Search Results (8,751)

This paper proposes a new approach to pixel-level fusion using the opposite frequency from the discrete wavelet transform with Gaussian or Difference of Gaussian. The low-frequency from discrete wavelet transform sub-band was fused with the Difference of Gaussian, while the high-frequency sub-bands were fused with Gaussian. The final fusion was reconstructed using an inverse discrete wavelet transform into one enhanced reconstructed image. These enhanced images were utilized to improve recognition performance in the face recognition system. The proposed method was tested against benchmark face datasets such as The Database of Faces (AT&T), the Extended Yale B Face Dataset, the BeautyREC Face Dataset, and the FEI Face Dataset. The results showed that our proposed method was robust and accurate against challenges such as lighting conditions, facial expressions, head pose, 180-degree rotation of the face profile, dark images, acquisition with time gap, and conditions where the person uses attributes such as glasses. The proposed method is comparable to state-of-the-art methods and generates high recognition performance (more than 99% accuracy). Full article

There is a growing recognition that food waste (FW) comprises a significant amount of unused energy. Indeed, FW shows great potential to produce methane (CH₄)-rich biogas via an anaerobic digestion (AD) process. Nevertheless, to ensure high AD process performance, deepening the knowledge of FW characteristics is required. Furthermore, the biogas yield is strongly influenced by several operational parameters. Taking into account the above, in the current study, based on the data in the literature, the physicochemical parameters of FW generated throughout the world are presented and discussed. In addition, the performance profile of the single-stage anaerobic mono-digestion process with the use of FW as a feedstock was investigated. The performed analysis clearly demonstrated that FW is characterized by significant variations in several parameters, such as pH, the total solid (TS) and volatile solid (VS) contents, the volatile solids to total solids ratio (VS/TS), soluble chemical oxygen demand (sCOD), the concentrations of VFAs and ammonium nitrogen (NH₄⁺-N), and the carbon-to-nitrogen ratio (C/N). Moreover, it was shown that the selected operational parameters, such as temperature, pH, the ratio of food waste to inoculum (I) (FW/I), and the organic loading rate (OLR), may have the most significant impact on the performance of the single-stage anaerobic mono-digestion process. In addition, it was found that most of the experimental investigations presented in the literature were conducted on a laboratory scale. Hence, in future research, more effort should be made to determine the biogas yield with the use of full-scale systems. To summarize, it should be clearly highlighted that the analysis presented in this study may have important implications for the management and application of FW as feedstock for an anaerobic mono-digestion process on an industrial scale. Full article

Background: This study aims to verify whether the blood flow velocity and the diameter size, measured through intra-carotid artery Doppler measurements performed on sepsis patients visiting the emergency department, are useful as tools for predicting the risk of early death. Methods: As a prospective study, this research was performed on sepsis patients who visited a local emergency medical center from August 2021 to February 2023. The sepsis patients’ carotid artery was measured using Doppler imaging, and they were divided into patients measured for the size of systolic and diastolic mean blood flow velocity and diameter size: those measured for their qSOFA (quick sequential organ failure assessment) score and those measured using the SIRS (systemic inflammatory response syndrome) criteria. By measuring and comparing their mortality prediction accuracies, this study sought to verify the usefulness of blood flow velocity and the diameter size of the intra-carotid artery as tools to predict early death. Results: This study was conducted on 1026 patients, excluding 45 patients out of the total of 1071 patients. All sepsis patients were measured using systolic and diastolic blood flow velocity and diameter by Doppler imaging of the intra-carotid artery, assessed using qSOFA and evaluated using SIRS criteria. The results of the analysis performed to compare the mortality prediction accuracy were as follows. First, the hazard ratio (95% CI) of the intra-carotid artery was significant (p < 0.05), at 1.020 (1.004–1.036); the hazard ratio (95% CI) of qSOFA was significant (p < 0.05), at 3.871 (2.526–5.931); and the hazard ratio (95% CI) of SIRS showed no significant difference, at 1.002 (0.995–1.009). After 2 h of infusion treatment, the diameter size was 4.72 ± 1.23, showing a significant difference (p < 0.05). After 2 h of fluid treatment, the blood flow velocity was 101 m/s ± 21.12, which showed a significant difference (p < 0.05). Conclusions: Measuring the mean blood flow velocity in the intra-carotid arteries of sepsis patients who visit the emergency department is useful for predicting the risk of death at an early stage. And this study showed that Doppler measurement of the diameter size of the carotid artery significantly increased after performing fluid treatment after early recognition. Full article

Crouch gait, also referred to as flexed knee gait, is an abnormal walking pattern, characterized by an excessive flexion of the knee, and sometimes also with anomalous flexion in the hip and/or the ankle, during the stance phase of gait. Due to the fact that the amount of clinical data related to crouch gait are scarce, it is difficult to find studies addressing this problem from a data-based perspective. Consequently, in this paper we propose a gait recognition strategy using synthetic data that have been obtained using a polynomial based-generator. Furthermore, though this study, we consider datasets that correspond to different levels of crouch gait severity. The classification of the elements of the datasets into the different levels of abnormality is achieved by using different algorithms like k-nearest neighbors (KNN) and Naive Bayes (NB), among others. On the other hand, to evaluate the classification performance we consider different metrics, including accuracy (Acc) and F measure (FM). The obtained results show that the proposed strategy is able to recognize crouch gait with an accuracy of more than 92%. Thus, it is our belief that this recognition strategy may be useful during the diagnosis phase of crouch gait disease. Finally, the crouch gait recognition approach introduced here may be extended to identify other gait abnormalities. Full article

Long-tailed data distribution (i.e., minority classes occupy most of the data, while most classes have very few samples) is a common problem in image classification. In this paper, we propose a novel multimodal framework for long-tailed data recognition. In the first stage, long-tailed data are used for visual-semantic contrastive learning to obtain good features, while in the second stage, class-balanced data are used for classifier training. The proposed framework leverages the advantages of multimodal models and mitigates the problem of class imbalance in long-tailed data recognition. Experimental results demonstrate that the proposed framework achieves competitive performance on the CIFAR-10-LT, CIFAR-100-LT, ImageNet-LT, and iNaturalist2018 datasets for image classification. Full article

Across the globe, landslides cause significant loss of life, injuries, and widespread damage to homes and infrastructure. Therefore, assessing and analyzing landslide hazards is crucial to human, environmental, cultural, economic, and social sustainability. This study utilizes ArcGIS 10.8 and Python 3.9 to create landslide databases for Niigata Prefecture (NIG), Iwate and Miyagi Prefectures (IWT-MYG), and Hokkaido (HKD), drawing on data obtained from the National Research Institute for Earth Science and Disaster Resilience, Japan. A distinguishing feature of this study is the application of a Convolutional Neural Network (CNN), which significantly outperforms traditional machine learning models in image-based pattern recognition by extracting contextual information from surrounding areas, a distinct advantage in image and pattern recognition tasks. Unlike conventional methods that often require manual feature selection and engineering, CNNs automate feature extraction, enabling a more nuanced understanding of complex patterns. By experimenting with CNN input window sizes ranging from 3 × 3 to 27 × 27 pixels and employing diverse sampling techniques, we demonstrate that larger windows enhance the model’s predictive accuracy by capturing a wider range of environmental interactions critical for effective landslide modeling. CNN models with 19 × 19 pixel windows typically yield the best overall performance, with CNN-19 achieving an AUC of 0.950, 0.982 and 0.969 for NIG, HKD, and IWT-MYG, respectively. Furthermore, we improve prediction reliability using oversampling and a random window-moving method. For instance, in the NIG region, the AUC of the oversampling CNN-19 is 0.983, while the downsampling AUC is 0.950). These techniques, less commonly applied in traditional machine learning approaches to landslide detection, help address the issue of data imbalance often seen in landslide datasets, where instances of landslides are far outnumbered by non-landslide occurrences. While challenges remain in enhancing the model’s generalization, this research makes significant progress in developing more robust and adaptable tools for landslide prediction, which are vital for ensuring environmental and societal resilience. Full article

The accuracy of data perception in Internet of Things (IoT) systems is fundamental to achieving scientific decision-making and intelligent control. Given the frequent occurrence of sensor failures in complex environments, a rapid and accurate fault diagnosis and handling mechanism is crucial for ensuring the stable operation of the system. Addressing the challenges of insufficient feature extraction and sparse sample data that lead to low fault diagnosis accuracy, this study explores the construction of a fault diagnosis model tailored for agricultural sensors, with the aim of accurately identifying and analyzing various sensor fault modes, including but not limited to bias, drift, accuracy degradation, and complete failure. This study proposes an improved dung beetle optimization–support vector machine (IDBO-SVM) diagnostic model, leveraging the optimization capabilities of the former to finely tune the parameters of the Support Vector Machine (SVM) to enhance fault recognition under conditions of limited sample data. Case analyses were conducted using temperature and humidity sensors in air and soil, with comprehensive performance comparisons made against mainstream algorithms such as the Backpropagation (BP) neural network, Sparrow Search Algorithm–Support Vector Machine (SSA-SVM), and Elman neural network. The results demonstrate that the proposed model achieved an average diagnostic accuracy of 94.91%, significantly outperforming other comparative models. This finding fully validates the model’s potential in enhancing the stability and reliability of control systems. The research results not only provide new ideas and methods for fault diagnosis in IoT systems but also lay a foundation for achieving more precise, efficient intelligent control and scientific decision-making. Full article

Remote sensing and computer vision technologies are increasingly leveraged for rapid post-disaster building damage assessment, becoming a crucial and practical approach. In this context, the accuracy of employing various AI models in pixel-level change detection methods is significantly dependent on the consistency between pre- and post-disaster building images, particularly regarding variations in resolution, viewing angle, and lighting conditions; in object-level feature recognition methods, the low richness of semantic details of damaged buildings in images leads to a poor detection accuracy. This paper proposes a novel method, OCD-BDA (Object-Level Change Detection for Post-Disaster Building Damage Assessment), as an alternative to pixel-level change detection and object-level feature recognition methods. Inspired by human cognitive processes, this method incorporates three key steps: an efficient sample acquisition for object localization, labeling via HGC (Hierarchical and Gaussian Clustering), and model training and prediction for classification. Furthermore, this study establishes a change detection dataset based on Google Earth imagery of regions in Hatay Province before and after the Turkish earthquake. This dataset is characterized by pixel inconsistency and significant differences in photographic angles and lighting conditions between pre- and post-disaster images, making it a valuable test dataset for other studies. As a result, in the experiments of comparative generalization capabilities, OCD-BDA demonstrated a significant improvement, achieving an accuracy of 71%, which is twice that of the second-ranking method. Moreover, OCD-BDA exhibits superior performance in tasks with small sample amounts and rapid training time. With only 1% of the training samples, it achieves a prediction accuracy exceeding that of traditional transfer learning methods with 60% of samples. Additionally, it completes assessments across a large disaster area (450 km²) with 93% accuracy in under 23 min. Full article

As the demand for high-frequency and high-power electronic devices has increased, gallium nitride (GaN), particularly in the context of high-electron mobility transistors (HEMTs), has attracted considerable attention. However, the ‘self-heating effect’ of GaN HEMTs represents a significant limitation regarding both performance and reliability. Diamond, renowned for its exceptional thermal conductivity, represents an optimal material for thermal management in HEMTs. This paper proposes a novel method for directly depositing diamond films onto N-polar GaN (NP-GaN) epitaxial layers. This eliminates the complexities of the traditional diamond growth process and the need for temporary substrate steps. Given the relative lag in the development of N-polar material growth technologies, which are marked by surface roughness issues, and the recognition that the thermal boundary resistance (TBR_GaN/diamond) represents a critical factor constraining efficient heat transfer, our study has introduced a series of optimizations to enhance the quality of the diamond nucleation layer while ensuring that the integrity of the GaN buffer layer remains intact. Moreover, chemical mechanical polishing (CMP) technology was employed to effectively reduce the surface roughness of the NP-GaN base, thereby providing a more favorable foundation for diamond growth. The optimization trends observed in the thermal performance test results are encouraging. Integrating diamond films onto highly smooth NP-GaN epitaxial layers demonstrates a reduction in TBR_GaN/diamond compared to that of diamond layers deposited onto NP-GaN with higher surface roughness that had undergone no prior process treatment. Full article

The presence of gray mold can seriously affect the yield and quality of strawberries. Due to their susceptibility and the rapid spread of this disease, it is important to develop early, accurate, rapid, and non-destructive disease identification strategies. In this study, the early detection of strawberry leaf diseases was performed using hyperspectral imaging combining multi-dimensional features like spectral fingerprints and vegetation indices. Firstly, hyperspectral images of healthy and early affected leaves (24 h) were acquired using a hyperspectral imaging system. Then, spectral reflectance (616) and vegetation index (40) were extracted. Next, the CARS algorithm was used to extract spectral fingerprint features (17). Pearson correlation analysis combined with the SPA method was used to select five significant vegetation indices. Finally, we used five deep learning methods (LSTMs, CNNs, BPFs, and KNNs) to build disease detection models for strawberries based on individual and fusion characteristics. The results showed that the accuracy of the recognition model based on fused features ranged from 88.9% to 96.6%. The CNN recognition model based on fused features performed best, with a recognition accuracy of 96.6%. Overall, the fused feature-based model can reduce the dimensionality of the classification data and effectively improve the predicting accuracy and precision of the classification algorithm. Full article

With the deep integration of psychology and artificial intelligence technology and other related technologies, eye control technology has achieved certain results at the practical application level. However, it is found that the accuracy of the current single-modal eye control technology is still not high, which is mainly caused by the inaccurate eye movement detection caused by the high randomness of eye movements in the process of human–computer interaction. Therefore, this study will propose an intent recognition method that fuses facial expressions and eye movement information and expects to complete an eye control method based on the fusion of facial expression and eye movement information based on the multimodal intent recognition dataset, including facial expressions and eye movement information constructed in this study. Based on the self-attention fusion strategy, the fused features are calculated, and the multi-layer perceptron is used to classify the fused features, so as to realize the mutual attention between different features, and improve the accuracy of intention recognition by enhancing the weight of effective features in a targeted manner. In order to solve the problem of inaccurate eye movement detection, an improved YOLOv5 model was proposed, and the accuracy of the model detection was improved by adding two strategies: a small target layer and a CA attention mechanism. At the same time, the corresponding eye movement behavior discrimination algorithm was combined for each eye movement action to realize the output of eye behavior instructions. Finally, the experimental verification of the eye–computer interaction scheme combining the intention recognition model and the eye movement detection model showed that the accuracy of the eye-controlled manipulator to perform various tasks could reach more than 95 percent based on this scheme. Full article

The rise of mobile communication, low-power chips, and the Internet of Things has made smartwatches increasingly popular. Equipped with inertial measurement units (IMUs), these devices can recognize user activities through artificial intelligence (AI) analysis of sensor data. However, most existing AI-based activity recognition algorithms require significant computational power and storage, making them unsuitable for low-power devices like smartwatches. Additionally, discrepancies between training data and real-world data often hinder model generalization and performance. To address these challenges, we propose LIMUNet and its smaller variant LIMUNet-Tiny—lightweight neural networks designed for human activity recognition on smartwatches. LIMUNet utilizes depthwise separable convolutions and residual blocks to reduce computational complexity and parameter count. It also incorporates a dual attention mechanism specifically tailored to smartwatch sensor data, improving feature extraction without sacrificing efficiency. Experiments on the PAMAP2 and LIMU datasets show that the LIMUNet improves recognition accuracy by 2.9% over leading lightweight models while reducing parameters by 88.3% and computational load by 58.4%. Compared to other state-of-the-art models, LIMUNet achieves a 9.6% increase in accuracy, with a 60% reduction in parameters and a 57.8% reduction in computational cost. LIMUNet-Tiny further reduces parameters by 75% and computational load by 80%, making it even more suitable for resource-constrained devices. Full article

Ferroelectret nanogenerators (FENGs) have garnered attention due to their unique porous structure and excellent piezoelectric performance. However, most existing FENGs lack sufficient stretchability and flexibility, limiting their application in the field of wearable electronics. In this regard, we have focused on the development of an ultrathin, stretchable, and twistable ferroelectret nanogenerator (UST-FENG) based on Ecoflex, which is made up of graphene, Ecoflex, and anhydrous ethanol, with controllable pore shape and density. The UST-FENG has a thickness of only 860 µm, a fracture elongation rate of up to 574%, and a Young’s modulus of only 0.2 MPa, exhibiting outstanding thinness and excellent stretchability. Its quasi-static piezoelectric coefficient is approximately 38 pC/N. Utilizing this UST-FENG device can enable the recognition of facial muscle movements such as blinking and speaking, thereby helping to monitor people’s facial conditions and improve their quality of life. The successful application of the UST-FENG in facial muscle recognition represents an important step forward in the field of wearable systems for the human face. Full article

Emotion classification is a challenge in affective computing, with applications ranging from human–computer interaction to mental health monitoring. In this study, the classification of emotional states using electroencephalography (EEG) data were investigated. Specifically, the efficacy of the combination of various feature selection methods and hyperparameter tuning of machine learning algorithms for accurate and robust emotion recognition was studied. The following feature selection methods were explored: filter (SelectKBest with analysis of variance (ANOVA) F-test), embedded (least absolute shrinkage and selection operator (LASSO) tuned using Bayesian optimization (BO)), and wrapper (genetic algorithm (GA)) methods. We also executed hyperparameter tuning of machine learning algorithms using BO. The performance of each method was assessed. Two different EEG datasets, EEG Emotion and DEAP Dataset, containing 2548 and 160 features, respectively, were evaluated using random forest (RF), logistic regression, XGBoost, and support vector machine (SVM). For both datasets, the experimented three feature selection methods consistently improved the accuracy of the models. For EEG Emotion dataset, RF with LASSO achieved the best result among all the experimented methods increasing the accuracy from 98.78% to 99.39%. In the DEAP dataset experiment, XGBoost with GA showed the best result, increasing the accuracy by 1.59% and 2.84% for valence and arousal. We also show that these results are superior to those by the previous other methods in the literature. Full article

The integration of communication and sensing (ICAS) in optical networks is an inevitable trend in building intelligent, multi-scenario, application-converged communication systems. However, due to the impact of nonlinear effects, co-fiber transmission of sensing signals and communication signals can cause interference to the communication signals, leading to an increased bit error rate (BER). This paper proposes a noncoherent solution based on the alternate polarization chirped return-to-zero frequency shift keying (Apol-CRZ-FSK) modulation format to realize a 4 × 100 Gbps dense wavelength division multiplexing (DWDM) optical network. Simulation results show that compared to traditional modulation formats, such as chirped return-to-zero frequency shift keying (CRZ-FSK) and differential quadrature phase shift keying (DQPSK), this solution demonstrates superior resistance to nonlinear effects, enabling longer transmission distances and better transmission performance. Moreover, to meet the transmission requirements and signal sensing and recognition needs in future optical networks, this study employs the Inception-ResNet-v2 convolutional neural network model to identify three modulation formats. Compared with six deep learning methods including AlexNet, ResNet50, GoogleNet, SqueezeNet, Inception-v4, and Xception, it achieves the highest performance. This research provides a low-cost, low-complexity, and high-performance solution for signal transmission and signal recognition in high-speed optical networks designed for integrated communication and sensing. Full article