Search Results (1,149)

Event cameras, as bio-inspired visual sensors, offer significant advantages in their high dynamic range and high temporal resolution for visual tasks. These capabilities enable efficient and reliable motion estimation even in the most complex scenes. However, these advantages come with certain trade-offs. For instance, current event-based vision sensors have low spatial resolution, and the process of event representation can result in varying degrees of data redundancy and incompleteness. Additionally, due to the inherent characteristics of event stream data, they cannot be utilized directly; pre-processing steps such as slicing and frame compression are required. Currently, various pre-processing algorithms exist for slicing and compressing event streams. However, these methods fall short when dealing with multiple subjects moving at different and varying speeds within the event stream, potentially exacerbating the inherent deficiencies of the event information flow. To address this longstanding issue, we propose a novel and efficient Asynchronous Spike Dynamic Metric and Slicing algorithm (ASDMS). ASDMS adaptively segments the event stream into fragments of varying lengths based on the spatiotemporal structure and polarity attributes of the events. Moreover, we introduce a new Adaptive Spatiotemporal Subject Surface Compensation algorithm (ASSSC). ASSSC compensates for missing motion information in the event stream and removes redundant information, thereby achieving better performance and effectiveness in event stream segmentation compared to existing event representation algorithms. Additionally, after compressing the processed results into frame images, the imaging quality is significantly improved. Finally, we propose a new evaluation metric, the Actual Performance Efficiency Discrepancy (APED), which combines actual distortion rate and event information entropy to quantify and compare the effectiveness of our method against other existing event representation methods. The final experimental results demonstrate that our event representation method outperforms existing approaches and addresses the shortcomings of current methods in handling event streams with multiple entities moving at varying speeds simultaneously. Full article

Due to the challenges posed by limited size and features, positional and noise issues, and dataset imbalance and simplicity, small object detection is one of the most challenging tasks in the field of object detection. Consequently, an increasing number of researchers are focusing on this area. In this paper, we propose a Directional Enhanced Adaptive (DEA) detection framework for small targets. This framework effectively combines the detection accuracy advantages of two-stage methods with the detection speed advantages of one-stage methods. Additionally, we introduce a Multi-Scale Object Adaptive Slicing (MASA) module and an improved IoU-based aggregation module that integrate with this framework to enhance detection performance. For better comparison, we use the F1 score as one of the evaluation metrics. The experimental results demonstrate that our DEA framework improves the performance of various backbone detection networks and achieves better comprehensive detection performance than other proposed methods, even though our network has not been trained on the test dataset while others have. Full article

Background: Alzheimer’s disease (AD) is a progressive and irreversible neurodegenerative condition that increasingly impairs cognitive functions and daily activities. Given the incurable nature of AD and its profound impact on the elderly, early diagnosis (at the mild cognitive impairment (MCI) stage) and intervention are crucial, focusing on delaying disease progression and improving patients’ quality of life. Methods: This work aimed to develop an automatic sMRI-based method to detect AD in three different stages, namely healthy controls (CN), mild cognitive impairment (MCI), and AD itself. For such a purpose, brain sMRI images from the ADNI database were pre-processed, and a set of 22 texture statistical features from the sMRI gray-level co-occurrence matrix (GLCM) were extracted from various slices within different anatomical planes. Different combinations of features and planes were used to feed classical machine learning (cML) algorithms to analyze their discrimination power between the groups. Results: The cML algorithms achieved the following classification accuracy: 85.2% for AD vs. CN, 98.5% for AD vs. MCI, 95.1% for CN vs. MCI, and 87.1% for all vs. all. Conclusions: For the pair AD vs. MCI, the proposed model outperformed state-of-the-art imaging source studies by 0.1% and non-imaging source studies by 4.6%. These results are particularly significant in the field of AD classification, opening the door to more efficient early diagnosis in real-world settings since MCI is considered a precursor to AD. Full article

Background/Objectives: Computer-aided detection (CAD) systems for lung nodule detection often face challenges with 5 mm computed tomography (CT) scans, leading to missed nodules. This study assessed the efficacy of a deep learning-based slice thickness reduction technique from 5 mm to 1 mm to enhance CAD performance. Methods: In this retrospective study, 687 chest CT scans were analyzed, including 355 with nodules and 332 without nodules. CAD performance was evaluated on nodules, to which all three radiologists agreed. Results: The slice thickness reduction technique significantly improved the area under the receiver operating characteristic curve (AUC) for scan-level analysis from 0.867 to 0.902, with a p-value < 0.001, and nodule-level sensitivity from 0.826 to 0.916 at two false positives per scan. Notably, the performance showed greater improvements on smaller nodules than larger nodules. Qualitative analysis confirmed that nodules mistaken for ground glass on 5 mm scans could be correctly identified as part-solid on the refined 1 mm CT, thereby improving the diagnostic capability. Conclusions: Applying a deep learning-based slice thickness reduction technique significantly enhances CAD performance in lung nodule detection on chest CT scans, supporting the clinical adoption of refined 1 mm CT scans for more accurate diagnoses. Full article

To aid the diagnosis of chronic obstructive pulmonary disease (COPD), a local-to-global deep framework with group attentions and slice-aware loss is designed in this paper, which utilizes the chest CT sequences of the patients as the network input. To fully mine the medical hints submerged in the CT slices, two types of group attentions are designed to extract local–global features of the grouped slices. Specifically, in each group, a group local attention block (GLAB) and a group global attention block (GGAB) are designed to extract local features in the CT slices and long-range dependencies among the grouped slices. To alleviate the influence of different numbers of CT slices in the chest CT sequences for different patients, a slice-aware loss is proposed by incorporating a normalized coefficient into the cross-entropy loss. Experimental results indicate that the designed deep model performs a good COPD identification on a real COPD dataset with 96.08% accuracy, 94.12% sensitivity, 97.06% specificity, and 95.32% AUC, which is superior to some existing deep learning methods. Full article

This study presents an integrated approach that combines the Levenberg–Marquardt (LM) and Luus–Jaakola (LJ) algorithms to enhance parameter estimation for various applications. The LM algorithm, known for its precision in solving non-linear least squares problems, is effectively paired with the LJ algorithm, a robust stochastic optimization method, to improve accuracy and computational efficiency. This hybrid LM-LJ methodology is demonstrated through several case studies, including the optimization of MESH equations in distillation processes, modeling controlled diffusion in biopolymer films, and analyzing heat and mass transfer during the drying of cylindrical quince slices. By overcoming the convergence issues typical of gradient-based methods and performing global searches without initial parameter bounds, this approach effectively handles complex models and closely aligns simulation results with experimental data. These capabilities highlight the versatility of this approach in engineering and environmental modeling, significantly enhancing parameter estimation in systems governed by differential equations. Full article

Lung cancer, the leading cause of cancer-related deaths globally, presents significant challenges in early detection and diagnosis. The effective analysis of pulmonary medical imaging, particularly computed tomography (CT) scans, is critical in this endeavor. Traditional diagnostic methods, which are manual and time-intensive, underscore the need for innovative, efficient, and accurate detection approaches. To address this need, we introduce the Adaptive Range Slice Grouping Network (ARSGNet), a novel deep learning framework that enhances early lung cancer diagnosis through advanced segmentation and classification techniques in CT imaging. ARSGNet synergistically integrates the strengths of EfficientNet and Transformer architectures, leveraging their superior feature extraction and contextual processing capabilities. This hybrid model proficiently handles the complexities of 3D CT images, ensuring precise and reliable lung nodule detection. The algorithm processes CT scans using short slice grouping (SSG) and long slice grouping (LSG) techniques to extract critical features from each slice, culminating in the generation of nodule probabilities and the identification of potential nodular regions. Incorporating shapley additive explanations (SHAP) analysis further enhances model interpretability by highlighting the contributory features. Our extensive experimentation demonstrated a significant improvement in diagnostic accuracy, with training accuracy increasing from 0.9126 to 0.9817. This advancement not only reflects the model’s efficient learning curve but also its high proficiency in accurately classifying a majority of training samples. Given its high accuracy, interpretability, and consistent reduction in training loss, ARSGNet holds substantial potential as a groundbreaking tool for early lung cancer detection and diagnosis. Full article

Background/Objectives: Glioblastomas (GBMs) are dreadful brain tumors with abysmal survival outcomes. GBM extracellular vesicles (EVs) dramatically affect normal brain cells (largely astrocytes) constituting the tumor microenvironment (TME). We asked if EVs from different GBM patient-derived spheroid lines would differentially alter recipient brain cell phenotypes. This turned out to be the case, with the net outcome of treatment with GBM EVs nonetheless converging on increased tumorigenicity. Methods: GBM spheroids and brain slices were derived from neurosurgical patient tissues following informed consent. Astrocytes were commercially obtained. EVs were isolated from conditioned culture media by ultrafiltration, concentration, and ultracentrifugation. EVs were characterized by nanoparticle tracking analysis, electron microscopy, biochemical markers, and proteomics. Astrocytes/brain tissues were treated with GBM EVs before downstream analyses. Results: EVs from different GBMs induced brain cells to alter secretomes with pro-inflammatory or TME-modifying (proteolytic) effects. Astrocyte responses ranged from anti-viral gene/protein expression and cytokine release to altered extracellular signal-regulated protein kinase (ERK1/2) signaling pathways, and conditioned media from EV-treated cells increased GBM cell proliferation. Conclusions: Astrocytes/brain slices treated with different GBM EVs underwent non-identical changes in various omics readouts and other assays, indicating “personalized” tumor-specific GBM EV effects on the TME. This raises concern regarding reliance on “model” systems as a sole basis for translational direction. Nonetheless, net downstream impacts from differential cellular and TME effects still led to increased tumorigenic capacities for the different GBMs. Full article

The extraction of thin bedrock coal seams with thick alluvium poses a challenging issue in the realm of coal safety production in China. Especially for mining under aquifers, knowing the development height of water-conducting fracture zones above the goaf is crucial for coal mine safety and production. Taking the 11092 working face of lower slice mining in Zhaogu No. 1 Mine as an example, the failure transfer process of the overlying strata is analyzed first. On this basis, the development height of the water-conducting fracture zone is predicted using empirical formulas and the BP neural network. According to the empirical formula, the height of the roof caving zone ranges from 6.93 m to 27.72 m, while the height of the water-conducting fracture zone ranges from 22.17 m to 71.73 m. The BP neural network predicts that the development height of the water-conducting fracture zone in the working face after mining is 56.83 m. CDEM numerical simulation is employed to analyze the development height of two zones of overburden rock. The findings indicate that with a mining height of 2.5 m and a cumulative mining height of 6 m, the maximum caving ratio is 2.61. It is observed that for a cumulative mining thickness of less than 6 m, a bedrock thickness of not less than 30 m, and a clay layer thickness exceeding 5 m, the clay layer effectively obstructs the upward development of the water-conducting fracture zone. Finally, the prediction results of the development height of the two zones of overlying strata in the working face are verified by using the height observation method on the underground water-conducting fracture zone and the borehole peeping method. In conclusion, the height of the overlying strata after mining the lower slice working face in the first panel of the east can be used as a basis for determining the thickness of coal (rock) pillars for waterproofing and sand control safety during the mining of lower slice working faces in mines. Full article

Background/Objectives: The aim of this study was the investigation of any correlation between medial meniscal extrusion (MME) and T2 relaxation times. Furthermore, the impact of different meniscal morphologies on the femoral cartilage was assessed. Methods: Fifty-nine knees of fifty-five patients (twenty-four female, thirty-one male) with a mean age of 33.7 ± 9.2 years and without risk factors for MME or osteoarthritis were examined in a 3.0T MRI. MME was assessed quantitatively in accordance with BLOKS score. T2 maps were calculated from sagittal 2D MESE sequences. The region of interest was defined as the load-bearing cartilage at the medial femoral condyle and analysis was performed on two consecutive slices. T2 values were correlated to MME; furthermore, mean T2 values were compared in different grades of MME. Results: T2 values showed a strong correlation with increasing MME (r = 0.635; p < 0.001) in an exponential pattern. Analogously, knees with MME ≥ 3 mm showed statistically significant higher T2 values (p < 0.001) compared to knees with MME ≤ 2 mm and 2.1–2.9 mm; between the latter two, no differences in T2 values were found. Conclusions: T2 values showed a strong correlation with increasing MME. Consequently, MME ≥ 3 mm has a detectable impact on the cartilage of the femur. Full article

In this contribution, we address quantum transport in long periodic arrays whose basic cells, localized potentials $U\left(x\right)$, display certain particular features. We investigate under which conditions these “local” special characteristics can influence the tunneling behavior through the full structure. As the building blocks, we consider two types of $U\left(x\right)$s: combinations of either Pöschl–Teller, $U_0/{cosh}^2\left[\alpha x\right]$, potentials (for which the reflection and transmission coefficients are known analytically) or Gaussian-shaped potentials. For the latter, we employ an improved potential slicing procedure using basic barriers, like rectangular, triangular and trapezoidal, to approximate $U\left(x\right)$ and thus obtain its scattering amplitudes. By means of a recently derived method, we discuss scattering along lattices composed of a number, N, of these $U\left(x\right)$s. We find that near-resonance energies of an isolated $U\left(x\right)$ do impact the corresponding energy bands in the limit of very large Ns, but only when the cell is spatially asymmetric. Then, there is a very narrow opening (defect or rip) in the system conduction quasi-band, corresponding to the energy of the $U\left(x\right)$ quasi-state. Also, for specific $U_0$’s of a single Pöschl–Teller well, one has 100% transmission for any incident $E>0$. For the $U\left(x\right)$ parameters rather close to such a condition, the associated array leads to a kind of “reflection comb” for large Ns; $|T_N{\left(k\right)|}^2$ is not close to one only at very specific values of k, when $|T_N{|}^2\approx 0$. Finally, the examples here—illustrating how the anomalous transport comportment in finite but long lattices can be inherited from certain singular aspects of the $U\left(x\right)$s—are briefly discussed in the context of known effects in the literature, notably for lattices with asymmetric cells. Full article

The optical remote sensors carried by the Jilin-1 KF02 series satellites have an imaging resolution better than 0.5 m and a width of 150 km. There are radiometric problems, such as stripe noise, vignetting, and inter-slice chromatic aberration, in their raw images. In this paper, a relative radiometric correction method based on temperature normalization is proposed for the response characteristics of sensors and the structural characteristics of optical splicing of Jilin-1 KF02 series satellites cameras. Firstly, a model of temperature effect on sensor output is established to correct the variation of sensor response output digital number (DN) caused by temperature variation during imaging process, and the image is normalized to a uniform temperature reference. Then, the horizontal stripe noise of the image is eliminated by using the sensor scan line and dark pixel information, and the vertical stripe noise of the image is eliminated by using the method of on-orbit histogram statistics. Finally, the method of superposition compensation is used to correct the vignetting area at the edge of the image due to the lack of energy information received by the sensor so as to ensure the consistency of the image in color and image quality. The proposed method is verified by Jilin-1 KF02A on-orbit images. Experimental results show that the image response is uniform, the color is consistent, the average Streak Metrics (SM) is better than 0.1%, Root-Mean-Square Deviation of the Mean Line (RA) and Generalized Noise (GN) are better than 2%, Relative Average Spectral Error (RASE) and Relative Average Spectral Error (ERGAS) are greatly improved, which are better than 5% and 13, respectively, and the relative radiation quality is obviously improved after relative radiation correction. Full article

Despite the great success in the global exploration and development of reef reservoirs, research on bioclastic shoals under reefs is still in its infancy. Bioclastic shoal reservoirs are very thin, with multiple vertical levels and fast lateral changes, which makes accurate prediction of the reservoir’s location much tougher. To further implement the reservoir distribution, under the guidance of sequence stratigraphy, the prediction of thin shoals under the control of an isochronous stratigraphic framework was established. Using the combination of spectrum shaping and F-X domain noise suppression techniques and utilizing the signal-to-noise ratio spectrum set as the reference, logging curve as supervision, and well seismic calibration and isochronal amplitude slicing as quality control, the seismic frequency band was extended, and the seismic data resolution and signal-to-noise ratio were improved. After frequency extension, the global optimal seismic automatic interpretation technique was used to construct an isochronal stratigraphic framework model. Through waveform facies-controlled inversion and waveform facies-controlled simulation techniques, the elastic properties of the shoal reservoir were obtained, from which the planar distribution of the reservoir was accurately predicted. The above methods were applied to the prediction of the bioclastic shoal reservoir in the lower submember of the Changxing formation in the Yuanba gas field (China). The plane distribution of bioclastic shoal in the first and second levels was identified, which provides a guideline for the prediction of thin shoal reservoirs. Full article

This study presents an advanced framework integrating LLAMA_V2, a large language model, into Open Radio Access Network (O-RAN) systems. The focus is on efficient network slicing for various services. Sensors in IoT devices generate continuous data streams, enabling resource allocation through O-RAN’s dynamic slicing and LLAMA_V2’s optimization. LLAMA_V2 was selected for its superior ability to capture complex network dynamics, surpassing traditional AI/ML models. The proposed method combines sophisticated mathematical models with optimization and interfacing techniques to address challenges in resource allocation and slicing. LLAMA_V2 enhances decision making by offering explanations for policy decisions within the O-RAN framework and forecasting future network conditions using a lightweight LSTM model. It outperforms baseline models in key metrics such as latency reduction, throughput improvement, and packet loss mitigation, making it a significant solution for 5G network applications in advanced industries. Full article

Researchers of 5G-sliced Wireless Networks are faced with the task of achieving, at the same time, (i) mandatory isolation among network slices and (ii) the effective utilization of resource at Fifth Generation Base Station (gNB). This article proposes the second version of the Preemption-based service Prioritization (PP2) scheme that merges the capabilities of the classical Resource Reservation (RR) and Service Prioritization (SP) schemes and realizes the coexistence of non-TCP streaming and TCP elastic traffic at gNB. Analytical methods are given for Dynamic Resource Sharing (DRS) and Dynamic Resource Reallocation (DRR) with data rate reduction and service preemption. As main results, under some baseline scenario, the PP2 scheme, in comparison with RR, does increase the admission probability up to 99.999% at the system while ensuring 100% in system capacity utilization. Full article