An Adaptive Infrared Small-Target-Detection Fusion Algorithm Based on Multiscale Local Gradient Contrast for Remote Sensing.

Space vehicles such as missiles and aircraft have relatively long tracking distances. Infrared (IR) detectors are used for small target detection. The target presents point target characteristics, which lack contour, shape, and texture information. The high-brightness cloud edge and high noise have an impact on the detection of small targets because of the complex background of the sky and ground environment. Traditional template-based filtering and local contrast-based methods do not distinguish between different complex background environments, and their strategy is to unify small-target template detection or to use absolute contrast differences; so, it is easy to have a high false alarm rate. It is necessary to study the detection and tracking methods in complex backgrounds and low signal-to-clutter ratios (SCRs). We use the complexity difference as a prior condition for detection in the background of thick clouds and ground highlight buildings. Then, we use the spatial domain filtering and improved local contrast joint algorithm to obtain a significant area. We also provide a new definition of gradient uniformity through the improvement of the local gradient method, which could further enhance the target contrast. It is important to distinguish between small targets, highlighted background edges, and noise. Furthermore, the method can be used for parallel computing. Compared with the traditional space filtering algorithm or local contrast algorithm, the flexible fusion strategy can achieve the rapid detection of small targets with a higher signal-to-clutter ratio gain (SCRG) and background suppression factor (BSF).

Exploring Research on the Construction and Application of Knowledge Graphs for Aircraft Fault Diagnosis.

Fault diagnosis is crucial for repairing aircraft and ensuring their proper functioning. However, with the higher complexity of aircraft, some traditional diagnosis methods that rely on experience are becoming less effective. Therefore, this paper explores the construction and application of an aircraft fault knowledge graph to improve the efficiency of fault diagnosis for maintenance engineers. Firstly, this paper analyzes the knowledge elements required for aircraft fault diagnosis, and defines a schema layer of a fault knowledge graph. Secondly, with deep learning as the main method and heuristic rules as the auxiliary method, fault knowledge is extracted from structured and unstructured fault data, and a fault knowledge graph for a certain type of craft is constructed. Finally, a fault question-answering system based on a fault knowledge graph was developed, which can accurately answer questions from maintenance engineers. The practical implementation of our proposed methodology highlights how knowledge graphs provide an effective means of managing aircraft fault knowledge, ultimately assisting engineers in identifying fault roots accurately and quickly.

Green winner determination method based on environmental performance and minimum adjustment consensus in 4PL transportation service procurement.

Due to the intensified environmental protection consciousness of enterprises and consumers, the green winner determination (GWD) considering environmental performance becomes very important for the 4PL transportation service procurement. In this paper, a new GWD method is studied, which considers different types of attributes including those related to environmental performance and the consensus reaching process (CRP). To characterize multiple types of attributes, linguistic terms, interval numbers, and crisp numbers are combined. To achieve an acceptable consensus level among linguistic evaluations given by different experts, a minimum adjustment consensus model is constructed. And on this basis, an interactive CRP is proposed. Integrating the heterogeneous information addressing process and the CRP, a HC-VIKOR method is developed to promote the 4PL's operational efficiency and service quality. Further, a numerical example is designed to demonstrate the effectiveness of the proposed method. Sensitivity analysis reveals that both the acceptable consensus threshold and the weight of group utility have a significant influence on the winner determination result. Comparison analysis shows that the proposed method outperforms the existing methods. Our study not only extends the traditional winner determination but also provides decision support for the 4PL to provide transportation services efficiently.

Detection of Highway Pavement Damage Based on a CNN Using Grayscale and HOG Features.

Aiming at the demand for rapid detection of highway pavement damage, many deep learning methods based on convolutional neural networks (CNNs) have been developed. However, CNN methods with raw image data require a high-performance hardware configuration and cost machine time. To reduce machine time and to apply the detection methods in common scenarios, the CNN structure with preprocessed image data needs to be simplified. In this work, a detection method based on a CNN and the combination of the grayscale and histogram of oriented gradients (HOG) features is proposed. First, the Gamma correction was employed to highlight the grayscale distribution of the damage area, which compresses the space of normal pavement. The preprocessed image was then divided into several unit cells, whose grayscale and HOG were calculated, respectively. The grayscale and HOG of each unit cell were combined to construct the grayscale-weighted HOG (GHOG) feature patterns. These feature patterns were input to the CNN with a specific structure and parameters. The trained indices suggested that the performance of the GHOG-based method was significantly improved, compared with the traditional HOG-based method. Furthermore, the GHOG-feature-based CNN technique exhibited flexibility and effectiveness under the same accuracy, in comparison to those deep learning techniques that directly deal with raw data. Since the grayscale has a definite physical meaning, the present detection method possesses a potential application for the further detection of damage details in the future.

Application of U-Net with Global Convolution Network Module in Computer-Aided Tongue Diagnosis.

The rapid development of intelligent manufacturing provides strong support for the intelligent medical service ecosystem. Researchers are committed to building Wise Information Technology of 120 (WIT 120) for residents and medical personnel with the concept of simple smart medical care and through core technologies such as Internet of Things, Big Data Analytics, Artificial Intelligence, and microservice framework, to improve patient safety, medical quality, clinical efficiency, and operational benefits. Among them, how to use computers and deep learning technology to assist in the diagnosis of tongue images and realize intelligent tongue diagnosis has become a major trend. Tongue crack is an important feature of tongue states. Not only does change of tongue crack states reflect objectively and accurately changed circumstances of some typical diseases and TCM syndrome but also semantic segmentation of fissured tongue can combine the other features of tongue states to further improve tongue diagnosis systems' identification accuracy. Although computer tongue diagnosis technology has made great progress, there are few studies on the fissured tongue, and most of them focus on the analysis of tongue coating and body. In this paper, we do systematic and in-depth researches and propose an improved U-Net network for image semantic segmentation of fissured tongue. By introducing the Global Convolution Network module into the encoder part of U-Net, it solves the problem that the encoder part is relatively simple and cannot extract relatively abstract high-level semantic features. Finally, the method is verified by experiments. The improved U-Net network has a better segmentation effect and higher segmentation accuracy for fissured tongue image dataset. It can be used to design a computer-aided tongue diagnosis system.

Light absorption and hydrophobicity of a polystyrene/multiwall carbon nanotube composite with surface nanostructures.

This paper describes an investigation into how combined carbon nanotube doping and surface nanostructuring affects the surface properties of polystyrene. Multiwall carbon nanotubes (MWCNTs) have unique anisotropic electrical properties that can be utilized for light absorption, electromagnetic shielding and nanoscale electostatic forces. Polystyrene was doped with 5 wt% MWCNTs and the resulting composite was wetted onto a porous anodic alumina template to form a nanostructure surface of nanotubes. Scanning electron microscopy revealed a hierarchical surface structure with the composite nanotubes bundled together as the MWCNTs increased the attractive forces between the composite nanotubes. Water droplet testing revealed that this hierarchical surface structure was superhydrophobic. Though the presence of the MWCNTs caused a direct increase in absorption, the hierarchical surface structure increased reflection. The addition of 5 wt% of the anionic surfactant Sodium Dodecyl Benzene Sulfonate to ensure MWCNT dispersal did not significantly change hydrophobicity or light absorption despite the hierarchical surface structure becoming finer. The created composite has potential use as a surface layer on an organic surface cell as it provides reduced cleaning needs and electrical disturbance but further work is required to reduce the reflection.

Cross-Domain Transfer Learning for PCG Diagnosis Algorithm.

Cardiechema is a way to reflect cardiovascular disease where the doctor uses a stethoscope to help determine the heart condition with a sound map. In this paper, phonocardiogram (PCG) is used as a diagnostic signal, and a deep learning diagnostic framework is proposed. By improving the architecture and modules, a new transfer learning and boosting architecture is mainly employed. In addition, a segmentation method is designed to improve on the existing signal segmentation methods, such as R wave to R wave interval segmentation and fixed segmentation. For the evaluation, the final diagnostic architecture achieved a sustainable performance with a public PCG database.

Analyzing Liver Surface Indentation for In Vivo Refinement of Tumor Location in Minimally Invasive Surgery.

Manual palpation to update the position of subsurface tumor(s) is a normal practice in open surgery, but is not possible through the small incisions of minimally invasive surgery (MIS). This paper proposes a method that has the potential to use a simple constant-force indenter and the existing laparoscopic camera for tumor location refinement in MIS. The indenter floats with organ movement to generate a static surface deformation on the soft tissue, resolving problems of previous studies that require complicated measurement of force and displacement during indentation. By analyzing the deformation profile, we can intraoperatively update the tumor's location in real-time. Indentation experiments were conducted on healthy and "diseased" porcine liver specimens to obtain the deformation surrounding the indenter site. An inverse finite element (FE) algorithm was developed to determine the optimal material parameters of the healthy liver tissue. With these parameters, a computational model of tumorous tissue was constructed to quantitatively evaluate the effects of the tumor location on the induced deformation. By relating the experimental data from the "diseased" liver specimen to the computational results, we estimated the radial distance between the tumor and the indenter, as well as the angular position of the tumor relative to the indenter.

Mechanical characterization of porcine liver properties for computational simulation of indentation on cancerous tissue.

An accurate characterization of soft biological tissue properties is essential for a realistic simulation of surgical procedures. Unconfined uniaxial compression tests with specimens affixed to the fixtures are often performed to characterize the stress-stretch curves of soft biological tissues, with which the material parameters can be obtained. However, the constrained boundary condition causes non-uniform deformation during the uniaxial test, posing challenges for accurate measurement of tissue deformation. In this study, we measured the deformation locally at the middle of liver specimens and obtained the corresponding stress-stretch curves. Since the effect of the constrained boundary condition on the local deformation of specimen is minimized, the stress-stretch curves are thus more realistic. Subsequently, we fitted the experimental stress-stretch curves with several constitutive models and found that the first-order Ogden hyperelastic material model was most suitable for characterizing the mechanical properties of porcine liver tissues. To further verify the characterized material properties, we carried out indentation tests on porcine liver specimens and compared the experimental data with computational results by using finite element simulations. A good agreement was achieved. Finally, we constructed computational models of liver tissue with a tumor and investigated the effect of the tumor on the mechanical response of the tissue under indentation. The computational results revealed that the liver specimen with tumor shows a stiffer response if the distance between the tumor and the indenter is small.

Multifunctional Water Drop Energy Harvesting and Human Motion Sensor Based on Flexible Dual-Mode Nanogenerator Incorporated with Polymer Nanotubes.

In the world of increasing energy consumption, nanogenerators have shown great potential for energy harvesting and self-powered portable electronics. Herein, a flexible and dual-mode triboelectric nanogenerator (TENG) combining both vertical contact-separation and single electrical modes has been developed to convert environmental mechanical energy into electricity using highly encapsulated and multifunctional strategies. By introducing the polymer melt wetting technique, polymer nanotubes are fabricated on the surface of the TENG, which provides self-cleaning and hydrophobic features beneficial for water drop energy harvesting using the device. In such mechanical energy harvesting, the maximum output power of 0.025 mW and the open-circuit voltage of 41 V can be achieved. By designing the dimensions of the device, the dual-mode TENG is utilized as a self-powered sensor to detect human body motions such as phalanges' movement of fingers. The fabricated dual-mode TENG promotes the development of energy-harvesting and self-powered human motion sensors for artificial intelligent prosthetics, human kinematics, and human body recovery treatment.

eTPM: A Trusted Cloud Platform Enclave TPM Scheme Based on Intel SGX Technology.

Today cloud computing is widely used in various industries. While benefiting from the services provided by the cloud, users are also faced with some security issues, such as information leakage and data tampering. Utilizing trusted computing technology to enhance the security mechanism, defined as trusted cloud, has become a hot research topic in cloud security. Currently, virtual TPM (vTPM) is commonly used in a trusted cloud to protect the integrity of the cloud environment. However, the existing vTPM scheme lacks protections of vTPM itself at a runtime environment. This paper proposed a novel scheme, which designed a new trusted cloud platform security component, 'enclave TPM (eTPM)' to protect cloud and employed Intel SGX to enhance the security of eTPM. The eTPM is a software component that emulates TPM functions which build trust and security in cloud and runs in 'enclave', an isolation memory zone introduced by SGX. eTPM can ensure its security at runtime, and protect the integrity of Virtual Machines (VM) according to user-specific policies. Finally, a prototype for the eTPM scheme was implemented, and experiment manifested its effectiveness, security, and availability.

Enhanced nanoflow behaviors of polymer melts using dispersed nanoparticles and ultrasonic vibration.

In the micro/nano fabrication of polymer nanostructures, a key factor is the favorable nanoflow behavior of polymer melts. Compared with the fluidic hydrodynamics of simple liquids through micro- or macrochannels, the nanoflow behavior of polymer melts, however, is affected much more by nanoscale effects and surface interactions. Therefore, achieving a favorable nanoflow of polymer melts in nanochannels is the key to fabricate high quality polymer nanoproducts. In this paper, the improved nanoflow behaviors of polystyrene melts in ordered porous alumina templates with the addition of nanoparticles and ultrasonic vibration were reported for the first time. Compared with bulk polystyrene (PS), the nanoflow rate of PS melts was enhanced when nanoparticles, such as surface-modified nano-silica (nano-SiO(2)) or ß-cyclodextrin (ß-CD), were added in a dispersed phase into a polystyrene matrix due to the decrease of the melts' viscosity caused by interactions between nanoparticles and PS segments. The enhancement action of ß-CD was observed to be more significant than that of nano-SiO(2) based on the adsorption and the supramolecular self-assembly interactions between PS segments and ß-CD. The enhanced nanoflow rate has shown to be more pronounced under ultrasonic vibration than those of the static condition and the low frequency vibration attributed to the synergetic effects of mechanical vibration and ultrasonic oscillation. The nanoflow rate of polymer melts increases with the gradual increase of vibration frequency. The optimal nanoflow behavior can be obtained by simultaneously adding ß-CD as dispersed phase into PS matrix and applying ultrasonic vibration in one nanoflow system. These new findings will help the preparation of polymer-based functional nanocomposites, ultrasonic vibration-assisted nanofluidics, and micro/nano injection molding etc.