NDT, Volume 3, Issue 4 (December 2025) – 4 articles

Dielectric characterization offers valuable insights into fruit structure, ripening, and storage stability. However, systematic studies on apples are still limited. This work elucidates the electrical and physicochemical properties of a specific variety of apples, Malus domestica, using Electrochemical Impedance Spectroscopy (EIS), a non-destructive, fast and cost-effective technique, suitable for real-time quality assessments. The apple samples were analyzed over the frequency range of 20 Hz–120 MHz at 25 °C, and impedance data were modeled using equivalent circuits and dielectric relaxation models. Physicochemical analyses confirmed a high moisture content (84%, wwb), pH 4.81, TSS 14.58 °Brix, and acidity 0.64%, which is typical of fresh Red Delicious apples. Impedance spectra revealed semicircular and Warburg elements in Nyquist plots, indicating resistive, capacitive, and diffusive processes. Equivalent circuit fitting with the proposed R-C-Warburg impedance model outperformed (R² = 0.9946 and RMSE = 6.610) the classical Cole and Double-Shell models. The complex permittivity (ε) represented a frequency-dependent ionic diffusion, space-charge polarization, and dipolar relaxation decay, while electrical modulus analysis highlighted polarization and charge carrier dynamics. The translational hopping of charge carriers was confirmed through AC conductivity following Jonscher’s power law with an exponent of ƞ = 0.627. These findings establish a comprehensive dielectric profile and advanced circuit fitting for biological tissues, highlighting a promising non-invasive approach using EIS for real-time monitoring of fruit quality, with direct applications in post-harvest storage, supply chain management, and non-destructive quality assurance in the food industry. Full article

The Ground Penetrating Radar (GPR) method can image dielectric discontinuities in subsurface structures, which cause the reflection of electromagnetic (EM) waves. These discontinuities are imaged as reflectors in GPR sections, often distorted by diffracted energy. To focus the diffracted energy within the GPR sections, migration is commonly used. The migration velocity of GPR data is a low-wavenumber attribute crucial for effective migration. Obtaining a migration velocity model, typically close to a Root Mean Square (RMS) model, from zero-offset (ZO) data requires analysis of the available diffractions, whose density and (x, t) coverage are random. Thus, the accuracy and efficiency of such a velocity model, whether for migration or interval velocity model estimation, are not guaranteed. An alternative is the multipath summation method, which involves the weighted stacking of constant velocity migrated sections. Each stacked section contributes to the final stack, weighted by a scalar value dependent on the constant velocity value used and its relation to its estimated mean velocity of the section. This method effectively focuses the GPR diffractions in the presence of low heterogeneity. However, when the EM velocity varies dramatically, 2D weights are needed. In this study, with the aid of an Artificial Intelligence (AI) algorithm that detects diffractions and uses their kinematic information, we generate a diffraction velocity model. This model is then used to assign 2D weights for the weighted multipath summation, aiming to focus the scattered energy within the GPR section. We describe this methodology and demonstrate its application in enhancing the lateral continuity of reflections. We compare it with the 1D multipath summation using simulated data and present its application on marble assessment GPR data for imaging cracks and discontinuities in the subsurface structure. Full article

Skin cancer is one of the most prevalent and potentially lethal cancers worldwide, highlighting the need for accurate and timely diagnosis. Convolutional neural networks (CNNs) have demonstrated strong potential in automating skin lesion classification. In this study, we propose a multi-class classification model using EfficientNet-B0, a lightweight yet powerful CNN architecture, trained on the HAM10000 dermoscopic image dataset. All images were resized to 224 × 224 pixels and normalized using ImageNet statistics to ensure compatibility with the pre-trained network. Data augmentation and preprocessing addressed class imbalance, resulting in a balanced dataset of 7512 images across seven diagnostic categories. The baseline model achieved 77.39% accuracy, which improved to 89.36% with transfer learning by freezing the convolutional base and training only the classification layer. Full network fine-tuning with test-time augmentation increased the accuracy to 96%, and the final model reached 97.15% when combined with Monte Carlo dropout. These results demonstrate EfficientNet-B0’s effectiveness for automated skin lesion classification and its potential as a clinical decision support tool. Full article

The research work presents an artificial intelligence-driven, energy-aware data aggregation and routing protocol for wireless sensor networks (WSNs) with the primary objective of extending overall network lifetime. The proposed scheme leverages reinforcement learning in conjunction with deep Q-networks (DQNs) to adaptively optimize both Cluster Head (CH) selection and routing decisions. An adaptive clustering mechanism is introduced wherein factors such as residual node energy, spatial proximity, and traffic load are jointly considered to elect suitable CHs. This approach mitigates premature energy depletion at individual nodes and promotes balanced energy consumption across the network, thereby enhancing node sustainability. For data forwarding, the routing component employs a DQN-based strategy to dynamically identify energy-efficient transmission paths, ensuring reduced communication overhead and reliable sink connectivity. Performance evaluation, conducted through extensive simulations, utilizes key metrics including network lifetime, total energy consumption, packet delivery ratio (PDR), latency, and load distribution. Comparative analysis with baseline protocols such as LEACH, PEGASIS, and HEED demonstrates that the proposed protocol achieves superior energy efficiency, higher packet delivery reliability, and lower packet losses, while adapting effectively to varying network dynamics. The experimental outcomes highlight the scalability and robustness of the protocol, underscoring its suitability for diverse WSN applications including environmental monitoring, surveillance, and Internet of Things (IoT)-oriented deployments. Full article