bio-inspired distributed beetle antennae search (DBAS) is employed to optimize the multiportfolio selection algorithm. Simulation results demonstrate that DBAS efficiently and robustly selects the optimal portfolio [3]. The study proposes a method using macroeconomic factors to analyze market trends, employing flexible time series to represent key elements like returns and risks.…”

Section: Introductionmentioning

confidence: 99%

Monte carlo simulation with bilstm for day-ahead stock portfolio management

Shaikh,

Ramadass

2024

IJEECS

View full text Add to dashboard Cite

<div>Predicting stock price movement and optimizing day-ahead stock portfolios are challenging tasks due to the inherent complexity and volatility of financial markets. This study proposes a novel approach that combines bidirectional long short-term memory (BiLSTM) neural networks with monte carlo simulation (MCS) to enhance day-ahead stock portfolio management. In the proposed methodology, historical data of the top-performing 10 stocks from different sectors of the National Stock Exchange of India (NSEI) is obtained from 1 January 2004 to 30 June 2023 and utilized to train a BiLSTM model. This model effectively extracts intricate patterns and trends from the time series, leading to more accurate and robust stock price predictions. MCS generates different scenarios, considering various market conditions and uncertainties. These scenarios provide a comprehensive view of the portfolio’s performance under different conditions, thus mitigating the risk of relying solely on a single prediction. The study evaluates the proposed framework and compares its performance against traditional portfolio management strategies. Results demonstrate that the MCS with the BiLSTM approach outperforms traditional methods in terms of risk-adjusted returns and portfolio stability.</div>

show abstract

“…Historically, vast sets of rules or lexicons had to be manually created by professionals for both rule-based and lexicon approaches to medical entity recognition [ 7 , 8 , 9 ]. Using benchmark data from the i2b2 2009 drug challenge and a hybrid lexicon-based and rule-based model, [ 10 ] achieved an F1 score of 66.97% for the named entity recognition of pharmaceuticals.…”

Section: Introductionmentioning

confidence: 99%

Named Entity Recognition of Diabetes Online Health Community Data Using Multiple Machine Learning Models

Zhou

Liao

et al. 2023

Bioengineering

Self Cite

View full text Add to dashboard Cite

The rising prevalence of diabetes and the increasing awareness of self-health management have resulted in a surge in diabetes patients seeking health information and emotional support in online health communities. Consequently, there is a vast database of patient consultation information in these online health communities. However, due to the heterogeneity and incompleteness of the content, mining medical information and patient health data from these communities can be a challenge. To address this issue, we built the RoBERTa-BiLSTM-CRF (RBC) model for identifying entities in the online health community of diabetes. We selected 1889 question–answer texts from the most active online health community in China, Good Doctor Online, and used these public data to identify five types of entities. In addition, we conducted a comparative evaluation with three other commonly used models to validate the performance of our proposed model, including RoBERTa-CRF (RC), BilSTM-CRF (BC), and RoBERTa-Softmax (RS). The results showed that the RBC model achieved excellent performance on the test set, with an accuracy of 81.2% and an F1 score of 80.7%, outperforming the performance of traditional entity recognition models in named entity recognition in online medical communities for doctors and diabetes patients. The high performance of entity recognition in online health communities will provide a crucial knowledge source for constructing medical knowledge graphs. This integration would help alleviate the growing demand for medical consultations and the strain on healthcare resources, while assisting healthcare professionals in making informed decisions and providing personalized services to patients.

show abstract

Bio-inspired Machine Learning for Distributed Confidential Multi-Portfolio Selection Problem

Cited by 18 publications

References 58 publications

Wind Power Forecasting Based on WaveNet and Multitask Learning

Wind Power Forecasting Based on WaveNet and Multitask Learning

Monte carlo simulation with bilstm for day-ahead stock portfolio management

Named Entity Recognition of Diabetes Online Health Community Data Using Multiple Machine Learning Models

Contact Info

Product

Resources

About