Hierarchical Optimization Method for Federated Learning with Feature Alignment and Decision Fusion

In the realm of data privacy protection,federated learning aims to collaboratively train a global model.However,heterogeneous data between clients presents challenges,often resulting in slow convergence and inadequate accuracy of the global model.Utilizing shared feature representations alongside customized classifiers for individual clients emerges as a promising personalized solution.Nonetheless,previous research has frequently neglected the integration of global knowledge into local representation learning and the synergy between global and local classifiers,thereby limiting model performance.To tackle these issues,this study proposes a hierarchical optimization method for federated learning with feature alignment and the fusion of classification decisions(FedFCD).FedFCD regularizes the relationship between global and local feature representations to achieve alignment and incorporates decision information from the global classifier,facilitating the late fusion of decision outputs from both global and local classifiers.Additionally,FedFCD employs a hierarchical optimization strategy to flexibly optimize model parameters.Through experiments on the Fashion-MNIST,CIFAR-10 and CIFAR-100 datasets,we demonstrate the effectiveness and superiority of FedFCD.For instance,on the CIFAR-100 dataset,FedFCD exhibited a significant improvement in average test accuracy by 6.83%compared to four outstanding personalized federated learning approaches.Furthermore,extended experiments confirm the robustness of FedFCD across various hyperparameter values.

Ulva prolifera subpixel mapping with multiple-feature decision fusion

The unavoidable nature of Ulva prolifera mixed pixel in low-resolution remote sensing images would result in rough boundary of U.prolifera patches,omission of tiny patches,and overestimation of coverage area.The decomposition of U.prolifera mixed pixel addresses the issue of coverage area overestimation,and the remaining problems can be alleviated by subpixel mapping(SPM).Due to the drift and dissipation of U.prolifera,a suitable SPM method is the single image-based unsupervised method.However,the method has difficulties in detail reconstruction,insufficient learning of spectral information,and SPM error introduced by abundance deviation.Therefore,we proposed a multiple-feature decision fusion SPM(MFDFSPM)method.It involves three branches to obtain the spatial,abundance,and spectral features of U.prolifera while considers multi-feature information using the fusion strategy.Experiments on the Geostationary Ocean Color Imager images in the Yellow Sea of China indicate that the MFDFSPM overperforms several typical U.prolifera SPM methods in higher accuracy and stronger robustness in both SPM and abundance calculation,which produced subpixel map with more detailed spatial information and less noise.

Dependent Randomization in Parallel Binary Decision Fusion

We consider a parallel decentralized detection system employing a bank of local detectors(LDs)to access a commonly-observed phenomenon.The system makes a binary decision about the phenomenon,accepting one of two hypotheses(H_(0)("absent")or H_(1)("present")).The kth LD uses a local decision rule to compress its local observations yk into a binary local decision uk;uk=0 if the kth LD accepts H_(0)and uk=1 if it accepts H_(1).The kth LD sends its decision uk over a noiseless dedicated channel to a Data Fusion Center(DFC).The DFC combines the local decisions it receives from n LDs(u_(1),u_(2),...,u_(n))into a single binary global decision u_(0)(u_(0)=0 for accepting H_(0)or u_(0)=1 for accepting H_(1)).If each LD uses a single deterministic local decision rule(calculating uk from the local observations yk)and the DFC uses a single deterministic global decision rule(calculating u_(0)from the n local decisions),the team receiver operating characteristic(ROC)curve is in general non-concave.The system's performance under a Neyman-Pearson criterion may then be suboptimal in the sense that a mixed strategy may yield a higher probability of detection when the probability of false alarm is constrained not to exceed a certain value,α>0.Specifically,a"dependent randomization"detection scheme can be applied in certain circumstances to improve the system's performance by making the ROC curve concave.This scheme requires a coordinated and synchronized action between the DFC and the LDs.In this study,we specify when dependent randomization is needed,and discuss the proper response of the detection system if synchronization between the LDs and the DFC is temporarily lost.

Scheme of Cooperative Spectrum Sensing Based on Adaptive Decision Fusion Algorithm

Spectrum sensing is one of the core technologies for cognitive radios （CR）, where reliable detection of the signals of primary users （PUs） is precondition for implementing the CR systems. A cooperative spectrum sensing scheme based on an adaptive decision fusion algorithm for spectrum sensing in CR is proposed in this paper. This scheme can estimate the PU prior probability and the miss detection and false alarm probabilities of various secondary users （SU）, and make the local decision with the Chair-Varshney rule so that the decisions fusion can be done for the global decision. Simulation results show that the false alarm and miss detection probabilities resulted from the proposed algorithm are significantly lower than those of the single SU, and the performance of the scheme outperforms that of the cooperative detection by using the conventional decision fusion algorithms.

DECISION FUSION FOR WIRELESS SENSOR NETWORKS UNDER NAKAGAMI FADING CHANNELS

Decision fusion rules for Wireless Sensor Networks (WSNs) under Nakagami fading channels are investigated in this paper. Considering the application limitation of Likelihood Ratio Test fusion rule based on information of Channel Statistics using Series expansion (LRT-CSS),and the detection performance limitation of the Censoring based Mixed Fusion rule (CMF),a new LRT fusion rule based on information of channel statistics has been presented using Laplace approximation (LRT-CSL). Theoretical analysis and simulations show that the proposed fusion rule provides better detection performance than the Censoring based Mixed Fusion (CMF) and LRT-CSS fusion rules. Furthermore,compared with LRT-CSS fusion rule,the proposed fusion rule expands the application range of likelihood ratio test fusion rule.

Face recognition by decision fusion of two-dimensional linear discriminant analysis and local binary pattern

To investigate the robustness of face recognition algorithms under the complicated variations of illumination, facial expression and posture, the advantages and disadvantages of seven typical algorithms on extracting global and local features are studied through the experiments respectively on the Olivetti Research Laboratory database and the other three databases （the three subsets of illumination, expression and posture that are constructed by selecting images from several existing face databases）. By taking the above experimental results into consideration, two schemes of face recognition which are based on the decision fusion of the twodimensional linear discriminant analysis （2DLDA） and local binary pattern （LBP） are proposed in this paper to heighten the recognition rates. In addition, partitioning a face nonuniformly for its LBP histograms is conducted to improve the performance. Our experimental results have shown the complementarities of the two kinds of features, the 2DLDA and LBP, and have verified the effectiveness of the proposed fusion algorithms.

Multi-Model Fusion Framework Using Deep Learning for Visual-Textual Sentiment Classification

Multimodal Sentiment Analysis(SA)is gaining popularity due to its broad application potential.The existing studies have focused on the SA of single modalities,such as texts or photos,posing challenges in effectively handling social media data with multiple modalities.Moreover,most multimodal research has concentrated on merely combining the two modalities rather than exploring their complex correlations,leading to unsatisfactory sentiment classification results.Motivated by this,we propose a new visualtextual sentiment classification model named Multi-Model Fusion(MMF),which uses a mixed fusion framework for SA to effectively capture the essential information and the intrinsic relationship between the visual and textual content.The proposed model comprises three deep neural networks.Two different neural networks are proposed to extract the most emotionally relevant aspects of image and text data.Thus,more discriminative features are gathered for accurate sentiment classification.Then,a multichannel joint fusion modelwith a self-attention technique is proposed to exploit the intrinsic correlation between visual and textual characteristics and obtain emotionally rich information for joint sentiment classification.Finally,the results of the three classifiers are integrated using a decision fusion scheme to improve the robustness and generalizability of the proposed model.An interpretable visual-textual sentiment classification model is further developed using the Local Interpretable Model-agnostic Explanation model(LIME)to ensure the model’s explainability and resilience.The proposed MMF model has been tested on four real-world sentiment datasets,achieving(99.78%)accuracy on Binary_Getty(BG),(99.12%)on Binary_iStock(BIS),(95.70%)on Twitter,and(79.06%)on the Multi-View Sentiment Analysis(MVSA)dataset.These results demonstrate the superior performance of our MMF model compared to single-model approaches and current state-of-the-art techniques based on model evaluation criteria.

Fusion Strategy for Improving Medical Image Segmentation

In this paper,we combine decision fusion methods with four metaheuristic algorithms(Particle Swarm Optimization(PSO)algorithm,Cuckoo search algorithm,modification of Cuckoo Search(CS McCulloch)algorithm and Genetic algorithm)in order to improve the image segmentation.The proposed technique based on fusing the data from Particle Swarm Optimization(PSO),Cuckoo search,modification of Cuckoo Search(CS McCulloch)and Genetic algorithms are obtained for improving magnetic resonance images(MRIs)segmentation.Four algorithms are used to compute the accuracy of each method while the outputs are passed to fusion methods.In order to obtain parts of the points that determine similar membership values,we apply the different rules of incorporation for these groups.The proposed approach is applied to challenging applications:MRI images,gray matter/white matter of brain segmentations and original black/white images Behavior of the proposed algorithm is provided by applying to different medical images.It is shown that the proposed method gives accurate results;due to the decision fusion produces the greatest improvement in classification accuracy.

Machine Learning for Data Fusion:A Fuzzy AHP Approach for Open Issues

Data fusion generates fused data by combining multiple sources,resulting in information that is more consistent,accurate,and useful than any individual source and more reliable and consistent than the raw original data,which are often imperfect,inconsistent,complex,and uncertain.Traditional data fusion methods like probabilistic fusion,set-based fusion,and evidential belief reasoning fusion methods are computationally complex and require accurate classification and proper handling of raw data.Data fusion is the process of integrating multiple data sources.Data filtering means examining a dataset to exclude,rearrange,or apportion data according to the criteria.Different sensors generate a large amount of data,requiring the development of machine learning(ML)algorithms to overcome the challenges of traditional methods.The advancement in hardware acceleration and the abundance of data from various sensors have led to the development of machine learning(ML)algorithms,expected to address the limitations of traditional methods.However,many open issues still exist as machine learning algorithms are used for data fusion.From the literature,nine issues have been identified irrespective of any application.The decision-makers should pay attention to these issues as data fusion becomes more applicable and successful.A fuzzy analytical hierarchical process(FAHP)enables us to handle these issues.It helps to get the weights for each corresponding issue and rank issues based on these calculated weights.The most significant issue identified is the lack of deep learning models used for data fusion that improve accuracy and learning quality weighted 0.141.The least significant one is the cross-domain multimodal data fusion weighted 0.076 because the whole semantic knowledge for multimodal data cannot be captured.

A novel fuzzy sensor fusion algorithm

A novel fusion algorithm was given based on fuzzy similarity and fuzzy integral theory. First, it calculated the fuzzy similarity among a certain sensor＇s measurement values and the multiple sensors＇ objective prediction values to determine the importance weight of each sensor and realize multi-sensor data fusion. Then according to the determined importance weight, an intelligent fusion system based on fuzzy integral theory was given, which can solve FEI-DEO and DEI-DEO fusion problems and realize the decision fusion. Simulation results were proved that fuzzy integral algorithm has enhanced the capability of handling the uncertain information and improved the intelligence degrees

A New Deghosting Algorithm with Hypothesis Testing Data Fusion

Eliminating the false intersection (deghosting) is a difficult problem in a passive cross location system. Using a decentralized decision fusion topology, a new deghosting algorithm derived from hypothesis testing theory is developed. It uses the difference between ghosts and true targets in the statistical error, which occurs between their projection angles on a deghosting sensor and is measured from a deghosting sensor, and constructs a corresponding test statistic. Under the Gaussian assumption, ghosts and true targets are decided and discriminated by Chi-square distribution. Simulation results show the feasibility of the algorithm.

Support vector machine ensemble using rough sets theory

A support vector machine （SVM） ensemble classifier is proposed. Performance of SVM trained in an input space eonsisting of all the information from many sources is not always good. The strategy that the original input space is partitioned into several input subspaces usually works for improving the performance. Different from conventional partition methods, the partition method used in this paper, rough sets theory based attribute reduction, allows the input subspaces partially overlapped. These input subspaces can offer complementary information about hidden data patterns. In every subspace, an SVM sub-classifier is learned. With the information fusion techniques, those SVM sub-classifiers with better performance are selected and combined to construct an SVM ensemble. The proposed method is applied to decision-making of medical diagnosis. Comparison of performance between our method and several other popular ensemble methods is done. Experimental results demonstrate that our proposed approach can make full use of the information contained in data and improve the decision-making performance.

Simple,High-Performance Fusion Rule for Censored Decisions in Wireless Sensor Networks

Data selection-based summation fusion （DSSF） was developed to overcome the shortcomings ot previously developed likelihood ratio tests based on channel statistics （LRT-CS） for the problem of fusing censored binary decisions transmitted over Nakagami fading channels in a wireless sensor network （WSN）. The LRT-CS relies on detection probabilities of the local sensors, while the detection probabilities are a priori unknown for uncooperative targets. Also, for Nakagami fading channels, the LRT-CS involves an infinite series, which is cumbersome for real-time application. In contrast, the DSSF only involves data comparisons and additions and does not require the detection probabilities of local sensors. Furthermore, the performance of DSSF is only slightly degraded in comparison with the LRT-CS when the detection probabilities of local sensors are a priori unknown. Therefore, the DSSF should be used in a WSN with limited resources.

Performance Analysis of Distributed Neyman-Pearson Detection Systems

The performance of a distributed Neyman-Pearson detection system is considered with the decision rules of the sensors given and the decisions from different sensors being mutually independent conditioned on both hypothese. To achieve the better performance at the fusion center for a general detection system of n 〉 3 sensor configuration, the necessary and sufficient conditions are derived by comparing the probability of detec- tion at the fusion center with that of each of the sensors, with the constraint that the probability of false alarm at the fusion center is equal to that of the sensor. The conditions are related with the performances of the sensors and using the results we can predict the performance at the fusion center of a distributed detection system and can choose appropriate sensors to construct efficient distributed detection systems.

An Information Fusion Model of Innovation Alliances Based on the Bayesian Network

To solve the problem of information fusion from multiple sources in innovation alliances, an information fusion model based on the Bayesian network is presented. The multi-source information fusion process of innovation alliances was classified into three layers, namely, the information perception layer, the feature clustering layer,and the decision fusion layer. The agencies in the alliance were defined as sensors through which information is perceived and obtained, and the features were clustered. Finally, various types of information were fused by the innovation alliance based on the fusion algorithm to achieve complete and comprehensive information. The model was applied to a study on economic information prediction, where the accuracy of the fusion results was higher than that from a single source and the errors obtained were also smaller with the MPE less than 3%, which demonstrates the proposed fusion method is more effective and reasonable. This study provides a reasonable basis for decision-making of innovation alliances.

Intelligent wheelchair system based on s EMG and head gesture

Because the single channel surface electromyographic （sEMG） signals easily caused a complex operation during the real-time operation, an intelligent wheelchair system based on sEMG and head gesture was proposed in this paper. A distributed parallelly decision fusion algorithm fused classification results of the two signals to form a final judgment. After sEMG was decomposed by wavelet packet, feature information of some subspace was weaken, because subspace dimension was very large. To solve the problem, the paper proposed an improved wavelet packet decomposition algorithm, which extracted sample entropy from four subspaces of improved wavelet packet decomposition and took it as the feature information. Experimental results show that the intelligent wheelchair system based on sEMG and head gesture has not only a simple operation and shorter operating time, but also a better stability and security.