RESUMO
Early diagnosis and intervention of depression promote complete recovery, with its traditional clinical assessments depending on the diagnostic scales, clinical experience of doctors and patient cooperation. Recent researches indicate that functional near-infrared spectroscopy (fNIRS) based on deep learning provides a promising approach to depression diagnosis. However, collecting large fNIRS datasets within a standard experimental paradigm remains challenging, limiting the applications of deep networks that require more data. To address these challenges, in this paper, we propose an fNIRS-driven depression recognition architecture based on cross-modal data augmentation (fCMDA), which converts fNIRS data into pseudo-sequence activation images. The approach incorporates a time-domain augmentation mechanism, including time warping and time masking, to generate diverse data. Additionally, we design a stimulation task-driven data pseudo-sequence method to map fNIRS data into pseudo-sequence activation images, facilitating the extraction of spatial-temporal, contextual and dynamic characteristics. Ultimately, we construct a depression recognition model based on deep classification networks using the imbalance loss function. Extensive experiments are performed on the two-class depression diagnosis and five-class depression severity recognition, which reveal impressive results with accuracy of 0.905 and 0.889, respectively. The fCMDA architecture provides a novel solution for effective depression recognition with limited data.
Assuntos
Algoritmos , Aprendizado Profundo , Depressão , Espectroscopia de Luz Próxima ao Infravermelho , Humanos , Espectroscopia de Luz Próxima ao Infravermelho/métodos , Feminino , Masculino , Adulto , Depressão/diagnóstico , Depressão/diagnóstico por imagem , Adulto Jovem , Redes Neurais de Computação , Pessoa de Meia-IdadeRESUMO
Point scene instance mesh reconstruction is a challenging task since it requires both scene-level instance segmentation and instance-level mesh reconstruction from partial observations simultaneously. Previous works either adopt a detection backbone or a segmentation one, and then directly employ a mesh reconstruction network to produce complete meshes from incomplete instance point clouds. To further boost the mesh reconstruction quality with both local details and global smoothness, in this work, we propose JIMR, a joint framework with two cascaded stages for semantic and geometry understanding. In the first stage, we propose to perform both instance segmentation and object detection simultaneously. By making both tasks promote each other, this design facilitates subsequent mesh reconstruction by providing more precisely-segmented instance points and better alignment benefiting from predicted complete bounding boxes. In the second stage, we propose a complete-then-reconstruct procedure, where the completion module explicitly disentangles completion from reconstruction, and enables the usage of pre-trained weights of existing powerful completion and reconstruction networks. Moreover, we propose a comprehensive confidence score to filter proposals considering the quality of instance segmentation, bounding box detection, semantic classification, and mesh reconstruction at the same time. Experiments show that our proposed JIMR outperforms state-of-the-art methods regarding instance reconstruction qualitatively and quantitatively.
RESUMO
Most researchers focus on designing accurate crowd counting models with heavy parameters and computations but ignore the resource burden during the model deployment. A real-world scenario demands an efficient counting model with low-latency and high-performance. Knowledge distillation provides an elegant way to transfer knowledge from a complicated teacher model to a compact student model while maintaining accuracy. However, the student model receives the wrong guidance with the supervision of the teacher model due to the inaccurate information understood by the teacher in some cases. In this paper, we propose a dual-knowledge distillation (DKD) framework, which aims to reduce the side effects of the teacher model and transfer hierarchical knowledge to obtain a more efficient counting model. First, the student model is initialized with global information transferred by the teacher model via adaptive perspectives. Then, the self-knowledge distillation forces the student model to learn the knowledge by itself, based on intermediate feature maps and target map. Specifically, the optimal transport distance is utilized to measure the difference of feature maps between the teacher and the student to perform the distribution alignment of the counting area. Extensive experiments are conducted on four challenging datasets, demonstrating the superiority of DKD. When there are only approximately 6% of the parameters and computations from the original models, the student model achieves a faster and more accurate counting performance as the teacher model even surpasses it.
RESUMO
With the advent of the Internet of Everything, people can easily interact with their environments immersively. The idea of pervasive computing is becoming a reality, but due to the inconvenience of carrying silicon-based entities and a lack of fine-grained sensing capabilities for human-computer interaction, it is difficult to ensure comfort, esthetics, and privacy in smart spaces. Motivated by the rapid developments in intelligent fabric technology in the post-Moore era, we propose a novel computing approach that creates a paradigm shift driven by fabric computing and advocate a new concept of non-chip sensing in living spaces. We discuss the core notion and benefits of fabric computing, including its implementation, challenges, and future research opportunities.
RESUMO
Flexible sensors, friendly interfaces, and intelligent recognition are important in the research of novel human-computer interaction and the development of smart devices. However, major challenges are still encountered in designing user-centered smart devices with natural, convenient, and efficient interfaces. Inspired by the characteristics of textile-based flexible electronic sensors, in this article, we report a braided electronic cord with a low-cost, and automated fabrication to realize imperceptible, designable, and scalable user interfaces. The braided electronic cord is in a miniaturized form, which is suitable for being integrated with various occasions in life. To achieve high-precision interaction, a multi-feature fusion algorithm is designed to recognize gestures of different positions, different contact areas, and different movements performed on a single braided electronic cord. The recognized action results are fed back to varieties of interactive terminals, which show the diversity of cord forms and applications. Our braided electronic cord with the features of user friendliness, excellent durability and rich interaction mode will greatly promote the development of human-machine integration in the future.
Assuntos
Eletrônica , Têxteis , Humanos , GestosRESUMO
The 2019 novel coronavirus(COVID-19) spreads rapidly, and the large-scale infection leads to the lack of medical resources. For the purpose of providing more reasonable medical service to COVID-19 patients, we designed an novel adjuvant therapy system integrating warning, therapy, and post-therapy psychological intervention. The system combines data analysis, communication networks and artificial intelligence(AI) to design a guidance framework for the treatment of COVID-19 patients. Specifically, in this system, we first can use blood characteristic data to help make a definite diagnosis and classify the patients. Then, the classification results, together with the blood characteristics and underlying diseases disease characteristics of the patient, can be used to assist the doctor in treat treating the patient according to AI algorithms. Moreover, after the patient is discharged from the hospital, the system can monitor the psychological and physiological state at the data collection layer. And in the data feedback layer, this system can analyze the data and report the abnormalities of the patient to the doctor through communication network. Experiments show the effectiveness of our proposed system.
RESUMO
Abnormal or violent behavior by people with mental disorders is common. When individuals with mental disorders exhibit abnormal behavior in public places, they may cause physical and mental harm to others as well as to themselves. Thus, it is necessary to monitor their behavior using visual surveillance systems. However, it is challenging to automatically detect human abnormal behavior (especially for individuals with mental disorders) based on motion recognition technologies. To address these issues, in the current work, we propose an end-to-end abnormal behaviour detection framework from a new perspective in conjunction with the Graph Convolutional Network (GCN) and a 3D Convolutional Neural Network (3DCNN). Specifically, we first train a one-class classifier to extract features and estimate abnormality scores. To improve the performance of abnormal behavior detection, GCN is used to model the similarity between video clips for the correction of noisy labels. Then, based on this framework, GCN recognizes the normal behavior clips in the abnormal video and removes them, while the clips identified as abnormal behavior are retained. Finally, a 3D CNN is used to extract spatiotemporal features to classify different abnormal behaviors. In order to better detect the violent behavior of individuals with mental disorders, the paper focuses on the UCF-Crime dataset with various types of violent behaviors. By experimenting with this dataset, the classification accuracy reaches 37.9%, which is significantly better than that of the current state-of-the-art approaches.
Assuntos
Transtornos Mentais , Redes Neurais de Computação , Humanos , Transtornos Mentais/diagnóstico , Movimento (Física)RESUMO
Task caching, based on edge cloud, aims to meet the latency requirements of computation-intensive and data-intensive tasks (such as augmented reality). However, current task caching strategies are generally based on the unrealistic assumption of knowing the pattern of user task requests and ignoring the fact that a task request pattern is more user specific (e.g., the mobility and personalized task demand). Moreover, it disregards the impact of task size and computing amount on the caching strategy. To investigate these issues, in this paper, we first formalize the task caching problem as a non-linear integer programming problem to minimize task latency. We then design a novel intelligent task caching algorithm based on a multiarmed bandit algorithm, called M-adaptive upper confidence bound (M-AUCB). The proposed caching strategy cannot only learn the task patterns of mobile device requests online, but can also dynamically adjust the caching strategy to incorporate the size and computing amount of each task. Moreover, we prove that the M-AUCB algorithm achieves a sublinear regret bound. The results show that, compared with other task caching schemes, the M-AUCB algorithm reduces the average task latency by at least 14.8%.
RESUMO
Depression is the result of a complex interaction of social, psychological and physiological elements. Research into the brain disorders of patients suffering from depression can help doctors to understand the pathogenesis of depression and facilitate its diagnosis and treatment. Functional near-infrared spectroscopy (fNIRS) is a non-invasive approach to the detection of brain functions and activities. In this paper, a comprehensive fNIRS-based depression-processing architecture, including the layers of source, feature and model, is first established to guide the deep modeling for fNIRS. In view of the complexity of depression, we propose a methodology in the time and frequency domains for feature extraction and deep neural networks for depression recognition combined with current research. It is found that compared to non-depression people, patients with depression have a weaker encephalic area connectivity and lower level of activation in the prefrontal lobe during brain activity. Finally, based on raw data, manual features and channel correlations, the AlexNet model shows the best performance, especially in terms of the correlation features and presents an accuracy rate of 0.90 and a precision rate of 0.91, which is higher than ResNet18 and machine-learning algorithms on other data. Therefore, the correlation of brain regions can effectively recognize depression (from cases of non-depression), making it significant for the recognition of brain functions in the clinical diagnosis and treatment of depression.
Assuntos
Depressão , Espectroscopia de Luz Próxima ao Infravermelho , Encéfalo/diagnóstico por imagem , Humanos , Aprendizado de Máquina , Redes Neurais de ComputaçãoRESUMO
Future industrial cyber-physical system (CPS) devices are expected to request a large amount of delay-sensitive services that need to be processed at the edge of a network. Due to limited resources, service placement at the edge of the cloud has attracted significant attention. Although there are many methods of design schemes, the service placement problem in industrial CPS has not been well studied. Furthermore, none of existing schemes can optimize service placement, workload scheduling, and resource allocation under uncertain service demands. To address these issues, we first formulate a joint optimization problem of service placement, workload scheduling, and resource allocation in order to minimize service response delay. We then propose an improved deep Q-network (DQN)-based service placement algorithm. The proposed algorithm can achieve an optimal resource allocation by means of convex optimization where the service placement and workload scheduling decisions are assisted by means of DQN technology. The experimental results verify that the proposed algorithm, compared with existing algorithms, can reduce the average service response time by 8-10%.
RESUMO
In this paper, we present a mathematical model of an infectious disease according to the characteristics of the COVID-19 pandemic. The proposed enhanced model, which will be referred to as the SEIR (Susceptible-Exposed-Infectious-Recovered) model with population migration, is inspired by the role that asymptomatic infected individuals, as well as population movements can play a crucial role in spreading the virus. In the model, the infected and the basic reproduction numbers are compared under the influence of intervention policies. The experimental simulation results show the impact of social distancing and migration-in rates on reducing the total number of infections and the basic reproductions. And then, the importance of controlling the number of migration-in people and the policy of restricting residents' movements in preventing the spread of COVID-19 pandemic are verified.
RESUMO
In this paper, we propose a label-less learning for emotion cognition (LLEC) to achieve the utilization of a large amount of unlabeled data. We first inspect the unlabeled data from two perspectives, i.e., the feature layer and the decision layer. By utilizing the similarity model and the entropy model, this paper presents a hybrid label-less learning that can automatically label data without human intervention. Then, we design an enhanced hybrid label-less learning to purify the automatic labeled data. To further improve the accuracy of emotion detection model and increase the utilization of unlabeled data, we apply enhanced hybrid label-less learning for multimodal unlabeled emotion data. Finally, we build a real-world test bed to evaluate the LLEC algorithm. The experimental results show that the LLEC algorithm can improve the accuracy of emotion detection significantly.
Assuntos
Reconhecimento Facial Automatizado/métodos , Cognição , Aprendizado Profundo , Emoções , Interface para o Reconhecimento da Fala , Reconhecimento Facial Automatizado/tendências , Cognição/fisiologia , Aprendizado Profundo/tendências , Emoções/fisiologia , Humanos , Interface para o Reconhecimento da Fala/tendênciasRESUMO
From a traditional point of view, the value of information does not change during transmission. The Shannon information theory considers information transmission as a statistical phenomenon for measuring the communication channel capacity. However, in modern communication systems, information is spontaneously embedded with a cognitive link during the transmission process, which requires a new measurement that can incorporate continuously changing information values. In this paper, we introduce the concept of cognitive information value and a method of measuring such information. We first describe the characteristics of cognitive information followed by an introduction of the concept of cognitive information in measuring information popularity. The new measurement is based on the mailbox principle in the information value chain. This is achieved by encapsulating the information as a mailbox for transmission where the cognition is continuously implemented during the transmission process. Finally, we set up a cognitive communication system based on a combination of the traditional communication system and cognitive computing. Experimental results attest to the impact of incorporating cognitive value in the performance of 5G networks.
RESUMO
Body area networks (BANs) are configured with a great number of ultra-low power consumption wearable devices, which constantly monitor physiological signals of the human body and thus realize intelligent monitoring. However, the collection and transfer of human body signals consume energy, and considering the comfort demand of wearable devices, both the size and the capacity of a wearable device's battery are limited. Thus, minimizing the energy consumption of wearable devices and optimizing the BAN energy efficiency is still a challenging problem. Therefore, in this paper, we propose an energy harvesting-based BAN for smart health and discuss an optimal resource allocation scheme to improve BAN energy efficiency. Specifically, firstly, considering energy harvesting in a BAN and the time limits of human body signal transfer, we formulate the energy efficiency optimization problem of time division for wireless energy transfer and wireless information transfer. Secondly, we convert the optimization problem into a convex optimization problem under a linear constraint and propose a closed-form solution to the problem. Finally, simulation results proved that when the size of data acquired by the wearable devices is small, the proportion of energy consumed by the circuit and signal acquisition of the wearable devices is big, and when the size of data acquired by the wearable devices is big, the energy consumed by the signal transfer of the wearable device is decisive.
RESUMO
With the ever-growing number of mobile devices, there is an explosive expansion in mobile data services. This represents a challenge for the traditional cellular network architecture to cope with the massive wireless traffic generated by mobile media applications. To meet this challenge, research is currently focused on the introduction of a small cell base station (BS) due to its low transmit power consumption and flexibility of deployment. However, due to a complex deployment environment and low transmit power of small cell BSs, the coverage boundary of small cell BSs will not have a traditional regular shape. Therefore, in this paper, we discuss the coverage boundary of an ultra-dense small cell network and give its main features: aeolotropy of path loss fading and fractal coverage boundary. Simple performance analysis is given, including coverage probability and transmission rate, etc., based on stochastic geometry theory and fractal theory. Finally, we present an application scene and discuss challenges in the ultra-dense small cell network.
RESUMO
Recent trends show that Internet traffic is increasingly dominated by content, which is accompanied by the exponential growth of traffic. To cope with this phenomena, network caching is introduced to utilize the storage capacity of diverse network devices. In this paper, we first summarize four basic caching placement strategies, i.e., local caching, Device-to-Device (D2D) caching, Small cell Base Station (SBS) caching and Macrocell Base Station (MBS) caching. However, studies show that so far, much of the research has ignored the impact of user mobility. Therefore, taking the effect of the user mobility into consideration, we proposes a joint mobility-aware caching and SBS density placement scheme (MS caching). In addition, differences and relationships between caching and computation offloading are discussed. We present a design of a hybrid computation offloading and support it with experimental results, which demonstrate improved performance in terms of energy cost. Finally, we discuss the design of an incentive mechanism by considering network dynamics, differentiated user's quality of experience (QoE) and the heterogeneity of mobile terminals in terms of caching and computing capabilities.