Predicting sales and cross-border e-commerce supply chain management using artificial neural networks and the Capuchin search algorithm.

E-commerce provides a large selection of goods for sale and purchase, which promotes regular transactions and commodity flows. Efficient distribution of goods and precise estimation of customer wants are essential for cost reduction. In order to improve supply chain efficiency in the context of cross-border e-commerce, this article combines machine learning approaches with the Internet of Things. The suggested approach consists of two main stages. Order prediction is done in the first step to determine how many orders each merchant is expected to get in the future. In the second phase, allocation operations are conducted and resources required for each retailer are supplied depending on their needs and inventory, taking into account each store's inventory as well as the anticipated sales level. This suggested approach makes use of a weighted mixture of neural networks to anticipate sales orders. The Capuchin Search Algorithm (CapSA) is used in this weighted combination to concurrently enhance the learning and ensemble performance of models. This indicates that an effort is made to reduce the local error of the learning model at the model level via model weight adjustments and neural network configuration. To guarantee more accurate output from the ensemble model, the best weight for each individual component is found at the ensemble model level using the CapSA method. This method yields the ensemble model's final output in the form of weighted averages by choosing suitable weight values. With a Root Mean Squared Error of 2.27, the suggested technique has successfully predicted sales based on the acquired findings, showing a minimum decrease of 2.4 in comparison to the comparing methodologies. Additionally, the suggested method's strong performance is shown by the fact that it was able to minimize the Mean Absolute Percentage Error by 14.67 when compared to other comparison approaches.

Fibula allograft transplantation combined with locking plate for treatment of recurrent monostotic fibular fibrous dysplasia: A case report.

BACKGROUND: Fibrous dysplasia is a congenital disorder in which normal bone is replaced by fibro-osseous tissue or irregular trabeculae of woven bone intermixed with mature collagenous tissue. A single or multiple bones are affected. This rare bone disorder has three clinical patterns including monostotic, polyostotic, and that associated with McCune-Albright syndrome. Most studies report primary fibrous dysplasia. However, a few cases of recurrent monostotic fibular fibrous dysplasia have been reported. Here, we report a therapeutic strategy for recurrent fibular fibrous dysplasia. CASE SUMMARY: A 4-year-old boy was admitted for persistent pain in the left lower limb and abnormal gait over the previous 9 mo. He had no history of present or past illness. Preoperative imaging data showed erosion-like changes with bone expansion of the left middle and lower fibular segment. Tumor tissue in the fibular bone marrow cavity was removed by curettage, and rapid intraoperative pathological examination suggested fibular fibrous dysplasia. An allograft was implanted into the fibular medullary cavity. However, he was readmitted with clinical symptoms including persistent pain, abnormal gait, and local swelling at the age of 6 years. He was diagnosed with recurrent fibular fibrous dysplasia based on the second medical examination. He underwent fibular bone tumor radical resection and longus fibular allograft transplantation combined with fibular bone locking plate and screws. Good host bone to allogenic bone graft fusion was observed by the physician on postoperative regular follow-up. CONCLUSION: Radical resection of fibrous dysplasia and longus fibula allograft combined with internal fixation for reconstruction are suitable for the treatment of recurrent monostotic fibular fibrous dysplasia.

Surgery for fibrous dysplasia associated with aneurysmal-bone-cyst-like changes in right proximal femur: A case report.

BACKGROUND: Fibrous dysplasia associated with aneurysmal bone cyst (ABC)-like changes in the right proximal femur has a low incidence. It is considered more difficult to make early diagnosis than for single fibrous dysplasia. CASE SUMMARY: A 14-year-old woman was admitted because of persistent pain in the right hip and abnormal gait over the previous 2 mo. She had no history of present or past illness. Preoperative photography, enhanced computed tomography, and magnetic resonance imaging showed ground-glass appearance with cortical scalloping and expansion of the right proximal femur and femoral neck. Pathological examination by preoperative puncture biopsy revealed fibrous dysplasia of the right proximal femur. The patient was diagnosed with fibrous dysplasia based on medical history, physical examination, and results of laboratory, imaging and pathological examinations. According to final pathological examination, the patient was diagnosed with fibrous dysplasia of the right proximal femur associated with ABC. Curettage and allograft along with fixation of compression screws was performed for fibrous dysplasia associated with ABC-like changes. No obvious allograft absorption, loosening of fixation, or secondary fracture were observed during 6-months' follow-up with re-examination by plain radiography and computed tomography. Fibrous dysplasia associated with ABC-like changes in the right proximal femur has a low incidence and early diagnosis is considered more difficult than for single fibrous dysplasia. CONCLUSION: We report a cases of fibrous dysplasia associated with ABC-like changes in the right proximal femur treated with curettage and allograft along with hip compression screws.

Multimodal Attention Dynamic Fusion Network for Facial Micro-Expression Recognition.

The emotional changes in facial micro-expressions are combinations of action units. The researchers have revealed that action units can be used as additional auxiliary data to improve facial micro-expression recognition. Most of the researchers attempt to fuse image features and action unit information. However, these works ignore the impact of action units on the facial image feature extraction process. Therefore, this paper proposes a local detail feature enhancement model based on a multimodal dynamic attention fusion network (MADFN) method for micro-expression recognition. This method uses a masked autoencoder based on learnable class tokens to remove local areas with low emotional expression ability in micro-expression images. Then, we utilize the action unit dynamic fusion module to fuse action unit representation to improve the potential representation ability of image features. The state-of-the-art performance of our proposed model is evaluated and verified on SMIC, CASME II, SAMM, and their combined 3DB-Combined datasets. The experimental results demonstrated that the proposed model achieved competitive performance with accuracy rates of 81.71%, 82.11%, and 77.21% on SMIC, CASME II, and SAMM datasets, respectively, that show the MADFN model can help to improve the discrimination of facial image emotional features.

Multi-scale fusion visual attention network for facial micro-expression recognition.

Introduction: Micro-expressions are facial muscle movements that hide genuine emotions. In response to the challenge of micro-expression low-intensity, recent studies have attempted to locate localized areas of facial muscle movement. However, this ignores the feature redundancy caused by the inaccurate locating of the regions of interest. Methods: This paper proposes a novel multi-scale fusion visual attention network (MFVAN), which learns multi-scale local attention weights to mask regions of redundancy features. Specifically, this model extracts the multi-scale features of the apex frame in the micro-expression video clips by convolutional neural networks. The attention mechanism focuses on the weights of local region features in the multi-scale feature maps. Then, we mask operate redundancy regions in multi-scale features and fuse local features with high attention weights for micro-expression recognition. The self-supervision and transfer learning reduce the influence of individual identity attributes and increase the robustness of multi-scale feature maps. Finally, the multi-scale classification loss, mask loss, and removing individual identity attributes loss joint to optimize the model. Results: The proposed MFVAN method is evaluated on SMIC, CASME II, SAMM, and 3DB-Combined datasets that achieve state-of-the-art performance. The experimental results show that focusing on local at the multi-scale contributes to micro-expression recognition. Discussion: This paper proposed MFVAN model is the first to combine image generation with visual attention mechanisms to solve the combination challenge problem of individual identity attribute interference and low-intensity facial muscle movements. Meanwhile, the MFVAN model reveal the impact of individual attributes on the localization of local ROIs. The experimental results show that a multi-scale fusion visual attention network contributes to micro-expression recognition.

Genome of Lindera glauca provides insights into the evolution of biosynthesis genes for aromatic compounds.

Lindera glauca is a crucial source of diverse industrial oil and medicines. The spicy aroma of tender leaves is caused by the presence of abundant aromatic compounds. Here, we present its chromosome-level genome assembly comprising 12 pseudochromosomes (2,092.2 Mb; scaffold N50: 186.5 Mb), which was predicted to have 65,145 protein-coding genes. Comparative genomic analyses indicated two whole-genome duplication (WGD) events in the Lauraceae family, contributing to the production of numerous terpene synthase (TPS) genes. We identified 138 TPS genes in L. glauca. Comparative transcriptomic analyses revealed high expression of genes Lg03G2346 and Lg08G140 in TPS-a and Lg07G2961 and Lg12G971 in TPS-b subfamilies, which regulated the biosynthesis of the monoterpenoid ß-ocimene and sesquiterpenoid D-germacrene in L. glauca. The results suggested a molecular basis for species-specific terpenoid biosynthesis and provided a foundation for molecular breeding to produce desired characteristics and a valuable reference genome.

Potential risk of impertinent administration of methylprednisolone in lumbar spine surgery: A case report.

INTRODUCTION: Several complications of intravenous administration of Methylprednisolone in spine surgery have been reported previously. However, perioperative Addisonian crisis resulting from postoperative routine cessation of intravenous Methylprednisolone has been rarely reported. We here report a case of perioperative Addisonian crisis induced by postoperative routine cessation of intravenous Methylprednisolone. PRESENTATION OF CASE: To report a 56-year-old lady was diagnosed with Addisonian crisis on postoperative duration of lumbar spine surgery after routine cessation of intravenous Methylprednisolone on postoperative day 5. DISCUSSION: There are potential risk and medical complexity of the intravenous administration of Methylprednisolone perioperatively when patients underwent spine surgery, especially the patients with a history of adrenal insufficiency or hypothyroidism, and other endocrine diseases. The early diagnosis and effective replacement therapy after cessation of intravenous glucocorticoid to keep normal serum hormone levels can reduce risk and complication of Addisonian crisis. CONCLUSION: Addisonian crisis may be triggered by the discontinuation of exogenous glucocorticoid. Physicians need to be immediately aware of this potentially lethal complication in patients with endocrine system diseases.

Efficacy and complications of 125I seeds combined with percutaneous vertebroplasty for metastatic spinal tumors: A literature review.

To review the efficacy and complications of 125I seeds combined with percutaneous vertebroplasty for the treatment of metastatic spinal tumors. We searched PubMed/MEDLINE from its inception to November 2018 for articles on metastatic spinal tumors treated with 125I seeds combined with percutaneous vertebroplasty. A total of 273 articles were identified in PubMed/MEDLINE based on the search criteria. After deleting duplicate articles including two retrospective studies and three case control studies, five studies were included in this systematic review. In total, 161 patients aged from 49.2 to 62 years were included. The operative levels consisted of the thoracic vertebrae and lumbar vertebrae. Bone cement leakage occurred in 7 cases. None of the patients developed radiation myelopathy. Percutaneous vertebroplasty plus 125I seeds implantation is an effective palliative treatment and can alleviate back pain and enhance vertebral body strength in patients with end-stage spinal metastatic tumors. In future research, the effective dosage of 125I seeds implantation, the anchoring of seeds with safe distance, and the bone cement distribution in the vertebral body will be next research hotspot.

Assisted therapeutic system based on reinforcement learning for children with autism.

Assisted therapy is increasingly used in autism spectrum disorders (ASD) for improving social interaction and communication skills in recent years. A lot of studies have proven that the form of interactive games for therapy has a good effect on children with autism. Thus, our study provided an assisted therapeutic system based on Reinforcement Learning (RL) for children with ASD, which has five interactive subgames. As is well known, it is necessary to establish and maintain compelling interactions in therapeutic process. Therefore, we aim to adjust the interactive content according to the emotions of children with autism. However, due to the atypical and unusually differences in children with autism, most systems are based on off-line training of small samples of individuals and online recognition, so the existing assisted systems are limited in their ability to automatically update system parameters of new mappings. The integration of RL and Convolutional Neural Network (CNN)-Support Vector Regression (SVR) was used to deal with the updating online of prediction model's weights. The normalized emotion labels were evaluated by the therapists. Eleven children with autism as subjects were invited in this experiment and captured facial video images. The experiment lasted for five weeks of intermittent assisted therapy, and the results were evaluated for the system and the therapy effect. Finally, we achieved a general reduction in the root mean square error of the model prediction results and labels. Although there is no significant difference in Social Responsiveness Scale (SRS) scores before and after assisted therapy (p value = 0.60), in individual subjects (Sub. 1, Sub. 2 and Sub.3), the SRS total score is significantly reduced (Average drop of 19 points). These results demonstrate the effectiveness of prediction model based on RL and show the feasibility of assisted therapeutic system in children with autism.

Reinforcement Emotion-Cognition System: A Teaching Words Task.

The goal of this paper is to suggest a system for intelligent learning environments with robots modeling of emotion regulation and cognition based on quantitative motivation. A detailed interactive situation for teaching words is proposed. In this study, we introduce one bottom-up collaboration method for emotion-cognition interplay and behaviour decision-making. Integration with gross emotion regulation theory lets the proposed system adapt to natural interactions between students and the robot in emotional interaction. Four key ideas are advocated, and they jointly set up a reinforcement emotion-cognition system (RECS). First, the quantitative motivation is grounded on external interactive sensory detection, which is affected by memory and preference. Second, the emotion generation triggered by an initial motivation such as external stimulus is also influenced by the state in the previous time. Third, the competitive and cooperative relationship between emotion and motivation intervenes to make the decision of emotional expression and teaching actions. Finally, cognitive reappraisal, the emotion regulation strategy, is introduced for the establishment of emotion transition combined with personalized cognition. We display that this RECS increases the robot emotional interactive performance and makes corresponding teaching decision through behavioural and statistical analysis.

A Transductive Model-based Stress Recognition Method Using Peripheral Physiological Signals.

Existing research on stress recognition focuses on the extraction of physiological features and uses a classifier that is based on global optimization. There are still challenges relating to the differences in individual physiological signals for stress recognition, including dispersed distribution and sample imbalance. In this work, we proposed a framework for real-time stress recognition using peripheral physiological signals, which aimed to reduce the errors caused by individual differences and to improve the regressive performance of stress recognition. The proposed framework was presented as a transductive model based on transductive learning, which considered local learning as a virtue of the neighborhood knowledge of training examples. The degree of dispersion of the continuous labels in the y space was also one of the influencing factors of the transductive model. For prediction, we selected the epsilon-support vector regression (e-SVR) to construct the transductive model. The non-linear real-time features were extracted using a combination of wavelet packet decomposition and bi-spectrum analysis. The performance of the proposed approach was evaluated using the DEAP dataset and Stroop training. The results indicated the effectiveness of the transductive model, which had a better prediction performance compared to traditional methods. Furthermore, the real-time interactive experiment was conducted in field studies to explore the usability of the proposed framework.

Effect of Intra-wound Vancomycin for Spinal Surgery: A Systematic Review and Meta-analysis.

Intra-site prophylactic vancomycin in spine surgery is an effective method of decreasing the incidence of postsurgical wound infection. However, there are differences in the prophylactic programs used for various spinal surgeries. Thus, this systematic review and meta-analysis aimed to evaluate the effectiveness of using intra-wound vancomycin during spinal surgery and to explore the effects of dose-dependence and the method of administration in a subgroup analysis. A total of 628 citations or studies were searched in PubMed, Ovid, Web of Science, and Google Scholar that were published before August 2016 with the terms "local vancomycin", "intra-wound vancomycin", "intraoperative vancomycin", "intra-site vancomycin", "topical vancomycin", "spine surgery", and "spinal surgery". Finally, 19 retrospective cohort studies and one prospective case study were eligible for inclusion in the systematic review and meta-analysis. The odds of developing postsurgical wound infection without prophylactic local vancomycin use were 2.83-fold higher than the odds of experiencing wound infection with the use of intra-wound vancomycin (95% confidence interval, 2.03-3.95; P = 0.083; I2 = 32.2%). The subgroup analysis including the dosage and the method of administration, revealed different results compared to previous research. The value of I2 in the 1-g group was 27.2%, which was much lower than in the 2-g group (I2 = 57.6%). At the same time, the value of I2 was 0.0% (P = 0.792, OR = 2.70) when vancomycin powder was directly sprinkled into all layers of the wound. However, there is high heterogenicity (I2 = 60.0%, P = 0.007, OR = 2.83) when vancomycin powder is not exposed to the bone graft and instrumentation. There are differences found with the method of local application of vancomycin for reducing postoperative wounds and further studies are necessary, including investigations focusing on the dose-dependent effects during spinal or the topical pharmacokinetic and other orthopaedic surgeries.

Prevalence and correlates of suicidal ideation in SLE inpatients: Chinese experience.

Systemic lupus erythematosus (SLE) is a chronic autoimmune disease that affects multiple organs. Because of double damages of body and mind, SLE patients are in a potential risk of suicide. Many factors may contribute to the occurrence of suicide in SLE: socioeconomic factors, medical factors, mental health, family support and coping style. This study aims to investigate the prevalence and correlates of suicidal ideation in SLE inpatients in China in order to determine whether they had risk of suicide, and if so, what factors should be paid more attention to prevent suicide in wards. A total of 285 SLE patients were interviewed with questionnaires on suicidal ideation and socio-demographic characteristics, Beck Depression Inventory (BDI), Family APGAR and Trait Coping Style Questionnaire (TCSQ). Disease activity was assessed with SLE Disease Activity Index. The other medical information was collected from the patients' medical records. In total, 34.4% of SLE patients had current suicidal ideation. Significant individual risk factors for current suicidal ideation in SLE patients included having religious belief, heavy self-reported financial burdens, long duration of SLE, low level of family functioning and negative coping style. And in the presence of these risk factors, being separated, divorced or widowed, having premorbid suicidal ideation and depression were independent predictors of suicidal ideation. In summary, the rate of suicidal ideation in SLE patients in China is higher than that in other countries. Factors that contribute to risk of suicidal ideation include social and cultural domains and physical and psychological health. Although the association of suicidal ideation to religions and medical factors is still to be investigated, these findings may give some references to suicide prevention efforts for SLE patients in China.

[Personal psychological susceptibility of suicidal ideation in patients with systemic lupus erythematosus].

OBJECTIVE: To investigate the prevalence of suicidal ideation among systemic lupus erythematosus (SLE) patients and to assess the psychological susceptibility of suicidal ideation. METHODS: 324 SLE patients in Hefei city were interviewed with questionnaires, including Eysenck Personality Questionnaire (EPQ) and Trait Coping Style Questionnaire (TCSQ) and self-made questionnaire to collect information on suicidal ideation, social-demographic characteristics, etc. T test was used to compare the scores of personality and coping styles with national psychological norms. These odds ratios (95%CI) of the two factors for suicidal ideation were calculated by logistic regression, adjusted to socio-demographic factors. RESULTS: Current suicidal ideation was present in 108(33.3%) of 324 SLE patients. The standard scores of neuroticism (49.81 ± 10.03, t = 15.327, P < 0.01) and psychoticism (49.84 ± 9.73, t = 3.142, P < 0.01) were both higher than norms (neuroticism: 41.27 ± 9.42; psychoticism: 48.14 ± 9.74). The standard score of extrovision and introvision (50.43 ± 9.90) was lower than norm (57.75 ± 8.26) (t = -13.317, P < 0.01). Both scores of positive coping (34.36 ± 7.86) and negative coping (28.87 ± 7.79) were higher than norms of female healthy group (PC: 29.32 ± 8.96, NC: 22.34 ± 7.47) (t values were 11.543 and 15.102, P values all < 0.01) and patients' group (PC: 29.15 ± 9.28, NC: 25.36 ± 8.42) (t values were 8.122 and 11.932, P values all < 0.01). After adjusting the social-demographic variables, neurotic personality (OR = 1.110, 95%CI: 1.072 - 1.149) and high level of negative coping (OR = 1.069, 95%CI: 1.030 - 1.109) were significantly correlated with suicidal ideation in SLE patients. CONCLUSION: The rate of suicidal ideation in SLE patients in China was a little higher. Neurotic personality and negative coping were the psychological susceptibility of suicidal ideation in SLE patients.