Search Results (189)

The proliferation of Internet of Things (IoT) devices has amplified botnet risks, while traditional network-based intrusion detection systems (IDSs) struggle under encrypted and/or sparse traffic. Power consumption offers an effective side channel for device-level detection. Yet, prior studies typically focus on a single model family (often a convolutional neural network (CNN)) and rarely assess generalization across devices or compare broader model classes. In this paper, we conduct unified benchmarking and comparison of classical (SVM and RF), deep (CNN, LSTM, and 1D Transformer), and hybrid (CNN + LSTM, CNN + Transformer, and CNN + RF) models on the CHASE’19 dataset and a newly curated three-class botnet dataset, using consistent preprocessing and evaluation across single- and cross-device settings, reporting both accuracy and efficiency (latency and throughput). Experimental results demonstrate that Random Forest achieves the highest single-device accuracy (99.43% on the Voice Assistant with Seed 42), while CNN + Transformer shows a strong accuracy–efficiency trade-off in cross-device scenarios (94.02% accuracy on the combined dataset at ∼60,000 samples/s when using the best-performing Seed 42). These results offer practical guidance for selecting models under accuracy, latency, and throughput constraints and establish a reproducible baseline for power-side-channel IDSs. Full article

Accurately extracting the canopies of fruit trees is crucial to improve the estimation accuracy of CNC inversion as well as determine a reasonable application of nitrogen fertilizer. To date, existing studies have mainly focused on canopy extraction in scenarios with no grass or sparse grass cover, paying less attention to scenarios with a full grass cover. Thus, in this paper, a two-stage canopy extraction (TCE) method was proposed to address the issue of canopy extraction in scenarios with full grass cover. Firstly, the height difference between the canopies of pear trees and the ground grass was used to eliminate the interference of the ground grass and achieve a coarse-grained canopy extraction. Then, based on the extracted coarse-grained canopies and CIELAB color space, the color thresholds of the L*, a*, and b* channels were determined to remove the interference factors, e.g., branches, shadows, and trellises, for fine-grained canopy extraction by using data distribution from the three channels based on a histogram and the threshold of confidence interval. In canopy extraction experiments, the accuracy, recall, precision, and F1-score of TCE in scenarios with full grass cover can reach 91.725%, 95.789%, 91.284%, and 93.482%, respectively, demonstrating the effectiveness of TCE in addressing canopy extraction issues in this scenario. Thirdly, the RF algorithm was utilized to select suitable VIs based on R² and RMSE values, and CNC inversion models were constructed. In estimation experiments on CNC inversion, the R², RMSE, and nRMSE of the constructed CNC inversion based on TCE in a scenario with full grass cover were 0.724, 0.243, and 19.120%, respectively. A comparative analysis with the baseline method revealed that accurate canopy extraction contributed to a high estimation accuracy of CNC inversion. Therefore, our proposed method can provide technical support for the efficient and non-destructive monitoring of the canopy nutrient status in pear orchards. Full article

Accurate, non-invasive glucose monitoring remains a major challenge in biomedical sensing. We present a high-sensitivity planar microwave biosensor that progresses from a 2-cell hexagonal array to an 8-cell hexagonal array, and finally to a 16-cell double-honeycomb (DHC-CSRR) architecture to enhance field confinement and resonance strength. Full-wave simulations using Debye-modeled glucose phantoms demonstrate that the optimized 16-cell array on a Rogers RO3210 substrate substantially increases the electric field intensity and transmission response |S₂₁| sensitivity compared with FR-4 and previous multi-CSRR designs. In vitro measurements using pharmacy-grade glucose solutions (5–25%) and saline mixtures with added glucose, delivered through an acrylic channel aligned to the sensing region, confirm the simulated trends. In vivo, vector network analyzer (VNA) tests were conducted on four human subjects (60–150 mg/dL), comparing single- and dual-finger placements. The FR-4 substrate (${\mathsf{\epsilon }}_{\mathrm{r}}$ = 4.4) provided higher frequency sensitivity (2.005 MHz/(mg/dL)), whereas the Rogers RO3210 substrate (${\mathsf{\epsilon }}_{\mathrm{r}}$ = 10.2) achieved greater amplitude sensitivity (9.35 × 10⁻² dB/(mg/dL)); dual-finger contact outperformed single-finger placement for both substrates. Repeated intra-day VNA measurements yielded narrow 95% confidence intervals on |S₂₁|, with an overall uncertainty of approximately ±0.5 dB across the tested glucose levels. Motivated by the larger |S₂₁| response on Rogers, we adopted amplitude resolution as the primary metric and built a compact prototype using the AD8302-EVALZ with a custom 3D-printed enclosure to enhance measurement precision. In a cohort of 31 participants, capillary blood glucose was obtained using a commercial glucometer, after which two fingers were placed on the sensing region; quadratic voltage-to-glucose calibration yielded R² = 0.980, root–mean–square error (RMSE) = 2.316 mg/dL, overall accuracy = 97.833%, and local sensitivity = 1.099 mg/dL per mV, with anthropometric variables (weight, height, age) showing no meaningful correlation. Clarke Error Grid Analysis placed 100% of paired measurements in Zone A, indicating clinically acceptable agreement with the reference meter. Benchmarking against commercial continuous glucose monitoring systems highlights substrate selection as a dominant lever for amplitude sensitivity and positions the proposed fully non-invasive, consumable-free architecture as a promising route toward portable RF-based glucose monitors, while underscoring the need for larger cohorts, implementation on flexible biocompatible substrates, and future regulatory pathways. Full article

Curtain grouting is widely used to reduce the permeability of dam foundations, yet forecasting cement intake remains challenging because flow pathways are governed by the three-dimensional connectivity of rock fractures. We develop a hybrid framework that explicitly embeds 3D fracture connectivity into data-driven prediction. A discrete fracture network (DFN) is constructed and traversed using depth-first search (DFS) from each grouting hole segment to capture both direct and multistep connections. Six connectivity descriptors are computed—the number of reachable fractures (N), average inclination (I), average dip angle (D), cumulative connected volume (V), average radius (r), and average width (w)—and combined with construction parameters as model inputs. Cement intake is predicted using an integrated model that combines a Restricted Boltzmann Machine (RBM)-pretrained multilayer perceptron with channel-wise squeeze-and-excitation (SE) attention, where key hyperparameters are optimized via a genetic algorithm (GA). Applied to a curtain-grouting project (448 segments), the connectivity-aware model improves agreement with observations over a no-connectivity baseline: the correlation coefficient (R) increases from 0.938 to 0.972, while mean absolute error (MAE), mean absolute percentage error (MAPE), and root mean square error (RMSE) decrease by 27.1%, 12.2%, and 32.8%, respectively. Ablation studies validate the contributions of each component, confirming that RBM pretraining enhances generalization, SE attention improves feature selection, and ensemble aggregation stabilizes predictions. Compared to four optimized baseline models (SVR, RF, ELM, and LSTM), the proposed integrated method achieves improvements of 3–34% in R and reductions of 22–55% in MAE, 31–66% in RMSE, and 2–48% in MAPE on the held-out test set. This model provides engineers with a simple, cost-effective tool for accurate predictions to support better decision-making in grouting. Full article

In immersive digital devices, high environmental complexity can lead to rendering delays and loss of interactive details, resulting in a fragmented experience. This paper proposes a lightweight NeRF (Neural Radiance Fields) modeling and multimodal perception fusion method. First, a sparse hash code is constructed based on Instant-NGP (Instant Neural Graphics Primitives) to accelerate scene radiance field generation. Second, parameter distillation and channel pruning are used to reduce the model’s size and reduce computational overheads. Next, multimodal data from a depth camera and an IMU (Inertial Measurement Unit) is fused, and Kalman filtering is used to improve pose tracking accuracy. Finally, the optimized NeRF model is integrated into the Unity engine, utilizing custom shaders and asynchronous rendering to achieve low-latency viewpoint responsiveness. Experiments show that the file size of this method in high-complexity scenes is only 79.5 MB ± 5.3 MB, and the first loading time is only 2.9 s ± 0.4 s, effectively reducing rendering latency. The SSIM is 0.951 ± 0.016 at 1.5 m/s, and the GME is 7.68 ± 0.15 at 1.5 m/s. It can stably restore texture details and edge sharpness under dynamic viewing angles. In scenarios that support 3–5 people interacting simultaneously, the average interaction response delay is only 16.3 ms, and the average jitter error is controlled at 0.12°, significantly improving spatial interaction performance. In conclusion, this study provides effective technical solutions for high-quality immersive interaction in complex public scenarios. Future work will explore the framework’s adaptability in larger-scale dynamic environments and further optimize the network synchronization mechanism for multi-user concurrency. Full article

This paper presents an orthogonal time–frequency space (OTFS)-based integrated sensing and communication (ISAC) framework for vehicular-to-base-station (V2B) scenarios, where a synthetic road environment models vehicular mobility and multipath propagation with explicit ground truth. In the sensing stage, OTFS probing signals with Gray-coded quadrature amplitude modulation (QAM) are processed via inverse symplectic finite Fourier transform (ISFFT) and cyclic prefix orthogonal frequency-division multiplexing (CP-OFDM). The receiver applies cyclic prefix (CP) removal, fast Fourier transform (FFT), and symplectic finite Fourier transform (SFFT) to extract delay–Doppler (DD) responses. Channel estimation uses time–frequency least squares (TF-LS), robust background suppression, constant false alarm rate (CFAR) detection, and non-maximum suppression (NMS), yielding Precision = 0.79, Recall = 0.84, and F1 = 0.82. Communication decoding employs per-bin least squares, minimum mean-squared error (MMSE) equalization, and Gray-mapped QAM demapping. Across ten frames at 20 dB SNR, the system decoded $1.887\times {10}^8$ bits with $1.575\times {10}^5$ errors, producing a bit error rate (BER) of $8.34\times {10}^{-4}$. Error vector magnitude (EVM) analysis reports mean = 0.30%, median = 0.06%, confirming constellation stability. Random Forest (RF) and imbalanced RF (IRF) classifiers trained on augmented DD payloads achieve Precision = 0.94, Recall = 0.87, and F1 = 0.92. Results validate OTFS-ISAC as a robust framework for V2B communication and sensing. Full article

The rapid spread of unmanned aerial vehicles (UAVs) has created new challenges for airspace security, as drones are increasingly used for surveillance, smuggling, and potentially for attacks near critical infrastructure. A key difficulty lies in reliably distinguishing UAVs from visually similar birds in electro-optical surveillance channels, where complex backgrounds and visual noise often increase false alarms. To address this, we investigated recent YOLO architectures and developed an enhanced model named YOLOv12-ADBC, incorporating an adaptive hierarchical feature integration mechanism to strengthen multi-scale spatial fusion. This architectural refinement improves sensitivity to subtle inter-class differences between drones and birds. A dedicated dataset of 7291 images was used to train and evaluate five YOLO versions (v8–v12), together with the proposed YOLOv12-ADBC. Comparative experiments demonstrated that YOLOv12-ADBC achieved the best overall performance, with precision = 0.892, recall = 0.864, mAP50 = 0.881, mAP50–95 = 0.633, and per-class accuracy reaching 96.4% for drones and 80% for birds. In inference tests on three video sequences simulating realistic monitoring conditions, YOLOv12-ADBC consistently outperformed baselines, achieving a detection accuracy of 92.1–95.5% and confidence levels up to 88.6%, while maintaining real-time processing at 118–135 frames per second (FPS). These results demonstrate that YOLOv12-ADBC not only surpasses previous YOLO models but also offers strong potential as the optical module in multi-sensor fusion frameworks. Its integration with radar, RF, and acoustic channels is expected to further enhance system-level robustness, providing a practical pathway toward reliable UAV detection in modern airspace protection systems. Full article

This study develops an innovative unmanned aerial vehicle (UAV)-based intelligent system for winter wheat yield prediction, addressing the inefficiencies of traditional manual counting methods (with approximately 15% error rate) and enabling quantitative analysis of water–fertilizer interactions. By integrating an enhanced Faster Region-Based Convolutional Neural Network (Faster R-CNN) architecture with multi-source data fusion and machine learning, the system significantly improves both spike detection accuracy and yield forecasting performance. Field experiments during the 2022–2023 growing season captured high-resolution multispectral imagery for varied irrigation regimes and fertilization treatments. The optimized detection model incorporates ResNet-50 as the backbone feature extraction network, with residual connections and channel attention mechanisms, achieving a mean average precision (mAP) of 91.2% (calculated at IoU threshold 0.5) and 88.72% recall while reducing computational complexity. The model outperformed YOLOv8 by a statistically significant 2.1% margin (p < 0.05). Using model-generated spike counts as input, the random forest (RF) model regressor demonstrated superior yield prediction performance (R² = 0.82, RMSE = 324.42 kg·ha⁻¹), exceeding the Partial Least Squares Regression (PLSR) (R² +46%, RMSE-44.3%), Least Squares Support Vector Machine (LSSVM) (R² + 32.3%, RMSE-32.4%), Support Vector Regression (SVR) (R² + 30.2%, RMSE-29.6%), and Backpropagation (BP) Neural Network (R²+22.4%, RMSE-24.4%) models. Analysis of different water–fertilizer treatments revealed that while organic fertilizer under full irrigation (750 m³ ha⁻¹) conditions achieved maximum yield benefit (13,679.26 CNY·ha⁻¹), it showed relatively low water productivity (WP = 7.43 kg·m⁻³). Conversely, under deficit irrigation (450 m³ ha⁻¹) conditions, the 3:7 organic/inorganic fertilizer treatment achieved optimal WP (11.65 kg m⁻³) and WUE (20.16 kg∙ha⁻¹∙mm⁻¹) while increasing yield benefit by 25.46% compared to organic fertilizer alone. This research establishes an integrated technical framework for high-throughput spike monitoring and yield estimation, providing actionable insights for synergistic water–fertilizer management strategies in sustainable precision agriculture. Full article

Frequent channel migrations of the Yellow River, coupled with increasing human disturbances, have driven significant land cover changes in the Yellow River Delta (YRD) over time. Accurate estimation of aboveground biomass (AGB) and clarification of the impact of land cover changes on AGB are crucial for monitoring vegetation dynamics and supporting ecological management. However, field-based biomass samples are often time-consuming and labor-intensive, and the quantity and quality of such samples greatly affect the accuracy of AGB estimation. This study developed a robust AGB estimation framework for the YRD by synthesizing 4717 field-measured samples from the published scientific literature and integrating two critical ecological indicators: leaf area index (LAI) and length of growing season (LGS). A random forest (RF) model was employed to estimate AGB for the YRD from 2001 to 2022, achieving high accuracy (R² = 0.74). The results revealed a continuous spatial expansion of AGB over the past two decades, with higher biomass consistently observed in western cropland and along the Yellow River, whereas lower biomass levels were concentrated in areas south of the Yellow River. AGB followed a fluctuating upward trend, reaching a minimum of 204.07 g/m² in 2007, peaking at 230.79 g/m² in 2016, and stabilizing thereafter. Spatially, western areas showed positive trends, with an average annual increase of approximately 10 g/m², whereas central and coastal zones exhibited localized declines of around 5 g/m². Among the changes in land cover, cropland and wetland changes were the main contributors to AGB increases, accounting for 54.2% and 52.67%, respectively. In contrast, grassland change exhibited limited or even suppressive effects, contributing −6.87% to the AGB change. Wetland showed the greatest volatility in the interaction between area change and biomass density change, which is the most uncertain factor in the dynamic change in AGB. Full article

Oxide semiconductor gas sensors are widely used due to their low cost, rapid response, small footprint, and ease of integration. However, in complex gas mixtures their selectivity is often limited by inherent cross-sensitivity. To address this, we developed a reconfigurable sensor-array system that supports up to 12 chemiresistive sensors with four- or six-electrode configurations, independent thermal control, and programmable gas paths. As a representative case study, we designed a customized array for fish-spoilage biomarkers, intentionally leveraging the cross-sensitivity and broad-spectrum responses of metal-oxide sensors. Following principal component analysis (PCA) preprocessing, we evaluated convolutional neural network (CNN), random forest (RF), and particle swarm optimization–tuned support vector machine (PSO-SVM) classifiers. The RF model achieved 94% classification accuracy. Subsequent channel optimization (correlation analysis and feature-importance assessment) reduced the array from 12 to 8 sensors and improved accuracy to 96%, while simplifying the system. These results demonstrate that deliberately leveraging cross-sensitivity within a carefully selected array yields an information-rich odor fingerprint, providing a practical platform for complex gas-mixture identification and food-freshness assessment. Full article

The rapid advancement of underwater wireless communication technologies is critical to unlocking the full potential of marine resource exploration and environmental monitoring. This paper reviews recent progress in three primary modalities: underwater acoustic communication, radio frequency (RF) communication, and underwater optical wireless communication (UWOC), each designed to address specific challenges posed by complex underwater environments. Acoustic communication, while effective for long-range transmission, is constrained by ambient noise and high latency; recent innovations in noise reduction and data rate enhancement have notably improved its reliability. RF communication offers high-speed, short-range capabilities in shallow waters, but still faces challenges in hardware miniaturization and accurate channel modeling. UWOC has emerged as a promising solution, enabling multi-gigabit data rates over medium distances through advanced modulation techniques and turbulence mitigation. Additionally, bio-inspired approaches such as electric field communication provide energy-efficient and robust alternatives under turbid conditions. This paper further examines the practical integration of these technologies in underwater platforms, including autonomous underwater vehicles (AUVs), highlighting trade-offs between energy efficiency, system complexity, and communication performance. By synthesizing recent advancements, this review outlines the advantages and limitations of current underwater communication methods and their real-world applications, offering insights to guide the future development of underwater communication systems for robotic and vehicular platforms. Full article

Radio frequency (RF)-based wireless systems are broadly used in communication systems such as mobile networks, satellite links, and monitoring applications. These systems offer outstanding advantages over wired systems, particularly in terms of ease of installation. However, researchers are looking for safer alternatives as a result of worries about possible health problems connected to high-frequency radiofrequency transmission. Using the visible light spectrum is one promising approach; three cutting-edge technologies are emerging in this regard: Optical Camera Communication (OCC), Light Fidelity (Li-Fi), and Visible Light Communication (VLC). In this paper, we propose a Multiple-Input Multiple-Output (MIMO) modulation technology for Internet of Things (IoT) applications, utilizing an LED array and time-domain on-off keying (OOK). The proposed system is compatible with both rolling shutter and global shutter cameras, including commercially available models such as CCTV, webcams, and smart cameras, commonly deployed in buildings and industrial environments. Despite the compact size of the LED array, we demonstrate that, by optimizing parameters such as exposure time, camera focal length, and channel coding, our system can achieve up to 20 communication links over a 20 m distance with low bit error rate. Full article

Radio frequency fingerprint identification (RFFI) leverages the unique characteristics of radio signals resulting from inherent hardware imperfections for identification, making it essential for applications in telecommunications, cybersecurity, and surveillance. Despite the advancements brought by deep learning in enhancing RFFI accuracy, challenges persist in model deployment, particularly when transferring RFFI models across different receivers. Variations in receiver hardware can lead to significant performance declines due to shifts in data distribution. This paper introduces the source-free cross-receiver RFFI (SCRFFI) problem, which centers on adapting pre-trained RF fingerprinting models to new receivers without needing access to original training data from other devices, addressing concerns of data privacy and transmission limitations. We propose a novel approach called contrastive source-free cross-receiver network (CSCNet), which employs contrastive learning to facilitate model adaptation using only unlabeled data from the deployed receiver. By incorporating a three-pronged loss function strategy—minimizing information entropy loss, implementing pseudo-label self-supervised loss, and leveraging contrastive learning loss—CSCNet effectively captures the relationships between signal samples, enhancing recognition accuracy and robustness, thereby directly mitigating the impact of receiver variations and the absence of source data. Our theoretical analysis provides a solid foundation for the generalization performance of SCRFFI, which is corroborated by extensive experiments on real-world datasets, where under realistic noise and channel conditions, that CSCNet significantly improves recognition accuracy and robustness, achieving an average improvement of at least 13% over existing methods and, notably, a 47% increase in specific challenging cross-receiver adaptation tasks. Full article

The detection of abusive language in Roman Urdu is important for secure digital interaction. This work investigates machine learning (ML), deep learning (DL), and transformer-based methods for detecting offensive language in Roman Urdu comments collected from YouTube news channels. Extracted features use TF-IDF and Count Vectorizer for unigrams, bigrams, and trigrams. Of all the ML models—Random Forest (RF), Logistic Regression (LR), Support Vector Machine (SVM), and Naïve Bayes (NB)—the best performance was achieved by the same SVM. DL models involved evaluating Bi-LSTM and CNN models, where the CNN model outperformed the others. Moreover, transformer variants such as LLaMA 2 and ModernBERT (MBERT) were instantiated and fine-tuned with LoRA (Low-Rank Adaptation) for better efficiency. LoRA has been tuned for large language models (LLMs), a family of advanced machine learning frameworks, based on the principle of making the process efficient with extremely low computational cost with better enhancement. According to the experimental results, LLaMA 2 with LoRA attained the highest F1-score of 96.58%, greatly exceeding the performance of other approaches. To elaborate, LoRA-optimized transformers perform well in capturing detailed subtleties of linguistic nuances, lending themselves well to Roman Urdu offensive language detection. The study compares the performance of conventional and contemporary NLP methods, highlighting the relevance of effective fine-tuning methods. Our findings pave the way for scalable and accurate automated moderation systems for online platforms supporting multiple languages. Full article

This paper proposes a tree-based regression model for hybrid channel estimation in wireless sensor networks (WSNs) in generalized frequency division multiplexing (GFDM) over both visible light communication (VLC) and radio frequency (RF) links. The hybrid channel incorporates both additive white Gaussian noise (AWGN) and Rayleigh fading to mimic realistic environments. Traditional estimators, such as MMSE and LMMSE, often underperform in such heterogeneous and nonlinear conditions due to their analytical rigidity. To overcome these limitations, we introduce a data-driven approach using a decision tree regressor trained on 18,000 signal samples across 36 SNR levels. Simulation results show that support vector machine (SVM) achieved 91.34% accuracy and a BER of 0.0866 at 10 dB, as well as 96.77% accuracy with a BER of 0.0323 at 30 dB. Random forest achieved 91.01% accuracy and a BER of 0.0899 at 10 dB, as well as 97.88% accuracy with a BER of 0.0212 at 30 dB. The proposed tree model attained 90.83% and 97.63% accuracy with BERs of 0.0917 and 0.0237, respectively, at the corresponding SNR values. The distinguishing advantage of the tree model lies in its inference efficiency. It completes predictions on the test dataset in just 45.53 s, making it over three times faster than random forest (140.09 s) and more than four times faster than SVM (189.35 s). This significant reduction in inference time makes the proposed tree model particularly well suited for real-time and resource-constrained WSN scenarios, where fast and efficient estimation is often more critical than marginal gains in accuracy. The results also highlight a trade-off, where the tree model provides sub-optimal predictive performance while significantly reducing computational overhead, making it an attractive choice for low-power and latency-sensitive wireless systems. Full article