Search Results (425)

This research paper explores the use of machine learning to relate images of flame structure and luminosity to measured NOx emissions. Images of reactions produced by 16 aero-engine derived injectors for a ground-based turbine operated on a range of fuel compositions, air pressure drops, preheat temperatures and adiabatic flame temperatures were captured and postprocessed. The experimental investigations were conducted under atmospheric conditions, capturing CO, NO and NOx emissions data and OH* chemiluminescence images from 27 test conditions. The injector geometry and test conditions were based on a statistically designed test plan. These results were first analyzed using the traditional analysis approach of analysis of variance (ANOVA). The statistically based test plan yielded 432 data points, leading to a correlation for NOx emissions as a function of injector geometry, test conditions and imaging responses, with 70.2% accuracy. As an alternative approach to predicting emissions using imaging diagnostics as well as injector geometry and test conditions, a random forest machine learning algorithm was also applied to the data and was able to achieve an accuracy of 82.6%. This study offers insights into the factors influencing emissions in ground-based turbines while emphasizing the potential of machine learning algorithms in constructing predictive models for complex systems. Full article

Feature selection (FS) is a classic and challenging optimization task in most machine learning and data mining projects. Recently, researchers have attempted to develop more effective methods by using metaheuristic methods in FS. To increase population diversity and further improve the effectiveness of the beluga whale optimization (BWO) algorithm, in this paper, we propose a multi-strategies improved BWO (MSBWO), which incorporates improved circle mapping and dynamic opposition-based learning (ICMDOBL) population initialization as well as elite pool (EP), step-adaptive Lévy flight and spiral updating position (SLFSUP), and golden sine algorithm (Gold-SA) strategies. Among them, ICMDOBL contributes to increasing the diversity during the search process and reducing the risk of falling into local optima. The EP technique also enhances the algorithm′s ability to escape from local optima. The SLFSUP, which is distinguished from the original BWO, aims to increase the rigor and accuracy of the development of local spaces. Gold-SA is introduced to improve the quality of the solutions. The hybrid performance of MSBWO was evaluated comprehensively on IEEE CEC2005 test functions, including a qualitative analysis and comparisons with other conventional methods as well as state-of-the-art (SOTA) metaheuristic approaches that were introduced in 2024. The results demonstrate that MSBWO is superior to other algorithms in terms of accuracy and maintains a better balance between exploration and exploitation. Moreover, according to the proposed continuous MSBWO, the binary MSBWO variant (BMSBWO) and other binary optimizers obtained by the mapping function were evaluated on ten UCI datasets with a random forest (RF) classifier. Consequently, BMSBWO has proven very competitive in terms of classification precision and feature reduction. Full article

As an effective method for uncertain knowledge discovery and decision-making, the three-way decisions model has attracted extensive attention from scholars. However, in practice, the existing sequential three-way decision model often faces challenges due to factors such as missing data and unbalanced attribute granularity. To address these issues, we propose an intuitionistic fuzzy sequential three-way decision (IFSTWD) model, which introduces several significant contributions: (1) New intuitionistic fuzzy similarity relations. By integrating possibility theory, our model defines similarity and dissimilarity in incomplete information systems, establishing new intuitionistic fuzzy similarity relations and their cut relations. (2) Granulation method innovation. We propose a density neighborhood-based granulation method to partition decision attributes and introduce a novel criterion for evaluating attribute importance. (3) Enhanced decision process. By incorporating sequential three-way decision theory and developing a multi-level granularity structure, our model replaces the traditional equivalent relation in the decision-theoretic rough sets model, thus advancing the model’s applicability and effectiveness. The practical utility of our model is demonstrated through an example analysis of “Chinese + vocational skills” talent competency and validated through simulation experiments on the UCI dataset, showing superior performance compared to existing methods. Full article

Autonomous driving pays considerable attention to pedestrian trajectory prediction as a crucial task. Constructing effective pedestrian trajectory prediction models depends heavily on utilizing the motion characteristics of pedestrians, along with their interactions among themselves and between themselves and their environment. However, traditional trajectory prediction models often fall short of capturing complex real-world scenarios. To address these challenges, this paper proposes an enhanced pedestrian trajectory prediction model, M²Tames, which incorporates comprehensive motion, interaction, and semantic context factors. M²Tames provides an interaction module (IM), which consists of an improved multi-head mask temporal attention mechanism (M²Tea) and an Interaction Inference Module (I²). M²Tea thoroughly characterizes the historical trajectories and potential interactions, while I² determines the precise interaction types. Then, IM adaptively aggregates useful neighbor features to generate a more accurate interactive feature map and feeds it into the final layer of the U-Net encoder to fuse with the encoder’s output. Furthermore, by adopting the U-Net architecture, M²Tames can learn and interpret scene semantic information, enhancing its understanding of the spatial relationships between pedestrians and their surroundings. These innovations improve the accuracy and adaptability of the model for predicting pedestrian trajectories. Finally, M²Tames is evaluated on the ETH/UCY and SDD datasets for short- and long-term settings, respectively. The results demonstrate that M²Tames outperforms the state-of-the-art model MSRL by 2.49% (ADE) and 8.77% (FDE) in the short-term setting and surpasses the optimum Y-Net by 6.89% (ADE) and 1.12% (FDE) in the long-term prediction. Excellent performance is also shown on the ETH/UCY datasets. Full article

The growing problem of unsolicited text messages (smishing) and data irregularities necessitates stronger spam detection solutions. This paper explores the development of a sophisticated model designed to identify smishing messages by understanding the complex relationships among words, images, and context-specific factors, areas that remain underexplored in existing research. To address this, we merge a UCI spam dataset of regular text messages with real-world spam data, leveraging OCR technology for comprehensive analysis. The study employs a combination of traditional machine learning models, including K-means, Non-Negative Matrix Factorization, and Gaussian Mixture Models, along with feature extraction techniques such as TF-IDF and PCA. Additionally, deep learning models like RNN-Flatten, LSTM, and Bi-LSTM are utilized. The selection of these models is driven by their complementary strengths in capturing both the linear and non-linear relationships inherent in smishing messages. Machine learning models are chosen for their efficiency in handling structured text data, while deep learning models are selected for their superior ability to capture sequential dependencies and contextual nuances. The performance of these models is rigorously evaluated using metrics like accuracy, precision, recall, and F1 score, enabling a comparative analysis between the machine learning and deep learning approaches. Notably, the K-means feature extraction with vectorizer achieved 91.01% accuracy, and the KNN-Flatten model reached 94.13% accuracy, emerging as the top performer. The rationale behind highlighting these models is their potential to significantly improve smishing detection rates. For instance, the high accuracy of the KNN-Flatten model suggests its applicability in real-time spam detection systems, but its computational complexity might limit scalability in large-scale deployments. Similarly, while K-means with vectorizer excels in accuracy, it may struggle with the dynamic and evolving nature of smishing attacks, necessitating continual retraining. Full article

As a novel learning algorithm for feedforward neural networks, the twin extreme learning machine (TELM) boasts advantages such as simple structure, few parameters, low complexity, and excellent generalization performance. However, it employs the squared L2-norm metric and an unbounded hinge loss function, which tends to overstate the influence of outliers and subsequently diminishes the robustness of the model. To address this issue, scholars have proposed the bounded capped L2,p-norm metric, which can be flexibly adjusted by varying the p value to adapt to different data and reduce the impact of noise. Therefore, we substitute the metric in the TELM with the capped L2,p-norm metric in this paper. Furthermore, we propose a bounded, smooth, symmetric, and noise-insensitive squared fractional loss (SF-loss) function to replace the hinge loss function in the TELM. Additionally, the TELM neglects statistical information in the data; thus, we incorporate the Fisher regularization term into our model to fully exploit the statistical characteristics of the data. Drawing upon these merits, a squared fractional loss-based robust supervised twin extreme learning machine (SF-RSTELM) model is proposed by integrating the capped L2,p-norm metric, SF-loss, and Fisher regularization term. The model shows significant effectiveness in decreasing the impacts of noise and outliers. However, the proposed model’s non-convexity poses a formidable challenge in the realm of optimization. We use an efficient iterative algorithm to solve it based on the concave-convex procedure (CCCP) algorithm and demonstrate the convergence of the proposed algorithm. Finally, to verify the algorithm’s effectiveness, we conduct experiments on artificial datasets, UCI datasets, image datasets, and NDC large datasets. The experimental results show that our model is able to achieve higher ACC and F1 scores across most datasets, with improvements ranging from 0.28% to 4.5% compared to other state-of-the-art algorithms. Full article

In the process of using multi-channel ground-penetrating radar (GPR) for underground cavity exploration, the acquired 3D data include reflection data from underground cavities or various underground objects (structures). Reflection data from unspecified structures can interfere with the identification process of underground cavities. This study aims to identify underground cavities using a C-GAN model with an applied ResBlock technique. This deep learning model demonstrates excellent performance in the image domain and can automatically classify the presence of cavities by analyzing 3D GPR data, including reflection waveforms (A-scan), cross-sectional views (B-scan), and plan views (C-scan) measured from the ground under roads. To maximize the performance of the C-GAN model, a background filtering algorithm (BFA) was developed and applied to enhance the visibility and clarity of underground cavities. To verify the performance of the developed BFA, 3D data collected from roads in Seoul, Republic of Korea, using 3D GPR equipment were transformed, and the C-GAN model was applied. As a result, it was confirmed that the recall, an indicator of cavity prediction, improved by approximately 1.15 times compared to when the BFA was not applied. This signifies the verification of the effectiveness of the BFA. This study developed a special algorithm to distinguish underground cavities. This means that in the future, not only the advancement of separate equipment and systems but also the development of specific algorithms can contribute to the cavity exploration process. Full article

Background/Objectives: Given the importance of emotion recognition for communication purposes, and the impairment for such skill in CI users despite impressive language performances, the aim of the present study was to investigate the neural correlates of emotion recognition skills, apart from language, in adult unilateral CI (UCI) users during a music in noise (happy/sad) recognition task. Furthermore, asymmetry was investigated through electroencephalographic (EEG) rhythm, given the traditional concept of hemispheric lateralization for emotional processing, and the intrinsic asymmetry due to the clinical UCI condition. Methods: Twenty adult UCI users and eight normal hearing (NH) controls were recruited. EEG gamma and alpha band power was assessed as there is evidence of a relationship between gamma and emotional response and between alpha asymmetry and tendency to approach or withdraw from stimuli. The TAS-20 questionnaire (alexithymia) was completed by the participants. Results: The results showed no effect of background noise, while supporting that gamma activity related to emotion processing shows alterations in the UCI group compared to the NH group, and that these alterations are also modulated by the etiology of deafness. In particular, relative higher gamma activity in the CI side corresponds to positive processes, correlated with higher emotion recognition abilities, whereas gamma activity in the non-CI side may be related to positive processes inversely correlated with alexithymia and also inversely correlated with age; a correlation between TAS-20 scores and age was found only in the NH group. Conclusions: EEG gamma activity appears to be fundamental to the processing of the emotional aspect of music and also to the psychocognitive emotion-related component in adults with CI. Full article

This paper presents an interpretable, spiking neural classifier (IpT-SNC) with time-varying weights. IpT-SNC uses a two-layered spiking neural network (SNN) architecture in which weights of synapses are modeled using amplitude-modulated, time-varying Gaussian functions. Self-regulated particle swarm optimization (SRPSO) is used to update the amplitude, width, and centers of the Gaussian functions and thresholds of neurons in the output layer. IpT-SNC has been developed to improve the interpretability of spiking neural networks. The time-varying weights in IpT-SNC allow us to describe the rationale behind predictions in terms of specific input spikes. The performance of IpT-SNC is evaluated on ten benchmark datasets in the UCI machine learning repository and compared with the performance of other learning algorithms. According to the performance results, IpT-SNC enhances classification performance on testing datasets from a minimum of 0.5% to a maximum of 7.7%. The significance level of IpT-SNC with other learning algorithms is evaluated using statistical tests like the Friedman test and the paired t-test. Furthermore, on the challenging real-world BCI (Brain Computer Interface) competition IV dataset, IpT-SNC outperforms current classifiers by about 8% in terms of classification accuracy. The results indicate that IpT-SNC has better generalization performance than other algorithms. Full article

Explainable Artificial Intelligence (XAI) is a research area that clarifies AI decision-making processes to build user trust and promote responsible AI. Hence, a key scientific challenge in XAI is the development of methods that generate transparent and interpretable explanations while maintaining scalability and effectiveness in complex scenarios. Rule-based methods in XAI generate rules that can potentially explain AI inferences, yet they can also become convoluted in large scenarios, hindering their readability and scalability. Moreover, they often lack contrastive explanations, leaving users uncertain why specific predictions are preferred. To address this scientific problem, we explore the integration of computational argumentation—a sub-field of AI that models reasoning processes through defeasibility—into rule-based XAI systems. Computational argumentation enables arguments modelled from rules to be retracted based on new evidence. This makes it a promising approach to enhancing rule-based methods for creating more explainable AI systems. Nonetheless, research on their integration remains limited despite the appealing properties of rule-based systems and computational argumentation. Therefore, this study also addresses the applied challenge of implementing such an integration within practical AI tools. The study employs the Logic Learning Machine (LLM), a specific rule-extraction technique, and presents a modular design that integrates input rules into a structured argumentation framework using state-of-the-art computational argumentation methods. Experiments conducted on binary classification problems using various datasets from the UCI Machine Learning Repository demonstrate the effectiveness of this integration. The LLM technique excelled in producing a manageable number of if-then rules with a small number of premises while maintaining high inferential capacity for all datasets. In turn, argument-based models achieved comparable results to those derived directly from if-then rules, leveraging a concise set of rules and excelling in explainability. In summary, this paper introduces a novel approach for efficiently and automatically generating arguments and their interactions from data, addressing both scientific and applied challenges in advancing the application and deployment of argumentation systems in XAI. Full article

Mobile and wearable devices have revolutionized the field of continuous user activity monitoring. However, analyzing the vast and intricate data captured by the sensors of these devices poses significant challenges. Deep neural networks have shown remarkable accuracy in Human Activity Recognition (HAR), but their application on mobile and wearable devices is constrained by limited computational resources. To address this limitation, we propose a novel method called Knowledge Distillation for Human Activity Recognition (KD-HAR) that leverages the knowledge distillation technique to compress deep neural network models for HAR using inertial sensor data. Our approach transfers the acquired knowledge from high-complexity teacher models (state-of-the-art models) to student models with reduced complexity. This compression strategy allows us to maintain performance while keeping computational costs low. To assess the compression capabilities of our approach, we evaluate it using two popular databases (UCI-HAR and WISDM) comprising inertial sensor data from smartphones. Our results demonstrate that our method achieves competitive accuracy, even at compression rates ranging from 18 to 42 times the number of parameters compared to the original teacher model. Full article

LMNA-related dilated cardiomyopathy (DCM) is an autosomal-dominant genetic condition with cardiomyocyte and conduction system dysfunction often resulting in heart failure or sudden death. The condition is caused by mutation in the Lamin A/C (LMNA) gene encoding Type-A nuclear lamin proteins involved in nuclear integrity, epigenetic regulation of gene expression, and differentiation. The molecular mechanisms of the disease are not completely understood, and there are no definitive treatments to reverse progression or prevent mortality. We investigated possible mechanisms of LMNA-related DCM using induced pluripotent stem cells derived from a family with a heterozygous LMNA c.357-2A>G splice-site mutation. We differentiated one LMNA-mutant iPSC line derived from an affected female (Patient) and two non-mutant iPSC lines derived from her unaffected sister (Control) and conducted single-cell RNA sequencing for 12 samples (four from Patients and eight from Controls) across seven time points: Day 0, 2, 4, 9, 16, 19, and 30. Our bioinformatics workflow identified 125,554 cells in raw data and 110,521 (88%) high-quality cells in sequentially processed data. Unsupervised clustering, cell annotation, and trajectory inference found complex heterogeneity: ten main cell types; many possible subtypes; and lineage bifurcation for cardiac progenitors to cardiomyocytes (CMs) and epicardium-derived cells (EPDCs). Data integration and comparative analyses of Patient and Control cells found cell type and lineage-specific differentially expressed genes (DEGs) with enrichment, supporting pathway dysregulation. Top DEGs and enriched pathways included 10 ZNF genes and RNA polymerase II transcription in pluripotent cells (PP); BMP4 and TGF Beta/BMP signaling, sarcomere gene subsets and cardiogenesis, CDH2 and EMT in CMs; LMNA and epigenetic regulation, as well as DDIT4 and mTORC1 signaling in EPDCs. Top DEGs also included XIST and other X-linked genes, six imprinted genes (SNRPN, PWAR6, NDN, PEG10, MEG3, MEG8), and enriched gene sets related to metabolism, proliferation, and homeostasis. We confirmed Lamin A/C haploinsufficiency by allelic expression and Western blot. Our complex Patient-derived iPSC model for Lamin A/C haploinsufficiency in PP, CM, and EPDC provided support for dysregulation of genes and pathways, many previously associated with Lamin A/C defects, such as epigenetic gene expression, signaling, and differentiation. Our findings support disruption of epigenomic developmental programs, as proposed in other LMNA disease models. We recognized other factors influencing epigenetics and differentiation; thus, our approach needs improvement to further investigate this mechanism in an iPSC-derived model. Full article

Human activity recognition (HAR) typically uses wearable sensors to identify and analyze the time-series data they collect, enabling recognition of specific actions. As such, HAR is increasingly applied in human–computer interaction, healthcare, and other fields, making accurate and efficient recognition of various human activities. In recent years, deep learning methods have been extensively applied in sensor-based HAR, yielding remarkable results. However, complex HAR research, which involves specific human behaviors in varied contexts, still faces several challenges. To solve these problems, we propose a multi-head neural network based on the attention mechanism. This framework contains three convolutional heads, with each head designed using one-dimensional CNN to extract features from sensory data. The model uses a channel attention module (squeeze–excitation module) to enhance the representational capabilities of convolutional neural networks. We conducted experiments on two publicly available benchmark datasets, UCI-HAR and WISDM, to evaluate our model. The results were satisfactory, with overall recognition accuracies of 96.72% and 97.73% on their respective datasets. The experimental results demonstrate the effectiveness of the network structure for the HAR, which ensures a higher level of accuracy. Full article

Extreme learning machines (ELMs), single hidden-layer feedforward neural networks, are renowned for their speed and efficiency in classification and regression tasks. However, their generalization ability is often undermined by the random generation of hidden layer weights and biases. To address this issue, this paper introduces a Hierarchical Learning-based Chaotic Crayfish Optimization Algorithm (HLCCOA) aimed at enhancing the generalization ability of ELMs. Initially, to resolve the problems of slow search speed and premature convergence typical of traditional crayfish optimization algorithms (COAs), the HLCCOA utilizes chaotic sequences for population position initialization. The ergodicity of chaos is leveraged to boost population diversity, laying the groundwork for effective global search efforts. Additionally, a hierarchical learning mechanism encourages under-performing individuals to engage in extensive cross-layer learning for enhanced global exploration, while top performers directly learn from elite individuals at the highest layer to improve their local exploitation abilities. Rigorous testing with CEC2019 and CEC2022 suites shows the HLCCOA’s superiority over both the original COA and nine renowned heuristic algorithms. Ultimately, the HLCCOA-optimized extreme learning machine model, the HLCCOA-ELM, exhibits superior performance over reported benchmark models in terms of accuracy, sensitivity, and specificity for UCI breast cancer diagnosis, underscoring the HLCCOA’s practicality and robustness, as well as the HLCCOA-ELM’s commendable generalization performance. Full article

Human activity recognition (HAR) is a crucial task in various applications, including healthcare, fitness, and the military. Deep learning models have revolutionized HAR, however, their computational complexity, particularly those involving BiLSTMs, poses significant challenges for deployment on resource-constrained devices like smartphones. While BiLSTMs effectively capture long-term dependencies by processing inputs bidirectionally, their high parameter count and computational demands hinder practical applications in real-time HAR. This study investigates the approximation of the computationally intensive BiLSTM component in a HAR model by using a combination of alternative model components and data flipping augmentation. The proposed modifications to an existing hybrid model architecture replace the BiLSTM with standard and residual LSTM, along with convolutional networks, supplemented by data flipping augmentation to replicate the context awareness typically provided by BiLSTM networks. The results demonstrate that the residual LSTM (ResLSTM) model achieves superior performance while maintaining a lower computational complexity compared to the traditional BiLSTM model. Specifically, on the UCI-HAR dataset, the ResLSTM model attains an accuracy of 96.34% with 576,702 parameters, outperforming the BiLSTM model’s accuracy of 95.22% with 849,534 parameters. On the WISDM dataset, the ResLSTM achieves an accuracy of 97.20% with 192,238 parameters, compared to the BiLSTM’s 97.23% accuracy with 283,182 parameters, demonstrating a more efficient architecture with minimal performance trade-off. For the KU-HAR dataset, the ResLSTM model achieves an accuracy of 97.05% with 386,038 parameters, showing comparable performance to the BiLSTM model’s 98.63% accuracy with 569,462 parameters, but with significantly fewer parameters. Full article