Search

1 In the setting where participants are asked multiple similar possibly subjective multi-choice questions (e.g., Do you like Panda Express? Y/N; Do you like Chick-fil-A? Y/N), a series of peer prediction mechanisms have been designed to incentivize honest reports and some of them achieve dominantly truthfulness: Truth-telling is a dominant strategy and strictly dominates other "non-permutation strategy" with some mild conditions. However, those mechanisms require the participants to perform an infinite number of tasks. When the participants perform a finite number of tasks, these mechanisms only achieve approximated dominant truthfulness. The existence of a dominantly truthful multi-task peer prediction mechanism that only requires a finite number of tasks remains to be an open question that may have a negative result, even with full prior knowledge. This article answers this open question by proposing a family of mechanisms, VMI-Mechanisms, that are dominantly truthful with a finite number of tasks. A special case of this family, DMI-Mechanism, only requires ≥ 2C tasks where C is the number of choices for each question (C=2 for binary-choice questions). The implementation of these mechanisms does not require any prior knowledge (detail-free) and only requires ≥ 2 participants. To the best of our knowledge, any mechanism of the family is the first dominantly truthful peer prediction mechanism that works for a finite number of tasks. The core of these new mechanisms is a new family of information-monotone information measures: volume mutual information (VMI). VMI is based on a simple geometric information measure design method, the volume method. The volume method measures the informativeness of an object by "counting" the number of objects that are less informative than it. In other words, the more objects that the object of interest dominates, the more informative it is considered to be. Finally, in the setting where agents need to invest efforts to obtain their private signals, we show how to select the mechanism to optimally incentivize efforts among a proper set of VMI-Mechanisms. [ABSTRACT FROM AUTHOR]

Summary: In this paper, a non‐orthogonal multiple access (NOMA)‐based precoded quadrature spatial modulation (PQSM) technique (NOMA‐PQSM) has been proposed for the downlink scenario. In NOMA‐PQSM, two intended receiving antennas are activated at any time instant. One antenna is activated for the in‐phase component of the transmitted signal, and another one is activated for the quadrature phase component, on the basis of data bits. NOMA‐PQSM provides benefits like improved spatial diversity and spectral efficiency in comparison with spatial modulation. This work uses zero forcing (ZF) precoding over downlink flat fading Rayleigh multiple input multiple output (MIMO) channels, to limit the channel's deteriorating effect on transmitted signal, assuming perfect channel state information (CSI) at the transmitter. A low complexity receiver based on the successive interference cancellation is used. An expression for the upper bound of average bit error probability is derived. Moreover, the expressions for the sum mutual information of users and its lower bound are also derived. The proposed scheme is compared with the preprocessing aided spatial modulation (PSM)‐based counterpart. Monte Carlo simulations reveal that the NOMA‐PQSM scheme outperforms its orthogonal counterpart and the PSM scheme. [ABSTRACT FROM AUTHOR]

AbstractThe COVID-19 pandemic has profoundly impacted health, emphasizing the need for timely disease detection. Blood tests have become key diagnostic tools due to the virus’s effects on blood composition. Accurate COVID-19 prediction through machine learning requires selecting relevant features, as irrelevant features can lower classification accuracy. This study proposes Modified Mutual Information (MMI) for feature selection, ranking features by relevance and using backtracking to find the optimal subset. Support Vector Machines (SVM) are then used for classification. Results show that MMI with SVM achieves 95% accuracy, outperforming other methods, and demonstrates strong generalizability on various benchmark datasets. [ABSTRACT FROM AUTHOR]

Psychedelic drugs have profound effects on perception, cognition and mood. How psychedelics affect neural signaling to produce these effects remains poorly understood. We investigated the effect of the classic psychedelic psilocybin on neural activity patterns and spatial encoding in the retrosplenial cortex of head‐fixed mice navigating on a treadmill. The place specificity of neurons to distinct locations along the belt was reduced by psilocybin. Moreover, the stability of place‐related activity across trials decreased. Psilocybin also reduced the functional correlation among simultaneously recorded neurons. The 5‐HT2AR (serotonin 2A receptor) antagonist ketanserin blocked these effects. These data are consistent with proposals that psychedelics increase the entropy of neural signaling and provide a potential neural mechanism contributing to disorientation frequently reported by humans after taking psychedelics. [ABSTRACT FROM AUTHOR]

In NOMA achieving fairness in data transmission for all users is one of the key challenges. It implies a fair allocation of resources among users according to a given criterion. NOMA systems are based on the discreteness of the data source, since the specific nature of data allows to extract information in overloaded systems. Well-known C.E. Shannon capacity equation does not take into account the discrete nature of NOMA group signals, considering them as Gaussian source of information. Therefore, it does not take into account the characteristics of discrete signals used in NOMA systems, which makes it difficult to solve the optimization problem, especially for types of NOMA that use code division. For this task it is necessary to use DCMC capacity. When optimizing total capacity of DCMC, individual properties of users are not taken into account, as a result of which the allocation of resources with such optimization might not be fair. This paper proposes an approach to optimizing NOMA based on the analysis of an-individual mutual information (capacity). The proposed optimization approach allows analyzing the individual characteristics of each user in order to improve NOMA system performance by optimizing NOMA signals parameters. [ABSTRACT FROM AUTHOR]

This research introduces a Computer-Aided Diagnosis-system designed aimed at automated detections & classification of tomato leaf diseases, combining traditional handcrafted features with advanced deep learning techniques. The system's process encompasses preprocessing, feature extraction, feature fusion, and classification. It utilizes enhancement filters and segmentation algorithms to isolate with Regions-of-Interests (ROI) in images tomato leaves. These features based arranged in ABCD rule (Asymmetry, Borders, Colors, and Diameter) are integrated with outputs from a Convolutional Neural Network (CNN) pretrained on ImageNet. To address data imbalance, we introduced a novel evaluation method that has shown to improve classification accuracy by 15% compared to traditional methods, achieving an overall accuracy rate of 92% in field tests. By merging classical feature engineering with modern machine learning techniques under mutual information-based feature fusion, our system sets a new standard for precision in agricultural diagnostics. Specific performance metrics showcasing the effectiveness of our approach in automated detection and classifying of tomato leaf disease. [ABSTRACT FROM AUTHOR]

With the continuous expansion of the power grid, the issue of operational safety has attracted increasing attention. In power grid operation control, unauthorized operations are one of the primary causes of personal accidents. Therefore, preventing and monitoring unauthorized actions by power grid operators is of critical importance. First, multimodal violation data are integrated through information systems, such as the power grid management platform, to construct a historical case database. Next, word vectors for three types of operation-related factors are generated using natural language processing techniques, and key vectors are selected based on generalized correlation coefficients using mutual information, enabling effective dimensionality reduction. Independent component analysis is then employed for feature extraction and further dimensionality reduction, allowing for the effective characterization of operational scenarios. For each historical case, a risk score is derived from a violation risk prediction model constructed using the Random Forests (RF) algorithm. When a high-risk score is identified, the K-Nearest Neighbor (KNN) algorithm is applied to locate similar scenarios in the historical case database where violations may have occurred. Real-time violation risk assessment is performed for each operation, providing early warnings to operators, thereby reducing the likelihood of violations, and enhancing the safety of power grid operations. [ABSTRACT FROM AUTHOR]

Image comparison is a fundamental step for monitoring images and has wide applications in many disciplines of sciences, including satellite imaging, medical research, quality control and so forth. This problem, however, is complicated because (i) the observed images often contain noise, (ii) the image intensity functions are discontinuous and have spatial structures. In the literature, a vast majority of the methods are intensity-based. However, such an approach is often questionable in real life situations where small changes in the background may not indicate an actual meaningful change in the images as long as the boundaries of the image objects remain the same. In this article, we propose a flexible and effective image comparison method based on local pixel clustering and construct a test statistic based on the Variation of Information metric. This is a feature based image comparison technique where edges or the jump points are considered as the primary features. Numerical examples and statistical properties show that the proposed image comparison method performs well in various real life scenarios. [ABSTRACT FROM AUTHOR]

One effort to reduce stunting rates is to predict stunting status early in toddlers. This study applies Naive Bayes (NB) to build a stunting prediction model because it is simple and easy to use. This study proposes a filter-based feature weighting technique to overcome the NB assumption, which states that each feature has the same contribution to the target. The frequency of an event in a dataset influences the feature weighting using mutual information criteria. This is the gap in the filter-based ranking highlighted in this study. Therefore, this study proposes a feature-weighting method that combines mutual information with the MOORA (MI-MOORA) decision-making method. This technique makes it possible to include external factors as criteria for ranking important features. For stunting cases, the external consideration for ranking purposes is the assessment of nutrition experts based on their experience in dealing with stunted toddlers. The MI-MOORA technique makes the availability of clean water the most influential feature that contributes to the stunting status. In the ten best features, the MI-MOORA ranking results are dominated by family factors. Based on the performance evaluation results of NB and other classifiers, MI-MOORA can improve the performance of stunt prediction models. [ABSTRACT FROM AUTHOR]

Actionable Warning Identification (AWI) plays a significant role in improving the usability of static code analyzers. Recent studies show that actionable warning identification using machine learning is effective and works well within projects as long as there is sufficient amount of data available to train the models. Currently, the AWI classifier meets the issue of constrained performance on a small number of labeled warnings. We study the Cross Project Actionable Warning Identification (CP-AWI) for cases in which few or no data are available. CP-AWI uses the labeled data of a source project as training to construct a model for the target project. However, the difference in data distribution between the source project and the target project reduces the performance of warning identification. To solve this problem, this paper proposes a CP-AWI based on hybrid PCA-MI with machine learning. Firstly, Principal Component Analysis (PCA) is used to transform the features and adapt the feature dimensions between the source and target project datasets. Subsequently, Mutual Information (MI) is applied to measure the dependency between the input transformed features obtained from PCA and the target variable. Finally, machine learning models, Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), Decision Tree (DT), and Naïve Bayes (NB), are used to evaluate the proposed combination of the PCA-MI hybrid method for CP-AWI. The proposed CP-AWI system in our research, PCA-MI with RF, achieves the highest accuracy rate. This research is implemented on the eight open source java software project datasets (Ant, Cassandra, Commons.lang, Derby, Jmeter, Luence-solr, Maven, and Tomcat) and evaluated with standard evaluation metrics such as accuracy, Mean Squared Error (MAE) and Root Mean Squared Error (RMSE) and F-measure. The PCA-MI achieves an average 85% and 74% F-measure in compare to state-of-the-art methods indicates the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The peak-to-average power ratio (PAPR), commonly used to describe the amplitude variations of an OFDM (orthogonal frequency-division multiplex) signal, does not accurately reflect its impact on the system performance. This paper applies the mutual information as a metric to assess the effects of nonlinear PAPR reduction schemes on the performance of OFDM systems. Evaluation of the achieved mutual information shows that a significant capacity loss from clipping occurs only at high SNR (signal-to-noise ratio) and a simple compression/expansion technique is proposed to achieve close to optimal performance in this regime. The effectiveness of this method is validated through WER (word error rate) simulations with several modulation and coding schemes. [ABSTRACT FROM AUTHOR]

Human activity recognition is known as the backbone of the development of interactive systems, such as computer games. This process is usually performed by either vision-based or depth sensors. So far, various solutions have been developed for this purpose; however, all the challenges of this process have not been completely resolved. In this paper, a solution based on pattern recognition has been developed for labeling and scoring physical exercises performed in front of the Kinect sensor. Extracting the features from human skeletal joints and then generating relative descriptors among them is the first step of our method. This has led to quantification of the meaningful relationships between different parts of the skeletal joints during exercise performance. In this method, the discriminating descriptors of each exercise motion are used to identify the adaptive kernels of the Constrained Energy Minimization method as a target detector operator. The results indicated an accuracy of 95.9% in the labeling process of physical exercise motions. Scoring the exercise motions was the second step after the labeling process, in which a geometric method was used to interpolate numerical quantities extracted from descriptor vectors to transform into semantic scores. The results demonstrated the scoring process coincided with the scores derived by the sports coach by a 99.5 grade in the R2 index. [ABSTRACT FROM AUTHOR]

In the context of hyperspectral image (HSI) analysis, a widely used feature extraction method, Principal Components Analysis (PCA) suffers from limitations such as wavelength bias and a lack of consideration for local spectral information. While various segmentation based PCA methods attempt to address these issues by incorporating local relationships, they still overlook band similarity beyond immediate neighbours. To address these challenges, this paper introduces a novel approach called dependency based segmented PCA (dPCA). This method employs hierarchical clustering-driven mutual information-based segmentation, facilitating more comprehensive feature extraction from HSI data. By utilizing this dependency-based segmentation, both global and local structures are effectively captured, providing enhanced details for classification tasks. The proposed dPCA is evaluated on four prominent HSI datasets in remote sensing for land use classification, and the experimental results underscore its superiority over conventional PCA, and other segmentation based PCA methods in terms of classification performance. [ABSTRACT FROM AUTHOR]

Objectives: In order to effectively filter out complex noise components in GNSS coordinate time series and extract effective signals, we construct a denoising method based on parameter-optimized variational modal decomposition (VMD). Methods: First, the combination of permutation entropy and mutual information is used as fitness function, and the optimal parameter combination of the mode decomposition number K and the quadratic penalty factor α of VMD is obtained by using grey wolf optimization algorithm (GWO). Then the GNSS coordinate time series is decomposed into K eigen mode function components by VMD. Finally, the sample entropy is used to determine the effective modal component, which is reconstructed as an effective signal, so as to realize the effective separation of signal and noise.The GWO-VMD method is compared and analyzed with the empirical mode decomposition (EMD), wavelet denoising (WD) and IVMD methods by using the simulated signal and the measured data from 20 reference stations of the crustal movement observation network of China for experiments. Results: The simulated signal experiments show that the three denoising evaluation indexes of root mean square error,correlation coefficient and signal-to-noise ratio of GWO-VMD denoising signal are better than EMD, WD and IVMD methods. The experiments on the measured data show that the GWO-VMD method can reduce the amplitude of noise significantly. In terms of the velocity uncertainty of the reference station, the overall GWO-VMD method reduces the velocity uncertainty better than the EMD, WD and IVMD methods. Conclusions: The GWOVMD method can more effectively remove the noise from GNSS coordinate time series and better preserve the original characteristics of the signal, which can provide reliable data for subsequent analysis and processing. [ABSTRACT FROM AUTHOR]

Crop canopy temperature can often be acquired using the thermal imager. Non-contact and non-destructive automated detection can be expected to achieve for crop water stress status. Automatic image alignment can be used to treat the fuzzy edge distribution, strong noise, as well as shape and texture information lacking in thermal infrared images, according to the information complementarity between visible light and thermal infrared images. The automated extraction can be realized on the crop canopy temperature. This study aims to solve the problems of differences in the radiation, shape, and texture between visible light images and thermal infrared images, leading to the low align images of different modalities. Multimodal image registration was also proposed to integrate the improved brain storm optimization (BSO) and Powell algorithm. Firstly, the original visible light image was downsampled and cropped, according to the normalized cross-correlation value. The area with the most similarity region was obtained in the thermal infrared image under the same resolution; Then, the target area was extracted from the cropped image. The target area image and the original thermal infrared image were decomposed by wavelet transform, where the multilayered low-frequency information was retained; Thirdly, the primitive affine transformation matrix was obtained by the image moments in the low-resolution layer; At the same time, the global search was used to optimize the affine transform matrix in the low-resolution layer using the improved BSO; Fourthly, the optimization was used as the initial point of the Powell algorithm. The optimization was performed in the high-resolution layer; Lastly, the optimization in the previous step was input into the Powell algorithm again. The original image layer was optimized again to obtain the final affine transformation matrix. The original BSO optimization was improved for the optimal affine transformation matrix in the image alignment task. The specific improvements included the following five aspects: The BSO population distribution was initialized using a chaotic mapping function; The mutation range of new individual was modified; The number of K-means clusters was dynamically adjusted in the BSO by the elbow; The chaotic local search was incorporated into the strategy of individual variation; and the probability parameters were dynamically adjusted, according to the different BSO in the early and late stages. Mutual information (MI), normalized mutual information (NMI), root mean square error (RMSE) and mean structure similarity index measure (MSSIM) were taken as the evaluation indexes. A comparison was made with Powell optimization, genetic algorithm (GA) and BSO_Powell algorithm. Specifically, MI indexes were improved by 0.054 2, 0.076 9, 0.040 5, respectively; NMI indexes were improved by 0.015 9, 0.023 1, 0.052 7, respectively; RMSE indexes were reduced by 15.02, 13.03, 27.08, respectively; and MSSIM indexes were improved by 0.0523, 0.0488, 0.1224, respectively, in greenhouse data; In field data, MI indexes were improved by 0.064 2, 0.066 7, 0.035 5, respectively; NMI indexes were improved by 0.007 7, 0.0125, 0.0124, respectively; RMSE indexes were reduced by 14.06, 10.57, 15.40, respectively; and MSSIM indexes were improved by 0.047 1, 0.038 1, 0.042 9, respectively. The strong robustness can accurately achieved in the multimodal image registration tasks for potatoes under complex environments. [ABSTRACT FROM AUTHOR]

The high dimensionality of text data is a challenging issue that requires efficient methods to reduce vector space and improve classification accuracy. Existing filter-based methods fail to address the redundancy issue, resulting in the selection of irrelevant and redundant features. Information theory-based methods effectively solve this problem but are not practical for large amounts of data due to their high time complexity. The proposed method, termed semantic similarity-aware feature selection and redundancy removal (SS-FSRR), employs joint mutual information between the pairs of semantically related terms and the class label to capture redundant features. It is predicated on the assumption that semantically related terms imply potentially redundant ones, which can significantly reduce execution time by avoiding sequential search strategies. In this work, we use Word2Vec's CBOW model to obtain semantic similarity between terms. The efficiency of the SS-FSRR is compared to six state-of-the-art competitive selection methods for categorical data using two traditional classifiers (SVM and NB) and a robust deep learning model (LSTM) on seven datasets with 10-fold cross-validation, where experimental results show that the SS-FSRR outperforms the other methods on most tested datasets with high stability as measured by the Jaccard's Index. [ABSTRACT FROM AUTHOR]

The role of meteorological droughts and initial conditions (land and atmosphere) in soil moisture drought (SMD) propagation are not yet fully understood. This work uses a drought event‐based causal framework to investigate the relative importance of meteorological drought (MD) duration and intensity and initial conditions that result in surface and rootzone SMD, considering their event‐level propagation time (PT) over South Asia. Initially, spatial variability of drought propagation is assessed by the Propagation Ratio (PR) computed based on MD counts that trigger SMD at various lags. PR depicts 2–3 months slower rootzone propagation than at surface. The gradual decrease in PR with increasing regional aridity indicates faster propagation over humid regions. The causal impact of initial conditions and MD parameters on propagating SMD are evaluated using normalized mutual information and a newly proposed normalized conditional mutual information. We found greater importance of triggering MD parameters followed by initial soil moisture condition on propagating SMD. This behavior is more evident for the surface layer propagation at shorter PT. There is a confounding effect of initial atmospheric conditions on drought propagation through initial soil moisture, depicting the significance of land‐atmosphere interactions prior to propagation. In the rootzone propagation, initial soil moisture has a greater influence on propagation, especially at longer PT, indicating the significance of soil moisture persistence. Stronger causal links obtained through the joint influence of MD parameters on SMD suggest the importance of accounting for MD duration and intensity simultaneously, which are not considered in drought index‐based propagation studies. Plain Language Summary: Understanding the process of meteorological droughts transitioning to soil moisture droughts helps improve drought prediction capabilities and effectively manage agricultural water resources. This work explicitly addresses how meteorological drought "events" propagate into soil moisture drought "events" at surface and rootzone layers with variable propagation time—a critical aspect overlooked in the past. Our findings depict slower and weaker propagation to the rootzone layer compared to the surface layer and suggest that the transition rate is sensitive to regional aridity. Causal associations between initial land‐atmospheric conditions and triggering meteorological drought properties with propagating soil moisture droughts are established using novel entropy‐based mutual information metrics. We found higher importance of triggering drought parameters on propagating droughts both at surface and rootzone soil when their joint influence is considered rather than accounting for any individual initial condition or an individual triggering drought parameter. These causations also vary regionally and event‐wise with changes in propagation times. The current work advocates investigating drought propagation at the event level instead of using standardized timeseries information. The findings would also be helpful for future studies linking land‐atmosphere interactions with drought events. Key Points: Propagating surface soil moisture drought has greater impact of meteorological drought (MD) than initial land and atmospheric conditionsPropagating soil moisture drought (SMD) at rootzone has comparable influence of MD and initial soil moisture at longer propagation timesConsidering MD duration and intensity together yields higher causation between MD and propagating SMD than accounting for them exclusively [ABSTRACT FROM AUTHOR]

Label distribution learning, where deal with label ambiguity by describing the degree of relevance of each label to a specific instance. As a novel machine learning paradigm, the curse of dimensionality is one of the prominent problems. Feature selection is a vital preprocessing step to reduce the high dimensionality of data. However, most existing label distribution feature selection methods focus on selecting a feature subset that has relevant capabilities for all labels, ignoring label-specific features with the maximum discriminatory power for each label. To tackle this issue, a label distribution feature selection algorithm based on label-specific features is proposed in this paper. Initially, we introduce a feature selection optimization model for label distribution data that simultaneously considers common and label-specific features, leveraging sparse learning to further investigate the intricate relationships between features and labels. Subsequently, the label correlation coefficient is employed to enhance the collaborative learning effect of labels. Finally, the relevance between features and labels is taken into account to guide the feature selection process, which can effectively eliminate the redundant features. Comprehensive experiments demonstrate the advantage of our proposed method over other well-established feature selection algorithms for selecting label-specific features to label distribution data. [ABSTRACT FROM AUTHOR]

This paper presents a novel clustering approach that utilizes variational autoencoders (VAEs) with disentangled representations, enhancing the efficiency and effectiveness of clustering. Traditional VAE-based clustering models often conflate generative and clustering information, leading to suboptimal clustering performance. To overcome this, our model distinctly separates latent representations into two modules: one for clustering and another for generation. This separation significantly improves clustering performance. Additionally, we employ augmented data to maximize mutual information between cluster assignment variables and the optimized latent variables. This strategy not only enhances clustering effectiveness but also allows the construction of latent variables that synergistically combine clustering information from original data with generative information from augmented data. Through extensive experiments, our model demonstrates superior clustering performance without the need for pre-training, outperforming existing deep generative clustering models. Moreover, it achieves state-of-the-art clustering accuracy on certain datasets, surpassing models that require pre-training. [ABSTRACT FROM AUTHOR]

Machine learning model has been widely used to provide flood forecasting including the ensemble model. This paper proposed an ensemble of neural networks for long-term flood forecasting that combine the output of backpropagation neural network (BPNN) and extreme learning machine (ELM). The proposed ensemble neural networks model has been applied towards the rainfall data from eight rainfall stations of Kelantan River Basin to forecast the water level of Kuala Krai. The aim is to highlight the improvement on accuracy of the forecast. Prior to the development of such ensemble model, data are optimized in two steps which are decomposed it using discrete wavelet transform (DWT) to reduce variations in the rainfall series and selecting dominant features using entropy called mutual information (MI) for the model. The result of the experiments indicates that ensemble neural networks model based on the data decomposition and entropy feature selection has outperformed individually executed forecast model in term of RMSE, MSE and NSE. This study proved that the proposed method has reduce the data variance and provide better forecasting with minimal error. With minimal forecast error the generalization of the model is improved. [ABSTRACT FROM AUTHOR]

Dealing with high-dimensional datasets presents notable challenges for classification modelling, primarily due to complexity and susceptibility to overfitting. Traditional feature selection methods frequently struggle to guarantee improved classification performance by including more features. Instead, they often rely on utilising the entire feature set. To address these challenges, a robust feature selection algorithm known as ranked mutual information for support vector machines (rMI-SVM) has been introduced. This approach mitigates the risk of overfitting by selecting features that augment the classification model with additional information, thereby ensuring enhanced performance as more features are selected. rMI-SVM can accommodate datasets with missing values regardless of data linearity as it does not require additional parameters or preset the number of features needed. The proposed method offers a solution to the challenges posed by high-dimensional data, and explicitly identifies the optimal number of features required for a classification model, thus circumventing the necessity of using the full feature set. These findings are supported by receiver operating characteristic (ROC) curves, which highlight the effectiveness of rMI-SVM in outperforming existing baselines and delivering a superior classification model performance. [ABSTRACT FROM AUTHOR]

From a medical perspective, the 12 leads of the heart in an electrocardiogram (ECG) signal have functional dependencies with each other. Therefore, all these leads report different aspects of an arrhythmia. Their differences lie in the level of highlighting and displaying information about that arrhythmia. For example, although all leads show traces of atrial excitation, this function is more evident in lead II than in any other lead. In this article, a new model was proposed using ECG functional and structural dependencies between heart leads. In the prescreening stage, the ECG signals are segmented from the QRS point so that further analyzes can be performed on these segments in a more detailed manner. The mutual information indices were used to assess the relationship between leads. In order to calculate mutual information, the correlation between the 12 ECG leads has been calculated. The output of this step is a matrix containing all mutual information. Furthermore, to calculate the structural information of ECG signals, a capsule neural network was implemented to aid physicians in the automatic classification of cardiac arrhythmias. The architecture of this capsule neural network has been modified to perform the classification task. In the experimental results section, the proposed model was used to classify arrhythmias in ECG signals from the Chapman dataset. Numerical evaluations showed that this model has a precision of 97.02%, recall of 96.13%, F1-score of 96.57% and accuracy of 97.38%, indicating acceptable performance compared to other state-of-the-art methods. The proposed method shows an average accuracy of 2% superiority over similar works. [ABSTRACT FROM AUTHOR]

Introduction: In operational environments, human interaction and cooperation between individuals are critical to efficiency and safety. These states are influenced by individuals' cognitive and emotional states. Human factor research aims to objectively quantify these states to prevent human error and maintain constant performances, particularly in high-risk settings such as aviation, where human error and performance account for a significant portion of accidents. Methods: Thus, this study aimed to evaluate and validate two novel methods for assessing the degree of cooperation among professional pilots engaged in real-flight simulation tasks. In addition, the study aimed to assess the ability of the proposed metrics to differentiate between the expertise levels of operating crews based on their levels of cooperation. Eight crews were involved in the experiments, consisting of four crews of Unexperienced pilots and four crews of Experienced pilots. An expert trainer, simulating air traffic management communication on one side and acting as a subject matter expert on the other, provided external evaluations of the pilots' mental states during the simulation. The two novel approaches introduced in this study were formulated based on circular correlation and mutual information techniques. Results and discussion: The findings demonstrated the possibility of quantifying cooperation levels among pilots during realistic flight simulations. In addition, cooperation time is found to be significantly higher (p < 0.05) among Experienced pilots compared to Unexperienced ones. Furthermore, these preliminary results exhibited significant correlations (p < 0.05) with subjective and behavioral measures collected every 30 s during the task, confirming their reliability. [ABSTRACT FROM AUTHOR]

Purpose: The objective is to suggest time as an important variable to consider in the network model, specifically when discussing causality. Methods: There is a consideration of the context of functional connectivity because of the time importance of observing the feature inside the neuroscience context. A network model was constructed using the Bayesian network method, utilizing a dataset consisting of three rats' local field potentials. The model took into consideration the time delay of communication among brain areas, as recorded in this study. In pursuit of this objective, the delayed mutual information method was employed to ascertain the temporal delay between local field potentials and K2 score for the purpose of model comparison. Results: Bayesian network depicted the probabilistic relationship among rat's brain areas. Delayed mutual information captured the lag among brain areas, and after its appliance on the Bayesian network model, posed better results. Conclusion: The primary novelty of this research lies in its integration of minor delays within the Bayesian network approach, accomplished through the utilization of the delayed mutual information technique prior to its implementation. The suggested methodology incorporates an essential feature that supports the analysis of functional connectivity among brain areas, thereby providing support for the dynamics of neurophysiology. [ABSTRACT FROM AUTHOR]

Copyright of Telecommunication Engineering is the property of Telecommunication Engineering and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

One of the most significant issues in wireless sensor networks (WSNs) is security, which must be addressed to keep WSNs safe from malicious attacks. An intrusion detection system (IDS) is essential in analyzing network traffic and detecting abnormal events. However, these IDSs suffer from several drawbacks that affect their effectiveness and flexibility in accuracy, so they must overcome these drawbacks to improve the performance of IDS. These drawbacks include difficulties in determining the appropriate dataset, the problem of feature selection, and the issue of the imbalanced dataset and choosing the appropriate algorithms for the classification process in WSN. In this paper, a model for an anomaly‐based IDS in WSNs is proposed. This model applied mutual information (MI) for feature selection and the synthetic minority oversampling technique (SMOTE) for solving the imbalanced dataset problem. It used different machine learning (ML) algorithms, random forest (RF), decision tree (DT), support vector machine (SVM), and K‐nearest neighbors (KNNs) to analyze network traffic and binary classification or multiclass classification. To implement and evaluate the performance of the proposed model, the standard dataset NSL‐KDD is used. Python language is used to implement the proposed model in the Anaconda platform, and many evaluation metrics are also utilized to evaluate the performance of the proposed method. Experimental results show that the proposed model can detect intrusions using different ML algorithms with high accuracy. The results of the proposed model for different ML algorithms outperform the state‐of‐the‐art algorithms, and the maximum enhancement reached 15% in the accuracy metric. [ABSTRACT FROM AUTHOR]

Background: With the advance in single-cell RNA sequencing (scRNA-seq) technology, deriving inherent biological system information from expression profiles at a single-cell resolution has become possible. It has been known that network modeling by estimating the associations between genes could better reveal dynamic changes in biological systems. However, accurately constructing a single-cell network (SCN) to capture the network architecture of each cell and further explore cell-to-cell heterogeneity remains challenging. Results: We introduce SINUM, a method for constructing the SIngle-cell Network Using Mutual information, which estimates mutual information between any two genes from scRNA-seq data to determine whether they are dependent or independent in a specific cell. Experiments on various scRNA-seq datasets with different cell numbers based on eight performance indexes (e.g., adjusted rand index and F-measure index) validated the accuracy and robustness of SINUM in cell type identification, superior to the state-of-the-art SCN inference method. Additionally, the SINUM SCNs exhibit high overlap with the human interactome and possess the scale-free property. Conclusions: SINUM presents a view of biological systems at the network level to detect cell-type marker genes/gene pairs and investigate time-dependent changes in gene associations during embryo development. Codes for SINUM are freely available at https://github.com/SysMednet/SINUM. [ABSTRACT FROM AUTHOR]

Solar flares are significant occurrences in solar physics, impacting space weather and terrestrial technologies. Accurate classification of solar flares is essential for predicting space weather and minimizing potential disruptions to communication, navigation, and power systems. This study addresses the challenge of selecting the most relevant features from multivariate time-series data, specifically focusing on solar flares. We employ methods such as Mutual Information (MI), Minimum Redundancy Maximum Relevance (mRMR), and Euclidean Distance to identify key features for classification. Recognizing the performance variability of different feature selection techniques, we introduce an ensemble approach to compute feature weights. By combining outputs from multiple methods, our ensemble method provides a more comprehensive understanding of the importance of features. Our results show that the ensemble approach significantly improves classification performance, achieving values 0.15 higher in True Skill Statistic (TSS) values compared to individual feature selection methods. Additionally, our method offers valuable insights into the underlying physical processes of solar flares, leading to more effective space weather forecasting and enhanced mitigation strategies for communication, navigation, and power system disruptions. [ABSTRACT FROM AUTHOR]

To address the long-tail problem in MLTC where current methods often compromise the original data distribution, resulting in reduced generalization performance on real data and ineffective mitigation of the long-tail distribution issue, this paper proposed a method of multi-label text classification with long-tail distribution (MLTC-LD). Initially, it created a relationship matrix for label samples to compute dependencies between label samples. Then, considering the degree of relationships between label samples, it constructed a neighbor selector, which used information from neighbors with strong relationships as the main semantic features and as prior information. Finally, by incorporating this prior information through a graph attention neural network into the classifier, the method aimed to enrich the knowledge of categories with abundant head data to improve the performance of categories with sparse tail data. An extensive comparative analysis of MLTC-LD with eight baseline models across three different datasets was conducted. The experimental results show that MLTC-LD improves precision by 3.5%, 0.3%, and 1.5% respectively, compared to the best-performing HGLRN, demonstrating the effectiveness of this approach. [ABSTRACT FROM AUTHOR]

The article focuses on improving Multivariate Time Series (MTS) forecasting accuracy by considering both intra- and inter-series relationships, which are often overlooked in previous approaches, leading to degraded performance. It mentions the proposed DeepCN model addresses this by incorporating a comprehensive relationship learning mechanism, leveraging mutual information to capture multi-order intra- and inter-series couplings simultaneously.

In the era of big data, there exist complex structure between different classes labels. Hierarchical structure, among others, has become a representative one, which is mathematically depicted as a tree-like structure or directed acyclic graph. Most studies in the literature focus on static feature selection in hierarchical information system. In this study, in order to solve the incremental feature selection problem of hierarchical classification in a dynamic environment, we develop two incremental algorithms for this purpose (IHFSGR-1 and IHFSGR-2 for short). As a preliminary step, we propose a new uncertainty measure to quantify the amount of information contained in the hierarchical classification system, and based on this, we develop a non-incremental hierarchical feature selection algorithm. Next, we investigate the updating mechanism of this uncertainty measure upon the arrival of samples, and propose two strategies for adding and deleting features, leading to the development of two incremental algorithms. Finally, we conduct some comparative experiments with several non-incremental algorithms. The experimental results suggest that compared with several non-incremental algorithms, our incremental algorithms can achieve better performance in terms of the classification accuracy and two hierarchical evaluation metrics, and can significantly accelerate the fuzzy rough set-based hierarchical feature selection. [ABSTRACT FROM AUTHOR]

This paper considers a skill learning method that does not use information about a goal set for an agent. In reinforcement learning, such methods are called intrinsic motivation methods. The proposed algorithm is based on the calculation of the mutual information between the actions of the agent and its states. This approach makes it possible to learn skills that lead to the most uniform reachability of possible states. The skills formed by the algorithm are illustrated by an example of continuous control of the agent's movement. The usefulness of these skills in solving reinforcement learning problems is analyzed. [ABSTRACT FROM AUTHOR]

Studying gene regulatory networks (GRNs) is paramount for unraveling the complexities of biological processes and their associated disorders, such as diabetes, cancer, and Alzheimer's disease. Recent advancements in computational biology have aimed to enhance the inference of GRNs from gene expression data, a non-trivial task given the networks' intricate nature. The challenge lies in accurately identifying the myriad interactions among transcription factors and target genes, which govern cellular functions. This research introduces a cutting-edge technique, EGRC (Effective GRN Inference applying Graph Convolution with Self-Attention Graph Pooling), which innovatively conceptualizes GRN reconstruction as a graph classification problem, where the task is to discern the links within subgraphs that encapsulate pairs of nodes. By leveraging Spearman's correlation, we generate potential subgraphs that bring nonlinear associations between transcription factors and their targets to light. We use mutual information to enhance this, capturing a broader spectrum of gene interactions. Our methodology bifurcates these subgraphs into 'Positive' and 'Negative' categories. 'Positive' subgraphs are those where a transcription factor and its target gene are connected, including interactions among their neighbors. 'Negative' subgraphs, conversely, denote pairs without a direct connection. EGRC utilizes dual graph convolution network (GCN) models that exploit node attributes from gene expression profiles and graph embedding techniques to classify these. The performance of EGRC is substantiated by comprehensive evaluations using the DREAM5 datasets. Notably, EGRC attained an AUROC of 0.856 and an AUPR of 0.841 on the E. coli dataset. In contrast, the in silico dataset achieved an AUROC of 0.5058 and an AUPR of 0.958. Furthermore, on the S. cerevisiae dataset, EGRC recorded an AUROC of 0.823 and an AUPR of 0.822. These results underscore the robustness of EGRC in accurately inferring GRNs across various organisms. The advanced performance of EGRC represents a substantial advancement in the field, promising to deepen our comprehension of the intricate biological processes and their implications in both health and disease. [ABSTRACT FROM AUTHOR]

Object detection in unmanned aerial vehicle (UAV) aerial images has become increasingly important in military and civil applications. General object detection models are not robust enough against interclass similarity and intraclass variability of small objects, and UAV-specific nuisances such as uncontrolled weather conditions. Unlike previous approaches focusing on high-level semantic information, we report the importance of underlying features to improve detection accuracy and robustness from the information-theoretic perspective. Specifically, we propose a robust and discriminative feature learning approach through mutual information maximization (RD-MIM), which can be integrated into numerous object detection methods for aerial images. Firstly, we present the rank sample mining method to reduce underlying feature differences between the natural image domain and the aerial image domain. Then, we design a momentum contrast learning strategy to make object features similar to the same category and dissimilar to different categories. Finally, we construct a transformer-based global attention mechanism to boost object location semantics by leveraging the high interrelation of different receptive fields. We conduct extensive experiments on the VisDrone and Unmanned Aerial Vehicle Benchmark Object Detection and Tracking (UAVDT) datasets to prove the effectiveness of the proposed method. The experimental results show that our approach brings considerable robustness gains to basic detectors and advanced detection methods, achieving relative growth rates of 51.0% and 39.4% in corruption robustness, respectively. Our code is available at (accessed on 2 August 2024). [ABSTRACT FROM AUTHOR]

In Unsupervised Domain Adaptation (UDA) for person re-identification (re-ID), the primary challenge is reducing the distribution discrepancy between the source and target domains. This can be achieved by implicitly or explicitly constructing an appropriate intermediate domain to enhance recognition capability on the target domain. Implicit construction is difficult due to the absence of intermediate state supervision, making smooth knowledge transfer from the source to the target domain a challenge. To explicitly construct the most suitable intermediate domain for the model to gradually adapt to the feature distribution changes from the source to the target domain, we propose the Minimal Transfer Cost Framework (MTCF). MTCF considers all scenarios of the intermediate domain during the transfer process, ensuring smoother and more efficient domain alignment. Our framework mainly includes three modules: Intermediate Domain Generator (IDG), Cross-domain Feature Constraint Module (CFCM), and Residual Channel Space Module (RCSM). First, the IDG Module is introduced to generate all possible intermediate domains, ensuring a smooth transition of knowledge from the source to the target domain. To reduce the cross-domain feature distribution discrepancy, we propose the CFCM Module, which quantifies the difficulty of knowledge transfer and ensures the diversity of intermediate domain features and their semantic relevance, achieving alignment between the source and target domains by incorporating mutual information and maximum mean discrepancy. We also design the RCSM, which utilizes attention mechanism to enhance the model's focus on personnel features in low-resolution images, improving the accuracy and efficiency of person re-ID. Our proposed method outperforms existing technologies in all common UDA re-ID tasks and improves the Mean Average Precision (mAP) by 2.3% in the Market to Duke task compared to the state-of-the-art (SOTA) methods. [ABSTRACT FROM AUTHOR]

Deep clustering is a crucial task in machine learning and data mining that focuses on acquiring feature representations conducive to clustering. Previous research relies on self-supervised representation learning for general feature representations, such features may not be optimally suited for downstream clustering tasks. In this article, we introduce MICCF, a framework designed to bridge this gap and enhance clustering performance. MICCF enhances feature representations by combining mutual information constraints at different levels and employs an auxiliary alignment mutual information module for learning clustering-oriented features. To be specific, we propose a dual mutual information constraints module, incorporating minimal mutual information constraints at the feature level and maximal mutual information constraints at the instance level. This reduction in feature redundancy encourages the neural network to extract more discriminative features, while maximization ensures more unbiased and robust representations. To obtain clustering-oriented representations, the auxiliary alignment mutual information module utilizes pseudo-labels to maximize mutual information through a multi-classifier network, aligning features with the clustering task. The main network and the auxiliary module work in synergy to jointly optimize feature representations that are well-suited for the clustering task. We validate the effectiveness of our method through extensive experiments on six benchmark datasets. The results indicate that our method performs well in most scenarios, particularly on fine-grained datasets, where our approach effectively distinguishes subtle differences between closely related categories. Notably, our approach achieved a remarkable accuracy of 96.4% on the ImageNet-10 dataset, surpassing other comparison methods. The code is available at https://github.com/Li-Hyn/MICCF.git. [ABSTRACT FROM AUTHOR]

In NOMA achieving fairness in data transmission for all users is one of the key challenges. It implies a fair allocation of resources among users according to a given criterion. NOMA systems are based on the discreteness of the data source, since the specific nature of data allows to extract information in overloaded systems. Well-known C.E. Shannon capacity equation does not take into account the discrete nature of NOMA group signals, considering them as Gaussian source of information. Therefore, it does not take into account the characteristics of discrete signals used in NOMA systems, which makes it difficult to solve the optimization problem, especially for types of NOMA that use code division. For this task it is necessary to use DCMC capacity. When optimizing total capacity of DCMC, individual properties of users are not taken into account, as a result of which the allocation of resources with such optimization might not be fair. This paper proposes an approach to optimizing NOMA based on the analysis of an-individual mutual information (capacity). The proposed optimization approach allows analyzing the individual characteristics of each user in order to improve NOMA system performance by optimizing NOMA signals parameters.

Abstract The peak-to-average power ratio (PAPR), commonly used to describe the amplitude variations of an OFDM (orthogonal frequency-division multiplex) signal, does not accurately reflect its impact on the system performance. This paper applies the mutual information as a metric to assess the effects of nonlinear PAPR reduction schemes on the performance of OFDM systems. Evaluation of the achieved mutual information shows that a significant capacity loss from clipping occurs only at high SNR (signal-to-noise ratio) and a simple compression/expansion technique is proposed to achieve close to optimal performance in this regime. The effectiveness of this method is validated through WER (word error rate) simulations with several modulation and coding schemes.

Inflation expectations are a crucial variable for central banks. However, empirically examining their properties is challenging. This paper juxtaposes the properties of consumer and professional expectations. It also assesses the degree of forward- and backward-lookingness and the information content of expectations. We apply entropy-based measures (common information and mutual common information) to capture nonlinear dependencies and dynamic time warping to account for different lags in the relationships. The study covers 12 inflation-targeting economies from the European region. The results suggest that in most countries, professionals are more forward-looking, and consumers follow professionals. Both groups of economic agents present expectations that are aligned in terms of information content. However, cross-country differences occur. These results imply that, from the central bank’s point of view, communication and practices designed to shape expectations, even if understood mostly by specialists, are effective also for consumers. The novelty of this study lies in its use of alternative methods to tackle the formation and dependencies between heterogeneous expectations. This avoids the drawbacks of a standard approach and allows broader conclusions to be drawn.

Abstract Background With the advance in single-cell RNA sequencing (scRNA-seq) technology, deriving inherent biological system information from expression profiles at a single-cell resolution has become possible. It has been known that network modeling by estimating the associations between genes could better reveal dynamic changes in biological systems. However, accurately constructing a single-cell network (SCN) to capture the network architecture of each cell and further explore cell-to-cell heterogeneity remains challenging. Results We introduce SINUM, a method for constructing the SIngle-cell Network Using Mutual information, which estimates mutual information between any two genes from scRNA-seq data to determine whether they are dependent or independent in a specific cell. Experiments on various scRNA-seq datasets with different cell numbers based on eight performance indexes (e.g., adjusted rand index and F-measure index) validated the accuracy and robustness of SINUM in cell type identification, superior to the state-of-the-art SCN inference method. Additionally, the SINUM SCNs exhibit high overlap with the human interactome and possess the scale-free property. Conclusions SINUM presents a view of biological systems at the network level to detect cell-type marker genes/gene pairs and investigate time-dependent changes in gene associations during embryo development. Codes for SINUM are freely available at https://github.com/SysMednet/SINUM .

The identification of catalytic RNAs is typically achieved through primarily experimental means. However, only a small fraction of sequence space can be analyzed even with high-throughput techniques. Methods to extrapolate from a limited data set to predict additional ribozyme sequences, particularly in a human-interpretable fashion, could be useful both for designing new functional RNAs and for generating greater understanding about a ribozyme fitness landscape. Using information theory, we express the effects of epistasis (i.e., deviations from additivity) on a ribozyme. This representation was incorporated into a simple model of the epistatic fitness landscape, which identified potentially exploitable combinations of mutations. We used this model to theoretically predict mutants of high activity for a self-aminoacylating ribozyme, identifying potentially active triple and quadruple mutants beyond the experimental data set of single and double mutants. The predictions were validated experimentally, with nine out of nine sequences being accurately predicted to have high activity. This set of sequences included mutants that form a previously unknown evolutionary bridge between two ribozyme families that share a common motif. Individual steps in the method could be examined, understood, and guided by a human, combining interpretability and performance in a simple model to predict ribozyme sequences by extrapolation.

Computational models of gene regulations help to understand regulatory mechanisms and are extensively used in a wide range of areas, e.g., biotechnology or medicine, with significant benefits. Unfortunately, there are only a few computational gene regulatory models of whole genomes allowing static and dynamic analysis due to the lack of sophisticated tools for their reconstruction. Here, we describe Augusta, an open-source Python package for Gene Regulatory Network (GRN) and Boolean Network (BN) inference from the high-throughput gene expression data. Augusta can reconstruct genome-wide models suitable for static and dynamic analyses. Augusta uses a unique approach where the first estimation of a GRN inferred from expression data is further refined by predicting transcription factor binding motifs in promoters of regulated genes and by incorporating verified interactions obtained from databases. Moreover, a refined GRN is transformed into a draft BN by searching in the curated model database and setting logical rules to incoming edges of target genes, which can be further manually edited as the model is provided in the SBML file format. The approach is applicable even if information about the organism under study is not available in the databases, which is typically the case for non-model organisms including most microbes. Augusta can be operated from the command line and, thus, is easy to use for automated prediction of models for various genomes. The Augusta package is freely available at github.com/JanaMus/Augusta. Documentation and tutorials are available at augusta.readthedocs.io.

Considering the case where the response variable is a categorical variable and the predictor is a random function, two novel functional sufficient dimensional reduction (FSDR) methods are proposed based on mutual information and square loss mutual information. Compared to the classical FSDR methods, such as functional sliced inverse regression and functional sliced average variance estimation, the proposed methods are appealing because they are capable of estimating multiple effective dimension reduction directions in the case of a relatively small number of categories, especially for the binary response. Moreover, the proposed methods do not require the restrictive linear conditional mean assumption and the constant covariance assumption. They avoid the inverse problem of the covariance operator which is often encountered in the functional sufficient dimension reduction. The functional principal component analysis with truncation be used as a regularization mechanism. Under some mild conditions, the statistical consistency of the proposed methods is established. Simulation studies and real data analyzes are used to evaluate the finite sample properties of our methods. [ABSTRACT FROM AUTHOR]

In recent years, some researchers have combined deep learning methods such as semantic segmentation with a visual SLAM to improve the performance of classical visual SLAM. However, the above method introduces the uncertainty of the neural network model. To solve the above problems, an improved feature selection method based on information entropy and feature semantic uncertainty is proposed in this paper. The former is used to obtain fewer and higher quality feature points, while the latter is used to correct the uncertainty of the network in feature selection. At the same time, in the initial stage of feature point selection, this paper first filters and eliminates the absolute dynamic object feature points in the a priori information provided by the feature point semantic label. Secondly, the potential static objects can be detected combined with the principle of epipolar geometric constraints. Finally, the semantic uncertainty of features is corrected according to the semantic context. Experiments on the KITTI odometer data set show that compared with SIVO, the translation error is reduced by 12.63% and the rotation error is reduced by 22.09%, indicating that our method has better tracking performance than the baseline method. [ABSTRACT FROM AUTHOR]

The Gray map converts a symbol in Z 4 to a pair of binary symbols. Therefore, under the Gray map, a linear function from Z 4 n to Z 4 gives rise to a pair of boolean functions from F 2 2 n to F 2 . This paper studies such boolean functions. We state and prove a condition for the nonlinearity of such functions and derive closed-form expressions for them. Further, results related to the mutual information between random variables that satisfy such expressions have been derived. These results are then used to construct a couple of nonlinear boolean secret sharing schemes. These schemes are then analyzed for their closeness to 'perfectness' and their ability to resist 'Tompa–Woll'-like attacks. [ABSTRACT FROM AUTHOR]