Automated analysis for tumor segmentation and illness classification is hampered by the noise, low contrast, and ambiguity that are common in medical pictures. This work introduces a new 12-step fuzzy-based improvement pipeline that uses fuzzy entropy, fuzzy standard deviation, and histogram spread functions to enhance picture quality in CT, MRI, and X-ray modalities. The pipeline produces three improved versions per dataset, lowering BRISQUE scores from 28.8 to 21.7 (KiTS19), 30.3 to 23.4 (BraTS2020), and 26.8 to 22.1 (Chest X-ray). It is tested on KiTS19 (CT) for kidney tumor segmentation, BraTS2020 (MRI) for brain tumor segmentation, and Chest X-ray Pneumonia for classification. A Concatenated CNN (CCNN) uses the improved datasets to achieve a Dice coefficient of 99.60% (KiTS19, +2.40% over baseline), segmentation accuracy of 0.983 (KiTS19) and 0.981 (BraTS2020) versus 0.959 and 0.943 (CLAHE), and classification accuracy of 0.974 (Chest X-ray) versus 0.917 (CLAHE). A classic CNN is trained on original and CLAHE-filtered datasets. These outcomes demonstrate how well the pipeline works to improve image quality and increase segmentation/classification accuracy, offering a foundation for clinical diagnostics that is both scalable and interpretable.

This paper proposes a Cross-Representation Attention-Based Neural Network with fuzzy image enhancement for joint classification and segmentation of chest X-ray and kidney images. First, each input image is transformed into three complementary representations using histogram spread, fuzzy entropy, and fuzzy standard deviation-based enhancement. These representations emphasize different intensity distributions, informative regions, and local structural variations. A Cross-Representation Attention Fusion module then models multidirectional relationships among the enhanced representations and adaptively integrates their complementary features into a unified feature space. The fused features are processed by a shared encoder with task-specific classification and segmentation heads. The framework is evaluated for clinically relevant chest X-ray abnormalities, including pneumonia, pneumothorax, pleural effusion, and lung opacity, and for kidney-image classes comprising normal, tumor/renal cell carcinoma, and cystic renal mass cases. Experimental results show that the proposed method outperforms conventional and recent baseline models in both classification and segmentation. Ablation studies confirm that the fuzzy enhancement branches, cross-representation attention, and joint multi-task learning each contribute to the overall performance. Statistical and qualitative analyses further demonstrate the stability of the results and the model’s ability to localize relevant lesion regions. The proposed framework provides an effective and interpretable approach to unified medical image classification and segmentation while maintaining a reasonable balance between predictive performance and computational cost.

Diagnosing faults across different smart homes is hard: sensor names, layouts, and daily routines differ from home to home, so a model trained in one home rarely works in another. We study an ontology-guided framework for cross-home fault diagnosis, but our main contribution is a benchmark-validity audit—a systematic check of whether the datasets used to evaluate such systems actually measure fault detection. Using the public Center for Advanced Studies in Adaptive Systems (CASAS) smart-home datasets (homes hh101–hh110) and real household power data (HomeC, UMass Smart*), we show that much of the high cross-home accuracy reported on these benchmarks is an artifact of features that re-encode the labelling rules rather than evidence of transfer: when those features are removed, the macro-averaged F1 score (macro-F1) collapses toward the level obtained with randomly permuted labels. We therefore treat these datasets as semantic-transfer and benchmark-validity studies, not fault-detection results. The framework’s distinguishing component is a counterfactual calibration layer that returns a probability for its recommended intervention; on a controlled structural causal model with known interventions, it achieves a Brier skill score of $0.369$ for intervention-success probabilities. Separately, on the simulation-derived LBNL Fan Coil Unit benchmark, a conventional gradient-boosted multiclass fault classifier achieves accuracy comparable to a random forest but about six times lower expected calibration error ($0.026$ vs. $0.159$) under a scenario-matched split. This calibration advantage does not generalize to held-out simulation scenarios, where the calibration error rises to $0.372$; we report this negative result as a limitation. We are explicit about scope: the ontology reasoner and the real-stream causal graph are only partially implemented, and the counterfactual recommendations are validated only under controlled or simulated conditions, not in deployed homes. The results are intended for researchers who build or benchmark sensor-based fault-diagnosis models, for dataset curators, and for practitioners who need calibrated rather than merely accurate outputs. All code, the proxy-label rules, and the leakage audit are released.

Ensuring information integrity requires not only reducing decoding errors but also reducing the probability that corrupted data are accepted as valid. This research presents a hybrid integrity protection system that incorporates seeded universal hash verification, algebraic manipulation detection (AMD), and a binary Reed–Muller outer code. Transmission over the binary symmetric channel $\mathrm{B}\mathrm{S}\mathrm{C}\left(p\right)$, outer encoding using $\mathrm{R}\mathrm{M}(r, m)$, bounded-distance decoding, an ${\epsilon }_{\mathrm{A}\mathrm{M}\mathrm{D}}$-secure AMD layer, and a seeded 2-universal hash family with $\mathcal{l}$-bit output define the model used in the analysis. Under explicitly stated freshness and conditional-independence assumptions, the system-level undetected error probability is upper-bounded by the residual decoder-miscorrection probability multiplied by the AMD acceptance bound and the seeded universal hash collision bound. A conservative alternative is also provided for settings in which the required conditional independence cannot be guaranteed. In this context, an explicit upper bound for the undetected error probability is derived. The outcome makes clear the different functions of outer coding and post-decoding verification and results in a direct dependency on the parameters r, m, p, and l. Finite-length Monte Carlo validation for a concrete instantiation based on RM(2, 5) complements the theoretical study and verifies that the hybrid construction offers a lower empirical undetected error probability compared to the comparable outer-only, AMD-only, and hash-only variations. The study does not propose new coding or verification primitives. Its contribution is a finite-length layered acceptance model and a Reed–Muller-specific undetected error analysis that incorporates the code weight distribution and bounded-distance decoding regions. The resulting spectrum-based bound distinguishes decoder miscorrection from the broader event of exceeding the guaranteed correction radius and is evaluated together with post-decoding verification and redundancy overhead. The model’s formal manipulation detection and collision guarantees are provided by AMD and universal hash layers, while Reed–Muller code parameters and their standard distance formulas are conventional.

Top-loading smart vending cabinets require precise transaction-level product detection under strict hardware and deployment constraints. In this paper, “sensorless” refers specifically to the absence of auxiliary product-level sensing hardware, such as RFID tags, weight sensors, shelf load cells, or product-slot instrumentation; the system still uses two camera sensors. Conventional snapshot-difference methods compare only a small number of frames at the beginning and end of a transaction and therefore cannot explicitly represent intermediate product motion, such as pickup, return, inspection, occlusion, and shelf resettling. This paper proposes ZAB-Fusion, a dual-camera edge sensing framework with zone-aware multi-object tracking for sensorless smart vending cabinets. The framework combines a YOLO11-seg and RT-DETR detection ensemble with ByteTrack temporal association, projects product tracks into a three-zone vertical cabinet model, interprets compressed zone sequences using a finite-state event classifier, and integrates camera-specific event streams through an evidence-gated cross-camera fusion rule. The proposed method was evaluated on 220 in-service vending transactions containing 227 ground-truth TAKEN events and 87 RETURNED events across seven product classes. Compared with the snapshot-difference baseline, ZAB-Fusion improved recall from 0.665 to 0.925 and F1-score from 0.780 to 0.944, while maintaining a high precision of 0.963. At the transaction level, exact receipt accuracy increased from 0.645 to 0.900. Runtime analysis on an Intel N100 CPU-only edge device showed an average processing latency of 562 ms per transaction under the selected-frame inference protocol. The zone classification, finite-state event interpretation, and evidence-gated cross-camera fusion stages required only 3 ms in total. These results demonstrate that explicit motion semantics and auditable cross-camera evidence gating can improve sensorless retail transaction level recognition in sensorless smart vending cabinets without adding auxiliary product-level sensing hardware.

Accurate classification of pollen grains in microscopic images remains challenging because of noise, structural variability, background complexity, weak texture, and intra-class similarity. To address these issues, this study proposes a hybrid framework that integrates contour-signal modeling, spectral–wavelet analysis, and deep learning for robust microscopic pollen image recognition. In the proposed approach, microscopic pollen images are first converted into contour-based point-signal representations, allowing object boundaries to be analyzed as structured one-dimensional signals. To improve signal quality under real imaging conditions, the framework incorporates Gaussian, median, and contour-aware filtering together with defect-point detection and correction. The processed contour signals are then analyzed using Fourier transform, continuous wavelet transform, and discrete wavelet transform to extract complementary global and local descriptors. These enriched representations are provided to a convolutional neural network for final classification. Experiments conducted on a seven-class microscopic pollen-image dataset demonstrate that the proposed method outperforms conventional computer-vision and baseline deep-learning approaches. The best-performing hybrid configuration achieved an error rate of 6.4%, while the overall classification accuracy reached 0.977 with an F1-score of 0.966, compared with 0.837 for a traditional computer-vision pipeline. These results confirm that combining contour-based signal processing with hierarchical deep feature learning provides an effective and noise-robust strategy for microscopic pollen image recognition. However, the present validation is limited to pollen images, and further experiments on broader microscopic object datasets are required to assess generalization to other micro-object categories such as nanoparticles, fibers, rods, and synthetic microstructures.