Search Results (12,803)

We propose KoSim-GL, a large-scale vision-based geo-localization dataset for drone positioning in GPS-denied environments. Geo-localization estimates a drone’s location by matching drone-view imagery against a geo-referenced satellite image database, offering a reliable alternative to GPS under conditions such as signal jamming, spoofing, or degradation in dense urban canyons. Although this task is challenging due to the domain gap between drone-view and satellite-view imagery, existing benchmarks are built predominantly around urban environments in the United States and China, leaving South Korea largely unrepresented, despite its distinctive landscape in which mountainous terrain coexists with dense high-rise districts and low-rise residential neighborhoods. To address this gap, we introduce KoSim-GL, constructed from drone-view images captured via an AirSim- and ROS-based flight simulator and satellite images collected through the Google Maps Tile API, covering the urban area of Daejeon, South Korea. Its key feature is a multi-view configuration that simultaneously captures five views, one nadir and four oblique, at each flight position across altitudes from 100 m to 600 m, enabling robust localization even in feature-sparse environments where nadir-only matching is prone to fail. In total, KoSim-GL comprises 2,450,315 drone images and 1704 satellite images. We further provide systematic comparisons against five existing benchmarks and baseline evaluations of ten representative geo-localization models under single- and multi-view settings. Experimental results show that the multi-view configuration substantially improves localization performance; for example, FSRA improves Recall@1 from 44.08% (single-view) to 65.37% (multi-view), a gain of 21.29 percentage points. The dataset is publicly available. Full article

Product mismatch, arising from consumers’ inability to physically experience products before purchase, is a major cause of returns in e-commerce, eroding e-tailer profits and intensifying consumers’ concerns about returns. To alleviate these concerns, e-tailers have increasingly adopted return insurance (RI), which reduces consumers’ return freight costs. However, RI may encourage consumers to defer product selection from the pre-purchase search stage to the post-purchase evaluation stage, thereby exacerbating mismatch and increasing return rates. As a countermeasure in live-streaming commerce, augmented reality (AR) provides an immersive product experience that can reduce mismatch and returns. This study develops a game-theoretic model to analyze the strategic interplay between an e-tailer’s RI decision and a live streamer’s AR decision while incorporating consumer search effort. The results show that consumer search effort changes the relationship between the two strategies. When search effort is low, RI and AR function as strategic substitutes; when search effort is high, they function as strategic complements. These findings indicate that the value of a return-management strategy depends on consumer behavior and on the presence of the partner’s AR strategy. The study contributes to the literature on interdependent return-management strategies and provides actionable insights for e-commerce practitioners. Full article

In modern radar and electronic countermeasure systems, frequency-agile (FA) signal generators with low phase noise are of vital importance. The optoelectronic oscillator (OEO) is restricted by the periodic boundary condition (PBC), despite its superior performance in phase noise and frequency tunability. This paper proposes a new FA optoelectronic hybrid oscillator scheme, which employs a reconfigurable aperiodic FA filter and a dynamic frequency compensation module to collaboratively break the PBC limitation. It achieves fast switching and fine-grained frequency hopping at the 100 kHz level while maintaining low phase noise. Theoretical and experimental verification show that the system can generate arbitrary FA radio frequency (RF) signals from 1.95 GHz to 2.05 GHz with a tuning range of 10³ times the free spectral range (FSR), and the phase noise reaches −120 dBc/Hz at 10 kHz offset. This study provides a novel technical route for generating narrow-step frequency-agile signals and effectively improves target detection accuracy and anti-jamming performance in electronic warfare applications. Full article

Pathological complete response (pCR) after neoadjuvant chemotherapy (NACT) provides an endpoint for treatment evaluation in breast cancer. Multi-sequence breast MRI can support pCR prediction, but routine examinations may lack usable T1-weighted or T2-weighted sequences. Many models merge radiomic and deep features by concatenation, leaving the interaction between handcrafted descriptors and learned representations weakly specified. We developed a radiomics-guided framework for pCR prediction from multi-sequence breast MRI. The model uses a multi-branch 2.5D encoder for sequence-specific features, radiomics-guided channel recalibration, and masked token fusion to aggregate available sequence tokens. We evaluated the framework on 157 patients from the I-SPY1 Trial cohort with patient-level five-fold cross-validation, fixed sequence-combination analysis, and slice-window sensitivity analysis. The full model achieved 78.4% accuracy and 0.809 AUC, compared with 75.8% accuracy and 0.788 AUC for the strongest channel-concatenation baseline. In this cohort, radiomics-guided multi-sequence learning was feasible, with external validation required before clinical interpretation. Full article

Small object detection in remote sensing imagery is a fundamental task for visual information extraction, yet it remains challenging due to extremely small target scales, complex backgrounds, and the loss of discriminative feature information caused by repeated downsampling. To address these issues, this paper proposes a Wavelet-Convolution and Fine-Grained Preservation Network (WCFPNet) based on YOLOv8n. Specifically, a Wavelet-Convolution Module (WCM) is introduced into the backbone to decompose feature maps into low- and high-frequency sub-bands, thereby enhancing structural feature modeling and preserving subtle target details. To compensate for the weakened fine-grained information after repeated downsampling, an Enhanced Spatial Pyramid Pooling-Fast (ESPPF) module is embedded at the end of the backbone to strengthen multi-scale contextual aggregation. In addition, an Enhanced Feature Pyramid Network (EFPN) is designed in the neck to facilitate the propagation of shallow and intermediate fine-grained features to high-level semantic features through cross-level fusion and the Convolutional Block Attention Module (CBAM). Experiments on the NWPU VHR-10 dataset show that WCFPNet achieves 0.879 mAP@0.5 and 0.515 mAP@0.5:0.95, outperforming YOLOv8n by 1.7 and 2.5 percentage points, respectively. Moreover, the proposed WCFPNet achieves a competitive performance compared with several representative detectors while maintaining moderate model complexity. These results demonstrate the effectiveness of WCFPNet in challenging remote sensing scenes characterized by complex backgrounds, dense object distributions, and weak textures. Full article

Target tracking for Unmanned Aerial Vehicles (UAVs) can be significantly impacted by environmental factors such as lighting variations, background clutter, and target occlusion. To address these challenges, we developed a target tracking method that integrates both frequency-domain and spatial perception capabilities in UAV vision (FSTrack). Specifically: (1) we utilized the Swin Transformer as the core network to extract features from both the template and search images; (2) we introduced a Transformer-based module to enhance both frequency and spatial information, improving tracking accuracy under varying illumination conditions; (3) we designed a spatio-temporal feature fusion module with multiple multi-head self-attention mechanisms to precisely model the tracking state, thus increasing reliability in cluttered and occluded environments; and (4) we created a hybrid loss function to boost accuracy in both classification and regression tasks. Our experimental results on the UAV123, DTB70, and UAVDT datasets show that our approach not only surpasses current state-of-the-art methods in success rates and precision but also operates more swiftly. Full article

This paper presents a comparative analysis of three workspace discretization strategies, Cartesian, cylindrical and spherical, integrated into a graph-based path planning application developed in Python and connected to RoboDK. The study starts from the observation that the workspace of an articulated industrial robot is not naturally aligned with a uniform Cartesian partitioning, and this aspect can influence the internal structure of the graph and the planning effort. For the initial analysis, the three discretizations were tested for the same start-goal pair and for resolutions ranging from 1500 mm to 600 mm. All three variants led to the same validated route, with a length of 3292.215 mm, which shows that the main differences did not occur at the level of the final geometric solution, but at the level of the internal structure of the graph. On average, the spherical discretization generated the most compact graph, with 101.7 nodes and 256.4 edges, compared to 277.3 nodes and 724.9 edges for the Cartesian discretization. The average planning time was also shorter for the spherical discretization, 0.0069 s, compared to 0.0150 s for the Cartesian discretization and 0.0127 s for the cylindrical discretization. At the 600 mm resolution, the spherical discretization used approximately 63% fewer nodes and 66% fewer edges than the Cartesian discretization, while retaining a larger number of candidate routes. The evaluation was then extended by 180 additional trials, performed on two scenarios and on several start-goal pairs. Of these, 151 led to valid routes, corresponding to an overall success rate of 83.9%. The results show that the spatial representation influences the graph size, connectivity, planning time and length of validated routes. However, additional tests also show that these effects depend on the scenario and the criterion analyzed. The spherical discretization produced the most compact graphs, but did not lead in all cases to the shortest routes or the highest success rate. Therefore, the contribution of the paper consists in a controlled comparative evaluation of the influence of the spatial representation on a graph-based planning pipeline, not in demonstrating the universal superiority of a single discretization. Full article

The application of functional electrical stimulation (FES) to restore hand motor function remains challenging due to the difficulty of calibrating multi-channel stimulation to produce coordinated finger movements. This study proposes a compositional FES calibration framework to customize the stimulation of isolated finger actions and enable their combination into functional hand gestures. The proposed method was validated through a two-session experimental study involving thirteen participants. In the first session, subject-specific stimulation sites and parameters were identified for eight individual finger movements using a structured spatial grid defined over the forearm. The second session, conducted on a subset of five participants, evaluated the generation of seven hand gestures derived from combinations of the isolated movements. Results showed that ten of the thirteen participants achieved at least six movements, while three participants successfully elicited all targeted motions. Successfully elicited movements were generally well isolated, although thumb and ring/little finger extensions proved more difficult to isolate. The second session demonstrated that individually calibrated finger activations can be combined to produce coordinated multi-finger movement patterns, with average finger excursions matching the expected motions. Overall, these preliminary results support the use of compositional calibration strategies to achieve functional multi-finger control with multi-channel FES. Full article

Reliable temperature monitoring is essential for the thermal management and safe operation of modern telecommunication equipment. However, conventional temperature sensors are often relatively large and rigid, which limits their applicability for localized temperature measurement on compact electronic components. In this study, a flexible thin-film thermocouple based on NiCr–NiSi thermoelectric materials was developed for temperature monitoring of telecommunication equipment. The sensor adopts a multilayer structure consisting of a polyimide (PI) flexible substrate, an Al₂O₃ insulating layer, NiCr and NiSi thermoelectric films, and a SiO protective layer and was fabricated using magnetron sputtering. Static calibration experiments show that the fabricated sensor exhibits a thermoelectric sensitivity of approximately 40.45 µV/°C, which is close to the reference value of conventional K-type thermocouples, with a relative error of about 1.34%. Repeated heating–cooling cycles demonstrate good repeatability and stable thermoelectric characteristics. Dynamic tests under representative transient thermal conditions showed that the sensor could continuously capture temperature variations without signal interruption or abnormal fluctuations. To further quantify its dynamic behavior, a numerical step-response simulation was performed for the PI/Al₂O₃/NiCr–NiSi/SiO multilayer structure. The simulated thermal time constant and curve-extracted 90% response time were 0.0343 s and 0.0803 s, respectively, under the specified boundary conditions. Owing to its small thickness, low thermal mass, and good mechanical flexibility, the proposed thin-film thermocouple can be conformally attached to compact and curved electronic surfaces, indicating promising potential for real-time localized temperature monitoring of telecommunication equipment and other compact electronic systems. Full article

Multi-agent perceptual map construction and long-term maintenance constitute an important paradigm for improving adaptability and real-world applicability. With the outstanding capability of 3D Gaussian Splatting in preserving fine-grained texture details, a number of 3DGS-based real-time mapping approaches have recently emerged. However, these methods often struggle to cope with complex dynamics in real-world environments and lack the generalization needed to scale to multi-agent systems. Existing solutions typically rely on direct parameter concatenation or locally confined optimization, which are unable to explicitly model cross-agent observation reliability under temporal asynchrony and dynamic inconsistency, and therefore tend to amplify conflicting updates rather than resolve them. To address these limitations, we propose DGOMapping, an online system for multi-agent dynamic perceptual mapping. DGOMapping leverages an uncertainty-coupled 4DGS scene representation and a collaborative interaction mechanism via Gaussian perception-score exchange, enabling both real-time 4DGS construction and long-term map memory adjustment. Experiments on multiple real-world datasets demonstrate that DGOMapping effectively suppresses dynamic interference and exploits multi-agent collaboration, achieving state-of-the-art performance in both tracking and reconstruction. The proposed system therefore provides a practical sensing-oriented solution for collaborative perception and real-time dynamic environment mapping. Full article

Ionosphere status plays an important role in satellite communication and navigation systems. In this study, we developed an ANN model to predict the ionosphere status regarding the signal-to-noise ratio at non-line-of-sight, near-vertical incidence (NLOS-NVIS) at frequencies within the HF band. The channel sounding was performed by using two software-defined radios placed at a distance of 29 km apart. The databases regarding signal-to-noise ratio (SNR) data were collected for three ham radio bands: 30 m (10.140203 MHz), 40 m (7.040101 MHz) and 80 m (3.570101 MHz). Subsequently, each database was split into a 70% training set and a 30% testing set. In this configuration, the input vectors were represented by the exact time of day (hour and minute) at which the SNR value was predicted, which functioned as an output variable. Also, three error figures were used as indicators for predicting capability and comparing our ANN with other models. Full article

Electric dipole antennas can be designed in a variety of geometries and applied across a wide range of configurations. Appropriately designed dipole antennas can provide deep tissue penetration and low radiofrequency (RF) power deposition in magnetic resonance imaging (MRI), making them attractive for applications requiring safe and effective RF transmission in deep regions. On clinical 3 T MRI systems, however, conventional dipoles are too large in size for practical imaging of the head. Inspired by telecommunications designs, the present work adapts meandered dipoles (where the conductor is folded to shorten the antenna) with the resonance frequency controlled through trace geometry. Additionally, multi-channel configurations are considered to improve RF power transmission. A straight dipole was progressively transformed into meandered geometries and characterized using benchtop measurements and electromagnetic simulations. Analyses evaluated frequency response, near-field behavior, power-flow directionality, and distributions of local tissue heating and transmitted RF magnetic field in multi-channel arrays. A four-channel parallel-transmit (pTx) prototype was also used to show the feasibility of dipole-based head imaging at 3 T. The present work demonstrates a practical implementation of compact, low-heating dipole arrays for head MRI, with potential for extension to ultra-high-field or multinuclear imaging. Full article

Accurate brain tumor segmentation from magnetic resonance imaging (MRI) is essential for computer-assisted diagnosis, treatment planning, and disease monitoring. However, brain tumors usually exhibit irregular, heterogeneous, and multi-scale spatial patterns with complex and ambiguous boundaries. At the same time, the performance of deep segmentation models is often constrained by the limited availability of voxel-level annotations, which are expensive and time-consuming to obtain. To address these challenges, this paper proposes Semi-SwinUNeTR, a semi-supervised framework for 3D brain tumor segmentation with limited annotated data. The proposed method adopts SwinUNeTR as the segmentation backbone, enabling hierarchical volumetric representation learning through shifted-window self-attention while preserving the encoder–decoder structure required for dense prediction. On top of this backbone, we introduce a dual-consistency semi-supervised learning strategy, consisting of mean teacher-based model consistency and interpolation consistency-based data consistency. In addition, voxel-wise consistency weights are used to redistribute semi-supervised supervision toward structurally complex and boundary-irregular tumor regions without changing the SwinUNeTR backbone. Experiments on the BraTS 2019 benchmark demonstrate that the proposed framework achieves strong performance across different annotation ratios. The original Semi-SwinUNeTR achieves Dice scores of 84.93%, 86.25%, 87.05%, and 87.83% under the 10%, 20%, 40%, and 80% labeled-data settings, respectively. With the weighted consistency extension, the Dice scores are further improved to 85.64%, 87.94%, and 88.59% under the 10%, 20%, and 80% labeled-data settings, respectively, while the corresponding HD₉₅ values are reduced to 8.9826, 8.1854, and 7.4533. These results indicate that combining a SwinUNeTR backbone with complementary model consistency, data consistency, and voxel-wise consistency weighting is an effective strategy for semi-supervised volumetric medical image segmentation under limited annotation. Full article

The rapid progress of generative speech synthesis and voice-cloning technologies has enabled the creation of highly natural synthetic voices that pose a serious threat to telecommunication security. While most prior studies evaluate human ability to detect audio deepfakes using high-quality, studio-grade recordings, little is known about how real-world telecommunication channels affect perceptual detection. This study investigates the influence of three transmission scenarios—GSM (AMR-NB), VoLTE (AMR-WB), and VoIP with packet-loss modeling—on the human ability to distinguish natural speech from AI-generated speech. A custom speech corpus was developed, consisting of natural recordings from nine speakers and corresponding synthetic utterances generated using a state-of-the-art voice cloning system (ElevenLabs). All samples were processed through simulated telecommunication channels using real codec implementations. A listening test with 95 participants was conducted, involving binary classification (human vs. synthetic) and confidence ratings. Results show an overall detection accuracy of 54.8%, confirming that humans are poorly equipped to identify synthetic speech. Surprisingly, the highest accuracy was achieved for the narrowband GSM channel (63.7%), while VoLTE yielded the lowest performance (44.0%). The findings suggest that restricted bandwidth may emphasize prosodic irregularities typical of generative models, whereas high-quality channels mask synthetic artifacts, increasing susceptibility to voice spoofing. The results highlight the necessity of deploying additional security mechanisms in telecommunication systems relying on voice identity verification. Full article

Electromyographic (EMG) signals are increasingly used in wearable cyber–physical systems (CPS), where reliable movement recognition must be achieved under limited computational resources. In this study, we present a compact EMG processing framework that integrates signal acquisition, preprocessing, segmentation, and movement classification within a unified pipeline designed for embedded-oriented applications. The proposed approach combines a multi-channel EMG acquisition system with a lightweight one-dimensional convolutional neural network (1D CNN) developed according to TinyML principles, withprocessing input windows of size 32 × 3 and low computational complexity and memory requirements. Experimental evaluation was conducted on a dataset collected from 15 participants performing squat, walking, and running activities under realistic acquisition conditions. The proposed model achieved an accuracy of 0.9135, an F1-score of 0.9124, and a ROC AUC of approximately 0.96, demonstrating reliable classification performance. Following 8-bit quantization, the model size was reduced to approximately 2 KB, supporting deployment on resource-constrained embedded platforms. The results show that compact CNN architectures can effectively classify EMG-based movement patterns while maintaining a small computational footprint, providing a practical foundation for future wearable CPS and TinyML-enabled applications. Full article