Joint Supervision Research Articles

A Hybrid Multimodal Fusion Framework for sEMG-ACC-Based Hand Gesture Recognition

Hand gesture recognition (HGR) based on surface electromyogram (sEMG) and accelerometer (ACC) signals has attracted increasing attention. The design of an effective multimodal fusion strategy plays a vital role. Existing studies fuse sEMG and ACC either in a low-level data space or in a high-level decision space. These fusion strategies result in insufficiently representing intramodal specificity and intermodal association simultaneously. Meanwhile, current fusion methods tend to neglect multiscale characteristics and hierarchical relationships and rarely specifically take into account the possible low discrimination in similar gestures. To address these issues, we propose a novel and practical hybrid fusion (HyFusion) model with multiscale attention and metric learning, to improve the performance of HGR based on sEMG and ACC. In HyFusion, a fusion framework including parallel intramodal and intermodal branches is first designed to adequately explore intramodal specificity and intermodal association simultaneously. Furthermore, the fusion of multiscale hierarchical features in each branch is conducted through a multiscale spatial attention (SA) module to generate more effective features. Finally, with the joint supervision of softmax and metric learning loss, HyFusion extracts features that maximize intraclass aggregation and interclass differentiation, thus particularly facilitating distinguishing similar gestures. The proposed HyFusion is validated on three public datasets (Ninapro DB2, DB3, and DB7), involving transradial amputees and healthy subjects. The results demonstrate that HyFusion achieves state-of-the-art performance.

Short seller report and stock performance Empirical evidence from US-listed Chinese firms

In recent years, there have been a number of Chinese companies listing in the US market. At the same time, many of them delist from the US market. An important reason behind this is the issue of financial fraud. Most of these cases are due to short seller reports by activist short sellers. After short selling, financial and auditing problems are revealed, causing the share prices of these companies to collapse. This has raised concerns among US regulators about the quality of Chinese companies' auditing and prompted joint supervision by Chinese and US regulators. This paper uses Chinese companies listed in the US as samples to study the long and short term fluctuations of these companies' stock prices before and after the short seller reports were issued. After the short seller reports are released, the results show that the stock price can fall significantly in the short term, with the average CAR reaching 10%. Long term share prices are less affected, with 45% of short seller reports associating with negative price changes. This paper also examines the factors that influence the market's reaction to short seller reports. Companies that choose the accounting firms from the Big 4 see smaller share price declines in the short run compared to those that do not. In addition, small companies are more likely to recover from such negative events in the long run than large ones. The study of short selling reports is important. Some limitations and restrictions make it difficult for US regulators to fully monitor all Chinese companies. Therefore, individual investors can only obtain information through these short-selling reports, and then change their investment decisions to protect their interests.

Detection method of metal surface defect based on joint-supervision strategy

Detection of metal surface defect plays an important role in industry field. In order to detect the metal surface defects efficiently, an end-to-end joint supervision strategy defect detection algorithm network is designed, which contains two steps. Firstly, a segmentation network is to learn and train about targets labeled by pixel level. Secondly, a detection network is proposed to detect targets labeled by image level, considering the results of joint segmentation network. The joint loss function is applied to generate segmentation and detection results in the two networks. We have evaluated the proposed algorithm in KolektorSDD-a data set of industrial quality detection. Comparing with the traditional methods, better results in segmentation effect and detection accuracy are presented. The proposed algorithm is highly engineering valuable, and providing a research foundation for metal defect detection in a variety of industrial field.

FERA-Net: A Building Change Detection Method for High-Resolution Remote Sensing Imagery Based on Residual Attention and High-Frequency Features

Buildings can represent the process of urban development, and building change detection can support land use management and urban planning. However, existing building change detection models are unable to extract multi-scale building features effectively or fully utilize the local and global information of the feature maps, such as building edges. These defections affect the detection accuracy and may restrict further applications of the models. In this paper, we propose the feature-enhanced residual attention network (FERA-Net) to improve the performance of the ultrahigh-resolution remote sensing image change detection task. The FERA-Net is an end-to-end network with a U-shaped encoder–decoder structure. The Siamese network is used as the encoder with an attention-guided high-frequency feature extraction module (AGFM) extracting building features and enriching detail information, and the decoder applies a feature-enhanced skip connection module (FESCM) to aggregate the enhanced multi-level differential feature maps and gradually recover the change feature maps in this structure. The FERA-Net can generate predicted building change maps by the joint supervision of building change information and building edge information. The performance of the proposed model is tested on the WHU-CD dataset and the LEVIR-CD dataset. The experimental results show that our model outperforms the state-of-the-art models, with 93.51% precision and a 92.48% F1 score on the WHU-CD dataset, and 91.57% precision and an 89.58% F1 score on the LEVIR-CD dataset.

A Siamese Network Combining Multiscale Joint Supervision and Improved Consistency Regularization for Weakly Supervised Building Change Detection

Building change detection (BCD) from remote sensing images is essential in various practical applications. Recently, inspired by the achievement of deep learning in semantic segmentation (SS), methods that treat the BCD problem as a binary SS task using deep siamese networks have attracted increasing attention. However, similar to their counterparts, these approaches still face the challenge of collecting massive pixel-level annotations. To address this issue, this article presents a novel weakly supervised method for BCD from remote sensing images using image-level labels. The proposed method elaborately designs a siamese network to integrate a multiscale joint supervision (MJS) module and an improved consistency regularization (ICR) module into a unified framework to improve the so-called class activation maps (CAMs), which is vital for producing high-quality pseudomasks using image-level annotations to support pixel-level BCD. To be specific, the MSJ is used for generating refined multiscale CAMs to well capture changes at different scales corresponding to various buildings of varying sizes. The ICR contributes to improving the consistency of CAMs to highlight the boundaries of changed buildings. Extensive experiments on two public BCD datasets have demonstrated that the proposed method outperforms the current state-of-the-art approaches. Furthermore, the visual detection maps also indicate that the proposed method can achieve scale-adaptive change detection results and preserve object boundaries more effectively.

Semantic-aware multi-task learning for image aesthetic quality assessment

In recent years, image aesthetic quality assessment has attracted considerable attention due to the massive growth of digital images in social platforms and the Internet. However, automatically assessing aesthetic quality of an image is a challenging task, because image aesthetic is affected by various factors, and the criteria for judging the aesthetic of images with diverse semantic information are different. To this end, a Semantic-Aware Multi-task convolution neural network (SAM-CNN) for evaluating image aesthetic quality is proposed in this paper. The network can fuse intermediate features of different layers at different scales in CNN to obtain a more comprehensive and accurate aesthetic expression, under the joint supervision of image aesthetic quality assessment task and semantic classification task in a multi-task learning manner. Besides, by applying the attention mechanism, semantic information with a large receptive field extracted from deep layers is utilised to guide the network to focus on the key parts of features to be fused, to improve the effectiveness of feature fusion. Experimental results on the AVA dataset and Photo.net dataset demonstrate the effectiveness and superiority of the proposed SAM-CNN.

The place of myofascial syndrome in the genesis of headaches and facial pains

The article discusses the patterns of development and the main features of myofascial syndrome. Emphasis is placed on the myofascial syndrome involving head and face muscles with characterization of masks of the syndrome: irradiation zones of trigger point pain in the skeletal muscles of the cervical region are described (important role of the sternocleidomastoid muscle is emphasized), in the facial muscles and masticatory muscles. Trigger point properties are covered in detail, including painful and non-painful manifestations, such as tinnitus and congestion in the ear, dizziness, vertigo and hearing loss; as well as local vegetative symptoms. When diagnosing myofascial syndrome, it is necessary to specify in detail the anamnestic data (the time and conditions for the onset of the first manifestations), as well as to specify as many characteristics of pain as possible (the circumstances of its provocation and relief, the duration of the attack, the pain modality). The most important role belongs to palpation of the muscles with the definition of trigger points and muscle cords. The basic principles of therapy for myofascial syndrome are given: anesthesia, relaxation and stretching. Further, specific methods of drug, physiotherapeutic and manual procedures on the affected muscles are analyzed in detail. Two clinical cases from our own practice are presented, demonstrating the features of the myofascial syndrome clinical picture formation in the face area and the possibility of interrupting the pain phenomenon and non-painful manifestations by inactivating muscle triggers. The importance of joint supervision of a patient with myofascial syndrome by a multidisciplinary medical team, including, if necessary, not only neurologist and osteopath, but also an ENT doctor and a dentist, is emphasized. In conclusion, it was concluded that it is necessary to develop recommendations at the federal level for the diagnosis and treatment of myofascial syndrome.

Underwater Acoustic Target Recognition Based on Attention Residual Network.

Underwater acoustic target recognition is very complex due to the lack of labeled data sets, the complexity of the marine environment, and the interference of background noise. In order to enhance it, we propose an attention-based residual network recognition method (AResnet). The method can be used to identify ship-radiated noise in different environments. Firstly, a residual network is used to extract the deep abstract features of three-dimensional fusion features, and then a channel attention module is used to enhance different channels. Finally, the features are classified by the joint supervision of cross-entropy and central loss functions. At the same time, for the recognition of ship-radiated noise in other environments, we use the pre-training network AResnet to extract the deep acoustic features and apply the network structure to underwater acoustic target recognition after fine-tuning. The two sets of ship radiation noise datasets are verified, the DeepShip dataset is trained and verified, and the average recognition accuracy is 99%. Then, the trained AResnet structure is fine-tuned and applied to the ShipsEar dataset. The average recognition accuracy is 98%, which is better than the comparison method.

Research on integrated joint supervision and control system of shared integrated substation

By analyzing the related technical specifications and principles of state and electric power industry standard for supervision and control systems of substation, energy storage power station, photovoltaic power station, electric vehicle charging station and data cen..er. This paper puts forward the structure form and function requirements of the integrated joint supervision and control system for the sharing integrated substation which adopts a hierarchical partition structure. By analyzing various types of data in the station, it aims to realize multi-type functions such as operation monitoring, fault diagnosis, multi-station control and information management of each subsystem. Considering the substation is the core of the shared integrated substation, this paper puts forward a modular design scheme of the supervision and control system. Based on the supervision and control system of the substation, it connects all kinds of the subsystem such as the monitoring systems of electric vehicle charging station, photovoltaic power station, energy storage station and data center through unified interface, standardization protocol. The subsystem modules integrate to the unified platform through the security zone, and uses the unified strategy to upload information and issue instructions. According to different application scenarios, subsystem modules can be plug and play.

Dense context distillation network for semantic parsing of oblique UAV images

Semantic segmentation of oblique unmanned aerial vehicle (UAV) images serves as a foundation for many modern urban applications, such as road scene monitoring and semantic 3D modeling. However, objects in UAV images can vary intensely in size and undergo severe perspective distortion because of the oblique viewing style. Existing general segmentation models designed for ground and remote sensing images rarely considered these challenges specific to UAV images. Therefore, they have large difficulties in learning discriminative representation for simultaneously reasoning the extremely large and small objects in UAV images. In this paper, we propose a dense context distillation network (DCDNet) to learn distortion-robust feature representation for semantic segmentation of UAV images. The basic DCDNet is deployed as an dual-branch encoder–decoder architecture. To accomplish the goal of dense context distillation, DCDNet is first equipped with several cross-scale context selectors at different encoding stages to densely and selectively gather the useful context from low- to high-level dual-scale feature maps. A joint supervision is then applied to reinforce the learning of shallower features for distilling more low-level contexts that are vital to the reasoning of small or thin structures. A multi-scale feature aggregator is incorporated to adaptively fuse the long-range context during decoding, which absorbs the complementary merits of the dense context captured from feature maps of different levels. With the dense context distillation, DCDNet is more capable of offering the differently scaled objects with the required context for better learning and prediction. Extensive experiments on the challenging UAVid dataset demonstrate that our DCDNet can well adapt to the oblique UAV images, achieving a state-of-the-art segmentation performance with a mIoU score of 72.38%. • A DCDNet is proposed for semantic parsing of UAV images. • DCDNet offers enough context for reasoning the large and small road scene objects. • DCDNet achieves state-of-the-art segmentation performance.

The supervision and multi-sectoral guarantee mechanism of the global marine sulphur limit—assessment from Chinese shipping industry

To significantly reduce sulfur oxides emissions from fossil fuel-powered ships, reduce air pollution in ports and slow ocean acidification, the International Maritime Organization (IMO) has imposed the new 0.50%m/m limit (reduced from 3.50%m/m in the past) on sulphur in ships’ fuel oil. This has given rise to a host of issues regarding fuel replenishment operations, safe operation management, maritime regulation, and coordinated governance of air and climate. In response to ocean acidification and climate change, regulations on the use of low-sulfur oil or alternative fuels by ships greatly reduce sulfur oxide emissions, but have no significant impact on reducing greenhouse gas emissions. In fact, the refining process for low-sulfur fuels and the use of the gas cleaning system on ships both increase energy consumption and carbon dioxide emissions. To ensure the decarbonization process of shipping industry, there is an urgent need for a conceptual change in global ocean governance so as to promote the coordinated governance of air pollution and climate change. China’s conception of “a maritime community with a shared future” provides a new model for global ocean governance. The Chinese government has formulated regulations at different levels to promote the coordinated management of atmospheric pollutants and greenhouse gas emissions. Regarding supervision of sulfur oxide emissions from ships, this study proposes to build a multi-department collaborative supervision mechanism from marine fuel life cycle to enhance sulfur oxide monitoring and risk control capabilities. Specific measures of the proposed supervision mechanism include: the joint supervision of compliant fuel supply, the compliant fuel information disclosure platform, a joint law enforcement mechanism for atmospheric pollution, the ability of intelligent ship exhaust monitoring, and the construction of port power infrastructure.

Adversarially regularized joint structured clustering network

Deep clustering has achieved great success as its powerful ability to learn effective representation. Especially, graph network clustering has attracted more and more attention. Considering the great success of Graph Autoencoder (GAE) in encoding the graph structure and Deep Autoencoder (DAE) in extracting valuable representations from the data itself, in this paper, we construct an Adversarially regularized Joint Structured Clustering Network(AJSCN) by integrating GAE and DAE. The framework links GAE and DAE together by transferring the representation learned by DAE to the corresponding layer of GAE to alleviate the over-smoothing problem. Furthermore, the latent representation learned by GAE is enforced to match a prior distribution via an adversarial training scheme to avoid the free of any structure of latent space. We design a joint supervision mechanism to improve the clustering performance consisting of self-supervision and mutual supervision. The self-supervision is to learn more compact representations, and mutual-supervision makes different representations more consistent. Experiment results demonstrate the superiority of the proposed model against the state-of-the-art algorithms and achieve significant improvement on six benchmark datasets.

René Maunier (1915), Les idées sociologiques d’un philosophe arabe/The sociological ideas of an Arab philosopher in the 14th century

AbstractRené Maunier (1887‐1951) is usually considered to be the “founder” of “colonial sociology” in France. Much closer to the anthropologist Marcel Mauss than to the latter's uncle, Emile Durkheim, Maunier's academic career was largely connected to Arab countries like Egypt, and Algeria in particular, where he would teach for more than twenty years. Maunier's inclusion of Ibn Khaldûn into the history of sociology needs to be understood in line with the fact that at the time this article was published, the young Egyptian student Taha Hussein was beginning a thesis in France under the joint supervision of Durkheim and of the orientalist Paul Casanova. Defended in January 1918, three months after Durkheim's death, it was entitled Etude analytique et critique de la philosophie sociale d'Ibn Khaldoun (Analytic and critical study of Ibn Khaldoun's social philosophy).

Structure enhanced deep clustering network via a weighted neighbourhood auto-encoder

Structural deep clustering involves the use of neural networks for fusing semantic and structural representations for clustering tasks, and it has been receiving increasing attention. In some pioneering works, auto-encoder (AE)-specific representations were integrated with a graph convolutional network (GCN)-specific representation by delivering semantic information to the GCN module layer-by-layer. Although promising performance has been achieved in various applications, we observed that a vital aspect was overlooked in these works: the structural information may vanish in the learning process because of the over-smoothing problem of the GCN module, leading to non-representative features and, thus, deteriorating clustering performance. In this study, we address this issue by proposing a structure enhanced deep clustering network. The GCN-specific structural data representation is enhanced and supervised by its structural information. Specifically, the GCN-specific structural data representation is strengthened during the learning process by combining it with a structure enhanced semantic (SES) representation. A novel structure enhanced AE, named the weighted neighbourhood AE (wNAE), is employed to learn the SES representation for each data sample. Finally, we design a joint supervision strategy to uniformly guide the simultaneous learning of the wNAE and GCN modules and the clustering assignment. Experimental results for different datasets empirically validate the importance of semantic and neighbour-wise structure learning.

UPAYA GURU PENDIDIKAN AGAMA ISLAM DALAM MENINGKATKAN SELF CONTROL SISWA DI SMA NEGERI 3 BEKASI

This research is motivated by deviant behavior carried out by teenagers, especially students such as brawls, free sex, drug abuse, bullying, drunkenness, and so on. Most of the causes of this event is encouragement from peers. The purpose of this study was to determine the efforts of sIslamic Religious Education Teachers in increasing student self-control at SMA Negeri 3 Bekasi. With a qualitative descriptive method, this study tries to explore the extent to which a teacher can develop student self-control. The data collection techniques used were observation, interviews with Islamic Religious Education Teachers and documentation studies. The results showed that the teacher's efforts to improve student self-control were being uswah hasanah, making habituation, implementing joint supervision and mentoring policies and increasing discipline.

Boundary Constraint Network With Cross Layer Feature Integration for Polyp Segmentation.

Clinically, proper polyp localization in endoscopy images plays a vital role in the follow-up treatment (e.g., surgical planning). Deep convolutional neural networks (CNNs) provide a favoured prospect for automatic polyp segmentation and evade the limitations of visual inspection, e.g., subjectivity and overwork. However, most existing CNNs-based methods often provide unsatisfactory segmentation performance. In this paper, we propose a novel boundary constraint network, namely BCNet, for accurate polyp segmentation. The success of BCNet benefits from integrating cross-level context information and leveraging edge information. Specifically, to avoid the drawbacks caused by simple feature addition or concentration, BCNet applies a cross-layer feature integration strategy (CFIS) in fusing the features of the top-three highest layers, yielding a better performance. CFIS consists of three attention-driven cross-layer feature interaction modules (ACFIMs) and two global feature integration modules (GFIMs). ACFIM adaptively fuses the context information of the top-three highest layers via the self-attention mechanism instead of direct addition or concentration. GFIM integrates the fused information across layers with the guidance from global attention. To obtain accurate boundaries, BCNet introduces a bilateral boundary extraction module that explores the polyp and non-polyp information of the shallow layer collaboratively based on the high-level location information and boundary supervision. Through joint supervision of the polyp area and boundary, BCNet is able to get more accurate polyp masks. Experimental results on three public datasets show that the proposed BCNet outperforms seven state-of-the-art competing methods in terms of both effectiveness and generalization.

ZSE-DUO – duale Lotsenstruktur im Zentrum für Seltene Erkrankungen

Patients with an unclear diagnosis and suspected rare disease pose special challenges to physicians, among others. The ZSE-DUO project aims to establish whether patient care under the joint supervision of asomatic expert and amental health expert can improve diagnostic efficacy and precision, as well as shorten the time to diagnosis. ZSE-DUO has successfully recruited more than 1000patients at eleven national centres for rare diseases in acontrol and an intervention group. The findings are being analysed by three evaluating institutions. The study is currently in its final phase. The results will be published in further papers.

Development of a competence ecosystem for the future space workforce: strategies, practices and recommendations from international master programs in northern Sweden

Requirements from the global labor market have substantially changed in recent years. Graduate and post-graduate students with excellent subject knowledge, deep understanding of modern working methods, technical and higher-order thinking, engineering intuition and problem-solving skills are in great demand. They should also have professional skills such as well-developed abilities in communication and teamwork, usually in an international work environment. This review discusses the advantages of multidisciplinary study environment, educational strategies such as student-oriented teaching, project-based learning with its applicability to a “real-world” setting, active learning techniques, development of entrepreneurial skills, lessons learned and best practices from the international Master Program in Spacecraft Design and the Joint Master Program in Space Science and Technology – SpaceMaster at Luleå University of Technology in northern Sweden. The importance of complementarity between formal, informal and non-formal learning methods for science and engineering students has been specifically highlighted. Connections to the world of work, through active industry involvement in the education in a systematic way, e.g. External Advisory Board, shared services and facilities, joint projects and supervision of Master and PhD students, is recognised as a key success factor for professional training. A structural combination of modern pedagogical tools, strategic partnership with industry, business entities, academic partners and up-to-date multidisciplinary labs creates the conceptual framework for a Competence Ecosystem for fostering a new generation of space scientists and engineers.

Super-resolution reconstruction of biometric features recognition based on manifold learning and deep residual network

Background and objectiveIn daily life, face information has the characteristics of uniqueness and universality. However, in a real-world scene, the image information of the face acquired by the acquisition device often contains noises such as blurring and sharpening. As such, super-resolution reconstruction of face features recognition based on manifold learning is proposed in this paper. MethodsWe reconstruct low-resolution facial expression images, introduce a simplified residual block network and manifold learning, and propose joint supervision through a new hybrid loss function, which not only retains the color and characteristics of the image, but also retains the high-frequency information. The ResNet50 network uses the weight feature of information entropy to optimize the information of the pooling layer, and the esNet50 network uses the improved PSO algorithm to optimize the initial weight of the error back-propagation phase. ResultsIn the case of inputting extremely low resolution (6 × 6) facial expression images, the accuracy rate is increased by 9.091%. The accuracy of the high-resolution facial expressions after reconstruction with a size of 12×12 is 96.970%. The accuracy rate for happy expressions is 100%, the accuracy rate for anger, disgust, sadness, and surprise recognition is 97%, the accuracy rate for contempt is 94%, and the accuracy rate for fear is 88%. ConclusionsThe experimental results verify the feasibility and superiority of the system, and effectively improve the accuracy of low-resolution facial expressions.

Fusing Attention Features and Contextual Information for Scene Recognition

Aiming to obtain more discriminative features in scene images and overcome the impacts of intra-class differences and inter-class similarities, the paper proposes a scene recognition method that combines attention and context information. First, we introduce the attention mechanism and build a multi-scale attention model. Discriminative information considers salient objects and regions by means of channel attention and spatial attention. Besides, the central loss function joint supervision strategy is introduced to further reduce the misjudgment of intra-class differences. Second, a model based on multi-level context information is proposed to describe the positional relationship between objects, which can effectively alleviate the influence of the similarity of objects between classes. Finally, the two models are merged to give full play to the compatibility of features, so that the final feature representation not only focuses on the effective discriminant information, but also manifests the relative position relationship between significant objects. Extensive experiments have proved that the method in this paper effectively solves the problem of insufficient feature representation in scene recognition tasks, and improves the accuracy of scene recognition.