Search

Currently, depression has become a common mental disorder, especially among postgraduates. It is reported that postgraduates have a higher risk of depression than the general public, and they are more sensitive to contact with others. Thus, a non-contact and effective method for detecting people at risk of depression becomes an urgent demand. In order to make the recognition of depression more reliable and convenient, we propose a multi-modal gait analysis-based depression detection method that combines skeleton modality and silhouette modality. Firstly, we propose a skeleton feature set to describe depression and train a Long Short-Term Memory (LSTM) model to conduct sequence strategy. Secondly, we generate Gait Energy Image (GEI) as silhouette features from RGB videos, and design two Convolutional Neural Network (CNN) models with a new loss function to extract silhouette features from front and side perspectives. Then, we construct a multi-modal fusion model consisting of fusing silhouettes from the front and side views at the feature level and the classification results of different modalities at the decision level. The proposed multi-modal model achieved accuracy at 85.45% in the dataset consisting of 200 postgraduate students (including 86 depressive ones), 5.17% higher than the best single-mode model. The multi-modal method also shows improved generalization by reducing the gender differences. Furthermore, we design a vivid 3D visualization of the gait skeletons, and our results imply that gait is a potent biometric for depression detection.

Motivated by recent claims on the potential value of integration in warehouse management, this study evaluates the benefits arising from integrating the planning of order picking and packing processes in e-commerce warehouses. A set of research questions are proposed for exploring various benefits under different operational conditions and an experimental study is designed to answer them. In order to have a concrete model to represent the integrated planning method, a mixed-integer nonlinear programming model is developed, and then compared against a non-integrated variation. The experimental study makes the comparisons by analysing the collected empirical data from a real-life warehouse. Our findings indicate that integrated picking and packing planning can yield improved performance in different aspects under different configurations of objectives, order quantities, order categories or workforce allocation.

Generative Adversarial Networks (GANs) have shown remarkable success in producing realistic-looking images in the computer vision area. Recently, GAN-based techniques are shown to be promising for spatio-temporal-based applications such as trajectory prediction, events generation and time-series data imputation. While several reviews for GANs in computer vision have been presented, no one has considered addressing the practical applications and challenges relevant to spatio-temporal data. In this paper, we have conducted a comprehensive review of the recent developments of GANs for spatio-temporal data. We summarise the application of popular GAN architectures for spatio-temporal data and the common practices for evaluating the performance of spatio-temporal applications with GANs. Finally, we point out future research directions to benefit researchers in this area., This paper has been accepted by ACM Transactions on Intelligent Systems and Technology (TIST)

Most of the malignant melanomas are already in the middle and advanced stages when they are diagnosed, which is often accompanied by the metastasis and spread of other organs.Besides, the prognosis of patients is bleak. The characteristics of the local immune microenvironment in metastatic melanoma have important implications for both tumor progression and tumor treatment. In this study, data on patients with metastatic melanoma from the TCGA and GEO datasets were selected for immune, stromal, and estimate scores, and overlapping differentially expressed genes (DEGs) were screened. A nine-IRGs prognostic model (ALOX5AP, ARHGAP15, CCL8, FCER1G, GBP4, HCK, MMP9, RARRES2 and TRIM22) was established by univariate COX regression, LASSO and multivariate COX regression. Receiver operating characteristic (ROC) curves were used to test the predictive accuracy of the model. Immune infiltration was analyzed by using CIBERSORT, Xcell and ssGSEA in high-risk and low-risk groups. The immune infiltration of the high-risk group was significantly lower than that of the low-risk group. Immune checkpoint analysis revealed that the expression of PDCD1, CTLA4, TIGIT, CD274, HAVR2 and LAG3 were significantly different in groups with different levels of risk scores. WGCNA analysis found that the yellow-green module contained seven genes (ALOX5AP, FCER1G, GBP4, HCK, MMP9, RARRES2 and TRIM22) from the nine-IRG prognostic model, of which the yellow-green module had the highest correlation with risk scores. The results of GO and KEGG suggested that the genes in the yellow-green module were mainly enriched in immune-related biological processes. Finally, we analyzed the prognostic ability and expression characteristics of ALOX5AP, ARHGAP15, CCL8, FCER1G, GBP4, HCK, MMP9, RARRES2 and TRIM22 in metastatic melanoma. Overall, a prognostic model for metastatic melanoma based on the characteristics of the tumor immune microenvironment was established, which was helpful for further studies.It could function well in helping people to understand the characteristics of the immune microenvironment in metastatic melanoma and to find possible therapeutic targets.

Sentiment analysis in conversations has gained increasing attention in recent years for the growing amount of applications it can serve, e.g., sentiment analysis, recommender systems, and human-robot interaction. The main difference between conversational sentiment analysis and single sentence sentiment analysis is the existence of context information which may influence the sentiment of an utterance in a dialogue. How to effectively encode contextual information in dialogues, however, remains a challenge. Existing approaches employ complicated deep learning structures to distinguish different parties in a conversation and then model the context information. In this paper, we propose a fast, compact and parameter-efficient party-ignorant framework named bidirectional emotional recurrent unit for conversational sentiment analysis. In our system, a generalized neural tensor block followed by a two-channel classifier is designed to perform context compositionality and sentiment classification, respectively. Extensive experiments on three standard datasets demonstrate that our model outperforms the state of the art in most cases., 9 pages, 7 figures

Although desktop stereolithography (SLA) 3D printers and photopolymerizing resin have been used increasingly in dentistry to manufacture surgical templates, studies investigating their clinical application are lacking.The purpose of this in vitro study was to evaluate the effects of build angle on the accuracy, printing time, and material consumption of additively manufactured surgical templates made with a desktop SLA 3D printer and photopolymerizing resin material.Fifty surgical templates were fabricated from 1 master digital design file using a desktop SLA 3D printer and photopolymerizing resin material at 5 different build angles (0, 30, 45, 60, and 90 degrees) (n=10). All surgical templates were digitized and superimposed with the master design file using best-fit alignment in the surface matching software program. Dimensional differences between the sample files and the original master design files were compared, and the mean deviations were measured in the root mean square (measured in mm, representing accuracy). The printing time and resin consumption for each specimen were recorded based on the information in the 3D printing preparation software program. ANOVA and the Fisher least significant difference (LSD) test were used to estimate the effects of build angles on the root mean square, printing time, and resin consumption (α=.05 for all tests).The groups 0 degree (0.048 ±0.007 mm) and 45 degrees (0.053 ±0.012 mm) had statistically significant lower root mean square values when compared with those of groups 30 degrees (0.067 ±0.009 mm), 60 degrees (0.079 ±0.016 mm), and 90 degrees (0.097 ±0.017 mm) (P.001 for all comparisons, except P=.003 for groups 30 degrees versus 45 degrees). The group 90 degrees had statistically significant higher root mean square values than all other groups (P.001 for all comparisons, except P=.010 when compared with the group 60 degrees). For the printing time, the group 0 degree required significantly less printing time than all other groups (hour:minute, 1:26 ±0:03, P.001 for all comparisons). The group 90 degrees required significantly more printing time than all other groups (2:52 ±0:06, P.001 for all comparisons). For resin consumption, the groups 0 degree (11.58 ±0.21 mL), 30 degrees (11.32 ±0.16 mL), and 45 degrees (11.23 ±0.16 mL) consumed similar amounts of resin. However, there was statistical significance between groups 0 degree and 45 degrees (P=.016). The group 90 degrees consumed the significantly least amount of resin (9.86 ±0.40 mL, P.001 for all comparisons).With a desktop SLA 3D printer, the 0-degree and 45-degree build angles produced the most accurate surgical template, and the 90-degree build angle produced the least accurate surgical template. The 0-degree build angle required the shortest printing time but consumed the most resin in the printing process. The 90-degree build angle required the longest printing time but consumed the least amount of resin in the printing process.

Several nairo-like viruses have been discovered in ticks in recent years, but their relevance to public health remains unknown. Here, we found a patient who had a history of tick bite and suffered from a febrile illness was infected with a previously discovered RNA virus, Beiji nairovirus (BJNV), in the nairo-like virus group of the order Bunyavirales. We isolated the virus by cell culture assay. BJNV could induce cytopathic effects in the baby hamster kidney and human hepatocellular carcinoma cells. Negative-stain electron microscopy revealed enveloped and spherical viral particles, morphologically similar to those of nairoviruses. We identified 67 patients as BJNV infection in 2017–2018. The median age of patients was 48 years (interquartile range 41–53 years); the median incubation period was 7 days (interquartile range 3–12 days). Most patients were men (70%), and a few (10%) had underlying diseases. Common symptoms of infected patients included fever (100%), headache (99%), depression (63%), coma (63%), and fatigue (54%), myalgia or arthralgia (45%); two (3%) patients became critically ill and one died. BJNV could cause growth retardation, viremia and histopathological changes in infected suckling mice. BJNV was also detected in sheep, cattle, and multiple tick species. These findings demonstrated that the newly discovered nairo-like virus may be associated with a febrile illness, with the potential vectors of ticks and reservoirs of sheep and cattle, highlighting its public health significance and necessity of further investigation in the tick-endemic areas worldwide.

This technical report describes a workflow to fabricate an implant overdenture via digital duplication of an interim complete removable dental prosthesis and additive manufacturing (3D printing). An edentulous patient was provided with an interim maxillary denture after implant placement. After 4 months of healing, the existing interim denture was scanned, duplicated via 3D printing, and used to make the final impression, record the maxillomandibular interocclusal relationship, and transfer the esthetic information to the definitive implant overdenture. The framework of the implant overdenture was digitally designed and manufactured using a direct metal printing (DMP) system. This digital duplication workflow facilitated the implant overdenture fabrication with favorable clinical outcomes.

Accurate detection of void defects in ballastless track structures has become a core problem that needs urgent resolution for the maintenance and repair of high-speed railway (HSR) line structures in China. In this study, the root mean squaresynthetic aperture focusing technique (RMS-SAFT) ultrasound imaging method, which is suitable for the void defects of multi-layer structures, is proposed by combining the RMS velocity method and SAFT ultrasound imaging. First, a multi-layer sound velocity model (the relationship model between sound propagation time and sound propagation distance) of the HSR ballastless track is established. The sound propagation time is expressed as a function of the RMS of sound propagation speed as an independent variable. Second, the propagation time of the sound wave in the HSR ballastless track is calculated in accordance with the multi-layer sound velocity model and the obtained propagation time is substituted into the SAFT ultrasound imaging method for imaging. Lastly, the accuracy of the method is verified through a finite element simulation and an experiment. The results show that for the HSR ballastless track with minimal differences in the sound propagation speed at each layer, the sound propagation time calculated by the multi-layer sound wave model has high accuracy. The proposed RMS-SAFT ultrasound imaging method improves the accuracy of traditional SAFT imaging and realises accurate imaging of the void defects of HSR ballastless track.

Carbon dioxide (CO2) from the excessive consumption of fossil fuels has exhibited a huge threat to the planet's ecosystem. Electrocatalytic CO2 reduction into value-added chemicals has been regarded as a promising strategy in CO2 utilization and needs the development of advanced electrocatalysts for lowering the activation energy and enhancing selectivity in CO2 reduction. Two-dimensional (2D) materials, benefiting from their unique geometrical structures, have been extensively studied in the electrocatalytic CO2 reduction reaction (CO2RR). In this review, we systematically overview atomic-level engineering strategies in 2D electrocatalysts for the CO2RR, including thickness control, elemental doping, vacancy engineering, heterostructure construction, and single-atom loading. Meanwhile, we analyze the relationship between structures and activity in electrocatalysis, and present the future challenges and opportunities in the electrocatalytic CO2RR, and we hope that this review will offer helpful guidance for developing electrocatalysts for the CO2RR.

A tunable photonic microwave frequency up-conversion scheme using opto-electronic oscillator (OEO) based on a monolithic integrated three-section laser without any electro-optic modulator (EOM) or filter is proposed. By adjusting the monolithic integrated three-section laser to operate in the period-one (P1) dynamical state, the signal carrier frequency up-converted from the intermediate frequency (IF) to the frequency at the difference and the summation between the oscillation frequency of OEO and IF can be realized. The tunability of the up-converted frequency can also be greatly guaranteed just by altering the control currents of the monolithic integrated three-section laser induced P1 frequency. In this paper, an IF of 2 GHz with 10 Msymbol/s 16-QAM signals is successfully up-converted to 16 GHz and 20 GHz simultaneously. The up-converted frequencies can be tuned from 16 GHz/20 GHz to 19 GHz/23 GHz, and the error vector magnitudes (EVMs) of all those up-converted signals satisfy the limitation in satellite communication.

Many risk factors of cancer have been established, but the contribution of paternal age in this regard remains largely unexplored. To further understand the etiology of cancer, we investigated the relationship between paternal age and cancer incidence using PLCO cohort. Cox proportional hazards models were performed to assess the association between paternal age and the risk of cancers. During follow-up time (median 11.5 years), 18,753 primary cancers occurred. Paternal age was associated with reduced risk of cancers of the female genitalia (HR, 0.79; 95%CI, 0.66-0.94; P = 0.008) as well as cancers of the respiratory and intrathoracic organs (HR, 0.78; 95%CI, 0.63-0.97; P = 0.026). The association was stronger for lung cancer (HR, 0.67; 95%CI, 0.52-0.86; P = 0.002). The subgroup analysis suggested that age, gender, smoking and BMI were related to the decreased cancer incidence of the respiratory and intrathoracic organs, lung and the female genitalia. Positive linear associations were observed between paternal age and cancer incidence of the female genitalia, respiratory and intrathoracic organs and the lungs. These findings indicate that advanced paternal age is an independent protective factor against various cancers in offspring.

The widespread use of smartphones has brought great convenience to our daily lives, while at the same time we have been increasingly exposed to security threats. Keystroke security is essential to user privacy protection. In this paper, we present GazeRevealer, a novel side-channel based keystroke inference framework to infer sensitive inputs on smartphone from video recordings of victim's eye patterns captured from smartphone front camera. We observe that eye movements typically follow the keystrokes typing on the number-only soft keyboard during password input. By exploiting eye movement patterns, we are able to infer the passwords being entered. We propose a novel algorithm to extract sensitive eye images from video streams, and classify these images with Support Vector Classification. We also propose a novel classification enhancement algorithm to further improve classification accuracy. Compared with prior keystroke detection approaches, GazeRevealer does not require any external auxiliary devices, and it only relies on smartphone front camera. We evaluate the performance of GazeRevealer on several smartphones under different real-life usage scenarios. The results show that GazeRevealer achieves an inference rate of 77.89 percent for single key number and an inference rate of 84.38 percent for 6-digit password in the ideal case.

The prevalence of HIV-1 drug resistance is increasing worldwide and monitoring its emergence is important for the successful management of populations receiving combination antiretroviral therapy. It is likely that pre-existing drug resistance mutations linked on the same viral genomes are predictive of treatment failure. Because of the large number of sequences generated by ultrasensitive single-genome sequencing (uSGS) and other similar next-generation sequencing methods, it is difficult to assess each sequence individually for linked drug resistance mutations. Several software/programs exist to report the frequencies of individual mutations in large data sets, but they provide no information on linkage of resistance mutations. In this study, we report the HIV-DRLink program, a research tool that provides resistance mutation frequencies as well as their genetic linkage by parsing and summarizing the Sierra output from the Stanford HIV Database. The HIV-DRLink program should only be used on data sets generated by methods that eliminate artifacts due to polymerase chain reaction recombination, for example, standard single-genome sequencing or uSGS. HIV-DRLink is exclusively a research tool and is not intended to inform clinical decisions.

Polycystic ovary syndrome (PCOS) is a prevalent endocrine disorder and one of the most common causes of infertility in women. PCOS patients have been found with dysregulated miRNA, which is indicative of their roles as noninvasive biomarkers and novel therapeutic targets in PCOS. Herein, this study sets out to explore the mechanism of action of miR-199a-5p in PCOS in relation to the janus kinase/signal transducer and activator of transcription 3 (JAK/STAT3) pathway via Wilms’ tumor 1 (WT1) regulation in a rat model of PCOS. The expression of miR-199a-5p was highly expressed in ovarian cortical tissues and serum of PCOS patients, as examined by RT-qPCR. Ovarian granulosa cells (GCs) were harvested from PCOS rat model, followed by subsequent purification. Gain- and loss-of-function experiments of miR-199a-5p were performed to determine its functions in PCOS. Cell viability, cell apoptosis and serum hormone levels were assessed, the results of which showed that downregulation of miR-199a-5p contributed to the promotion of GC viability and inhibition of apoptosis, while simultaneously inducing the elevation of serum E2 level and reduction of serum AMH, PG, LH and FSH levels in the PCOS rat model. WT1 was identified as a target gene of miR-199a-5p by dual-luciferase reporter gene assay, and inhibition of miR-199a-5p resulted in the activation of WT1-mediated JAK/STAT3 pathway. The activated JAK/STAT3 pathway suppressed the development of PCOS by miR-199a-5p, indicating a mechanism by which miR-199a-5p could potentially prevent PCOS through the WT1-mediated JAK/STAT3 pathway.

For wide-angle scanning phased arrays, the efficiency of active elements is deteriorated with the increase of mutual impedance. This article demonstrates an effective strategy to control the mutual impedance among array elements by canceling the major coupling effect. The implemented wide-angle impedance matching (WAIM) of a wideband phased array verifies the validity of the proposed strategy. For the array element, to obtain wide-angle radiation and wideband characteristic, parallel slots with unequal lengths are deliberately etched on a low-profile substrate integrated cavity (SIC). The mutual impedance between two arbitrary elements is remarkably controlled and compensated by canceling the major coupling effect, which is realized by etching symmetrical slots and loading periodical loops within each element. With the controlled mutual impedance, the proposed array possesses excellent wide-angle scanning performance. Both the simulated and measured results indicate that the designed array steers its main beam from −70° to +70° in the xoz azimuth plane in a broad frequency range from 8.0 to 9.5 GHz. The active $S$ -parameter of each element remains lower than −10 dB in the operating band while the array scans. Due to the implemented WAIM, the total efficiency of the array exceeds 90% during the scan and the fluctuation of realized gain is less than 3 dB.

A dual-module machine learning scheme is proposed to reconstruct inhomogeneous scatterers with high contrasts and large electrical dimensions. The first nonlinear mapping module (NMM) is an extreme learning machine (ELM), which is used to convert the measured scattered fields at the receiver arrays into the preliminary images of the scatterers. The second image-enhancing module (IEM) is a convolutional neural network (CNN), which is used to refine further the images from the NMM to obtain high-accuracy pixel-based model parameter distribution in the inversion domain. Compared with the traditional approximate methods such as backpropagation, the NMM-IEM machine learning can produce the preliminary image with a much higher accuracy but the unknown weight matrices of the ELM are only solved once during training. Hence, the IEM connected to the NMM has a simple architecture and can be trained at a rather low cost. The performance of the proposed dual-module NMM-IEM scheme and the conventional variational Born iterative method is compared in terms of inversion of scatterers with different electrical sizes and contrasts. Meanwhile, the NMM-IEM is also assessed for the inversion of scatterers with high contrasts and large electrical dimensions and experimental data. Finally, the NMM-IEM is compared with the CNNs used in the previous works.

This study aims to examine the effects of experiential value in firm-initiated social media activities on brand attitude and purchase engagement. An online survey with the experimental design was used to collect data from 181 social media users who were over 18 years old. The results of this study showed that experiential value positively influenced both brand attitude and purchase engagement. In addition, brand attitude mediated the relationship between experiential value and purchase engagement. The most significant effects of experiential value on brand attitude and purchase engagement were observed at the medium level of participation required in the activity. It was also revealed that the more privacy concern customers had, the stronger the effect of experiential value on brand attitude became. In contrast, as privacy concern increased, the impact of experiential value on purchase engagement decreased. The study extends the current understanding of customer experience and provides important managerial implications.

Purpose: Magnetic resonance imaging (MRI) has great potential to improve prostate cancer diagnosis; however, subtle differences between cancer and confounding conditions render prostate MRI interpretation challenging. The tissue collected from patients who undergo radical prostatectomy provides a unique opportunity to correlate histopathology images of the prostate with preoperative MRI to accurately map the extent of cancer from histopathology images onto MRI. We seek to develop an open-source, easy-to-use platform to align presurgical MRI and histopathology images of resected prostates in patients who underwent radical prostatectomy to create accurate cancer labels on MRI. Methods: Here, we introduce RAdiology Pathology Spatial Open-Source multi-Dimensional Integration (RAPSODI), the first open-source framework for the registration of radiology and pathology images. RAPSODI relies on three steps. First, it creates a three-dimensional (3D) reconstruction of the histopathology specimen as a digital representation of the tissue before gross sectioning. Second, RAPSODI registers corresponding histopathology and MRI slices. Third, the optimized transforms are applied to the cancer regions outlined on the histopathology images to project those labels onto the preoperative MRI. Results: We tested RAPSODI in a phantom study where we simulated various conditions, for example, tissue shrinkage during fixation. Our experiments showed that RAPSODI can reliably correct multiple artifacts. We also evaluated RAPSODI in 157 patients from three institutions that underwent radical prostatectomy and have very different pathology processing and scanning. RAPSODI was evaluated in 907 corresponding histpathology-MRI slices and achieved a Dice coefficient of 0.97 ± 0.01 for the prostate, a Hausdorff distance of 1.99 ± 0.70 mm for the prostate boundary, a urethra deviation of 3.09 ± 1.45 mm, and a landmark deviation of 2.80 ± 0.59 mm between registered histopathology images and MRI. Conclusion: Our robust framework successfully mapped the extent of cancer from histopathology slices onto MRI providing labels from training machine learning methods to detect cancer on MRI.

BACKGROUND Minimal-fat angiomyolipoma (mf-AML) is often misdiagnosed as renal cell carcinoma before surgery. AIM To analyze the magnetic resonance imaging (MRI) features of mf-AML and the causes of misdiagnosis by MRI before operation. METHODS A retrospective analysis was performed on ten patients with mf-AML confirmed by surgical pathology, all of whom underwent preoperative MRI examination to analyze the morphological characteristics and MRI signals of the tumor. RESULTS MRI revealed a circular-like mass in 4/10 (40%) patients, an oval mass in 6/10 patients (60%), a mass with a capsule in 9/10 patients (90%), and a mass with a lipid component in 7/10 patients (70%). The diameter of the masses in all ten patients was from 11 to 47 mm; the diameter was between 11 mm and 40 mm in 8/10 (80%) patients and between 40 mm and 47 mm in 2/10 (20%) patients. CONCLUSION An oval morphological characteristic is strong evidence for the diagnosis of mf-AML, while a capsule and lipids are atypical manifestations of mf-AML.

In recent years, big datasets are often split into several subsets due to the storage requirements. We propose a parallel group Bayesian method for statistical inference in sparse big data. This method improves the existing methods in two aspects: the total datasets are also split into a data subset sequence and the parameter vector is divided into several sub-vectors. Besides, we add a weight sequence to optimize the sub-estimators when each of them has a different covariance matrix. We obtain several theoretical properties of the estimator. The results of numerical simulations show that our method is consistent with the theoretical results and is more effective than classic Markov chain Monte Carlo methods.

Drawing on the four dimensions of justice: distributive, procedural, interactional, and informational justice, this research examines justice as an antecedent of franchisee performance. Empirical r...

Brain region-of-interest (ROI) segmentation based on structural magnetic resonance imaging (MRI) scans is an essential step for many computer-aid medical image analysis applications. Due to low intensity contrast around ROI boundary and large inter-subject variance, it has been remaining a challenging task to effectively segment brain ROIs from structural MR images. Even though several deep learning methods for brain MR image segmentation have been developed, most of them do not incorporate shape priors to take advantage of the regularity of brain structures, thus leading to sub-optimal performance. To address this issue, we propose an anatomical attention guided deep learning framework for brain ROI segmentation of structural MR images, containing two subnetworks. The first one is a segmentation subnetwork, used to simultaneously extract discriminative image representation and segment ROIs for each input MR image. The second one is an anatomical attention subnetwork, designed to capture the anatomical structure information of the brain from a set of labeled atlases. To utilize the anatomical attention knowledge learned from atlases, we develop an anatomical gate architecture to fuse feature maps derived from a set of atlas label maps and those from the to-be-segmented image for brain ROI segmentation. In this way, the anatomical prior learned from atlases can be explicitly employed to guide the segmentation process for performance improvement. Within this framework, we develop two anatomical attention guided segmentation models, denoted as anatomical gated fully convolutional network (AG-FCN) and anatomical gated U-Net (AG-UNet), respectively. Experimental results on both ADNI and LONI-LPBA40 datasets suggest that the proposed AG-FCN and AG-UNet methods achieve superior performance in ROI segmentation of brain MR images, compared with several state-of-the-art methods.

Out-of-phase ventilation occurs when local regions of the lung reach their maximum or minimum volumes at breathing phases other than the global end inhalation or exhalation phases. This paper presents the N-phase local expansion ratio (LER $_{N}$ ) as a surrogate for lung ventilation. A common approach to estimate lung ventilation is to use image registration to align the end exhalation and inhalation 3DCT images and then analyze the resulting correspondence map. This 2-phase local expansion ratio (LER2) is limited because it ignores out-of-phase ventilation and thus may underestimate local lung ventilation. To overcome this limitation, LER $_{N}$ measures the maximum ratio of local expansion and contraction over the entire breathing cycle. Comparing LER2 to LER $_{N}$ provides a means for detecting and characterizing locations of the lung that experience out-of-phase ventilation. We present a novel in-phase/out-of-phase ventilation (IOV) function plot to visualize and measure the amount of high-function IOV that occurs during a breathing cycle. Treatment planning 4DCT scans collected during coached breathing from 32 human subjects with lung cancer were analyzed in this study. Results show that out-of-phase breathing occurred in all subjects and that the spatial distribution of out-of-phase ventilation varied from subject to subject. For the 32 subjects analyzed, 50% of the out-of-phase regions on average were mislabeled as low-function by LER2 (high-function threshold of 1.1, IOV threshold of 1.05). 4DCT and Xenon-enhanced CT of four sheep showed that LER8 is more accurate than LER2 for measuring lung ventilation.

This communication presents an artificial magnetic conductor (AMC) structure-loaded phased array with broadband low-RCS and wide-angle scanning performance. A substrate integrated with the cavity-backed antenna with wide beamwidth and decoupling cavity is used as the basic array element to increase the field-of-view scanning range of arrays. Meanwhile, a checkerboard-shaped AMC structure with a broadband region of 180° (±37°) phase difference is designed and loaded around the array to reduce its RCS in and out of the band. This communication is validated through measurements that matched well with simulations. The proposed array operates at 10.8 GHz and provides a wide scanning region from −70° to +70° in the H-plane with particularly small gain fluctuation (±1.5 dB). Moreover, the backscattering of the proposed array can be reduced to −6 dB for both TE and TM polarizations, covering the $X$ -, Ku -, and $K$ -bands. The proposed approach has the potential application in smart skin designs due to its low profile, powerful scanning ability, and broadband RCS reduction.

Purpose Little is known about the incidence, risk factors, and prognostic implications of acute kidney injury (AKI) in patients with acute exacerbation of chronic obstructive pulmonary disease (AECOPD) in China. In this study, we investigated the incidence, risk factors, and short-term outcomes of AKI in these patients. Patients and Methods We analyzed the records of 1768 patients admitted to Nanjing First Hospital with a principal diagnosis of AECOPD. Of these, 377 patients had AKI. Results AKI occurred in 377 patients (21%). Independent risk factors for AKI in patients with AECOPD were advanced age, coronary artery disease, anemia, cancer, chronic kidney disease, hypercapnic encephalopathy, acute respiratory failure, and mechanical ventilation. Patients with AKI had worse prognostic implications and were more likely to require mechanical ventilation (38.7% vs 19.1%, P

A angular radial staggered vane (ARSV) slow wave structure (SWS) is proposed for high power vacuum devices. Cooperating with an angular radial sheet electron beam (ARSEB), the SWS is designed for a W-band backward wave oscillator (BWO). The high frequency characteristics of the proposed SWS are studied by using simulation. The effects of the angle have been found out. The steady transmission of an angular sheet electron beam has been realized using a radial uniform magnetic field of ~ 1 T. The beam wave interactions are studied using particle-in-cell (PIC) simulation, a peak output power of 21 kW has been achieved at 100 GHz, with an electron efficiency of about 5%. The study of frequency versus beam voltage shows that the proposed BWO can be tunable in the frequency range of 79.8 GHz - 104.7 GHz and the output power is higher than 13 kW. The fabrication and cold test results are presented at the end.

For planetary landing missions, accurate surface relative state knowledge to safely land near science targets is required. However, the lack of on-board map poses a technical challenge in the process of implementing such a navigation system. Moreover, traditional feature point observations are not sufficient for guaranteeing robust performance of the algorithm under challenging environmental conditions like texture-less terrain. This paper presents a novel visual navigation scheme based on curve matching for planetary landing in unknown environments. An analytical measurement model, which contains the lander's current and previous states, is derived by using curve matches in descent images for the first time. The derived measurement model and the state information sensed by inertial measurement unit are integrated in unscented Kalman filter algorithm. Also, the observability of the proposed navigation system is analyzed. In particularly, the Fisher matrix is used to evaluate the navigation performance. It is shown that the superior accuracy of the proposed method is obtained compared to point-based approaches. Simulation results demonstrate the effectiveness and high accuracy of the proposed navigation method.

Background Primary lacrimal sac melanoma is an extremely rare condition with fewer than 50 cases reported so far. Clinically, its symptoms resemble those of dacryocystitis, leading to frequent misdiagnosis. During diagnosis, imaging examination is often performed to differentiate tumors from inflammation. In this report, we present a case of primary lacrimal sac melanoma and summarize the CT and MRI characteristics of lacrimal sac melanoma. Case presentation We report a 50-year-old female patient who had undergone a dacryocystectomy for the left lacrimal sac mass. Postoperative pathological examination confirmed the presence of primary malignant melanoma. Three months later, a lump in the lacrimal sac area was found. The patient underwent CT and MR examinations. CT scan demonstrated a partially well-defined soft mass in the fossa of left lacrimal sac extending into the nasolacrimal duct and anterior ethmoid sinus. MRI revealed an intermediate signal intensity on T1 and iso-or hyper-signal on T2 weighted images. Histopathological examination on biopsy confirmed recurrence of primary lacrimal sac melanoma. Discussion and conclusions None has described the CT and MR findings of primary lacrimal sac melanoma so far. Typically, MR images show hyperintensity signal on T1-weighted images and hypointense signal on T2-weighted images owing to the paramagnetic properties of melanin. In contrast to previous reports and the present case, most cases do not present these typical signals. Thus, reporting such radiological findings is important to create awareness on variant images of primary lacrimal sac melanoma. This will reduce misdiagnosis and mistreatment.

As the incidence of diabetes and cardiovascular comorbidities continues to rise, driven by increased prevalence of obesity and an aging population, so does the demand for percutaneous coronary intervention (PCI) to restore cardiac blood flow. Renin-angiotensin-aldosterone system (RAAS) inhibitors are commonly prescribed to hypertensive diabetic patients to prevent diabetic nephropathy. However, evidence suggests that angiotensin-converting enzyme inhibitors (ACEIs) and angiotensin receptor blockers (ARBs) may increase the risk of contrast-induced acute kidney injury (CIAKI) following coronary angiography (CAG) and PCI. We therefore conducted a retrospective, multicenter study applying the propensity score matching method to evaluate the impact of RAAS inhibition on CIAKI in diabetic patients undergoing CAG/PCI. Among 2240 subjects that met the inclusion criteria, 704 patients in the ACEIs/ARBs group were successfully matched to eligible control patients. The incidence of CIAKI (serum creatinine increase ≥0.5 mg/dl or ≥25% from baseline within 72 h post-CAG/PCI) was significantly higher in the ACEIs/ARBs group than in the control group (26.6% vs. 16.2%, P

TFE3 Xp11.2 translocation renal cell carcinoma (TFE3-RCC) generally progresses more aggressively compared with other RCC subtypes, but it is challenging to diagnose TFE3-RCC by traditional visual inspection of pathological images. In this study, we collect hematoxylin and eosin- stained histopathology whole-slide images of 74 TFE3-RCC cases (the largest cohort to date) and 74 clear cell RCC cases (ccRCC, the most common RCC subtype) with matched gender and tumor grade. An automatic computational pipeline is implemented to extract image features. Comparative study identifies 52 image features with significant differences between TFE3-RCC and ccRCC. Machine learning models are built to distinguish TFE3-RCC from ccRCC. Tests of the classification models on an external validation set reveal high accuracy with areas under ROC curve ranging from 0.842 to 0.894. Our results suggest that automatically derived image features can capture subtle morphological differences between TFE3-RCC and ccRCC and contribute to a potential guideline for TFE3-RCC diagnosis., Translocation renal cell carcinoma is an aggressive form of renal cancer that is often misdiagnosed to other subtypes. Here the authors demonstrated that by using machine learning and H&E stained whole-slide images, an accurate diagnose of this particular type of renal cancer can be achieved.

In this letter, a microstrip patch hybrid mode technique is introduced to design a 2-D wide-angle scanning planar phased array. The proposed element consists of a circular patch and four rectangular parasitic patches distributed around the circular patch. In order to obtain wider radiation beamwidth (BW) in two orthogonal azimuth planes, the TM11 mode of the circular patch and the zeroth-order resonant mode of the parasitic rectangular patches are separately excited. Experimental results show that the proposed element can obtain 3 dB BW more than 156° in the two orthogonal azimuth planes. Moreover, an 8 × 8 planar phased array formed by this element can realize wide-angle scanning in a range of about ±65° in the two orthogonal azimuth planes. In the above scanning range, the sidelobe levels of the phased array are always less than −7.8 dB, the scanning gain fluctuation is less than ±1.73 dB, and the main polarizations on the two orthogonal planes are both θ -polarized. In addition, the phased array has a simple structure, a low profile, and convenient fabrication.

This communication presents a novel compact broadband circularly polarized (CP) implantable patch antenna for biomedical applications in 2.4 GHz industrial, scientific, and medical (ISM) band. By employing slots on the patch plane and shorting method, the whole size (including the superstrate) of the designed antenna can be enormously reduced to $9.8\times 9.8\times1.27$ mm3, which is equivalent to $0.0784\lambda _{0}\times 0.0784\lambda _ {0}\times 0.0102\lambda _ {0}$ ( $\lambda _ {0}$ is the free-space wavelength at 2.4 GHz). Under the premise of keeping a slotless ground, not only a good size reduction is realized but also the impedance bandwidth and the axial ratio (AR) bandwidth are greatly improved. A simulated −10 dB impedance bandwidth of 21.5% with a 3 dB AR bandwidth of 15.8% is acquired in a skin phantom. The antenna also exhibits good robustness to different thicknesses of biocompatible coating. The influence of different body phantoms is discussed to evaluate the sensitivity of the proposed antenna. The experiments are carried out in both skin-mimicking gel and pork, and the respective measured impedance bandwidths are 25.9% and 25.7%. The CP purity is experimentally validated by comparing the communication link levels in two orthogonal polarization directions. The maximum specific absorption rate (SAR) value satisfies the IEEE standard safety guidelines.

A novel scheme is proposed for the enhancement of the gain and output power of terahertz (THz) traveling-wave tube (TWT) amplifiers. The scheme combines a slow-wave structure (SWS) and multigap resonant cavities, resulting in a complementary hybrid of traveling-wave and standing-wave elements, thus offering a compact circuit length. The idea has been verified by a specific design of a 220-GHz TWT amplifier by means of particle-in-cell (PIC) simulations. For an electron beam with a voltage of 21 kV and a current of 200 mA, a maximum gain of 42.22 dB and a 3-dB bandwidth of 6.5 GHz has been achieved while the overall circuit length is only 38 mm. For an input power of 11.25 mW, the CW peak power is predicted to be 187.5 W at 220 GHz, corresponding to an electronic efficiency of 4.47%. These simulation results predict a performance that well exceeds that reported for conventional TWTs, along with a significant reduction of the input power and circuit length.

Background Brainstem hemorrhage is an acute and severe neurosurgical disease. Cerebral hemorrhage is surgically treated via hematoma puncture drainage because of its minimally invasive nature. However, the placement of puncture must be extremely accurate due to the special anatomical location of the brainstem and its physiological functions. The present study aimed to evaluate whether the application of a three-dimensional (3D)-printed navigation mold achieved good outcomes in the surgical treatment of brainstem hemorrhage. Material and methods The present study included seven patients (three men and four women aged 40-56 y) who underwent 3D print–assisted hematoma puncture drainage between June 2016 and March 2018 at Binzhou Medical University Hospital. The amount of brainstem hemorrhage was 15-47 mL. We analyzed the basic surgical conditions, deviation distance, and postoperative clinical improvement. Results In all cases, the operation was completed successfully; no patient died or contracted an infection intraoperatively. The end of the puncture tube was located in the hematoma cavity in all cases. The deviation distance ranged from 2.5 to 7.2, and this distance gradually reduced with improvements in the technique. The hematoma drainage achieved satisfactory postoperative outcomes, with improvements in symptoms such as respiratory failure and hyperthermia. Conclusions Use of a 3D-printed navigation mold for puncture drainage of brainstem hemorrhage realized the purpose of individualized and precision medicine, which is important in maintaining the vital signs of patients with severe brainstem hemorrhage.

Multicolor lanthanide-doped upconversion nanoparticles have attracted extensive interest due to their application in biosensing, bioimaging, and therapeutics. Herein, a facile strategy of inert gadolinium or yttrium ion doping is proposed to implement tunable multicolor upconversion luminescence in a conventional single red emitting KMnF3 matrix through engineering the local crystal structure and controlling the energy exchanging transfer process. Variation of the Gd3+ or Y3+ doping content in the KMnF3:Yb3+/Er3+ lattice induces a gradual morphological transformation from cube to polyhedron, which arises from the increased lattice binding. The enlarged crystal cell size and the engineered local crystal structure enable the confinement of energy transfer as well as back transfer between Er3+ emitters and Mn2+ ions. Moreover, the partial replacement of Mn2+ ions by Gd3+ or Y3+ ions also weakens the intense interaction between Er3+ and Mn2+ ions. Based on the above functions caused by the precise control of the inert ion doping amount, a palette of multicolor UC luminescence shifting from red to green can be produced and immediately recognized by the naked eye. The results here provide the possibility of realizing simultaneous control of the physical dimensions as well as the luminescence properties of lanthanide-doped upconversion systems.

Automatic modulation classification (AMC) is a key technology of cognitive radio used in non-cooperative communication. Recently, deep learning has been applied to AMC tasks. In this paper, an AMC scheme based on deep learning is proposed, which combines random erasing and attention mechanism to achieve high classification accuracy. Firstly, we propose two data augmentation methods, random erasing at sample level and random erasing at amplitude/phase (AP) channel level. The former replaces training samples with noise information, while the latter replaces AP channel information of training samples with noise information. Erased data segments are randomly stitched to enable training data expansion. Training data of different qualities enables deep learning model to have stronger generalization capability and higher robustness. Then, we propose a single-layer Long Short-Term Memory (LSTM) model based on attention mechanism. In the first part of this model, we propose the signal embedding, which enables the input to contain modulation information more comprehensively and accurately. Then hidden state output by LSTM is input into the attention module, and weighting is applied to the hidden state to help the LSTM model capture the temporal features of modulated signals. Compared to a model without attention mechanism, this model has faster convergence speed and better classification performance. Lastly, we propose a random erasing-based test time augmentation (RE-TTA) method. Test data is randomly erased for multiple times and classification results are comprehensively evaluated, in order to further improve classification accuracy. Experimental results on dataset RML2016.10a show that classification accuracy of the proposed scheme is competitive compared with the state-of-the-art methods.

Background: Although the prostate-specific antigen (PSA) testing was widely used for early detection of prostate cancer (PCa), it is difficult for PSA to distinguish the PCa from benign prostatic hyperplasia (BPH) patients. Emerging evidence has shown that microRNA (miRNA) was a promising biomarker for PCa screening. Methods: We applied miRNA profiling from microarray or high-throughput sequencing in Gene Expression Omnibus (GEO) and The Cancer Genome Atlas (TCGA) databases to identify the differentially expressed miRNAs in PCa patients (n = 1,017) and controls (n = 413). Then, qRT-PCR analysis was used to validate the expression of candidate miRNAs in our independent cohort, include 66 PCa cases and 63 BPH patients diagnosed by biopsy. The area under the receiver operating characteristic curve (AUC) was conducted to evaluate the diagnostic efficacy of miRNAs and PSA. Results: In the microarray analysis, we identified two consistently differently expressed miRNAs (miR-103a-3p and let-7f-5p) between PCa patients and controls. In the subsequent qRT-PCR analysis, the let-7f-5p was upregulated in PCa compared with BPH patients (P=2.17E-07), but no statistically difference of miR-103a-3p expression was observed (P=0.456). The AUC was 0.904 for combination of lef-7f-5p and PSA, which was significantly higher than that of let-7f-5p (0.782) or PSA (0.795) alone (P=7.55E-04 and P=2.09E-03, respectively). Besides, the results of decision curve analysis and nomogram prediction indicated that combination of let-7f-5p and PSA had superior predictive accuracy of PCa. Conclusions: Our study suggests that plasma let-7f-5p combining PSA could serve as potentially diagnostic biomarkers for PCa.

Automated methods for detecting prostate cancer and distinguishing indolent from aggressive disease on Magnetic Resonance Imaging (MRI) could assist in early diagnosis and treatment planning. Existing automated methods of prostate cancer detection mostly rely on ground truth labels with limited accuracy, ignore disease pathology characteristics observed on resected tissue, and cannot selectively identify aggressive (Gleason Pattern≥4) and indolent (Gleason Pattern=3) cancers when they co-exist in mixed lesions. In this paper, we present a radiology-pathology fusion approach, CorrSigNIA, for the selective identification and localization of indolent and aggressive prostate cancer on MRI. CorrSigNIA uses registered MRI and whole-mount histopathology images from radical prostatectomy patients to derive accurate ground truth labels and learn correlated features between radiology and pathology images. These correlated features are then used in a convolutional neural network architecture to detect and localize normal tissue, indolent cancer, and aggressive cancer on prostate MRI. CorrSigNIA was trained and validated on a dataset of 98 men, including 74 men that underwent radical prostatectomy and 24 men with normal prostate MRI. CorrSigNIA was tested on three independent test sets including 55 men that underwent radical prostatectomy, 275 men that underwent targeted biopsies, and 15 men with normal prostate MRI. CorrSigNIA achieved an accuracy of 80% in distinguishing between men with and without cancer, a lesion-level ROC-AUC of 0.81±0.31 in detecting cancers in both radical prostatectomy and biopsy cohort patients, and lesion-levels ROC-AUCs of 0.82±0.31 and 0.86±0.26 in detecting clinically significant cancers in radical prostatectomy and biopsy cohort patients respectively. CorrSigNIA consistently outperformed other methods across different evaluation metrics and cohorts. In clinical settings, CorrSigNIA may be used in prostate cancer detection as well as in selective identification of indolent and aggressive components of prostate cancer, thereby improving prostate cancer care by helping guide targeted biopsies, reducing unnecessary biopsies, and selecting and planning treatment.

A fractured implant is considered a catastrophic failure that leads to the loss of the implant and the prosthesis. Available methods of implant removal include the reverse screw technique, use of trephines, or osteotomies around the implant. In case of a fractured implant, the access hole for the reverse screw technique is impossible, leading to the need for an osteotomy. When the apical part of the fractured implant is embedded in bone, finding the piece may lead to a more ample osteotomy and significant bone loss, complicating future implant placement. This technique presented utilized a CAD-CAM surgical template that was designed with the purpose of improving accuracy in finding the fractured part with minimal osteotomy, allowing for simultaneous placement of a new implant in the same site, with additional bone graft, utilizing the same template.

PURPOSE To evaluate the fracture resistance behaviors of titanium-zirconium, one-piece zirconia, and two-piece zirconia implants restored by zirconia crowns and different combinations of abutment materials (zirconia and titanium) and retention modes (cement-retained and screw-retained zirconia crowns). MATERIAL AND METHODS Three research groups (n=12) were evaluated according to combinations of abutment material, retention mode, and implant type. In the control group (TTC), titanium-zirconium implants (∅ 4.1 mm RN, 12 mm, Roxolid; Straumann USA, Andover, MA) and prefabricated titanium abutments (RN synOcta Cementable Abutment, H 5.5 mm; Straumann USA) were used to support cement-retained zirconia crowns. In the second group (ZZC), one-piece zirconia implants (PURE Ceramic Implant Monotype, ∅ 4.1 mm RD, 12 mm, AH 5.5 mm; Straumann USA) were used to support cement-retained zirconia crowns. In the third group (ZTS), two-piece zirconia implants (PURE Ceramic Implant, ∅ 4.1 mm RD, 12 mm) and prefabricated titanium abutments (CI RD PUREbase Abutment, H 5.5 mm) were used to support screw-retained zirconia crowns. All zirconia crowns were manufactured in the same anatomic contour with a 5-axis dental mill and blended 3 and 5 mol% yttria-stabilized zirconia (LayZir A2). Implants were inserted into specimen holders made of epoxy resin-glass fiber composite. All specimens were then subject to artificial aging in an incubator at 37°C for 90 days. Fracture resistance of specimen assemblies was tested under static compression load using the universal testing machine based on ISO14801 specification. The peak fracture loads were recorded. All specimens were examined at the end of the test microscopically at 5× and 10× magnification to detect any catastrophic failures. Comparisons between groups for differences in peak fracture load were made using Wilcoxon Rank Sum tests and Weibull and Kaplan-Meier survival analyses (α = 0.05). RESULTS The TTC group (942 ± 241 N) showed significantly higher peak fracture loads than the ZZC (645 ± 165 N) and ZTS (650 ± 124 N) groups (p < 0.001), while there was no significant difference between ZZC and ZTS groups (p = 0.940). The survival probability based on the Weibull and Kaplan-Meier models demonstrated different failure molds between titanium-zirconium and zirconia implants, in which the TTC group remained in the plastic strain zone for a longer period before fracture when compared to ZZC and ZTS groups. Catastrophic failures, with implant fractures at the embedding level or slightly below, were only observed in the ZZC and ZTS groups. CONCLUSIONS Cement-retained zirconia crowns supported by titanium-zirconium implants and prefabricated titanium abutments showed superior peak fracture loads and better survival probability behavior. One-piece zirconia implants with cement-retained zirconia crowns and two-piece zirconia implants with screw-retained zirconia crowns on prefabricated titanium abutment showed similar peak fracture loads and survival probability behavior. Titanium-zirconium and zirconia implants could withstand average intraoral mastication loads in the incisor region. This study was conducted under static load, room temperature (21.7°C), and dry condition, and full impacts of intraoral hydrothermal aging and dynamic loading conditions on the zirconia implants should be considered and studied further.

Statement of problem Three-dimensional radiographic assessment of buccal bone thickness and its integrity from cone beam computed tomography (CBCT) plays an essential role in immediate implant placement. However, the accuracy of CBCT measurements for the assessment of buccal bone thickness adjacent to maxillary anterior teeth is not well understood. Purpose The purpose of this observational study was to evaluate the accuracy of measuring the buccal bone thickness of maxillary anterior teeth from CBCT compared with direct measurement from histologic sections. A secondary objective was to analyze whether a minimal level of buccal bone thickness of maxillary anterior teeth can be detected from the CBCT scan. Material and methods Five embalmed human cadavers with a complete anterior dentition were included in this study, providing 30 teeth for evaluation. After preparing reference notches at the gingival margin of each tooth, the anterior segments were scanned. The buccal bone thickness at 3, 5, and 7 mm from the notches was measured on the cross-sections obtained from the CBCT and histomorphometric images for a total of 90 sites. The CBCT measurements were compared with the histomorphometric measurements, and their agreement was assessed by using the Bland-Altman plots and intraclass correlation coefficients. The sensitivity and specificity of buccal bone detection were calculated from the CBCT scan. Results Histologic examination showed absence of the buccal bone in 29 sites (32%). The mean ±standard deviation thickness of the buccal bone was 0.52 ±0.05 mm (range: 0 to 1.97 mm) from the CBCT analysis and 0.40 ±0.05 mm (range: 0 to 1.67 mm) from histology. Measurements obtained from the CBCT sections significantly overestimated the buccal bone thickness when compared with the histologic evaluation (P=.001). The intraclass correlation coefficient of buccal bone thickness between the CBCT and histology was ≤0.53, an agreement considered as poor. The sensitivity of the CBCT as a diagnostic tool to detect the presence or absence of the buccal bone was 75.4%, and the specificity was 65.5%. Conclusions The buccal bone thickness of maxillary anterior teeth was less than 2 mm at all sites as measured with both CBCT and histology evaluations. CBCT measurements had relatively low accuracy and reliability for the measurement of buccal bone thickness. These findings should be considered when using CBCT as a measuring tool for thin bone structures.

INTRODUCTION AND OBJECTIVE:MRI is a powerful tool for prostate cancer diagnosis, yet interobserver variability remains problematic and false positive and false negative findings are common. Trainin...

It is important for aquaculture monitoring, scientific planning, and management to extract offshore aquaculture areas from medium-resolution remote sensing images. However, in medium-resolution images, the spectral characteristics of offshore aquaculture areas are complex, and the offshore land and seawater seriously interfere with the extraction of offshore aquaculture areas. On the other hand, in medium-resolution images, due to the relatively low image resolution, the boundaries between breeding areas are relatively fuzzy and are more likely to ‘adhere’ to each other. An improved U-Net model, including, in particular, an atrous spatial pyramid pooling (ASPP) structure and an up-sampling structure, is proposed for offshore aquaculture area extraction in this paper. The improved ASPP structure and up-sampling structure can better mine semantic information and location information, overcome the interference of other information in the image, and reduce ‘adhesion’. Based on the northeast coast of Fujian Province Sentinel-2 Multispectral Scan Imaging (MSI) image data, the offshore aquaculture area extraction was studied. Based on the improved U-Net model, the F1 score and Mean Intersection over Union (MIoU) of the classification results were 83.75% and 73.75%, respectively. The results show that, compared with several common classification methods, the improved U-Net model has a better performance. This also shows that the improved U-Net model can significantly overcome the interference of irrelevant information, identify aquaculture areas, and significantly reduce edge adhesion of aquaculture areas.

In this paper, a terahertz band transceiver with agile beam steering is proposed. The system works in 220GHz frequency band and consists of double feed horns and a shared reflector. It transmits a single frequency at 216GHz, and receives from 213GHz-219GHz except 216GHz. Test results show that the switching time between two beams of the terahertz agile beam-steering system is only ~30ns.