Federated Learning (FL) offers a promising approach for collaborative model training in healthcare while preserving data privacy. However, existing FL methods often fall short in addressing two critical challenges: client-level fairness and compounded uncertainty from data heterogeneity and privacy-preserving mechanisms. We propose fair-LDP, a fairness-aware Local Differential Privacy framework that promotes fairness and privacy via uncertainty-guided aggregation in federated healthcare AI. fair-LDP leverages evidential neural networks (ENNs) to quantify predictive uncertainty and introduces a novel strategy that uses uncertainty-driven local differential privacy to guide fairness-aware updates while preserving data privacy. This ensures equitable performance across clients with varying data quality while mitigating the influence of unreliable or outlier updates. fair-LDP incorporates an adaptive mechanism that adjusts each client's privacy budget based on model performance, balancing fairness, privacy, and accuracy. We evaluate fair-LDP on real-world healthcare datasets under both IID and non-IID settings. Our experimental results show that it consistently outperforms state-of-the-art fairness-aware and privacy-preserving FL baselines, with no added computational overhead, while maintaining privacy guarantees comparable to homomorphic encryption and secure multiparty computation. By integrating uncertainty modeling, fairness-aware aggregation, and adaptive local differential privacy, fair-LDP provides a practical and principled solution for responsible, equitable, and privacy-preserving federated learning in healthcare.

The Competitive Influence Maximization (CIM) problem involves entities competing to maximize influence in online social networks (OSNs). While Deep Reinforcement Learning (DRL) methods have shown promise, most assume binary user opinions and overlook behavioral factors. We introduce DRIM, a novel DRL-based CIM framework using Subjective Logic (SL) to incorporate user preferences and uncertainty, optimizing seed selection to spread true information while countering false information. DRIM’s Uncertainty-based Opinion Model (UOM) provides a realistic representation of user opinions. Results demonstrate that UOM maintains over 80% true influence against advanced misinformation, and DRIM outperforms state-of-the-art methods by up to 45% in influence and 77% in speed. DRIM also excels in limited-resource scenarios, networks with 10% invisibility, and when users are inclined to doubt true information.

Deep neural networks (DNNs) have been shown to perform well on exclusive, multi-class classification tasks. However, when different classes have similar visual features, it becomes challenging for human annotators to differentiate them. When an image is ambiguous, such as a blurry one where an annotator can't distinguish between a husky and a wolf, it may be labeled with both classes: {husky, wolf}. This scenario necessitates the use of composite set labels. In this paper, we propose a novel framework called Hyper-Evidential Neural Network (HENN) that explicitly models predictive uncertainty caused by composite set labels in training data in the context of the belief theory called Subjective Logic (SL). By placing a Grouped Dirichlet distribution on the class probabilities, we treat predictions of a neural network as parameters of hyper-subjective opinions and learn the network that collects both single and composite evidence leading to these hyper-opinions by a deterministic DNN from data. We introduce a new uncertainty type called vagueness originally designed for hyper-opinions in SL to quantify composite classification uncertainty for DNNs. Our experiments prove that HENN outperforms its state-of-the-art counterparts based on four image datasets. The code and datasets are available at: https://shorturl.at/dhoqx.

Early event detection aims to detect events even before the event is complete. However, most of the existing methods focus on an event with a single label but fail to be applied to cases with multiple labels. Another non-negligible issue for early event detection is a prediction with overconfidence due to the high vacuity uncertainty that exists in the early time series. It results in an over-confidence estimation and hence unreliable predictions. To this end, technically, we propose a novel framework, Multi-Label Temporal Evidential Neural Network (MTENN), for multi-label uncertainty estimation in temporal data. MTENN is able to quality predictive uncertainty due to the lack of evidence for multi-label classifications at each time stamp based on belief/evidence theory. In addition, we introduce a novel uncertainty estimation head (weighted binomial comultiplication (WBC)) to quantify the fused uncertainty of a sub-sequence for early event detection. We validate the performance of our approach with state-of-the-art techniques on real-world audio datasets.

Intent mining is critical for controlling the spread of false information across online social networks (OSNs). To this end, we develop deep reinforcement learning (DRL) agents guided by a delayed reward based on intent prediction using a classifier of long short-term memory (LSTM). Additionally, we incorporate an uncertainty-aware function that leverages subjective opinions derived from Subjective Logic (SL). Through evaluation using an annotated fake news tweet dataset, our results demonstrate that our intent classification framework surpasses competing methods in terms of intent accuracy. Our intent mining solutions using DRL algorithms can support effective and efficient intervention strategies for fake news spreading on OSNs.

Cancer classification using microarray gene expression data has received high interest because of its capability of performing cancer diagnosis computationally. However, researchers often faced difficulty in analyzing the data to achieve an accurate cancer diagnosis due to the size and noise issues in the microarray gene expression data. Therefore, it is important to perform feature extraction procedure to enhance the performance in cancer diagnosis. In this study, an approach is proposed by integrating wavelet-based feature extraction and visual analysis for cancer classification. Feature extraction is performed with wavelet transform and validates with a statistical test to determine only statistically valuable features. Visual analysis is also conducted to inspect not only the distribution of features but also the patterns of the cancer data. With cancer datasets, the performances of three machine learning (ML) algorithms for cancer classification are measured to show the effectiveness of the approach. From the performance evaluation study, we found that our approach has an ability to classifying cancers accurately.

Since data size is continuously increasing, analyzing large-scale data is considered as one of the major research challenges in computational data analysis. Although researchers have proposed numerous approaches, most of them still suffer from analyzing the data efficiently. To overcome the limitation, identifying the optimal number of features is critical for analyzing the data. In this paper, we introduce a newly designed feature selection technique, called Summit Selection, which boosts model performances by determining optimal features in noisy mixed data. First, testing all features is conducted to determine an initial base feature that satisfies a pre-defined criterion for maintaining the highest performance score. Then, a continuous evaluation is managed to build a model by successively adding or removing features based solely on the performance score tested with chosen computational models. To show the effectiveness of our proposed technique, a performance evaluation study was conducted to determine fraudulent activities in the UCSD Data Mining Contest 2009 Dataset. We compared our proposed technique with different feature extraction techniques such as PCA, ANOVA test, and Mutual Information (MI). Specifically, multiple machine learning techniques such as Decision Tree, Random Forest, and k-Nearest Neighbor (KNN) are tested with the feature extraction techniques to determine performance differences. As results, we found that our proposed technique showed about 8.78% performance improvement in detecting fraudulent activities. Since our technique can be extended to a cloud computing environment, we also performed a scalability testing with a known distributed cloud computing model (i.e., Apache Spark).

Recent advances and innovations in smart sensor technologies, energy storage, data communications, and distributed computing paradigms are enabling technological breakthroughs in very large sensor networks. There is an emerging surge of next-generation sensor-rich computers in consumer mobile devices as well as tailor-made field platforms wirelessly connected to the Internet. Billions of such sensor computers are posing both challenges and opportunities in relation to scalable and reliable management of the peta- and exa-scale time series being generated over time. This paper presents a Cloud-computing approach to this issue based on the two well-known data storage and processing paradigms: Bigtable and MapReduce.

Abstract Principle Component Analysis (PCA) is a widely used mathematical technique in many fields for factor and trend analysis, dimension reduction, etc. However, it is often considered to be a “black box” operation whose results are difficult to interpret and sometimes counter‐intuitive to the user. In order to assist the user in better understanding and utilizing PCA, we have developed a system that visualizes the results of principal component analysis using multiple coordinated views and a rich set of user interactions. Our design philosophy is to support analysis of multivariate datasets through extensive interaction with the PCA output. To demonstrate the usefulness of our system, we performed a comparative user study with a known commercial system, SAS/INSIGHT's Interactive Data Exploration. Participants in our study solved a number of high‐level analysis tasks with each interface and rated the systems on ease of learning and usefulness. Based on the participants' accuracy, speed, and qualitative feedback, we observe that our system helps users to better understand relationships between the data and the calculated eigenspace, which allows the participants to more accurately analyze the data. User feedback suggests that the interactivity and transparency of our system are the key strengths of our approach.

This paper describes a framework we have developed for the visual analysis of large-scale phylogeny hierarchies populated with the genomic data of various organisms. This framework allows the user to quickly browse the phylogeny hierarchy of organisms from the highest level down to the level of an individual genome for the desired organism of interest. Based on this framework, the user can initiate gene-finding and gene-matching analyses and view the resulting annotated coding potential graphs in the same multi-scale visualization framework, permitting correlative analysis and further investigation. This paper introduces our framework and describes the data structures and algorithms that support it.

An Interaction Task in Virtual Reality is such that a user can modify a computer generated virtual world using various techniques. But current interaction techniques cannot be applicable for most virtual environments due to their inefficiency and inconvenience. In this paper, we propose a selection and manipulation technique called the Finger-gesture. We evaluate its usefulness by conducting quantitative and qualitative experiments within a specific environment. Results indicate our new technique is more efficient in selection and modification tasks than other existing techniques including Go-Go and Ray-casting in terms of the task completion time and accuracy.