Since the breakdown of the Bretton Woods system in the early 1970s, the foreign exchange (FX) market has become an important focus of both academic and practical research. There are many reasons why FX is important, but one of most important aspects is the determination of foreign investment values. Therefore, FX serves as the backbone of international investments and global trading. Additionally, because fluctuations in FX affect the value of imported and exported goods and services, such fluctuations have an important impact on the economic competitiveness of multinational corporations and countries. Therefore, the volatility of FX rates is a major concern for scholars and practitioners. Forecasting FX volatility is a crucial financial problem that is attracting significant attention based on its diverse implications. Recently, various deep learning models based on artificial neural networks (ANNs) have been widely employed in finance and economics, particularly for forecasting volatility. The main goal of this study was to predict FX volatility effectively using ANN models. To this end, we propose a hybrid model that combines the long short-term memory (LSTM) and autoencoder models. These deep learning models are known to perform well in time-series prediction for forecasting FX volatility. Therefore, we expect that our approach will be suitable for FX volatility prediction because it combines the merits of these two models. Methodologically, we employ the Foreign Exchange Volatility Index (FXVIX) as a measure of FX volatility. In particular, the three major FXVIX indices (EUVIX, BPVIX, and JYVIX) from 2010 to 2019 are considered, and we predict future prices using the proposed hybrid model. Our hybrid model utilizes an LSTM model as an encoder and decoder inside an autoencoder network. Additionally, we investigate FXVIX indices through subperiod analysis to examine how the proposed model’s forecasting performance is influenced by data distributions and outliers. Based on the empirical results, we can conclude that the proposed hybrid method, which we call the autoencoder-LSTM model, outperforms the traditional LSTM method. Additionally, the ability to learn the magnitude of data spread and singularities determines the accuracy of predictions made using deep learning models. In summary, this study established that FX volatility can be accurately predicted using a combination of deep learning models. Our findings have important implications for practitioners. Because forecasting volatility is an essential task for financial decision-making, this study will enable traders and policymakers to hedge or invest efficiently and make policy decisions based on volatility forecasting.

/pdf/forecasting-foreign-exchange-volatility-using-deep-learning-rglv27dc7h.pdf

Forecasting Foreign Exchange Volatility Using Deep Learning Autoencoder-LSTM Techniques

Malware traffic classification (MTC) is a key technology for anomaly and intrusion detection in secure Industrial Internet of Things (IIoT). Traditional MTC methods based on port, payload, and statistic depend on the manual-designed features, which have low accuracy. Recently, deep-learning methods have attracted a significant attention due to their high accuracy in terms of classification. However, in practical application scenarios, deep-learning methods require a large amount of labeled samples for training, while the available labeled samples for training are very rare. Furthermore, the preparation of a large amount of labeled samples requires a lot of labor costs. To solve these problems, this article proposes three methods based on semisupervised learning (SSL), transfer learning (TL), and domain adaptive (DA), respectively. Our proposed methods use a large amount of unlabeled data collected in the Internet traffic, which can greatly improve the classification accuracy with few labeled samples. Then, we use the DA method to solve the mismatch problem between the source domain and the target domain in the TL process. The proposed method is not only applicable to the shallow network but also to the deep neural network structure, and can achieve better classification results. Experimental results show that our proposed methods can satisfy the requirement of MTC in the case of few labeled samples in IIoT. The source code for all the experiments is available at GitHub.The code of this article can be downloaded from GitHub link: https://github.com/yzjh/Keras-MTC-DA-Ladder.

Malware Traffic Classification Using Domain Adaptation and Ladder Network for Secure Industrial Internet of Things

In the electricity market, different pricing models can be applied to increase market competitiveness. Different electricity systems use different market structures. Uniform marginal pricing, zonal marginal pricing, and nodal marginal pricing methods are commonly used market structures. For markets wishing to move from a uniform pricing structure to a more competitive zonal pricing structure, the determination of price zones is critical for achieving a competitive market that generates accurate price signals. Three different pricing zone detection algorithms are analyzed in this paper including the k-means clustering and queen/rook spatially constraint clustering. Finally, the results of a case study for the Turkish electricity system are shared to compare each method.

https://www.mdpi.com/1996-1073/14/4/1014/pdf

Determination of Price Zones during Transition from Uniform to Zonal Electricity Market: A Case Study for Turkey

Malware traffic classification (MTC) is a key technology for anomaly and intrusion detection in secure Industrial Internet of Things (IIoT). Traditional MTC methods based on port, payload, and statistic depend on the manual-designed features, which have low accuracy. Recently, deep-learning methods have attracted a significant attention due to their high accuracy in terms of classification. However, in practical application scenarios, deep-learning methods require a large amount of labeled samples for training, while the available labeled samples for training are very rare. Furthermore, the preparation of a large amount of labeled samples requires a lot of labor costs. To solve these problems, this article proposes three methods based on semisupervised learning (SSL), transfer learning (TL), and domain adaptive (DA), respectively. Our proposed methods use a large amount of unlabeled data collected in the Internet traffic, which can greatly improve the classification accuracy with few labeled samples. Then, we use the DA method to solve the mismatch problem between the source domain and the target domain in the TL process. The proposed method is not only applicable to the shallow network but also to the deep neural network structure, and can achieve better classification results. Experimental results show that our proposed methods can satisfy the requirement of MTC in the case of few labeled samples in IIoT. The source code for all the experiments is available at GitHub.The code of this article can be downloaded from GitHub link: <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/yzjh/Keras-MTC-DA-Ladder</uri> . 

Mining fuzzy association rules from database

For the network service construction and optimization of wireless cell, the effective scene division is an important basis for formulating more accurate network construction schemes and optimization strategies. The traditional cell scene division method is manually divided according to the single-dimensional business indicators, but there are some problems such as the inaccuracy of division and the inability to visualize. In this paper, we propose a cell scene division and visualization method based on autoencoder and K-means algorithm. We train an autoencoder network to conduct the dimension reduction of the wireless perception key quality indicator (KQI) data of cells, and then use elbow method and K-means algorithm to cluster the dimension-reduced data precisely. Through statistical analysis and comparison of indicators of cells in different classes obtained by clustering, we finally achieve accurate cell scene division and visualization.

/pdf/cell-scene-division-and-visualization-based-on-autoencoder-2tgzuf6ybm.pdf

Cell Scene Division and Visualization Based on Autoencoder and K-Means Algorithm

The ever-increasing amount of data in cellular networks poses challenges for network operators to monitor the quality of experience (QoE). Traditional key quality indicators (KQIs)-based hard decision methods are difficult to undertake the task of QoE anomaly detection in the case of big data. To solve this problem, in this paper, we propose a KQIs-based QoE anomaly detection framework using semi-supervised machine learning algorithm, i.e., iterative positive sample aided one-class support vector machine (IPS-OCSVM). There are four steps for realizing the proposed method while the key step is combining machine learning with the network operator's expert knowledge using OCSVM. Our proposed IPS-OCSVM framework realizes QoE anomaly detection through soft decision and can easily fine-tune the anomaly detection ability on demand. Moreover, we prove that the fluctuation of KQIs thresholds based on expert knowledge has a limited impact on the result of anomaly detection. Finally, experiment results are given to confirm the proposed IPS-OCSVM framework for QoE anomaly detection in cellular networks.

/pdf/semi-supervised-machine-learning-aided-anomaly-detection-ylmmpitku7.pdf

Semi-Supervised Machine Learning Aided Anomaly Detection Method in Cellular Networks

Cellular network performance is often evaluated by key performance indicator (KPI) and key quality indicator (KQI). The association between KQI and KPI is the most critical step to optimize the performance of cellular network. Traditional association methods between KPI and KQI are based on the end-to-end evaluation. However, these methods require professional engineers to evaluate cellular network performance, and the man-manned evaluation is often inaccurate and labor-consuming, which cannot find out the caused factor of deterioration networks. In order to solve the problem, we propose a machine learning based quantitative association rule mining (QARM) method called SWP-RF, which consists of sliding-window partitioning (SWP) and random forest (RF), to associate KPI with KQI. Specifically, we first use SWP to discretize continuous attributes into boolean values, which is adopted to mine its association rules. The warning intervals and the warning points is obtained by SWP. Next, we use RF feature importance to measure the association between KPI and KQI. The priority of the association strength between all KPIs and each KQI can be obtained by RF. Finally, we select the warning points and the association strength priority as optimal output solution. Experiments are conducted over the actual data from telecom operators and the results confirm the feasibility and accuracy of the proposed method.

/pdf/machine-learning-based-quantitative-association-rule-mining-156de31fl3.pdf

Machine Learning Based Quantitative Association Rule Mining Method for Evaluating Cellular Network Performance

Wireless user perception (WeUP) is considered one of the most important factors in designing next-generation wireless communications systems. The recognition of WeUP involves lots of labor cost up to now. In order to solve this problem, this paper proposes an accuracy recognition algorithm for WeUP based on dimensional reduction and semi-supervised clustering. Usually, the WeUP is highly reflected in the key quality indicator (KQI). we build up a database of KQI including more than 1000 cells to train a deep belief autoencoder (DBA) for dimensional reduction (DR). Then we feed the historical unlabeled and manual-labeled negative data set after dimensional reduction into semi-supervised clustering model. After that, we find out a recognition range, which is the most similar to manual-labeled objects with unsatisfied WeUP. Simulation results show that our proposed method achieves an accurate recognition of unsatisfied WeUP over 93%.The study indicates that dimensional reduction and semi-supervised machine learning method is effective in recognizing unsatisfied WeUP in wireless networks.

WeUp: Wireless User Perception Based on Dimensional Reduction and Semi-Supervised Clustering

Cellular network performance is often evaluated by key performance indicator (KPI) and key quality indicator (KQI). The association between KQI and KPI is the most critical step to optimize the performance of cellular networks. Traditional association methods between KPI and KQI are based on the end-to-end evaluation. However, these methods require professional engineers to evaluate cellular network performance, and the man-manned evaluation is often inaccurate and labor-consuming, which cannot find out the main caused factor of deterioration networks. In order to solve the problem, we propose a machine learning-based quantitative association rule mining (QARM) method called SWP to associate KPI with KQI. Specifically, we mainly discretize continuous attributes into boolean values and then the association rules of these boolean values are mined by QARM algorithms, such as the Apriori algorithm. Finally, we select the warning intervals and the warning points obtained by SWP method as an optimal output solution. Experiments are conducted over the actual data from telecom operators and the results confirm the feasibility and accuracy of the proposed method

Kaixuan Zhang

Papers

Cell Scene Division and Visualization Based on Autoencoder and K-Means Algorithm

Semi-Supervised Machine Learning Aided Anomaly Detection Method in Cellular Networks

Machine Learning Based Quantitative Association Rule Mining Method for Evaluating Cellular Network Performance

WeUp: Wireless User Perception Based on Dimensional Reduction and Semi-Supervised Clustering

Cellular Network Performance using Machine Learning based Quantitative Association Rule Mining Method