Soft Computing Letters最新文献

Speech recognition systems have made tremendous progress since the last few decades. They have developed significantly in identifying the speech of the speaker. However, there is a scope of improvement in speech recognition systems in identifying the nuances and accents of a speaker. It is known that any specific natural language may possess at least one accent. Despite the identical word phonemic composition, if it is pronounced in different accents, we will have sound waves, which are different from each other. Differences in pronunciation, in accent and intonation of speech in general, create one of the most common problems of speech recognition. If there are a lot of accents in language we should create the acoustic model for each separately. We carry out a systematic analysis of the problem in the accurate classification of accents. We use traditional machine learning techniques and convolutional neural networks, and show that the classical techniques are not sufficiently efficient to solve this problem. Using spectrograms of speech signals, we propose a multi-class classification framework for accent recognition. In this paper, we focus our attention on the French accent. We also identify its limitation by understanding the impact of French idiosyncrasies on its spectrograms.

Encouraging the use of public transport is essential to combat congestion and pollution in an urban environment. To achieve this, the reliability of arrival time prediction should be improved as this is one area of improvement frequently requested by passengers. The development of accurate predictive algorithms requires good quality data, which is often not available. Here we demonstrate a method to synthesise data using a reference curve approach derived from very limited real world data without reliable ground truth. This approach allows the controlled introduction of artefacts and noise to simulate their impact on prediction accuracy. To illustrate these impacts, a recurrent neural network next-step prediction is used to compare different scenarios in two different UK cities. The results show that a realistic data synthesis is possible, allowing for controlled testing of predictive algorithms. It also highlights the importance of reliable data transmission to gain such data from real world sources. Our main contribution is the demonstration of a synthetic data generator for public transport data, which can be used to compensate for low data quality. We further show that this data generator can be used to develop and enhance predictive algorithms in the context of urban bus networks if high-quality data is limited, by mixing synthetic and real data.

Factorization machine (FM) is a promising model-based algorithm for collaborative filtering (CF), but can bring inferior performances if datasets include users having low confidence. In this paper, a robust FM model is proposed by introducing the noise clustering-based noise rejection mechanism into Fuzzy FM, which utilizes fuzzy memberships of users for considering the responsibility of each user in FM modeling. By automatically updating fuzzy memberships with user-wise criteria of prediction errors, the FM model is better fitted to reliable users and is expected to improve the generalization ability for predicting the preference degrees of unknown items. The characteristics of the proposed method are demonstrated through numerical experiments with MovieLens movie evaluation data such that the prediction ability for not only the training ratings but also the test ratings of reliable users can be improved by carefully tuning the noise sensitivity weight.

The foreign exchange (FOREX) market is one of the biggest financial markets in the world. More than 5.1 trillion dollars are traded each day in the FOREX market by banks, retail traders, corporations, and individuals. Due to complex, volatile, and high fluctuation, it is quite difficult to guess the price ahead of the actual time. Traders and investors continuously look for new methods to outperform the market and to earn a higher profit. Therefore, researchers around the world are continuously coming up with new forecasting models to successfully predict the nature of this unsettled market. This paper presents a new model that combines two powerful neural networks used for time series prediction: Gated Recurrent Unit (GRU) and Long Short Term Memory (LSTM), for predicting the future closing prices of FOREX currencies. The first layer of our proposed model is the GRU layer with 20 hidden neurons and the second layer is the LSTM layer with 256 hidden neurons. We have applied our model on four major currency pairs: EUR/USD, GBP/USD, USD/CAD, and USD/CHF. The prediction is done for 10 minutes timeframe using the data from January 1, 2017 to December 31, 2018, and 30 minutes timeframe using the data from January 1, 2019 to June 30, 2020 as a proof-of-concept. The performance of the model is validated using MSE, RMSE, MAE, and $R^2$ score. Moreover, we have compared the performance of our model against a standalone LSTM model, a standalone GRU model and simple moving average (SMA) based statistical model where the proposed hybrid GRU-LSTM model outperforms all models for 10-mins timeframe and for 30-mins timeframe provides the best result for GBP/USD and USD/CAD currency pairs in terms of MSE, RMSE, and MAE performance metrics. But in terms of $R^2$ score, our system outperforms all compared models and thus proves itself as the least risky model among all.

This paper presents a new multi-attribute decision-making (MADM) method, named as R-method, for ranking of Pareto-optimal solutions and selecting the best solution in multi- and many-objective optimization problems. The compromise among the optimization objectives is different for each Pareto-optimal solution and, hence, the solution that has the best compromise among the objectives can be considered as the best solution. The proposed R-method is used to identify such best compromise solution. The method ranks the objectives based on their importance for the given optimization problem and ranks the alternative solutions (i.e. Pareto-optimal solutions) based on their data corresponding to the objectives. The ranks assigned to the objectives and the ranks assigned to the alternative solutions with respect to each of the objectives are converted to appropriate weights and the final composite scores of the alternative solutions are computed using these weights. The final ranking of alternative solutions is done based on the composite scores. The steps of the proposed method are described along with a pseudocode. Three examples are considered to demonstrate and validate the proposed method. The first example contains 4-objectives and 50 alternative solutions, the second example contains 6-objectives and 30 alternative solutions, and the third example contains 3-objectives and 25 alternative solutions. The results of the proposed method are compared with those of the other widely used MADM methods for the three examples considered. Also, the proposed method is compared with four well-known ranking methods to demonstrate its rationality in assigning weights to the ranks of the objectives and the alternative solutions. The proposed method is comparatively easier, more logical, and can be used for choosing the best compromise solution in multi- and many-objective optimization problems.

Cancer detection using gene expression data has been a major trend of research for the last decade. Microarray gene expression data is one of the most challenging types of data due to high dimensionality and rarity of available samples. Feature redundancy greatly contributes to the difficulty of prediction task. Therefore, it is essential to apply feature selection to datasets to reduce the number of features selected for the classification task. In this paper, a novel two-staged framework is proposed to confront curse of dimensionality in microarray data using data complexity measures and a customized cultural algorithm, incorporating a static belief space into the genetic algorithm in order to reduce the search space and prioritize important genes. Experimental results indicate highly improved accuracy and reduction in number of selected genes compared to the state-of-the-art methods on Gli85, Colon, DLBCL, SMK and CNS datasets.

Selecting a team for executing a project is not an easy task. As any project involves monetary implications, management of a company employs a careful approach in choosing a project team. Several variations of Multi Criteria Decision Making (MCDM) Models are available in the literature and practice. We propose a modified intutionistic fuzzy approach to project team selection. We have combined the MCDM with dynamic weightage for each parameter. The main design parameters in this model are the conversion of input data into the fuzzified form, design of non - membership grade and the calculation of indeterministic values from membership and non- membership grades. Finally, the fuzzified output is converted into a crisp set, known as defuzzification. This method helps in determining the most skilled candidates in the order of their ability from a group of applicants.

Stock market prediction is the process of forecasting future prices of stocks. Stock market prediction is a challenging process as a result of uncertainties that influence the market change of price. This paper proposes a nature-inspired algorithm, called Auditory Algorithm (AA), which follows the pathway of the auditory system like that of the human ear. The performance of AA is compared with that of high performance machine learning algorithms and continuous-time stochastic process. The machine learning algorithms used in this paper are Logistic Regression (LR), Support Vector Machine (SVM), Feed forward neural network (FFN) and Recurrent Neural Network (RNN) while continuous-time models such as Stochastic Differential Equation (SDE) and Geometric Brownian Motion (GBM) are also used. The results show that the overall performance of AA is superior to that of other algorithms compared in this paper, as it drastically reduced the forecast error to the barest minimum.

This article has been withdrawn: please see Elsevier Policy on Article Withdrawal (http://www.elsevier.com/locate/withdrawalpolicy). This article has been withdrawn at the request of the authors. The authors apologize for the inconvenience caused.