International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems

A schema database functions as a repository for interconnected data points, facilitating comprehension of data structures by organizing information into tables with rows and columns. These databases utilize established connections to arrange data, with attribute values linking related tuples. This integrated approach to data management and distributed processing enables schema databases to maintain models even when the working set size surpasses available RAM. However, challenges such as data quality, storage, scarcity of data science professionals, data validation, and sourcing from diverse origins persist. Notably, while schema databases excel at reviewing transactions, they often fall short in updating them effectively. To address these issues, a Chimp-based radial basis neural model (CbRBNM) is employed. Initially, the Schemaless database was considered and integrated into the Python system. Subsequently, compression functions were applied to both schema and schema-less databases to optimize relational data size by eliminating redundant files. Performance validation involved calculating compression parameters, with the proposed method achieving memory usage of 383.37Mb, a computation time of 0.455s, a training time of 167.5ms, and a compression rate of 5.60%. Extensive testing demonstrates that CbRBNM yields a favorable compression ratio and enables direct searching on compressed data, thereby enhancing query performance.

Instead of storing data in rows, a columnar database is a type of Database Management System (DBMS). To speed up the processing and reply to a question, a columnar database’s job is to efficiently write and read data to and from hard disc storage. One of the most crucial methods in the creation of column-oriented database systems is compression. For columns with Zero-length string types, all heavier and light-in-weight compression techniques have limitations. Processing of transactions online, these databases are substantially more effective for online analytical processing than for online transactional processing. This indicates that although they are made to examine transactions, they are not very effective at updating them. To overcome these issues a Zero Length Recurrent based Fruit Fly Optimization (ZLRFF) model is used. Additionally, a reduction technique is known as ZLRFF was designed to achieve a high compression ratio and allow straight lookups on compressed material without decompression first. ZLRFF’s main goal is to divide a Zero-length string written column vertically into smaller columns that can each be compressed using a separate lightweight compression technique. To search directly on compressed data, we also provide a search technique we call FF-search. Extensive testing demonstrates that ZLRFF supports direct searching on compressed data in addition to achieving a decent compression ratio, which enhances query performance.

Multimodal Sentiment Analysis (MSA) is a growing area of emotional computing that involves analyzing data from three different modalities. Gathering data from Multimodal Sentiment analysis in Car Reviews (MuSe-CaR) is challenging due to data imbalance across modalities. To address this, an effective data augmentation approach is proposed by combining dynamic synthetic minority oversampling with a multimodal elicitation conditional generative adversarial network for emotion recognition using audio, text, and visual data. The balanced data is then fed into a granular elastic-net regression with a hybrid feature selection method based on dandelion fick’s law optimization to analyze sentiments. The selected features are input into a multilabel wavelet convolutional neural network to classify emotion states accurately. The proposed approach, implemented in python, outperforms existing methods in terms of trustworthiness (0.695), arousal (0.723), and valence (0.6245) on the car review dataset. Additionally, the feature selection method achieves high accuracy (99.65%), recall (99.45%), and precision (99.66%). This demonstrates the effectiveness of the proposed MSA approach, even with three modalities of data.

Subspace clustering is an effective way to analyze high-dimensional data. The main problems of the conventional subspace clustering techniques are as follows: first, conventional clustering methods can not describe categorical attribute space in more detail; second, most subspace-clustering techniques failure to process dynamic data effectively; finally, lack of effective noise recognition leads to the decline of the efficiency of incremental subspace-clustering analysis. We address the above problems by an incremental subspace-clustering algorithm — called ICE. With attribute subspace constructed by a rough set-based weight computing method, ICE obtains clustering results through initial and incremental clustering stage. Utilizing the original cluster results generated from initial clustering stage, we adopt merging and splitting operation to dynamic adjust cluster-structure in incremental clustering stage. Before achieving the final results, a polymerization-based noise recognition technique is employed to automatically identify noise from sparse clusters without human threshold intervention. We implement ICE on synthetic and real-world datasets. The experimental results reveal that incremental subspace-clustering method can achieves satisfactory performance on extensibility, accuracy and robustness.

Investors usually invest not only in risky assets but also in risk-free assets and face not only portfolio risk but also background risk. This paper discusses an uncertain portfolio selection problem in risky assets and risk-free assets with monotone increasing multiplicative background risk (MBR), which is prevalent but less research has been done. To do so, we first propose an uncertain mean-risk index model based on uncertainty theory where the security return and MBR are regarded as uncertain variables and give the deterministic form of the model. Then for further analysis, we discuss the critical constraint and optimality condition of the model. Based on the discussion, we study the influence of uncertain MBR on the investors’ decisions. Finally, we provide the case analysis to illustrate the application of our method and the analysis results.