Multimodal deep learning-based diagnostic model for BPPV.

BACKGROUND: Benign paroxysmal positional vertigo (BPPV) is a prevalent form of vertigo that necessitates a skilled physician to diagnose by observing the nystagmus and vertigo resulting from specific changes in the patient's position. In this study, we aim to explore the integration of eye movement video and position information for BPPV diagnosis and apply artificial intelligence (AI) methods to improve the accuracy of BPPV diagnosis. METHODS: We collected eye movement video and diagnostic data from 518 patients with BPPV who visited the hospital for examination from January to March 2021 and developed a BPPV dataset. Based on the characteristics of the dataset, we propose a multimodal deep learning diagnostic model, which combines a video understanding model, self-encoder, and cross-attention mechanism structure. RESULT: Our validation test on the test set showed that the average accuracy of the model reached 81.7%, demonstrating the effectiveness of the proposed multimodal deep learning method for BPPV diagnosis. Furthermore, our study highlights the significance of combining head position information and eye movement information in BPPV diagnosis. We also found that postural and eye movement information plays a critical role in the diagnosis of BPPV, as demonstrated by exploring the necessity of postural information for the diagnostic model and the contribution of cross-attention mechanisms to the fusion of postural and oculomotor information. Our results underscore the potential of AI-based methods for improving the accuracy of BPPV diagnosis and the importance of considering both postural and oculomotor information in BPPV diagnosis.

Deployment and Allocation Strategy for MEC Nodes in Complex Multi-Terminal Scenarios.

Mobile edge computing (MEC) has become an effective solution for insufficient computing and communication problems for the Internet of Things (IoT) applications due to its rich computing resources on the edge side. In multi-terminal scenarios, the deployment scheme of edge nodes has an important impact on system performance and has become an essential issue in end-edge-cloud architecture. In this article, we consider specific factors, such as spatial location, power supply, and urgency requirements of terminals, with respect to building an evaluation model to solve the allocation problem. An evaluation model based on reward, energy consumption, and cost factors is proposed. The genetic algorithm is applied to determine the optimal edge node deployment and allocation strategies. Moreover, we compare the proposed method with the k-means and ant colony algorithms. The results show that the obtained strategies achieve good evaluation results under problem constraints. Furthermore, we conduct comparison tests with different attributes to further test the performance of the proposed method.

Exercise for Stroke Rehabilitation: A Bibliometric Analysis of Global Research From 2001 to 2021.

Objective: To make a bibliometric analysis of global trends in research into exercise interventions for stroke between 2001 and 2021. Method: This study did the systematic literature from 2001 to 2021 in Web of Science Core Collection. CiteSpace software was used to analyze the relationship of publications with countries, journals, authors, references, and keywords. Results: A total of 3,484 publications were obtained in the bibliometric analysis. The number of publications increased gradually over the period. The United States have the most number of publications. The journal stroke had the most citations per paper (106.95) and the highest impact factor (IF 2020, 7.194). The most high frequency keywords are "stroke," "rehabilitation," and "recovery," the top of burst key words are "health," "speed," and "aerobic exercise". Conclusion: These findings provide the trends of exercise for stroke s and provided the potential research frontiers in the past 20 years. It will be a useful basis for further research into focus issues, cooperators, development trends.

Disease Classification Based on Eye Movement Features With Decision Tree and Random Forest.

Medical research shows that eye movement disorders are related to many kinds of neurological diseases. Eye movement characteristics can be used as biomarkers of Parkinson's disease, Alzheimer's disease (AD), schizophrenia, and other diseases. However, due to the unknown medical mechanism of some diseases, it is difficult to establish an intuitive correspondence between eye movement characteristics and diseases. In this paper, we propose a disease classification method based on decision tree and random forest (RF). First, a variety of experimental schemes are designed to obtain eye movement images, and information such as pupil position and area is extracted as original features. Second, with the original features as training samples, the long short-term memory (LSTM) network is used to build classifiers, and the classification results of the samples are regarded as the evolutionary features. After that, multiple decision trees are built according to the C4.5 rules based on the evolutionary features. Finally, a RF is constructed with these decision trees, and the results of disease classification are determined by voting. Experiments show that the RF method has good robustness and its classification accuracy is significantly better than the performance of previous classifiers. This study shows that the application of advanced artificial intelligence (AI) technology in the pathological analysis of eye movement has obvious advantages and good prospects.

ECM coating modification generated by optimized decellularization process improves functional behavior of BMSCs.

Bone mesenchymal stem cells (BMSCs) have been widely applied in tissue engineering and regenerative medicine. However, small number of BMSCs and loss of stem cell characteristics after expansion in vitro limited clinical use of BMSCs. In the present study, osteoblasts were cultured to lay down extracellular matrix (ECM) and then the cells were removed (decellularization) to generate ECM coating substrates. The decellularization process was optimized to maximally remove cells and cellular components, along with integrated ECM retained which was demonstrated to be beneficial for BMSCs expansion in vitro. After decellularization, only less than 2% of residual DNA and cellular proteins were detected in TFFF-ECM (decellularized by triton X-100 (T) and three freeze/thaw cycles (FFF)), which was much less than that in TN-ECM generated by traditional decellularization method (triton X-100 (T) and NH4OH (N)). Meanwhile, ECM components and structure were preserved best after decellularization by TFFF method. More ECM proteins were detected, and structure proteins (fibronectin and collagen) exhibited as classic network fibers in TFFF-ECM. Functionally, all kinds of decellularized ECM (dECM) were demonstrated to promote BMSCs proliferation and osteogenic differentiation capacity, thus maintain the stemness of BMSCs. Importantly, cells cultured on TFFF-ECM grew faster than the cells on other kinds of dECM at early stage and TFFF-ECM was beneficial to preserve stemness of BMSCs with high expression of OCT4 and NANOG when cultured in vitro. Proteomic analysis showed the proteins in ECM functioned in multiple biological activities and signaling pathways, which contributed to stemness maintenance of BMSC. Thus, the mild decellularization process optimized in this study enhanced the effectiveness of dECM for BMSCs culture in vitro and maybe further applied to BMSCs based tissue repair.

SECOND: Sparsely Embedded Convolutional Detection.

LiDAR-based or RGB-D-based object detection is used in numerous applications, ranging from autonomous driving to robot vision. Voxel-based 3D convolutional networks have been used for some time to enhance the retention of information when processing point cloud LiDAR data. However, problems remain, including a slow inference speed and low orientation estimation performance. We therefore investigate an improved sparse convolution method for such networks, which significantly increases the speed of both training and inference. We also introduce a new form of angle loss regression to improve the orientation estimation performance and a new data augmentation approach that can enhance the convergence speed and performance. The proposed network produces state-of-the-art results on the KITTI 3D object detection benchmarks while maintaining a fast inference speed.

A Cell-Engineered Small Intestinal Submucosa-Based Bone Mimetic Construct for Bone Regeneration.

Extracellular matrix (ECM)-ornamented biomaterials have attracted attention due to their high potential to improve the biofunctionality of original materials. It is thought that ECM with a bone mimetic microenvironment generated by the specific induction of osteoblasts would be more beneficial for bone regeneration than a regular ECM. In this study, we developed an osteogenic and mineralized ECM construct (Os/M-ECM-SIS) under the guidance of osteoblasts on a small intestinal submucosa (SIS) scaffold cotreated with icariin and calcium. The generated Os/M-ECM-SIS scaffolds exhibited similar morphology and inorganic components as natural bone and higher mechanical strength than ECM-SIS. Cell adhesion, proliferation, and differentiation of osteoblasts and fibroblasts were also enhanced in the cells cultured on the Os/M-ECM-SIS scaffolds. The Os/M-ECM-SIS scaffolds even promoted transdifferentiation of fibroblasts with an upregulation of osteogenic differentiation markers. In a calvarial defect model, new bone formation was greatly enhanced in defects implanted with the Os/M-ECM-SIS scaffolds compared with ECM-SIS scaffolds. Further study showed that the Os/M-ECM-SIS scaffolds promoted bone regeneration in vitro and in vivo via the Bmp/Smad-signaling pathway. Thus, this work proposes a valuable method for generating a mineralized bone mimetic scaffold with SIS as off-the-shelf bone graft substitute that provides an excellent osteogenic microenvironment, making it suitable for application in bone tissue engineering.

A Strategic Bargaining Game for a Spectrum Sharing Scheme in Cognitive Radio-Based Heterogeneous Wireless Sensor Networks.

In Wireless Sensor Networks (WSNs), unlicensed users, that is, sensor nodes, have excessively exploited the unlicensed radio spectrum. Through Cognitive Radio (CR), licensed radio spectra, which are owned by licensed users, can be partly or entirely shared with unlicensed users. This paper proposes a strategic bargaining spectrum-sharing scheme, considering a CR-based heterogeneous WSN (HWSN). The sensors of HWSNs are discrepant and exist in different wireless environments, which leads to various signal-to-noise ratios (SNRs) for the same or different licensed users. Unlicensed users bargain with licensed users regarding the spectrum price. In each round of bargaining, licensed users are allowed to adaptively adjust their spectrum price to the best for maximizing their profits. . Then, each unlicensed user makes their best response and informs licensed users of "bargaining" and "warning". Through finite rounds of bargaining, this scheme can obtain a Nash bargaining solution (NBS), which makes all licensed and unlicensed users reach an agreement. The simulation results demonstrate that the proposed scheme can quickly find a NBS and all players in the game prefer to be honest. The proposed scheme outperforms existing schemes, within a certain range, in terms of fairness and trade success probability.

[Investigation of fast filter of ECG signals with lifting wavelet and smooth filter].

The lifting wavelet is used to decompose the original ECG signals and separate them into the approach signals with low frequency and the detail signals with high frequency, based on frequency characteristic. Parts of the detail signals are ignored according to the frequency characteristic. To avoid the distortion of QRS Complexes, the approach signals are filtered by an adaptive smooth filter with a proper threshold value. Through the inverse transform of the lifting wavelet, the reserved approach signals are reconstructed, and the three primary kinds of noise are limited effectively. In addition, the method is fast and there is no time delay between input and output.