RESUMEN
With the aging of the social population structure, the number of empty-nesters is also increasing. Therefore, it is necessary to manage empty-nesters with data mining technology. This paper proposed an empty-nest power user identification and power consumption management method based on data mining. Firstly, an empty-nest user identification algorithm based on weighted random forest was proposed. Compared with similar algorithms, the results indicate that the performance of the algorithm is the best, and the identification accuracy of empty-nest users is 74.2%. Then a method for analyzing the electricity consumption behavior of empty-nest users based on fusion clustering index adaptive cosine K-means was proposed, which can adaptively select the optimal number of clusters. Compared with similar algorithms, the algorithm has the shortest running time, the smallest Sum of the Squared Error (SSE), and the largest mean distance between clusters (MDC), which are 3.4281 s, 31.6591 and 13.9513, respectively. Finally, an anomaly detection model with an Auto-regressive Integrated Moving Average (ARIMA) algorithm and an isolated forest algorithm was established. The case analysis shows that the recognition accuracy of abnormal electricity consumption for empty-nest users was 86%. The results indicate that the model can effectively detect the abnormal behavior of empty-nest power users and help the power department to better serve empty-nest users.
RESUMEN
In this Letter, dual-wavelength-injection period-one (P1) laser dynamics is proposed for the first time, to the best of our knowledge, to generate frequency-modulated microwave signals. By injecting light with two different wavelengths into a slave laser to excite P1 dynamics, the P1 oscillation frequency can be modulated without external control of the optical injection strength. The system is compact and stable. The frequency and bandwidth of the generated microwave signals can be easily adjusted by tuning the injection parameters. Through both simulations and experiments, the properties of the proposed dual-wavelength injection P1 oscillation are revealed, and the feasibility of the frequency-modulated microwave signal generation is verified. We believe that the proposed dual-wavelength injection P1 oscillation is an extension of laser dynamics theory, and the signal generation method is a promising solution for generating broadband frequency-modulated signals with good tunability.
RESUMEN
Photonics-based high-resolution 3D radar imaging is demonstrated in which a convolutional neural network (CNN)-assisted back projection (BP) imaging method is applied to implement fast and noise-resistant image construction. The proposed system uses a 2D radar array with each element being a broadband radar transceiver realized by microwave photonic frequency multiplication and mixing. The CNN-assisted BP image construction is achieved by mapping low-resolution images to high-resolution images with a pre-trained 3D CNN, which greatly reduces the computational complexity and enhances the imaging speed compared with basic BP image construction. Besides, using noise-free or low-noise ground truth images for training the CNN, the CNN-assisted BP imaging method can suppress the noises, which helps to generate high-quality images. In the experiment, 3D radar imaging with a K-band photonics-based radar having a bandwidth of 8 GHz is performed, in which the imaging speed is enhanced by a factor of â¼55.3 using the CNN-assisted BP imaging method. By comparing the peak signal to noise ratios (PSNR) of the generated images, the noise-resistant capability of the CNN-assisted BP method is soundly verified.
RESUMEN
Millimeter-level resolution through-the-wall radar (TWR) imaging is demonstrated using a broadband nonlinear frequency-modulated (NLFM) signal that is generated by an optically injected semiconductor laser. The proposed system uses period-one dynamics of a semiconductor laser, together with an optical frequency downconversion technique to generate NLFM signals, which addresses the problem of traditional period-one oscillation not being able to generate broadband signals in the low-frequency region. In the experiment, an NLFM signal having a broad bandwidth of 18.5 GHz (1.5-20 GHz) is generated with a corresponding radar range resolution of 8.1 mm. Using this signal, TWR imaging is demonstrated, in which the use of the NLFM signal achieves good side-lobe suppression during pulse compression, and a modified back projection imaging algorithm with sub-aperture weighting is proposed to improve the imaging quality.
RESUMEN
The COVID-19 pandemic and influenza outbreaks have underscored the critical need for predictive models that can effectively integrate spatial and temporal dynamics to enable accurate epidemic forecasting. Traditional time-series analysis approaches have fallen short in capturing the intricate interplay between these factors. Recent advancements have witnessed the incorporation of graph neural networks and machine learning techniques to bridge this gap, enhancing predictive accuracy and providing novel insights into disease spread mechanisms. Notable endeavors include leveraging human mobility data, employing transfer learning, and integrating advanced models such as Transformers and Graph Convolutional Networks (GCNs) to improve forecasting performance across diverse geographies for both influenza and COVID-19. However, these models often face challenges related to data quality, model transferability, and potential overfitting, highlighting the necessity for more adaptable and robust approaches. This paper introduces the Graph Attention-based Spatial Temporal (GAST) model, which employs graph attention networks (GATs) to overcome these limitations by providing a nuanced understanding of epidemic dynamics through a sophisticated spatio-temporal analysis framework. Our contributions include the development and validation of the GAST model, demonstrating its superior forecasting capabilities for influenza and COVID-19 spread, with a particular focus on short-term, daily predictions. The model's application to both influenza and COVID-19 datasets showcases its versatility and potential to inform public health interventions across a range of infectious diseases.
Asunto(s)
COVID-19 , Gripe Humana , Análisis Espacio-Temporal , Humanos , COVID-19/epidemiología , COVID-19/virología , Gripe Humana/epidemiología , Redes Neurales de la Computación , SARS-CoV-2 , Predicción/métodos , Pandemias , Aprendizaje Automático , EpidemiasRESUMEN
Accurate medical image segmentation is critical for disease quantification and treatment evaluation. While traditional U-Net architectures and their transformer-integrated variants excel in automated segmentation tasks. Existing models also struggle with parameter efficiency and computational complexity, often due to the extensive use of Transformers. However, they lack the ability to harness the image's intrinsic position and channel features. Research employing Dual Attention mechanisms of position and channel have not been specifically optimized for the high-detail demands of medical images. To address these issues, this study proposes a novel deep medical image segmentation framework, called DA-TransUNet, aiming to integrate the Transformer and dual attention block (DA-Block) into the traditional U-shaped architecture. Also, DA-TransUNet tailored for the high-detail requirements of medical images, optimizes the intermittent channels of Dual Attention (DA) and employs DA in each skip-connection to effectively filter out irrelevant information. This integration significantly enhances the model's capability to extract features, thereby improving the performance of medical image segmentation. DA-TransUNet is validated in medical image segmentation tasks, consistently outperforming state-of-the-art techniques across 5 datasets. In summary, DA-TransUNet has made significant strides in medical image segmentation, offering new insights into existing techniques. It strengthens model performance from the perspective of image features, thereby advancing the development of high-precision automated medical image diagnosis. The codes and parameters of our model will be publicly available at https://github.com/SUN-1024/DA-TransUnet.
RESUMEN
Multiple myeloma (MM) is the second most common hematologic malignancy, which primarily occurs in the elderly. Cellular senescence is considered to be closely associated with the occurrence and progression of malignant tumors including MM, and lncRNA can mediate the process of cellular senescence by regulating key signaling pathways such as p53/p21 and p16/RB. However, the role of cellular senescence related lncRNAs (CSRLs) in MM development has never been reported. Herein, we identified 11 CSRLs (AC004918.5, AC103858.1, AC245100.4, ACBD3-AS1, AL441992.2, ATP2A1-AS1, CCDC18-AS1, LINC00996, TMEM161B-AS1, RP11-706O15.1, and SMURF2P1) to build the CSRLs risk model, which was confirmed to be highly associated with overall survival (OS) of MM patients. We further demonstrated the strong prognostic value of the risk model in MM patients receiving different regimens, especially for those with three-drug combination of bortezomib, lenalidomide, and dexamethasone (VRd) as first-line therapy. Not only that, our risk model also excels in predicting the OS of MM patients at 1, 2, and 3 years. In order to verify the function of these CSRLs in MM, we selected the lncRNA ATP2A1-AS1 which presented the largest expression difference between high-risk groups and low-risk groups for subsequent analysis and validation. Finally, we found that down-regulation of ATP2A1-AS1 can promote cellular senescence in MM cell lines. In conclusion, the CSRLs risk model established in present study provides a novel and more accurate method for predicting MM patients' prognosis and identifies a new target for MM therapeutic intervention.
Asunto(s)
Mieloma Múltiple , ARN Largo no Codificante , Humanos , Anciano , Mieloma Múltiple/genética , Mieloma Múltiple/tratamiento farmacológico , ARN Largo no Codificante/genética , ARN Largo no Codificante/metabolismo , Pronóstico , Bortezomib/farmacología , Bortezomib/uso terapéutico , Lenalidomida/uso terapéutico , Regulación Neoplásica de la Expresión Génica , Proteínas de la Membrana/metabolismo , Proteínas Adaptadoras Transductoras de Señales/metabolismoRESUMEN
Chimeric antigen receptor (CAR) engineering of natural killer (NK) cells is an attractive research field in tumor immunotherapy. While CAR is genetically engineered to express certain molecules, it retains the intrinsic ability to recognize tumor cells through its own receptors. Additionally, NK cells do not depend on T cell receptors for cytotoxic killing. CAR-NK cells exhibit some differences to CAR-T cells in terms of more precise killing, numerous cell sources, and increased effectiveness in solid tumors. However, some problems still exist with CAR-NK cell therapy, such as cytotoxicity, low transfection efficiency, and storage issues. Immune checkpoints inhibit immune cells from performing their normal killing function, and the clinical application of immune checkpoint inhibitors for cancer treatment has become a key therapeutic strategy. The application of CAR-T cells and immune checkpoint inhibitors is being evaluated in numerous ongoing basic research and clinical studies. Immune checkpoints may affect the function of CAR-NK cell therapy. In this review, we describe the combination of existing CAR-NK cell technology with immune checkpoint therapy and discuss the research of CAR-NK cell technology and future clinical treatments. We also summarize the progress of clinical trials of CAR-NK cells and immune checkpoint therapy.
Asunto(s)
Receptores Quiméricos de Antígenos , Receptores Quiméricos de Antígenos/genética , Inhibidores de Puntos de Control Inmunológico/uso terapéutico , Células Asesinas Naturales , Inmunoterapia/métodos , Receptores de Antígenos de Linfocitos TRESUMEN
Recycling of used plastic bottles is an important measure to protect the environment and save energy. Usually, bottles in different colors have different value for recycling. Classification of plastic bottles recycling based on image recognition during recycling is an effective way, where the position and color recognition are the key technologies. To classify the plastic bottles on the conveyor belt, their position relationships are firstly defined as three categories, i.e. disjoint, adjacent and overlapping. The disjoint ones can be easily identified by the ratio of concave and convex area based on their image. For the adjacent and overlapping bottles, a combination method called distance transformation and threshold segmentation is proposed to distinguish their position relationships. Once the adjacent bottles are identified, the method of concave point search based on convex hull will be used to separate the adjacent recycled bottles further. Then, the color of both the disjoint and adjacent bottles is identified because it is too complex and difficult to recognize color of and separate the overlapping bottles. In the aspect of color recognition, the colors of recycled bottles are divided into seven categories in the sorting process. Color features of the bottom section are used to represent the one of the recycled bottle because there may be a bottle cap and a label on the top and in the middle of the bottle, respectively, resulting in the wrong recognition. ReliefF algorithm is applied to select color features of recycled bottles and the color is identified by support vector machine (SVM) algorithm. The influence of training sample size on classification model is studied and the experimental results show that the accuracy of color recognition of recycled bottles reach 94.7%.
Asunto(s)
Reciclaje , Máquina de Vectores de Soporte , Algoritmos , ColorRESUMEN
OBJECTIVES: To reveal whether B-myb is involved in preventing senescence of vascular endothelial cells, and if so, to identify possible mechanisms for it. MATERIALS AND METHODS: C57/BL6 male mice and primary human aortic endothelial cells (HAECs) were used. Bleomycin was applied to induce stress-related premature senescence. B-myb knockdown was achieved using an siRNA technique and cell senescence was assessed using the senescence-associated ß-galactosidase (SA-ß-gal) assay. Intracellular reactive oxygen species (ROS) production was analysed using an ROS assay kit and cell proliferation was evaluated using KFluor488 EdU kit. Capillary tube network formation was determined by Matrigel assay. Expressions of mRNA and protein levels were detected by real-time PCR and western blotting. RESULTS: B-myb expression significantly decreased, while p53 and p21 expressions increased in the aortas of aged mice. This expression pattern was also found in replicative senescent HAECs and senescent HAECs induced by bleomycin. B-myb knockdown resulted in upregulation of p22phox , ROS accumulation and cell senescence of HAECs. Downregulation of B-myb significantly inhibited cell proliferation and capillary tube network formation and activated the p53/p21 signalling pathway. Blocking ROS production or inhibiting p53 activation remarkably attenuated SA-ß-gal activity and delayed cell senescence induced by B-myb-silencing. CONCLUSION: Downregulation of B-myb induced senescence by upregulation of p22phox and activation of the ROS/p53/p21 pathway, in our vascular endothelial cells, suggesting that B-myb may be a novel candidate for regulating cell senescence to protect against endothelial senescence-related cardiovascular diseases.
Asunto(s)
Proteínas de Ciclo Celular/metabolismo , Proliferación Celular/fisiología , Células Endoteliales/metabolismo , Especies Reactivas de Oxígeno/metabolismo , Transducción de Señal , Transactivadores/metabolismo , Animales , Senescencia Celular/fisiología , Regulación hacia Abajo , Masculino , Ratones Endogámicos C57BL , ARN Interferente Pequeño/metabolismo , Transducción de Señal/fisiología , Proteína p53 Supresora de Tumor/metabolismoRESUMEN
Endothelial dysfunction caused by endothelial cells senescence and chronic inflammation is tightly linked to the development of cardiovascular diseases. NLRP3 (NOD-like receptor family pyrin domain-containing3) inflammasome plays a central role in inflammatory response that is associated with diverse inflammatory diseases. This study explores the effects and possible mechanisms of NLRP3 inflammasome in endothelial cells senescence. Results show an increment of pro-inflammatory cytokine interleukin (IL) -1ß secretion and caspase-1 activation during the senescence of endothelial cells induced by bleomycin. Moreover, secreted IL-1ß promoted endothelial cells senescence through up-regulation of p53/p21 protein expression. NLRP3 inflammasome was found to mediate IL-1ß secretion through the production of ROS (reactive oxygen species) during the senescence of endothelial cells. Furthermore, the association of TXNIP (thioredoxin-interacting protein) with NLRP3 induced by ROS promoted NLRP3 inflammasome activation in senescent endothelial cells. In addition, the expressions of NLRP3 inflammasome related genes, ASC (apoptosis associated speck-like protein containing a CARD), TXNIP, cleaved caspase-1 and IL-1ß, were also increased in vitro and in vivo studies. These findings indicate that endothelial senescence could be mediated through ROS and NLRP3 inflammasome signaling pathways, suggesting a potential target for the prevention of endothelial senescence-related cardiovascular diseases.