The multi-lead electrocardiogram (ECG) is widely utilized in clinical diagnosis and monitoring of cardiac conditions. The advancement of deep learning has led to the emergence of automated multi-lead ECG diagnostic networks, which have become essential in the fields of biomedical engineering and clinical cardiac disease diagnosis. Intelligent ECG diagnosis techniques encompass Recurrent Neural Networks (RNN), Transformers, and Convolutional Neural Networks (CNN). While CNN is capable of extracting local spatial information from images, it lacks the ability to learn global spatial features and temporal memory features. Conversely, RNN relies on time and can retain significant sequential features. However, they are not proficient in extracting lengthy dependencies of sequence data in practical scenarios. The self-attention mechanism in the Transformer model has the capability of global feature extraction, but it does not adequately prioritize local features and cannot extract spatial and channel features. This paper proposes STFAC-ECGNet, a model that incorporates CAMV-RNN block, CBMV-CNN block, and TSEF block to enhance the performance of the model by integrating the strengths of CNN, RNN, and Transformer. The CAMV-RNN block incorporates a coordinated adaptive simplified self-attention module that adaptively carries out global sequence feature retention and enhances spatial–temporal information. The CBMV-CNN block integrates spatial and channel attentional mechanism modules in a skip connection, enabling the fusion of spatial and channel information. The TSEF block implements enhanced multi-scale fusion of image spatial and sequence temporal features. In this study, comprehensive experiments were conducted using the PTB-XL large publicly available ECG dataset and the China Physiological Signal Challenge 2018 (CPSC2018) database. The results indicate that STFAC-ECGNet surpasses other cutting-edge techniques in multiple tasks, showcasing robustness and generalization.
Temperature climate is an essential component of weather forecasting and is vital in predicting future weather patterns. Accurate temperature predictions can assist individuals and organizations in preparing for potential weather-related events such as heat waves or cold snaps. However, achieving precise temperature predictions necessitates thoroughly comprehending the underlying factors influencing climate patterns. The study utilized two models, LSTM and DLSTM, to forecast daily air temperature using 1097 data points gathered from central and southern regions of Tabriz city of Iran in Asia from 2017 to 2019. The results indicated that the proposed model had a high accuracy rate for predicting daily air temperature for test data, with RMSEDLSTM = 0.08 °C and R-SquareDLSTM = 0.99. The DLSTM algorithm is known for its high speed, accuracy, time series prediction, noise reduction capabilities for data, the large volume of data processing, and improved performance of predicted data. In summary, while both LSTM and DLSTM are used for predicting data points, DLSTM is a more advanced version that includes multiple layers of memory cells and is better suited for handling complex sequences of events.
Missing data introduce uncertainty in data mining, but existing set-valued approaches ignore frequency information. We propose unsupervised attribute reduction algorithms for multiset-valued data to address this gap. First, we define a multiset-valued information system (MSVIS) and establish -tolerance relation to form the information granules. Then, -information entropy and -information amount are introduced as uncertainty measures. Finally, these two UMs are used to design two unsupervised attribute reduction algorithms in an MSVIS. The experimental results demonstrate the superiority of the proposed algorithms, achieving average reductions of 50% in attribute subsets while improving clustering accuracy and outlier detection performance. Parameter analysis further validates the robustness of the framework under varying missing rates.
Target detection in Synthetic Aperture Radar (SAR) imagery is consistently hampered by speckle noise, geometric distortions, and complex scattering characteristics. Existing detection methods often remain confined to the spatial domain, struggling to capture global structural information and effectively leverage the rich data present in the frequency domain. To address these limitations, this paper introduces FMD-Net (Frequency, Multi-dimensional, Dynamic Net), a detection framework centered on the deep integration of frequency domain analysis with an advanced attention-based architecture. Frequency domain analysis allows for the extraction of periodic textures and global structures while simultaneously suppressing noise, compensating for the limitations of purely spatial-domain approaches. FMD-Net introduces a set of synergistic modules that dynamically filter and enhance features in the frequency space, adaptively modulate multi-dimensional features to handle scale and shape variations, and meticulously recover fine details for small targets through content-aware upsampling. FMD-Net achieves a mean Average Precision (mAP50-95) of 68.9% on the SHSA dataset. Furthermore, it attains a competitive (mAP50-95) of 67.6% on the challenging MSAR dataset and 63.6% on the FUSAR-Ship dataset. These results suggest that FMD-Net demonstrates competitive performance against state-of-the-art methods, showing noticeable improvements in detection accuracy and robustness, especially for small targets and within complex, cluttered scenes.
This study focuses on the satisfaction of college students' majors, employing both gray relational analysis and fuzzy comprehensive evaluation methods for comprehensive assessment. Through gray relational analysis, the correlation between factors such as curriculum offerings, competence and infrastructure, student perception, and employment confidence, and the satisfaction of college students' majors is explored, with the determination of the weights of each factor. Subsequently, fuzzy comprehensive evaluation method is applied to comprehensively evaluate the satisfaction of college students' majors, with the weights of each factor and evaluation indicators being fuzzified to derive the comprehensive evaluation results. The results indicate that there is a high correlation between the evaluation of the major's curriculum design in the course setting and the allocation of course credits and hours with students' employment confidence. However, student evaluations and practical components still require improvement. According to the entropy weight method's weight calculation results, the manner and impact of student evaluations carry the greatest weight.
The -nearest-neighbor (KNN) rule is a widely adopted classification technique in machine learning and pattern recognition. Notably, rough set models exhibit a robust capability for decision approximation, making them particularly valuable in handling complex and imprecise data. In practical applications, information systems (IS) often comprise diverse structures of information values. A three-way heterogeneous information system (3HIS) refers to an IS where attribute values encompass three distinct data types: scaled (continuous), ordinal (ranked), and nominal (categorical). This article investigates uncertainty measurement in a 3HIS by leveraging the KNN approach. First, we introduce a specialized distance function designed to compute the dissimilarity between any two information values within each attribute, accounting for the heterogeneity of data types. Building upon this, we propose an enhanced KNN model tailored for a 3HIS, which effectively captures local data structures. By using this model, we construct information granules that facilitate granular computing in heterogeneous data environments. Subsequently, we develop uncertainty quantification tools based on information entropy and information granulation, enabling a rigorous assessment of data inconsistency and ambiguity. To validate the effectiveness of these measurements, we conduct dispersion analysis from a statistical perspective, comparing various uncertainty metrics. Furthermore, we introduce a novel unsupervised attribute reduction algorithm for a 3HIS. The algorithm optimizes feature selection by minimizing redundancy while preserving discriminative power. To evaluate its performance, we employ cluster analysis to demonstrate its efficacy in enhancing data interpret-ability and classification accuracy. These findings provide significant insights into the fundamental nature of uncertainty in a 3HIS.