In recent years, Sign Language Recognition (SLR) has become an additional topic of discussion in the human–computer interface (HCI) field. The most significant difficulty confronting SLR recognition is finding algorithms that will scale effectively with a growing vocabulary size and a limited supply of training data for signer-independent applications. Due to its sensitivity to shape information, automated SLR based on hidden Markov models (HMMs) cannot characterize the confusing distributions of the observations in gesture features with sufficiently precise parameters. In order to simulate uncertainty in hypothesis spaces, many scholars provide an extension of the HMMs, utilizing higher-order fuzzy sets to generate interval-type-2 fuzzy HMMs. This expansion is helpful because it brings the uncertainty and fuzziness of conventional HMM mapping under control. The neutrosophic sets are used in this work to deal with indeterminacy in a practical SLR setting. Existing interval-type-2 fuzzy HMMs cannot consider uncertain information that includes indeterminacy. However, the neutrosophic hidden Markov model successfully identifies the best route between states when there is vagueness. This expansion is helpful because it brings the uncertainty and fuzziness of conventional HMM mapping under control. The neutrosophic three membership functions (truth, indeterminate, and falsity grades) provide more layers of autonomy for assessing HMM’s uncertainty. This approach could be helpful for an extensive vocabulary and hence seeks to solve the scalability issue. In addition, it may function independently of the signer, without needing data gloves or any other input devices. The experimental results demonstrate that the neutrosophic HMM is nearly as computationally difficult as the fuzzy HMM but has a similar performance and is more robust to gesture variations.

Sign language recognition (SLR) plays a crucial role in bridging the communication gap between deaf individuals and the hearing population. However, achieving subject-independent SLR remains a significant challenge due to variations in signing styles, hand shapes, and movement patterns among users. Traditional Markov Chain-based models struggle with generalizing across different signers, often leading to reduced recognition accuracy and increased uncertainty. These limitations arise from the inability of conventional models to effectively capture diverse gesture dynamics while maintaining robustness to inter-user variability. To address these challenges, this study proposes an adaptive SLR framework that integrates Markov Chains with a Niching Genetic Algorithm (NGA). The NGA optimizes the transition probabilities and structural parameters of the Markov Chain model, enabling it to learn diverse signing patterns while avoiding premature convergence to suboptimal solutions. In the proposed SLR framework, GA is employed to determine the optimal transition probabilities for the Markov Chain components operating across multiple signing contexts. To enhance the diversity of the initial population and improve the model’s adaptability to signer variations, a niche model is integrated using a Context-Based Clearing (CBC) technique. This approach mitigates premature convergence by promoting genetic diversity, ensuring that the population maintains a wide range of potential solutions. By minimizing gene association within chromosomes, the CBC technique enhances the model’s ability to learn diverse gesture transitions and movement dynamics across different users. This optimization process enables the Markov Chain to better generalize subject-independent sign language recognition, leading to improved classification accuracy, robustness against signer variability, and reduced misclassification rates. Experimental evaluations demonstrate a significant improvement in recognition performance, reduced error rates, and enhanced generalization across unseen signers, validating the effectiveness of the proposed approach.

Uncertainty-aware soft sensors in sign language recognition (SLR) integrate methods to quantify and manage the uncertainty in their predictions. This is particularly crucial in SLR due to the variability in sign language gestures and differences in individual signing styles. Managing uncertainty allows the system to handle variations in signing styles, lighting conditions, and occlusions more effectively. While current techniques for handling uncertainty in SLR systems offer significant benefits in terms of improved accuracy and robustness, they also come with notable disadvantages. High computational complexity, data dependency, scalability issues, sensor and environmental limitations, and real-time constraints all pose significant hurdles. The aim of the work is to develop and evaluate a Type-2 Neutrosophic Hidden Markov Model (HMM) for SLR that leverages the advanced uncertainty handling capabilities of Type-2 neutrosophic sets. In the suggested soft sensor model, the Foot of Uncertainty (FOU) allows Type-2 Neutrosophic HMMs to represent uncertainty as intervals, capturing the range of possible values for truth, falsity, and indeterminacy. This is especially useful in SLR, where gestures can be ambiguous or imprecise. This enhances the model’s ability to manage complex uncertainties in sign language gestures and mitigate issues related to model drift. The FOU provides a measure of confidence for each recognition result by indicating the range of uncertainty. By effectively addressing uncertainty and enhancing subject independence, the model can be integrated into real-life applications, improving interactions, learning, and accessibility for the hearing-impaired. Examples such as assistive devices, educational tools, and customer service automation highlight its transformative potential. The experimental evaluation demonstrates the superiority of the Type-2 Neutrosophic HMM over the Type-1 Neutrosophic HMM in terms of accuracy for SLR. Specifically, the Type-2 Neutrosophic HMM consistently outperforms its Type-1 counterpart across various test scenarios, achieving an average accuracy improvement of 10%.

Background/Objectives: Reliable skin-lesion AI requires evaluation beyond the development distribution. This study assessed whether a source-developed multi-class system preserves discrimination and reliability when transferred to an unseen smartphone-acquired domain. Methods: A source-only multimodal four-class classifier was developed using HAM10000 and Derm7pt and evaluated on PAD-UFES-20 without target-domain adaptation. Reliability was assessed using class-specific calibration, uncertainty-based error detection, class-conditional conformal prediction, selective classification, demographic subgroup auditing, controlled ablation, and an independent DDI out-of-distribution (OOD) and explainability (XAI) audit. Results: Across five prespecified seeds, macro-F1 decreased from 74.27 ± 1.36% on the source domain to 54.92 ± 2.60% on PAD-UFES-20. Calibration, conformal efficiency, and selective coverage also deteriorated externally, although macro-AUROC remained comparatively preserved. The independent DDI audit showed limited OOD separation, while explanation stability was interpreted only as descriptive evidence. Ablation analysis indicated that clinical metadata contributed importantly to external performance. Conclusions: Internally reproducible discrimination did not guarantee reliable external behavior. These findings support explicit external reliability auditing and specialist-supervised selective decision support before cross-device deployment.

Human Activity Recognition (HAR) is a pivotal research area for applications such as automated surveillance, smart homes, security, healthcare, and human behavior analysis. Traditional machine-learning approaches often rely on manual feature engineering, which can limit generalization. Although deep learning has improved HAR through automatic representation learning, achieving high detection performance under computational constraints remains challenging. This paper proposes an efficient HAR framework that combines deep learning with hybrid optimization. Surveillance videos are first decomposed into frames, and a keyframe selection stage identifies distinctive frames to reduce redundancy and computational cost while preserving informative content. Motion and appearance features are then extracted using Histogram of Oriented Optical Flow (HOOF) and a ResNet-101 model, respectively, and concatenated into a unified feature representation. Classification is performed using an Inception-based Long Short-Term Memory (Incept-LSTM) network, which is fine-tuned via the proposed Tricky Predator Optimization (TricP) over a restricted, low-dimensional parameter vector. TricP is inspired by predator poaching behavior and the social dynamics of Latrans to enhance exploration and exploitation during search. Experiments on the UCF-Crime dataset show that the proposed method achieves 96.84% specificity, 92.16% sensitivity, and 93.62% accuracy.

With the exponential rise in digital information, the need for an effective multi-document text summarization technique which can provide concise, informative, coherent and reduce redundant information is growing increasingly. The conventional extractive summarization methods are used separately to generate the sentences maximization or sentence ranking based on statistical methods, which is hard to get the accurate estimation about the importance of sentences and to set suitable weights for the features that determine it. This paper aims to overcome these drawbacks and introduces a hybrid Fuzzy–Whale Optimization Algorithm (F-WOA) model for extractive multi-document text summarization. The Whale Optimization Algorithm (WOA) is used to optimize the weights of the extracted features, and the Mamdani Fuzzy Inference System (MFIS) uses the weighted features to estimate the importance of each sentence. First, all the input documents are preprocessed, and eight linguistic and statistical features are extracted. Each candidate weight vector is evaluated by passing the weighted features through the MFIS and measuring the topic relevance, cohesion, and readability of the resulting summary. The best weights are then used by the MFIS to score the sentences, and the top-ranked non-redundant sentences form the final summary. The experiments were performed on the benchmark datasets DUC-2002, DUC-2004, DUC-2006, and DUC-2007 with the ROUGE-1, ROUGE-2, and ROUGE-L evaluation metrics. Experimental results achieved ROUGE-1, ROUGE-2, and ROUGE-L F-scores of up to 50.79, 25.60, and 31.75, respectively. Comparative analysis shows that the integration of fuzzy logic into WOA enhances the quality of the summaries compared to the WOA-only variant that scores sentence with a weighted sum of the features.