Mutual Information Method Research Articles

Characterization of ground oscillations induced by underground mining

We examine ground acceleration during M1.5 and M2.0 seismic events induced by underground mining at Upper Silesian coal basin and Legnica Glogow copper mine, respectively, using methods of nonlinear time series analysis, in order to confirm its stochastic nature. Recorded time series are firstly embedded into the adequate phase space using the mutual information and box-assisted methods. After this, we performed stationarity test, by which we confirmed that the examined ground acceleration belongs to a group of stationary processes. Surrogate data testing is applied then, which resulted in following: (1) horizontal ground acceleration at Legnica Glogow copper mine represents stationary linear stochastic processes with Gaussian inputs, (2) ground acceleration at Upper Silesian coal basin originates from a stationary Gaussian linear process that has been distorted by a monotonic, instantaneous, time-independent non-linear function, (3) vertical ground acceleration at Legnica Glogow copper mine could not be ascribed to any of the examined processes, probably due to high level of instrumental or background noise. Low values of determinism coefficient (c≤0.7), negative values of maximum Lyapunov exponent and quick saturation of neighboring points distance with the increase of embedding dimension indicate the absence of determinism in the observed ground acceleration time series.

Task-State EEG Signal Classification for Spatial Cognitive Evaluation Based on Multiscale High-Density Convolutional Neural Network.

In this study, a multi-scale high-density convolutional neural network (MHCNN) classification method for spatial cognitive ability assessment was proposed, aiming at achieving the binary classification of task-state EEG signals before and after spatial cognitive training. Besides, the multi-dimensional conditional mutual information method was used to extract the frequency band features of the EEG data. And the coupling features under the combination of multi-frequency bands were transformed into multi-spectral images. At the same time, the idea of Densenet was introduced to improve the multi-scale convolutional neural network. Firstly, according to the discreteness of multispectral EEG image features, two-scale convolution kernels were used to calculate and learn useful channel and frequency band feature information in multispectral image data. Secondly, to enhance feature propagation and reduce the number of parameters, the dense network was connected after the multi-scale convolutional network, and the learning rate change function of the stochastic gradient descent algorithm was optimized to objectively evaluate the training effect. The experimental results showed that compared with the classical convolution neural network (CNN) and multi-scale convolution neural network, the proposed MHCNN had better classification performance in the six frequency band combinations with the highest accuracy of 98%: Theta-Alpha2-Gamma, Alpha2-Beta2-Gamma, Beta1-Beta2-Gamma, Theta-Beta2-Gamma, Theta- Alpha1-Gamma, and Alpha1-Alpha2-Gamma. By comparing the classification results of six frequency band combinations, it was found that the combination of the Theta-Beta2-Gamma band had the best classification effect. The MHCNN classification method proposed in this research could be used as an effective biological indicator of spatial cognitive training effect and could be extended to other brain function evaluations.

Multi-dimensional conditional mutual information with application on the EEG signal analysis for spatial cognitive ability evaluation

This study aims to explore an effective method to evaluate spatial cognitive ability, which can effectively extract and classify the feature of EEG signals collected from subjects participating in the virtual reality (VR) environment; and evaluate the training effect objectively and quantitatively to ensure the objectivity and accuracy of spatial cognition evaluation, according to the classification results. Therefore, a multi-dimensional conditional mutual information (MCMI) method is proposed, which could calculate the coupling strength of two channels considering the influence of other channels. The coupled characteristics of the multi-frequency combination were transformed into multi-spectral images, and the image data were classified employing the convolutional neural networks (CNN) model. The experimental results showed that the multi-spectral image transform features based on MCMI are better in classification than other methods, and among the classification results of six band combinations, the best classification accuracy of Beta1–Beta2–Gamma combination is 98.3%. The MCMI characteristics on the Beta1–Beta2–Gamma band combination can be a biological marker for the evaluation of spatial cognition. The proposed feature extraction method based on MCMI provides a new perspective for spatial cognitive ability assessment and analysis.

Reconstruction of Phase Space and Eigenvalue Decomposition from a Biological Time Series: A Malayalam Speech Signal Case Study

Our objective is to describe the speech production system from a non-linear physiological system perspective and reconstruct the attractor from the experimental speech data. Mutual information method is utilized to find out the time delay for embedding. The False Nearest Neighbour (FNN) method and Principal Component Analysis (PCA) method are used for optimizing the embedding dimension of time series. The time series obtained from the typical non-linear systems, Lorenz system and Rössler system, is used to standardize the methods and the Malayalam speech vowel time series of both genders of different age groups, sampled at three sampling frequencies (16[Formula: see text]kHz, 32[Formula: see text]kHz, 44.1[Formula: see text]kHz), are taken for analysis. It was observed that time delay varies from sample to sample and, it ought to be better to figure out the time delay with the embedding dimension analysis. The embedding dimension is shown to be independent of gender, age and sampling frequency and can be projected as five. Hence a five-dimensional hyperspace will probably be adequate for reconstructing attractor of speech time series.

A multi-label emoji classification method using balanced pointwise mutual information-based feature selection

The availability of social media such as twitter allows users to express their feeling, emotions and opinions toward a topic. Emojis are graphic symbols that are regarded as the new generation of emoticons and an effective way of conveying feelings and emotions in social media. With the surging popularity of Emojis, the researchers in the area of Emotion Classification strive to understand the emotion correlated to each Emoji. Two of the most the successful approaches in emoji analysis rely on: 1) official Unicode description and 2) manually built emoji lexicons. Since the use of emoji is socially determined, the former approach is not aligned with intended semantic and usage, which leads researchers to opt for emoji lexicons. To overcome problem of lexicon-based approach, we proposed a method to classify emojis automatically. Therefore, we present a modified Pointwise Mutual Information (PMI) method, called Balanced Pointwise Mutual Information-Based (B-PMI), to develop a balanced weighted emoji classification based on the semantic similarity. Further, deep neural network is used to represent emoji in vector form (emoji embedding) to extend the pre-trained word embeddings. We carefully evaluated the proposed method in multiple twitter datasets that are employed in sentiment and emotion classification using machine learning (ML) and deep learning (DL) approaches. In both approaches, extending word embedding with the proposed emoji embedding improved results. The DL-based approach achieved the highest f1-score of 70.01% for sentiment classification, and accuracy score of 56.36% for emotion classification. ML-based approach obtained accuracy score of 52.17% in emotion classification.

Hybrid Selection Method of Feature Variables and Prediction Modeling for Municipal Solid Waste Incinerator Temperature.

It is difficult to establish an accurate mechanism model for prediction incinerator temperatures due to the comprehensive complexity of the municipal solid waste (MSW) incineration process. In this paper, feature variables of incineration temperature are selected by combining with mutual information (MI), genetic algorithms (GAs) and stochastic configuration networks (SCNs), and the SCN-based incinerator temperature model is obtained simultaneously. Firstly, filter feature selection is realized by calculating the MI value between each feature variable and the incinerator temperature from historical data. Secondly, the fitness function of GAs is defined by the root mean square error of the incinerator temperature obtained by training SCNs, and features obtained by MI methods are searched iteratively to complete the wrapper feature selection, where the SCN-based incinerator temperature prediction model is obtained. Finally, the proposed model is verified by MSW incinerator temperature historical data. The results show that the SCN-based prediction model using the hybrid selection method can better predict the change trend of incinerator temperature, which proves that the SCNs has great development potential in the field of prediction modeling.

Mutating fuzzy logic model with various rigorous meta-heuristic algorithms for soil moisture content estimation

Soil moisture content (SMC) prediction can contribute to diverse geo-science engineering applications such as plantation, crops production, and several irrigation activities. Although, there have been several methodologies introduced for the SMS estimation, methods are still associated with challenges and limitations (e.g., time-consuming, high cost, and the need for large data sets). In the current research, the motivation was inspired to develop new data-intelligence models that are capable to estimate SMC accurately and reliably. Several hybridized adaptive neuro fuzzy inference system (NF) models were developed. The feasibility of four meta-heuristic algorithms including the gray wolf optimization (GWO), Bee algorithm (BA), Firefly algorithm (FA), and imperialistic competitive algorithm (ICA), were used to improve the predictability performance of the NF model. The performances of the hybrid models were tested at two different climate characteristics (i.e., humid and arid) and four different soil depths (5, 10, 20, and 50 cm). The dataset used in this study were consisted of ten years with daily scale. Practical inputs predictors for the prediction matrix were identified using the mutual information method (MI) and correlation coefficient, which included maximum and minimum temperature, solar radiation, and soil temperature. K-Fold technique and various indices were used to evaluate hybrid models. Despite the promising results of all developed models, the NF-FA is superior to the others in both climates. The average results of all depths (in humid climate) using correlation coefficient (r), mean absolute percentage error (MAPE), and scattering index (SI) were 0.924, 6.089%, and 0.074, respectively. While in the arid climate, NF-FA model attained 0.903, 14.439%, and 0.176 in r, MAPE, and SI, respectively. The evaluation of different depths and climates showed that NF-FA yielded the best accuracy within humid climates and depths of 20 and 10 cm had the lowest estimation error in humid and arid climates. This study introduced the FA algorithm as an efficient tool in NF development to estimate SMC by readily available inputs without knowing soil physical parameters.

Mechanical Fault Diagnosis of High Voltage Circuit Breaker based on Improved GSO-SVM Algorithm

The vibration signal generated by the transmission and impact of mechanical components of circuit breaker has chaotic performances, which is difficult to be analysed by conventional signal processing methods. The phase space reconstruction of vibration signal is worked on, and the signal reconstruction parameters are calculated by mutual information method and Cao algorithm respectively. The vibration signal is reconstructed into a high-dimensional space, and its permutation entropy is calculated as a feature vector. Support vector machine (SVM) is used to identify the failure type of circuit breaker, and PSO improved GSA hybrid algorithm is used to optimize the parameters of SVM so as to obtain high recognition accuracy. The experiment is carried out with the measured vibration signal of the typical operation state of the circuit breaker. The results show that the characteristics of circuit breaker vibration signals can be extracted accurately with the combination of phase space reconstruction and permutation entropy. By using PSO-GSA-SVM, the fault types of circuit breakers can be identified quickly and effectively, and the problems of path distortion, energy leakage and mode overlap of existing diagnosis methods can be solved.

Examining optimum prediction time of rainfall dynamics based on chaotic perspective at different temporal scales: a case study in Bojonegoro, Indonesia

As the driving force of the hydrological system, rain has severe impact when dealing with petroleum mining activities, especially in protecting assets and safety. Rainfall has high variability, both spatial and temporal (chaotic data). Due to this reason, ones can only create long-range prediction using the stochastic method. Here we use the Lyapunov exponent to analyze the nonlinear pattern of rainfall dynamics. This method is useful for identifying chaotic deportment in rainfall data. This study uses rainfall data for six years obtained from one of the largest petroleum mining sites in Bojonegoro, Indonesia. Rainfall dynamics have been analyzed on three different time scales, namely daily data, 5-day, and 10-day. The time delay (τ) was obtained by using the Average Mutual Information (AMI) method for the three-rainfall series (3, 2, 3, respectively). The observed rainfall data in Bojonegoro show signs of chaos as the finite correlation dimensions (m) attain values about 4 for all time scales. The maximum Lyapunov exponent λmax for each of three-rainfall series in Bojonegoro is 0.111, 0.057, 0.062, respectively. These values were analyzed to find the optimum prediction time of rainfall occurrence to perform better forecasting. The result shows that the optimum range of prediction time for daily, 5-day, and 10-day have 9, 18, and 16 times longer than their temporal scale.

Polarimetry feature parameter deriving from Mueller matrix imaging and auto-diagnostic significance to distinguish HSIL and CSCC

High-grade squamous intraepithelial lesion (HSIL) is regarded as a serious precancerous state of cervix, and it is easy to progress into cervical invasive carcinoma which highlights the importance of earlier diagnosis and treatment of cervical lesions. Pathologists examine the biopsied cervical epithelial tissue through a microscope. The pathological examination will take a long time and sometimes results in high inter- and intra-observer variability in outcomes. Polarization imaging techniques have broad application prospects for biomedical diagnosis such as breast, liver, colon, thyroid and so on. In our team, we have derived polarimetry feature parameters (PFPs) to characterize microstructural features in histological sections of breast tissues, and the accuracy for PFPs ranges from 0.82 to 0.91. Therefore, the aim of this paper is to distinguish automatically microstructural features between HSIL and cervical squamous cell carcinoma (CSCC) by means of polarization imaging techniques, and try to provide quantitative reference index for pathological diagnosis which can alleviate the workload of pathologists. Polarization images of the H&E stained histological slices were obtained by Mueller matrix microscope. The typical pathological structure area was labeled by two experienced pathologists. Calculate the polarimetry basis parameter (PBP) statistics for this region. The PBP statistics (stat_PBPs) are screened by mutual information (MI) method. The training method is based on a linear discriminant analysis (LDA) classifier which finds the most simplified linear combination from these stat_PBPs and the accuracy remains constant to characterize the specific microstructural feature quantitatively in cervical squamous epithelium. We present results from 37 clinical patients with analysis regions of cervical squamous epithelium. The accuracy of PFP for recognizing HSIL and CSCC was 83.8% and 87.5%, respectively. This work demonstrates the ability of PFP to quantitatively characterize the cervical squamous epithelial lesions in the H&E pathological sections. Significance: Polarization detection technology provides an efficient method for digital pathological diagnosis and points out a new way for automatic screening of pathological sections.

Impact of climate change on hydro-climatological parameters in North Cyprus: application of artificial intelligence-based statistical downscaling models

Abstract There are many environmental challenges in water-limited places in the 21st century, particularly in dry and semi-arid regions, due to the threat of climate change caused by the greenhouse effect. This study intends to explore and assess the influence of climate change on hydro-climatological parameters using statistical downscaling and future forecasts of mean monthly precipitation and temperature throughout Famagusta (Mağusa), Nicosia (Lefkoşa), and Kyrenia (Girne) stations, North Cyprus. To achieve the study's goal, 13 predictors of BNU-ESM GCMs from CMIP5 were used at a grid point in the Karfas region. To find the primary predictors, GCM data were screened using mutual information (MI) and correlation coefficient (CC) feature extraction methods prior to downscaling modeling. A neural network (ANN), an adaptive neuro fuzzy inference system (ANFIS), and multiple linear regression (MLR) models were employed as the downscaling models. We used the best downscaling model as a benchmark for future precipitation and temperature estimates for the period 2018–2040 under the RCP4.5 scenario. In the future, Famagusta and Nicosia would have up to 22% less rain, and Famagusta and Kyrenia will have 2.9% greater heat. The findings of this research could be useful in decision-making, as well as water resource management and climate change.

Analysis on oral medication rules of traditional Chinese medicine prescriptions for prevention of COVID-19

ObjectiveTo analyze the medication rules of traditional Chinese medicine (TCM) preventive oral prescriptions for COVID-19. MethodsThe preventive oral prescriptions for COVID-19 published by national and provincial health and wellness committees, administrations of TCM, medical institutions at all levels, medical masters and Chinese medicine experts were collected to establish a database, manual screening was carried out according to the inclusion and exclusion criteria, and frequency statistics, association rule analysis. The mutual information method, entropy hierarchical clustering and other methods were improved through Excel and the TCM inheritance auxiliary platform V2.5 to mine the rules and characteristics of medication. ResultsThe selected 157 prescriptions contained a total of 130 TCMs. The top five TCMs with the highest use frequency were Glycyrrhizae Radix et Rhizoma (86), Astragali Radix (80), Lonicerea Japonicae Flos (70), Atractylodis Macrocephalae Rhizoma (62), Saposhnikoviae Radix (60). In accordance with TCM efficacy classification, most of them were medicines for qi-tonifying (279), followed by medicines for clearing heat and drying dampness (163), dispelling pathogenic wind-cold (126), resolving dampness (111), as well as dispelling pathogenic wind-heat (99). The characteristics of four-natures of the selected medicines are as follows: most of them were cold (59), followed by warm (38) and mild (21). In terms of five-taste, most of them were sweet (26) and acrid-and-bitter (24), followed by sweet-and-bitter (20), bitter (20) and acrid (15). For the meridian attribution, the five-zang organs and six-fu organs were all involved, most of them attributed to lung meridian (80), followed by stomach meridian (57) and spleen meridian (40). Based on association rule analysis, 12 commonly used medicine combinations with two or three TCMs were found. The commonly used medicinal pairs included Astragali Radix and Saposhnikoviae Radix (51), Astragali Radix and Atractylodis Macrocephalae Rhizoma (46), Atractylodis Macrocephalae Rhizoma and Saposhnikoviae Radix (43), Astragali Radix and Atractylodis Macrocephalae Rhizoma and Saposhnikoviae Radix (38), Forsythiae Fructus and Astragali Radix (37), and so on. In addition, 14 core combinations of medicines were obtained by complex system entropy cluster analysis, on this basis, six new prescriptions were screened out based on unsupervised entropy hierarchical clustering analysis. According to The Catalogue of Edible TraditionalChineseMedicinalMaterials, TraditionalChineseMedicinalMaterials for Health Food, and New Resources of Food published by National Health Commission of the People’s Republic of China, there are 35 species belonging to the group of edible traditionalChinesemedicinalmaterials, 20 species belonging to the group of new resources of food, 31 species belonging to the group of traditionalChinesemedicinalmaterials for health food, 19.11% of the preventive oral prescriptions for COVID-19 were composed of the medicines belonging to the above three groups. Besides, there are 11 toxic species, and 24.84% of the preventive oral prescriptions for COVID-19 contained toxic TCMs. ConclusionWe found that invigorating qi and resolving dampness were the main treatment used to prevent for COVID-19, combined with the methods for strengthening vital energy and eliminating pathogenic factors. Most of the preventive oral prescriptions for COVID-19 were treated in lung, spleen and stomach meridians. In the process of selecting prescriptions and using TCMs to prevent for COVID-19, the safety of preventive medicines was also emphasized. And the theory of “Preventive Treatment of Disease” was embodied in these preventive oral prescriptions for COVID-19. For the prescriptions containing toxic TCMs, specialattentionshould bepaidto their safety in clinical application.

Evolution of global fossil fuel trade dependencies

Trade relationships contribute greatly to energy security and trade efficiency, which are increasing vital in energy trade. Thus, trade relationships are worthy of further investigation, especially in relation to fossil fuels trade (including coal, crude oil, and natural gas), due to their high share of the global energy trade. To deeply reveal the trade relationships in fossil fuel trade, this paper contributes to investigate its dynamic dependencies. The point-wise mutual information method was applied to quantify fossil fuel trade dependencies, and the complex networks method was used to analyze the communities in the fossil fuel trade dependency network. The modeling results show that China and Japan had high trade dependencies with Turkmenistan, Kazakhstan, and Uzbekistan in importing natural gas. There is great market space in South America region as for the USA's oil trade. Countries such as China, Australia, the United Kingdom, the Russian Federation, and Germany, which are leading members in each community, can play leadership roles in addressing the climate-trade dilemma. It is suggested that the leading countries in the communities play leadership roles and exert their great influence in the communities to address specific issues, such as solving the climate-trade dilemma.

CrossModalNet: exploiting quality preoperative images for multimodal image registration

A long-standing problem in image-guided radiotherapy is that inferior intraoperative images present a difficult problem for automatic registration algorithms. Particularly for digital radiography (DR) and digitally reconstructed radiograph (DRR), the blurred, low-contrast, and noisy DR makes the multimodal registration of DR–DRR challenging. Therefore, we propose a novel CNN-based method called CrossModalNet to exploit the quality preoperative modality (DRR) for handling the limitations of intraoperative images (DR), thereby improving the registration accuracy. The method consists of two parts: DR–DRR contour predictions and contour-based rigid registration. We have designed the CrossModal Attention Module and CrossModal Refine Module to fully exploit the multiscale crossmodal features and implement the crossmodal interactions during the feature encoding and decoding stages. Then, the predicted anatomical contours of DR–DRR are registered by the classic mutual information method. We collected 2486 patient scans to train CrossModalNet and 170 scans to test its performance. The results show that it outperforms the classic and state-of-the-art methods with 95th percentile Hausdorff distance of 5.82 pixels and registration accuracy of 81.2%. The code is available at https://github.com/lc82111/crossModalNet.

A Medical Image Registration Method Based on Progressive Images.

Background Medical image registration is an essential task for medical image analysis in various applications. In this work, we develop a coarse-to-fine medical image registration method based on progressive images and SURF algorithm (PI-SURF) for higher registration accuracy. Methods As a first step, the reference image and the floating image are fused to generate multiple progressive images. Thereafter, the floating image and progressive image are registered to get the coarse registration result based on the SURF algorithm. For further improvement, the coarse registration result and the reference image are registered to perform fine image registration. The appropriate progressive image has been investigated by experiments. The mutual information (MI), normal mutual information (NMI), normalized correlation coefficient (NCC), and mean square difference (MSD) similarity metrics are used to demonstrate the potential of the PI-SURF method. Results For the unimodal and multimodal registration, the PI-SURF method achieves the best results compared with the mutual information method, Demons method, Demons+B-spline method, and SURF method. The MI, NMI, and NCC of PI-SURF are improved by 15.5%, 1.31%, and 7.3%, respectively, while MSD decreased by 13.2% for the multimodal registration compared with the optimal result of the state-of-the-art methods. Conclusions The extensive experiments show that the proposed PI-SURF method achieves higher quality of registration.

Daily Power Generation Forecasting Method for a Group of Small Hydropower Stations Considering the Spatial and Temporal Distribution of Precipitation—South China Case Study

This paper proposes a multimodal deep learning method for forecasting the daily power generation of small hydropower stations that considers the temporal and spatial distribution of precipitation, which compensates for the shortcomings of traditional forecasting methods that do not consider differences in the spatial distribution of precipitation. First, the actual precipitation values measured by ground weather stations and the spatial distribution of precipitation observed by meteorological satellite remote sensing are used to complete the missing precipitation data through linear interpolation, and the gridded precipitation data covering a group of small hydropower stations are constructed. Then, considering the time lag between changes in the daily power generation of the group of small hydropower stations and precipitation, the partial mutual information method is used to estimate the “time difference” between the two, and combined with the precipitation grid data, a data set of the temporal and spatial distribution of precipitation is generated. Finally, using only the temporal and spatial distribution of precipitation and historical power generation data, a multimodal deep learning network based on a convolutional neural network (CNN) and multilayer perceptron (MLP) is constructed, and a highly accurate prediction model for the daily power generation of small hydropower stations is obtained. Taking the real power generation data of a group of small hydropower stations in southern China as an example, after considering the temporal and spatial distribution of precipitation, the prediction accuracy of the proposed method is as high as 93%, which is approximately 5.8% higher than before considering the temporal and spatial distribution of precipitation. In addition, compared with mainstream methods such as support vector regression (SVR) and the long–short-term memory network (LSTM) (the average accuracy is about 87%), and the average accuracy improvement of the proposed method is approximately 6%.

Classifier Performance Evaluation for Lightweight IDS Using Fog Computing in IoT Security

In this article, a Host-Based Intrusion Detection System (HIDS) using a Modified Vector Space Representation (MVSR) N-gram and Multilayer Perceptron (MLP) model for securing the Internet of Things (IoT), based on lightweight techniques and using Fog Computing devices, is proposed. The Australian Defence Force Academy Linux Dataset (ADFA-LD), which contains exploits and attacks on various applications, is employed for the analysis. The proposed method is divided into the feature extraction stage, the feature selection stage, and classification modeling. To maintain the lightweight criteria, the feature extraction stage considers a combination of 1-gram and 2-gram for the system call encoding. In addition, a Sparse Matrix is used to reduce the space by keeping only the weight of the features that appear in the trace, thus ignoring the zero weights. Subsequently, Linear Correlation Coefficient (LCC) is utilized to compensate for any missing N-gram in the test data. In the feature selection stage, the Mutual Information (MI) method and Principle Component Analysis (PCA) are utilized and then compared to reduce the number of input features. Following the feature selection stage, the modeling and performance evaluation of various Machine Learning classifiers are conducted using a Raspberry Pi IoT device. Further analysis of the effect of MLP parameters, such as the number of nodes, number of features, activation, solver, and regularization parameters, is also conducted. From the simulation, it can be seen that different parameters affect the accuracy and lightweight evaluation. By using a single hidden layer and four nodes, the proposed method with MI can achieve 96% accuracy, 97% recall, 96% F1-Measure, 5% False Positive Rate (FPR), highest curve of Receiver Operating Characteristic (ROC), and 96% Area Under the Curve (AUC). It also achieved low CPU time usage of 4.404 (ms) milliseconds and low energy consumption of 8.809 (mj) millijoules.

Predicting with the quantify intensities of transcription factor-target genes binding using random forest technique

With the rapid development of technology, this development led to the emergence of microarray technology. It has the effect of studying the levels of gene expression in a way that makes it easier for researchers to observe the expression levels of millions of genes at the same time in a single experiment. Development also helped in the emergence of powerful tools to identify interactions between target genes and regulatory factors. The main aim of this study is to build models to predicate the relationship (Interaction) between Transcription Factors (TFs) proteins and target genes by selecting the subset of important genes (Relevant genes) from original dataset. The proposed methodology comprises into three major stages: the genes selection, merge datasets and the prediction stage. The process of reducing the computational space of gene data has been accomplished by using proposed mutual information method for genes selection based on the data of gene expression. In the prediction, the proposed prediction regression techniques are utilized to predict with binding rate between single TF-target gene. It has been compared the efficiency of two different proposed regression techniques including: Linear Regression and Random Forest Regression. Two available data sets have been utilized to achieve the objectives of this study: Gene’s expression data of Yeast Cell Cycle dataset and Transcription Factors dataset. The evaluation of predictions performance has been performed depending on two performance prediction measures (Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) with (10) Folds-Cross Validation.

Surface Electromyography and Electroencephalogram-Based Gait Phase Recognition and Correlations Between Cortical and Locomotor Muscle in the Seven Gait Phases.

The classification of gait phases based on surface electromyography (sEMG) and electroencephalogram (EEG) can be used to the control systems of lower limb exoskeletons for the rehabilitation of patients with lower limb disorders. In this study, the slope sign change (SSC) and mean power frequency (MPF) features of EEG and sEMG were used to recognize the seven gait phases [loading response (LR), mid-stance (MST), terminal stance (TST), pre-swing (PSW), initial swing (ISW), mid-swing (MSW), and terminal swing (TSW)]. Previous researchers have found that the cortex is involved in the regulation of treadmill walking. However, corticomuscular interaction analysis in a high level of gait phase granularity remains lacking in the time–frequency domain, and the feasibility of gait phase recognition based on EEG combined with sEMG is unknown. Therefore, the time–frequency cross mutual information (TFCMI) method was applied to research the theoretical basis of gait control in seven gait phases using beta-band EEG and sEMG data. We firstly found that the feature set comprising SSC of EEG as well as SSC and MPF of sEMG was robust for the recognition of seven gait phases under three different walking speeds. Secondly, the distribution of TFCMI values in eight topographies (eight muscles) was different at PSW and TSW phases. Thirdly, the differences of corticomuscular interaction between LR and MST and between TST and PSW of eight muscles were not significant. These insights enrich previous findings of the authors who have carried out gait phase recognition and provide a theoretical basis for gait recognition based on EEG and sEMG.

MMIM: An Interpretable Regularization Method for Neural Networks (Student Abstract)

In deep learning models, most of network architectures are designed artificially and empirically. Although adding new structures such as convolution kernels in CNN is widely used, there are few methods to design new structures and mathematical tools to evaluate feature representation capabilities of new structures. Inspired by ensemble learning, we propose an interpretable regularization method named Minimize Mutual Information Method(MMIM), which minimize the generalization error by minimizing the mutual information of hidden neurons. The experimental results also verify the effectiveness of our proposed MMIM.