Search Results (252)

Accurate teeth segmentation and orientation are fundamental in modern oral healthcare, enabling precise diagnosis, treatment planning, and dental implant design. In this study, we present a comprehensive approach to teeth segmentation and orientation from panoramic X-ray images, leveraging deep-learning techniques. We built an end-to-end instance segmentation network that uses an encoder–decoder architecture reinforced with grid-aware attention gates along the skip connections. We introduce oriented bounding box (OBB) generation through principal component analysis (PCA) for precise tooth orientation estimation. Evaluating our approach on the publicly available DNS dataset, comprising 543 panoramic X-ray images, we achieve the highest Intersection-over-Union (IoU) score of 82.43% and a Dice Similarity Coefficient (DSC) score of 90.37% among compared models in teeth instance segmentation. In OBB analysis, we obtain the Rotated IoU (RIoU) score of 82.82%. We also conduct detailed analyses of individual tooth labels and categorical performance, shedding light on strengths and weaknesses. The proposed model’s accuracy and versatility offer promising prospects for improving dental diagnoses, treatment planning, and personalized healthcare in the oral domain. Full article

Event-based vision sensors (EVSs), often referred to as neuromorphic cameras, operate by responding to changes in brightness on a pixel-by-pixel basis. In contrast, traditional framing cameras employ some fixed sampling interval where integrated intensity is read off the entire focal plane at once. Similar to traditional cameras, EVSs can suffer loss of sensitivity through scenes with high intensity and dynamic clutter, reducing the ability to see points of interest through traditional event processing means. This paper describes a method to reduce the negative impacts of these types of EVS clutter and enable more robust target detection through the use of individual pixel frequency analysis, background suppression, and statistical filtering. Additionally, issues found in normal frequency analysis such as phase differences between sources, aliasing, and spectral leakage are less relevant in this method. The statistical filtering simply determines what pixels have significant frequency content after the background suppression instead of focusing on the actual frequencies in the scene. Initial testing on simulated data demonstrates a proof of concept for this method, which reduces artificial scene noise and enables improved target detection. Full article

Nutrition plays a fundamental role in promoting health and preventing chronic diseases, with bioactive food components offering a therapeutic potential in biomedical applications. Among these, edible oils are recognised for their functional properties, which contribute to disease prevention and metabolic regulation. The proposed study aims to evaluate the quality of four bioactive oils (olive oil, sunflower oil, tomato seed oil, and pumpkin seed oil) by analysing their thermal behaviour through infrared (IR) imaging. The study designed a customised electronic system to acquire thermographic signals under controlled temperature and humidity conditions. The acquisition system was used to extract thermal data. Analysis of the acquired thermal signals revealed characteristic heat absorption profiles used to infer differences in oil properties related to stability and degradation potential. A hybrid deep learning model that integrates Convolutional Neural Networks (CNNs) with Long Short-Term Memory (LSTM) units was used to classify and differentiate the oils based on stability, thermal reactivity, and potential health benefits. A signal analysis showed that the AI-based method improves both the accuracy (achieving an F1-score of 93.66%) and the repeatability of quality assessments, providing a non-invasive and intelligent framework for the validation and traceability of nutritional compounds. Full article

With the diversification of space applications, the tracking of maneuvering targets has gradually gained attention. Issues such as their wide range of movement and observation outliers caused by human operation are worthy of in-depth discussion. This paper presents a novel distributed diffusion multi-noise Interacting Multiple Model (IMM) filter for maneuvering target tracking in heavy-tailed noise. The proposed approach leverages parallel Gaussian and Student-t filters to enhance robustness against non-Gaussian process and measurement noise. This hybrid filter is implemented as a node within a distributed network, where the diffusion algorithm leads to the global state asymptotically reaching consensus as the filtering time progresses. Furthermore, a fusion of multiple motion models within the IMM algorithm enables robust tracking of maneuvering targets across the distributed network and process outlier caused by maneuver compared to previous studies. Simulation results demonstrate the effectiveness of the proposed filter in tracking maneuvering targets. Full article

Accurate peak detection in the frequency domain is fundamental to reliable range estimation in Frequency-Modulated Continuous-Wave (FMCW) radar systems, particularly in challenging conditions characterized by a low signal-to-noise ratio (SNR) and phase noise impairments. This paper presents a comprehensive comparative analysis of five peak detection algorithms: FFT thresholding, Cell-Averaging Constant False Alarm Rate (CA-CFAR), a simplified Matrix Pencil Method (MPM), SVD-based detection, and a novel Learned Thresholded Subspace Projection (LTSP) approach. The proposed LTSP method leverages singular value decomposition (SVD) to extract the dominant signal subspace, followed by signal reconstruction and spectral peak analysis, enabling robust detection in noisy and spectrally distorted environments. Each technique was analytically modeled and extensively evaluated through Monte Carlo simulations across a wide range of SNRs and oscillator phase noise levels, from $-100$ dBc/Hz to $-70$ dBc/Hz. Additionally, real-world validation was performed using a custom-built harmonic FMCW radar prototype operating in the 2.4–2.5 GHz transmission band and 4.8–5.0 GHz harmonic reception band. Results show that CA-CFAR offers the highest resilience to phase noise, while the proposed LTSP method delivers competitive detection performance with improved robustness over conventional FFT and MPM techniques. Furthermore, the hardware feasibility of each algorithm is assessed for implementation on a Xilinx FPGA platform, highlighting practical trade-offs between detection performance, computational complexity, and resource utilization. These findings provide valuable guidance for the design of real-time, embedded FMCW radar systems operating under adverse conditions. Full article

This study investigates the use of a custom-built 10 GHz continuous wave micro-Doppler radar system to analyze external vibrations of idling vehicles under various conditions. Scenarios included different gear engagements with one occupant and parked gear with up to four occupants. Motivated by security concerns, such as the threat posed by idling vehicles with multiple occupants, the research explores how micro-Doppler signatures can indicate vehicle readiness to move. Experiments focused on a mid-size SUV, with similar trends seen in other vehicles. Radar data were compared to in situ accelerometer measurements, confirming that the radar system can detect subtle frequency changes, especially during gear shifts. The system’s sensitivity enables it to distinguish variations tied to gear state and passenger load. Extracted features like frequency and magnitude show strong potential for use in machine learning models, offering a non-invasive, remote sensing method for reliably identifying vehicle operational states and occupancy levels in security or monitoring contexts. Spectrogram and PSD analyses reveal consistent tonal vibrations around 30 Hz, tied to engine activity, with harmonics at 60 Hz and 90 Hz. Gear shifts produce impulse signatures primarily below 20 Hz, and transient data show distinct peaks at 50, 80, and 100 Hz. Key features at 23 Hz and 45 Hz effectively indicate engine and gear states. Radar and accelerometer data align well, supporting the potential for remote sensing and machine learning-based classification. Full article

Analyzing and measuring the similarity between two signals is a common task in many vibration-based structural health monitoring applications. Coherence between input and response signals serves as a convenient indicator of damage, based on the premise that nonlinearity due to damage in a linear system manifests as a loss of coherence in specific frequency bands. Because input excitations in civil structures are difficult to measure, damage indicators based on the coherence between two response signals have been developed. These indicators have shown promise in detecting nonlinear behavior in structures that were initially linear. This paper proposes a new damage indicator based on Mutual Information, a nonlinear extension of the squared correlation coefficient, to quantify the similarity between two signals without making assumptions about the nature of their interactions or the underlying dynamics of the system. Mutual Information is distinguished from other nonlinear similarity metrics due to its ability to capture all types of nonlinear dependencies, its high computational efficiency, and its invariance to invertible transformations, such as scaling. The proposed approach is demonstrated using a standard dataset containing experimental data from a three-story aluminum frame structure under 17 different damage states. The results show that the proposed metric can detect deviations from the baseline state due to changes in mass, stiffness, or newly induced nonlinear behavior, suggesting its potential for monitoring changes in the structural system. Full article

Power converters in the smart grid systems are essential to link renewable energy sources with all grid appliances and equipment. However, this raises the possibility of electromagnetic interference (EMI) between the smart grid elements. Hence, spread spectrum (SS) modulation techniques have been used to mitigate the EMI peaks generated from the power converters. Consequently, the performance of the nearby communication systems is affected under the presence of EMI, which is not covered in many situations. In this paper, the behavior of the G3 Power Line Communication (PLC) channel is evaluated in terms of the Shannon–Hartley equation in the presence of SS-modulated EMI from a buck converter. The SS-modulation technique used is the Random Carrier Frequency Modulation with Constant Duty cycle (RCFMFD). Moreover, The analysis is validated by experimental results obtained with a test setup reproducing the parasitic coupling between the PLC system and the power converter. Full article

Accurate modeling of the power–cadence relationship is essential for assessing maximal anaerobic power (Pmax) of the lower limbs. Experimental data points from Force–Velocity tests during cycling do not always reflect the maximal and cadence-specific power individuals can produce. The quality of the models and the accuracy of Pmax estimation is potentially compromised by the inclusion of non-maximal data points. This study evaluated a novel residual-based filtering method that selects five strategically located, maximal data points to improve model fit and Pmax prediction. Twenty-three recreationally active male participants (age: 26 ± 5 years; height: 178 ± 5 cm; body mass: 73 ± 11 kg) completed a Force–Velocity test consisting of multiple maximal cycling efforts on a stationary ergometer. Power and cadence data were used to generate third-order polynomial models: from all data points (High Number, HN), from the highest power value in each 5-RPM interval (Moderate Number, MN), and from five selected data points (Low Number, LN). The LN model yielded the best goodness of fit (R² = 0.995 ± 0.008; SEE = 29 ± 15 W), the most accurate estimates of experimentally measured peak power (mean absolute percentage error = 1.45%), and the highest Pmax values (1220 ± 168 W). Selecting a limited number of maximal data points improves the modeling of individual power–cadence relationships and Pmax assessment. Full article

This paper presents a novel framework addressing the fundamental challenge of concurrent real-time audio acquisition and motor control in resource-constrained mobile robotics. The ESP32-based system integrates a digital MEMS microphone with rover mobility through a unified Bluetooth protocol. Key innovations include (1) a dual-thread architecture enabling non-blocking concurrent operation, (2) an adaptive eight-bit compression algorithm optimizing bandwidth while preserving audio quality, and (3) a mathematical model for real-time resource allocation. A comprehensive empirical evaluation demonstrates consistent control latency below 150 ms with 90–95% audio packet delivery rates across varied environments. The framework enables mobile acoustic sensing applications while maintaining responsive motor control, validated through comprehensive testing in 40–85 dB acoustic environments at distances up to 10 m. A performance analysis demonstrates the feasibility of high-fidelity mobile acoustic sensing on embedded platforms, opening new possibilities for environmental monitoring, surveillance, and autonomous acoustic exploration systems. Full article

Instrument recognition is a crucial aspect of music information retrieval, and in recent years, machine learning-based methods have become the primary approach to addressing this challenge. However, existing models often struggle to accurately identify multiple instruments within music tracks that vary in length and quality. One key issue is that the instruments of interest may not appear in every clip of the audio sample, and when they do, they are often unevenly distributed across different sections of the track. Additionally, in polyphonic music, multiple instruments are often played simultaneously, leading to signal overlap. Using the same overlapping audio signals as partial classification features for different instruments will reduce the distinguishability of features between instruments, thereby affecting the performance of instrument recognition. These complexities present significant challenges for current instrument recognition models. Therefore, this paper proposes a multi-instance multi-scale graph attention neural network (MMGAT) with label semantic embeddings for instrument recognition. MMGAT designs an instance correlation graph to model the presence and quantitative timbre similarity of instruments at different positions from the perspective of multi-instance learning. Then, to enhance the distinguishability of signals after the overlap of different instruments and improve classification accuracy, MMGAT learns semantic information from the labels of different instruments as embeddings and incorporates them into the overlapping audio signal features, thereby enhancing the differentiability of audio features for various instruments. MMGAT then designs an instance-based multi-instance multi-scale graph attention neural network to recognize different instruments based on the instance correlation graphs and label semantic embeddings. The effectiveness of MMGAT is validated through experiments and compared to commonly used instrument recognition models. The experimental results demonstrate that MMGAT outperforms existing approaches in instrument recognition tasks. Full article

Recently, STDenseNet (SpatioTemporal Densely connected convolutional Network) showed remarkable performance in predicting network traffic by leveraging the inductive bias of convolution layers. However, it is known that such convolution layers can only barely capture long-term spatial and temporal dependencies. To solve this problem, we propose Attention-DenseNet (ADNet), which effectively incorporates an attention module into STDenseNet to learn representations for long-term spatio-temporal patterns. Specifically, we explored the optimal positions and the types of attention modules in combination with STDenseNet. Our key findings are as follows: i) attention modules are very effective when positioned between the last dense module and the final feature fusion module, meaning that the attention module plays a key role in aggregating low-level local features with long-term dependency. Hence, the final feature fusion module can easily exploit both global and local information; ii) the best attention module is different depending on the spatio-temporal characteristics of the dataset. To verify the effectiveness of the proposed ADNet, we performed experiments on the Telecom Italia dataset, a well-known benchmark dataset for network traffic prediction. The experimental results show that, compared to STDenseNet, our ADNet improved RMSE performance by 3.72%, 2.84%, and 5.87% in call service (Call), short message service (SMS), and Internet access (Internet) sub-datasets, respectively. Full article

In a previous work, we identified the importance of rotation invariance in the standard complex-valued theory of linear time-invariant (LTI) systems and proposed a generalized vector-valued (VV) definition of convolution that reinterprets the complex-valued product of the traditional formalism as a scale rotation within the framework of geometric algebra. Based on this convolution definition, we characterized linear rotation-invariant time-invariant (LRITI) systems by defining and using a VV impulse response—effectively generalizing time-domain analysis for VV signals and LRITI systems. In this work, we provide a compatible frequency-domain analysis for VV signals and LRITI systems. First, VV bivector exponential signals are shown to be eigenfunctions of LRITI systems. A Fourier transform is defined, and we propose two generalized definitions of frequency response: the first valid for bivector exponentials in an arbitrary plane and the second valid for a general signal decomposed into a set of totally orthogonal planes (TOPs). Finally, we establish a convolution property for the Fourier transform with respect to TOPs. Together, these results provide compatible time-domain and frequency-domain analyses, thereby enabling a more comprehensive analysis of VV signals and LRITI systems. Full article

This work presents an on-field noise analysis during the class breaks in Greek school units (a high school and a senior high school) based on the design and deployment of low-cost IoT sensor nodes and IoT platforms. The course breaks form 20% of a regular school day, during which intense mobility and high noise levels usually evolve. Indoor noise levels, along with environmental conditions, have been measured through a wireless network that comprises IoT nodes that integrate humidity, temperature, and acoustic level sensors. PM₁₀ and PM_2.5 values have also been acquired through data sensors located nearby the school complex. School buildings that have been recently renovated for minimizing their energy footprint and CO₂ emissions have been selected in comparison with similar works in academia. The data are collected, shipped, and stored into a time-series database in cloud facilities where an IoT platform has been developed for processing and analysis purposes. The findings show that low-cost sensors can efficiently monitor noise levels after proper adjustments. Additionally, the statistical evaluation of the received sensor measurements has indicated that ubiquitous high noise levels during the course breaks potentially affect teachers’ leisure time, despite the thermal isolation of the facilities. Within this context, we prove that the proposed IoT Sensor Network could form a tool to essentially monitor school infrastructures and thus to prompt for improvements regarding the building facilities. Several guides to further mitigate noise and achieve high-quality levels in learning institutes are also described. Full article

The analysis of electrocardiogram (ECG) signals is profoundly affected by the presence of electromyographic (EMG) noise, which can lead to substantial misinterpretations in healthcare applications. To address this challenge, we present ECGDnet, an innovative architecture based on Transformer technology, specifically engineered to denoise multi-channel ECG signals. By leveraging multi-head self-attention mechanisms, positional embeddings, and an advanced sequence-to-sequence processing architecture, ECGDnet effectively captures both local and global temporal dependencies inherent in cardiac signals. Experimental validation on real-world datasets demonstrates ECGDnet’s remarkable efficacy in noise suppression, achieving a Signal-to-Noise Ratio (SNR) of 19.83, a Normalized Mean Squared Error (NMSE) of 0.9842, a Reconstruction Error (RE) of 0.0158, and a Pearson Correlation Coefficient (PCC) of 0.9924. These results represent significant improvements from traditional deep learning approaches while maintaining complex signal morphology and effectively mitigating noise interference. Full article