Multiple Sclerosis(MS)poses significant health risks.Patients may face neurodegeneration,mobility issues,cognitive decline,and a reduced quality of life.Manual diagnosis by neurologists is prone to limitations,making ...Multiple Sclerosis(MS)poses significant health risks.Patients may face neurodegeneration,mobility issues,cognitive decline,and a reduced quality of life.Manual diagnosis by neurologists is prone to limitations,making AI-based classification crucial for early detection.Therefore,automated classification using Artificial Intelligence(AI)techniques has a crucial role in addressing the limitations of manual classification and preventing the development of MS to advanced stages.This study developed hybrid systems integrating XGBoost(eXtreme Gradient Boosting)with multi-CNN(Convolutional Neural Networks)features based on Ant Colony Optimization(ACO)and Maximum Entropy Score-based Selection(MESbS)algorithms for early classification of MRI(Magnetic Resonance Imaging)images in a multi-class and binary-class MS dataset.All hybrid systems started by enhancing MRI images using the fusion processes of a Gaussian filter and Contrast-Limited Adaptive Histogram Equalization(CLAHE).Then,the Gradient Vector Flow(GVF)algorithm was applied to select white matter(regions of interest)within the brain and segment them from the surrounding brain structures.These regions of interest were processed by CNN models(ResNet101,DenseNet201,and MobileNet)to extract deep feature maps,which were then combined into fused feature vectors of multi-CNN model combinations(ResNet101-DenseNet201,DenseNet201-MobileNet,ResNet101-MobileNet,and ResNet101-DenseNet201-MobileNet).The multi-CNN features underwent dimensionality reduction using ACO and MESbS algorithms to remove unimportant features and retain important features.The XGBoost classifier employed the resultant feature vectors for classification.All developed hybrid systems displayed promising outcomes.For multiclass classification,the XGBoost model using ResNet101-DenseNet201-MobileNet features selected by ACO attained 99.4%accuracy,99.45%precision,and 99.75%specificity,surpassing prior studies(93.76%accuracy).It reached 99.6%accuracy,99.65%precision,and 99.55%specificity in binary-class classification.These results demonstrate the effectiveness of multi-CNN fusion with feature selection in improving MS classification accuracy.展开更多
Objective To construct a precise model for identifying traditional Chinese medicine(TCM)constitutions;thereby offering optimized guidance for clinical diagnosis and treatment plan-ning;and ultimately enhancing medical...Objective To construct a precise model for identifying traditional Chinese medicine(TCM)constitutions;thereby offering optimized guidance for clinical diagnosis and treatment plan-ning;and ultimately enhancing medical efficiency and treatment outcomes.Methods First;TCM full-body inspection data acquisition equipment was employed to col-lect full-body standing images of healthy people;from which the constitutions were labelled and defined in accordance with the Constitution in Chinese Medicine Questionnaire(CCMQ);and a dataset encompassing labelled constitutions was constructed.Second;heat-suppres-sion valve(HSV)color space and improved local binary patterns(LBP)algorithm were lever-aged for the extraction of features such as facial complexion and body shape.In addition;a dual-branch deep network was employed to collect deep features from the full-body standing images.Last;the random forest(RF)algorithm was utilized to learn the extracted multifea-tures;which were subsequently employed to establish a TCM constitution identification mod-el.Accuracy;precision;and F1 score were the three measures selected to assess the perfor-mance of the model.Results It was found that the accuracy;precision;and F1 score of the proposed model based on multifeatures for identifying TCM constitutions were 0.842;0.868;and 0.790;respectively.In comparison with the identification models that encompass a single feature;either a single facial complexion feature;a body shape feature;or deep features;the accuracy of the model that incorporating all the aforementioned features was elevated by 0.105;0.105;and 0.079;the precision increased by 0.164;0.164;and 0.211;and the F1 score rose by 0.071;0.071;and 0.084;respectively.Conclusion The research findings affirmed the viability of the proposed model;which incor-porated multifeatures;including the facial complexion feature;the body shape feature;and the deep feature.In addition;by employing the proposed model;the objectification and intel-ligence of identifying constitutions in TCM practices could be optimized.展开更多
This review focused on the diagnosis and clinical features of multiple sclerosis(MS) in China. We have identified the published researching information from 1976 to 2008 in China. The key issues related to the diagnos...This review focused on the diagnosis and clinical features of multiple sclerosis(MS) in China. We have identified the published researching information from 1976 to 2008 in China. The key issues related to the diagnosis and clinical features of MS in China were summarized. The first patient with MS in China was reported in 1926 from Xiehe hospital. Case reports on MS has been increasing during recent decades. Almost all the patients with MS were confirmed by the McDonald criteria(1977) before1984. After the...展开更多
Objective: To study clinical features of the patients with multiple myeloma(MM) accompanied by renal insufficiency and investigate the related risk factors of renalimpairment. Methods: A control study of clinical char...Objective: To study clinical features of the patients with multiple myeloma(MM) accompanied by renal insufficiency and investigate the related risk factors of renalimpairment. Methods: A control study of clinical characteristics was performed between 91 patientswith renal insufficiency due to MM and 165 patients with normal renal function in MM during the sameperiod. The data were statistically analyzed by chi-square test and logistic regression analysis.Results: Renal insufficiency was the initial presentation in 48 (52.7%) of the 91 patients, and 30(62.5%) of the 48 patients were misdiagnosed. The prognosis of group with renal insufficiency wassignificantly poorer than that of group with normal renal function: mortality in 3 months, 3months-1 year was 26/91 vs 14/165 (P 【 0.0001), 14/91 vs 12/165 (P 【 0.05) respectively, andpatients survived 】 1 year was 18/91 vs 95/165 (P 【 0.0001). The incidence of hypercalcemia,hyperuricemic, severe anemia, high serum M-protein concentration and lytic bone lesions weresignificantly higher in renal insufficiency group than those in control group (P 【 0.05). Logisticregression analysis identified 5 risk factors of renal impairment, including, severe anemia(Exp(β)=13.819, P 【 0.0001), use of nephrotoxic drugs (Exp(β)=6.217, P = 0.001), high serumM-protein concentration (Exp(β) = 5.026, P = 0.001), male (Exp(β)=3.745, P=0.006), andhypercalcemia (Exp(β)=3A72, P=0.006), but age, serum density of uric acid, type of serum M-protein,and Bence Jones proteinuria were not significantly associated with renal insufficiency. Conclusion:Renal insufficiency was a common early complication of MM, which often resulted in misdiagnosis.The status of these patients tended to be very bad, with many other complications, when MM wasdiagnosed, so their prognosis was poor. The occurrence of renal insufficiency in patients with MMand hypercalcemia, severe anemia, high serum M-protein concentration, especially use of nephrotoxicdrugs should be alert.展开更多
It is easy for teenagers to view pornographic pictures on social networks. Many researchers have studied the detection of real pornographic pictures, but there are few studies on those that are artificial. In this wor...It is easy for teenagers to view pornographic pictures on social networks. Many researchers have studied the detection of real pornographic pictures, but there are few studies on those that are artificial. In this work, we studied how to detect artificial pornographic pictures, especially when they are on social networks. The whole detection process can be divided into two stages： feature selection and picture detection. In the feature selection stage, seven types of features that favour picture detection were selected. In the picture detection stage, three steps were included. 1） In order to alleviate the imbalance in the number of artificial pornographic pictures and normal ones, the training dataset of artificial pornographic pictures was expanded. Therefore, the features which were extracted from the training dataset can also be expanded too. 2） In order to reduce the time of feature extraction, a fast method which extracted features based on the proportionally scaled picture rather than the original one was proposed. 3） Three tree models were compared and a gradient boost decision tree （GBDT） was selected for the final picture detection. Three sets of experimental results show that the proposed method can achieve better recognition precision and drastically reduce the time cost of the method.展开更多
The performance of decoding algorithm is one of the important influential factors to determine the communication quality of optical camera communication(OCC) system. In this paper, we first propose a decoding algorith...The performance of decoding algorithm is one of the important influential factors to determine the communication quality of optical camera communication(OCC) system. In this paper, we first propose a decoding algorithm with adaptive thresholding based on the captured pixel values under an ideal environment, and then we further propose a decoding algorithm with multiple features, which is more suitable under the existence of the interference of light sources. The algorithm firstly determines the light-emitting diode(LED) array profile information by removing the interfering light sources through geometric features, and then identifies the LED state by calculating two grayscale features, the average gray ratio(AGR) and the gradient radial inwardness(GRI) of the LEDs, and finally obtains the LED state matrix. The experimental results show that the bit error ratio(BER) of the decoding algorithm with multiple features decreases from 1×10^(-2) to 5×10^(-4) at 80 m.展开更多
The quality of expert ranking directly affects the expert retrieval precision.According to the characteristics of the expert entity,an expert ranking model based on the list with multiple features was proposed.Firstly...The quality of expert ranking directly affects the expert retrieval precision.According to the characteristics of the expert entity,an expert ranking model based on the list with multiple features was proposed.Firstly,multiple features was selected through the analysis of expert pages;secondly,in order to learn parameters through gradient descent and construct expert ranking model,all features were integrated into ListNet ranking model;finally,expert ranking contrast experiment will be performed using the trained model.The experimental results show that the proposed method has a good effect,and the value of NDCG@1 increased14.2%comparing with the pairwise method with expert ranking.展开更多
BACKGROUND：Devic＇s neuromyelitis optica （DNMO） and multiple sclerosis in Asian populations have been considered to be the same disease. However, there is an increasing number of studies suggesting that DNMO and mu...BACKGROUND：Devic＇s neuromyelitis optica （DNMO） and multiple sclerosis in Asian populations have been considered to be the same disease. However, there is an increasing number of studies suggesting that DNMO and multiple sclerosis are different diseases.OBJECTIVE：Little information is available regarding comparisons of DNMO patients between China and other countries, as well as clinical manifestations of Chinese patients with DNMO and multiple sclerosis. The present study performed a multi-center, pathological, retrospective analysis.DESIGN, TIME AND SETTING：A retrospective analysis of clinical data from seven patients with DNMO diagnosed between 1957 and 1998.PARTICIPANTS：Data from Chinese DNMO patients was provided by the Shanghai Second Medical University, Sun Yat-sen University of Medical Sciences and the First Affiliated Hospital of Harbin Medical University in China.METHODS：Clinical and pathological data from Chinese patients with DNMO were retrospectively analyzed. The clinical characteristics of DNMO were compared between Chinese and Caucasian patients. In addition, clinical and pathological differences between DNMO and multiple sclerosis Chinese patients were compared.MAIN OUTCOME MEASURES：Clinical and pathological features of Chinese patients with DNMO.RESULTS：All seven Chinese patients with DNMO exhibited abrupt onset of vision disturbance, with a disease course of 3 clays to 9 years. DNMO recurred in two of the patients. Demyelinating lesions were observed in all patients, with necrotic lesions and gitter cells in five patients, collagenous hyperplasia in one patient, and perivascular inflammatory cell infiltration in six patients. Comparison between Chinese and Caucasian DNMO patients revealed no significant differences in age at onset, clinical onset, duration, or interval between optic neuritis and myelitis. Compared with Chinese multiple sclerosis patients, Chinese DNMO patients presented with fewer recurrences, higher occurrence of necrosis, perivascular inflammatory cell infiltration and gitter cells, and a lower occurrence of collagenous hyperplasia.CONCLUSION：There was no difference in DNMO clinical features between Chinese and Caucasian patients. However, the clinical and pathological features of DNMO were different compared with multiple sclerosis in Chinese patients. Results suggested that the characteristics of DNMO in Chinese patients were significantly different than multiple sclerosis.展开更多
This study sought to analyze the clinical features and prognosis of multiple myeloma with isolated extramedullary relapse and with the absence of systemic progression.The clinical features and outcome were retrospecti...This study sought to analyze the clinical features and prognosis of multiple myeloma with isolated extramedullary relapse and with the absence of systemic progression.The clinical features and outcome were retrospectively analyzed in six multiple myeloma patients.These patients had secretory multiple myeloma at diagnosis.When relapsed,the dissociation between medullary and extramedullary response was detected.The serum or urine monoclonal component was extremely low or absent.The plasma cells in bone marrow were 〈5%.All patients received new targeted therapies（thalidomide or bortezomib） before extramedullary relapse.It is difficult to achieve second remission for them.Even in those showing response,the duration of response was extremely short.The median of overall survival from diagnosis and from extramedullary relapse was 19 months and 6 months,respectively.The overall survival was significantly shorter compared to the patients without extramedullary involvement（84 months,P= 0.001）.These patients exhibited a special and rare relapse pattern.Patients with this relapse pattern were resistant to current therapies,including novel targeted agents and associated with poor prognosis.展开更多
Considering that real communication signals corrupted by noise are generally nonstationary, and timefrequency distributions are especially suitable for the analysis of nonstationary signals, time-frequency distributio...Considering that real communication signals corrupted by noise are generally nonstationary, and timefrequency distributions are especially suitable for the analysis of nonstationary signals, time-frequency distributions are introduced for the modulation classification of communication signals： The extracted time-frequency features have good classification information, and they are insensitive to signal to noise ratio （SNR） variation. According to good classification by the correct rate of a neural network classifier, a multilayer perceptron （MLP） classifier with better generalization, as well as, addition of time-frequency features set for classifying six different modulation types has been proposed. Computer simulations show that the MLP classifier outperforms the decision-theoretic classifier at low SNRs, and the classification experiments for real MPSK signals verify engineering significance of the MLP classifier.展开更多
Since leaks in high-pressure pipelines transporting crude oil can cause severe economic losses,a reliable leak risk assessment can assist in developing an effective pipeline maintenance plan and avoiding unexpected in...Since leaks in high-pressure pipelines transporting crude oil can cause severe economic losses,a reliable leak risk assessment can assist in developing an effective pipeline maintenance plan and avoiding unexpected incidents.The fast and accurate leak detection methods are essential for maintaining pipeline safety in pipeline reliability engineering.Current oil pipeline leakage signals are insufficient for feature extraction,while the training time for traditional leakage prediction models is too long.A new leak detection method is proposed based on time-frequency features and the Genetic Algorithm-Levenberg Marquardt(GA-LM)classification model for predicting the leakage status of oil pipelines.The signal that has been processed is transformed to the time and frequency domain,allowing full expression of the original signal.The traditional Back Propagation(BP)neural network is optimized by the Genetic Algorithm(GA)and Levenberg Marquardt(LM)algorithms.The results show that the recognition effect of a combined feature parameter is superior to that of a single feature parameter.The Accuracy,Precision,Recall,and F1score of the GA-LM model is 95%,93.5%,96.7%,and 95.1%,respectively,which proves that the GA-LM model has a good predictive effect and excellent stability for positive and negative samples.The proposed GA-LM model can obviously reduce training time and improve recognition efficiency.In addition,considering that a large number of samples are required for model training,a wavelet threshold method is proposed to generate sample data with higher reliability.The research results can provide an effective theoretical and technical reference for the leakage risk assessment of the actual oil pipelines.展开更多
Objective To analyze the clinical features of the multiple trauma patients combined with spine and spinal cord injuries.Methods A retrospective study was performed in143multiple trauma patients combined with spine and...Objective To analyze the clinical features of the multiple trauma patients combined with spine and spinal cord injuries.Methods A retrospective study was performed in143multiple trauma patients combined with spine and spinal展开更多
Remote sensing image classification is the basis of remote sensing image analysis and understanding.It aims to assign each pixel an object class label.To achieve satisfactory classification accuracy,single feature is ...Remote sensing image classification is the basis of remote sensing image analysis and understanding.It aims to assign each pixel an object class label.To achieve satisfactory classification accuracy,single feature is not enough.Multiple features are usually integrated in remote sensing image classification.In this paper,a method based on neural network to combine multiple features was proposed.A single network was used to perform the task instead of ensemble of neural networks.A special architecture of network was designed to fit the task.The method effectively avoids the problems in direct conjunction of multiple features.Experiments on Indian93 data set show that the method has obvious advantages over conjunction of features on both recognition rate and training time.展开更多
In order to improve the performance of speech emotion recognition, a novel feature fusion method is proposed. Based on the global features, the local information of different kinds of features is utilized. Both the gl...In order to improve the performance of speech emotion recognition, a novel feature fusion method is proposed. Based on the global features, the local information of different kinds of features is utilized. Both the global and the local features are combined together. Moreover, the multiple kernel learning method is adopted. The global features and each kind of local feature are respectively associated with a kernel, and all these kernels are added together with different weights to obtain a mixed kernel for nonlinear mapping. In the reproducing kernel Hilbert space, different kinds of emotional features can be easily classified. In the experiments, the popular Berlin dataset is used, and the optimal parameters of the global and the local kernels are determined by cross-validation. After computing using multiple kernel learning, the weights of all the kernels are obtained, which shows that the formant and intensity features play a key role in speech emotion recognition. The classification results show that the recognition rate is 78. 74% by using the global kernel, and it is 81.10% by using the proposed method, which demonstrates the effectiveness of the proposed method.展开更多
This paper considers the problem of target and jamming recognition for the pulse Doppler radar fuze(PDRF).To solve the problem,the matched filter outputs of the PDRF under the action of target and jamming are analyzed...This paper considers the problem of target and jamming recognition for the pulse Doppler radar fuze(PDRF).To solve the problem,the matched filter outputs of the PDRF under the action of target and jamming are analyzed.Then,the frequency entropy and peak-to-peak ratio are extracted from the matched filter output of the PDRF,and the time-frequency joint feature is constructed.Based on the time-frequency joint feature,the naive Bayesian classifier(NBC)with minimal risk is established for target and jamming recognition.To improve the adaptability of the proposed method in complex environments,an online update process that adaptively modifies the classifier in the duration of the work of the PDRF is proposed.The experiments show that the PDRF can maintain high recognition accuracy when the signal-to-noise ratio(SNR)decreases and the jamming-to-signal ratio(JSR)increases.Moreover,the applicable analysis shows that he ONBCMR method has low computational complexity and can fully meet the real-time requirements of PDRF.展开更多
Scene recognition is a popular open problem in the computer vision field.Among lots of methods proposed in recent years,Convolutional Neural Network(CNN)based approaches achieve the best performance in scene recogniti...Scene recognition is a popular open problem in the computer vision field.Among lots of methods proposed in recent years,Convolutional Neural Network(CNN)based approaches achieve the best performance in scene recognition.We propose in this paper an advanced feature fusion algorithm using Multiple Convolutional Neural Network(Multi-CNN)for scene recognition.Unlike existing works that usually use individual convolutional neural network,a fusion of multiple different convolutional neural networks is applied for scene recognition.Firstly,we split training images in two directions and apply to three deep CNN model,and then extract features from the last full-connected(FC)layer and probabilistic layer on each model.Finally,feature vectors are fused with different fusion strategies in groups forwarded into SoftMax classifier.Our proposed algorithm is evaluated on three scene datasets for scene recognition.The experimental results demonstrate the effectiveness of proposed algorithm compared with other state-of-art approaches.展开更多
In this paper we propose a multiple feature approach for the normalization task which can map each disorder mention in the text to a unique unified medical language system（UMLS）concept unique identifier（CUI）. We d...In this paper we propose a multiple feature approach for the normalization task which can map each disorder mention in the text to a unique unified medical language system（UMLS）concept unique identifier（CUI）. We develop a two-step method to acquire a list of candidate CUIs and their associated preferred names using UMLS API and to choose the closest CUI by calculating the similarity between the input disorder mention and each candidate. The similarity calculation step is formulated as a classification problem and multiple features（string features,ranking features,similarity features,and contextual features） are used to normalize the disorder mentions. The results show that the multiple feature approach improves the accuracy of the normalization task from 32.99% to 67.08% compared with the Meta Map baseline.展开更多
Objective To investigate the endoscopic and pathological features and the independent risk factors for early esophageal cancer combined with multiple primary cancer.Methods Endoscopic and pathological features of 324 ...Objective To investigate the endoscopic and pathological features and the independent risk factors for early esophageal cancer combined with multiple primary cancer.Methods Endoscopic and pathological features of 324 patients diagnosed as having early esophageal cancer from January 2013 to January 2022 in Beijing FriendshipHospital wereretrospectivelycollected.Independent risk factors for early esophageal cancer combined with multiple primary cancer were selected by multivariate logistic regression analysis.Results Among the 324 patients with early esophageal cancer,47(14.51%)patients(29 metachronous and 18 synchronous)had multiple primary cancer.Multivariate logistic regression analysis showed that alcohol drinking≥5 standard drinks/day(OR=6.23,95%CI:2.49-15.57,P<0.001),submucosal layer invasion(0R=2.80,95%Cl:1.07-7.30,P=0.036),lesion location at lower esophagus(0R=4.18,95%CI:1.98-8.97,P<0.001)and multiple lesions in esophagus(0R=3.30,95%CI:1.57-6.92,P=0.002)were independent risk factors for early esophageal cancer combined with multiple primary cancer.Conclusion Alcohol drinking≥5 standard drinks/day,submucosal layer invasion,lower lesions location,and multiple lesions in the esophagus are independent risk factors that are more likely to develop multiple primary cancer in patients with early esophageal cancer.It is recommended to prioritize monitoring patients with these factors,and enhance endoscopic follow-up and assessment.展开更多
This paper presents a tool wear monitoring method in drilling process using cutting force signal. The kurtosis coefficient and the energy of a special frequency band of cutting force signals were taken as the signal f...This paper presents a tool wear monitoring method in drilling process using cutting force signal. The kurtosis coefficient and the energy of a special frequency band of cutting force signals were taken as the signal features of tool wear as well as the mean value and the standard deviation from the time and frequency domain. The relationships between the signal feature and tool wear were discussed; then the vectors constituted of the signal features were input to the artificial neural network for fusion in order to realize intelligent identification of tool wear. The experimental results show that the artificial neural network can realize fusion of multiple features effectively, but the identification precision and the extending ability are not ideal owing to the relationship between the features and the tool wear being fuzzy and not certain.展开更多
In recent years,simultaneous localization and mapping in dynamic environments(dynamic SLAM)has attracted significant attention from both academia and industry.Some pioneering work on this technique has expanded the po...In recent years,simultaneous localization and mapping in dynamic environments(dynamic SLAM)has attracted significant attention from both academia and industry.Some pioneering work on this technique has expanded the potential of robotic applications.Compared to standard SLAM under the static world assumption,dynamic SLAM divides features into static and dynamic categories and leverages each type of feature properly.Therefore,dynamic SLAM can provide more robust localization for intelligent robots that operate in complex dynamic environments.Additionally,to meet the demands of some high-level tasks,dynamic SLAM can be integrated with multiple object tracking.This article presents a survey on dynamic SLAM from the perspective of feature choices.A discussion of the advantages and disadvantages of different visual features is provided in this article.展开更多
文摘Multiple Sclerosis(MS)poses significant health risks.Patients may face neurodegeneration,mobility issues,cognitive decline,and a reduced quality of life.Manual diagnosis by neurologists is prone to limitations,making AI-based classification crucial for early detection.Therefore,automated classification using Artificial Intelligence(AI)techniques has a crucial role in addressing the limitations of manual classification and preventing the development of MS to advanced stages.This study developed hybrid systems integrating XGBoost(eXtreme Gradient Boosting)with multi-CNN(Convolutional Neural Networks)features based on Ant Colony Optimization(ACO)and Maximum Entropy Score-based Selection(MESbS)algorithms for early classification of MRI(Magnetic Resonance Imaging)images in a multi-class and binary-class MS dataset.All hybrid systems started by enhancing MRI images using the fusion processes of a Gaussian filter and Contrast-Limited Adaptive Histogram Equalization(CLAHE).Then,the Gradient Vector Flow(GVF)algorithm was applied to select white matter(regions of interest)within the brain and segment them from the surrounding brain structures.These regions of interest were processed by CNN models(ResNet101,DenseNet201,and MobileNet)to extract deep feature maps,which were then combined into fused feature vectors of multi-CNN model combinations(ResNet101-DenseNet201,DenseNet201-MobileNet,ResNet101-MobileNet,and ResNet101-DenseNet201-MobileNet).The multi-CNN features underwent dimensionality reduction using ACO and MESbS algorithms to remove unimportant features and retain important features.The XGBoost classifier employed the resultant feature vectors for classification.All developed hybrid systems displayed promising outcomes.For multiclass classification,the XGBoost model using ResNet101-DenseNet201-MobileNet features selected by ACO attained 99.4%accuracy,99.45%precision,and 99.75%specificity,surpassing prior studies(93.76%accuracy).It reached 99.6%accuracy,99.65%precision,and 99.55%specificity in binary-class classification.These results demonstrate the effectiveness of multi-CNN fusion with feature selection in improving MS classification accuracy.
基金National Key Research and Development Program of China(2022YFC3502302)National Natural Science Foundation of China(82074580)Graduate Research Innovation Program of Jiangsu Province(KYCX23_2078).
文摘Objective To construct a precise model for identifying traditional Chinese medicine(TCM)constitutions;thereby offering optimized guidance for clinical diagnosis and treatment plan-ning;and ultimately enhancing medical efficiency and treatment outcomes.Methods First;TCM full-body inspection data acquisition equipment was employed to col-lect full-body standing images of healthy people;from which the constitutions were labelled and defined in accordance with the Constitution in Chinese Medicine Questionnaire(CCMQ);and a dataset encompassing labelled constitutions was constructed.Second;heat-suppres-sion valve(HSV)color space and improved local binary patterns(LBP)algorithm were lever-aged for the extraction of features such as facial complexion and body shape.In addition;a dual-branch deep network was employed to collect deep features from the full-body standing images.Last;the random forest(RF)algorithm was utilized to learn the extracted multifea-tures;which were subsequently employed to establish a TCM constitution identification mod-el.Accuracy;precision;and F1 score were the three measures selected to assess the perfor-mance of the model.Results It was found that the accuracy;precision;and F1 score of the proposed model based on multifeatures for identifying TCM constitutions were 0.842;0.868;and 0.790;respectively.In comparison with the identification models that encompass a single feature;either a single facial complexion feature;a body shape feature;or deep features;the accuracy of the model that incorporating all the aforementioned features was elevated by 0.105;0.105;and 0.079;the precision increased by 0.164;0.164;and 0.211;and the F1 score rose by 0.071;0.071;and 0.084;respectively.Conclusion The research findings affirmed the viability of the proposed model;which incor-porated multifeatures;including the facial complexion feature;the body shape feature;and the deep feature.In addition;by employing the proposed model;the objectification and intel-ligence of identifying constitutions in TCM practices could be optimized.
文摘This review focused on the diagnosis and clinical features of multiple sclerosis(MS) in China. We have identified the published researching information from 1976 to 2008 in China. The key issues related to the diagnosis and clinical features of MS in China were summarized. The first patient with MS in China was reported in 1926 from Xiehe hospital. Case reports on MS has been increasing during recent decades. Almost all the patients with MS were confirmed by the McDonald criteria(1977) before1984. After the...
文摘Objective: To study clinical features of the patients with multiple myeloma(MM) accompanied by renal insufficiency and investigate the related risk factors of renalimpairment. Methods: A control study of clinical characteristics was performed between 91 patientswith renal insufficiency due to MM and 165 patients with normal renal function in MM during the sameperiod. The data were statistically analyzed by chi-square test and logistic regression analysis.Results: Renal insufficiency was the initial presentation in 48 (52.7%) of the 91 patients, and 30(62.5%) of the 48 patients were misdiagnosed. The prognosis of group with renal insufficiency wassignificantly poorer than that of group with normal renal function: mortality in 3 months, 3months-1 year was 26/91 vs 14/165 (P 【 0.0001), 14/91 vs 12/165 (P 【 0.05) respectively, andpatients survived 】 1 year was 18/91 vs 95/165 (P 【 0.0001). The incidence of hypercalcemia,hyperuricemic, severe anemia, high serum M-protein concentration and lytic bone lesions weresignificantly higher in renal insufficiency group than those in control group (P 【 0.05). Logisticregression analysis identified 5 risk factors of renal impairment, including, severe anemia(Exp(β)=13.819, P 【 0.0001), use of nephrotoxic drugs (Exp(β)=6.217, P = 0.001), high serumM-protein concentration (Exp(β) = 5.026, P = 0.001), male (Exp(β)=3.745, P=0.006), andhypercalcemia (Exp(β)=3A72, P=0.006), but age, serum density of uric acid, type of serum M-protein,and Bence Jones proteinuria were not significantly associated with renal insufficiency. Conclusion:Renal insufficiency was a common early complication of MM, which often resulted in misdiagnosis.The status of these patients tended to be very bad, with many other complications, when MM wasdiagnosed, so their prognosis was poor. The occurrence of renal insufficiency in patients with MMand hypercalcemia, severe anemia, high serum M-protein concentration, especially use of nephrotoxicdrugs should be alert.
基金Projects(61573380,61303185) supported by the National Natural Science Foundation of ChinaProjects(2016M592450,2017M612585) supported by the China Postdoctoral Science FoundationProjects(2016JJ4119,2017JJ3416) supported by the Hunan Provincial Natural Science Foundation of China
文摘It is easy for teenagers to view pornographic pictures on social networks. Many researchers have studied the detection of real pornographic pictures, but there are few studies on those that are artificial. In this work, we studied how to detect artificial pornographic pictures, especially when they are on social networks. The whole detection process can be divided into two stages： feature selection and picture detection. In the feature selection stage, seven types of features that favour picture detection were selected. In the picture detection stage, three steps were included. 1） In order to alleviate the imbalance in the number of artificial pornographic pictures and normal ones, the training dataset of artificial pornographic pictures was expanded. Therefore, the features which were extracted from the training dataset can also be expanded too. 2） In order to reduce the time of feature extraction, a fast method which extracted features based on the proportionally scaled picture rather than the original one was proposed. 3） Three tree models were compared and a gradient boost decision tree （GBDT） was selected for the final picture detection. Three sets of experimental results show that the proposed method can achieve better recognition precision and drastically reduce the time cost of the method.
基金supported by the Department of Science and Technology of Jilin Province (No.20200401122GX)。
文摘The performance of decoding algorithm is one of the important influential factors to determine the communication quality of optical camera communication(OCC) system. In this paper, we first propose a decoding algorithm with adaptive thresholding based on the captured pixel values under an ideal environment, and then we further propose a decoding algorithm with multiple features, which is more suitable under the existence of the interference of light sources. The algorithm firstly determines the light-emitting diode(LED) array profile information by removing the interfering light sources through geometric features, and then identifies the LED state by calculating two grayscale features, the average gray ratio(AGR) and the gradient radial inwardness(GRI) of the LEDs, and finally obtains the LED state matrix. The experimental results show that the bit error ratio(BER) of the decoding algorithm with multiple features decreases from 1×10^(-2) to 5×10^(-4) at 80 m.
基金Supported by the National Natural Science Foundation of China(61175068)
文摘The quality of expert ranking directly affects the expert retrieval precision.According to the characteristics of the expert entity,an expert ranking model based on the list with multiple features was proposed.Firstly,multiple features was selected through the analysis of expert pages;secondly,in order to learn parameters through gradient descent and construct expert ranking model,all features were integrated into ListNet ranking model;finally,expert ranking contrast experiment will be performed using the trained model.The experimental results show that the proposed method has a good effect,and the value of NDCG@1 increased14.2%comparing with the pairwise method with expert ranking.
文摘BACKGROUND：Devic＇s neuromyelitis optica （DNMO） and multiple sclerosis in Asian populations have been considered to be the same disease. However, there is an increasing number of studies suggesting that DNMO and multiple sclerosis are different diseases.OBJECTIVE：Little information is available regarding comparisons of DNMO patients between China and other countries, as well as clinical manifestations of Chinese patients with DNMO and multiple sclerosis. The present study performed a multi-center, pathological, retrospective analysis.DESIGN, TIME AND SETTING：A retrospective analysis of clinical data from seven patients with DNMO diagnosed between 1957 and 1998.PARTICIPANTS：Data from Chinese DNMO patients was provided by the Shanghai Second Medical University, Sun Yat-sen University of Medical Sciences and the First Affiliated Hospital of Harbin Medical University in China.METHODS：Clinical and pathological data from Chinese patients with DNMO were retrospectively analyzed. The clinical characteristics of DNMO were compared between Chinese and Caucasian patients. In addition, clinical and pathological differences between DNMO and multiple sclerosis Chinese patients were compared.MAIN OUTCOME MEASURES：Clinical and pathological features of Chinese patients with DNMO.RESULTS：All seven Chinese patients with DNMO exhibited abrupt onset of vision disturbance, with a disease course of 3 clays to 9 years. DNMO recurred in two of the patients. Demyelinating lesions were observed in all patients, with necrotic lesions and gitter cells in five patients, collagenous hyperplasia in one patient, and perivascular inflammatory cell infiltration in six patients. Comparison between Chinese and Caucasian DNMO patients revealed no significant differences in age at onset, clinical onset, duration, or interval between optic neuritis and myelitis. Compared with Chinese multiple sclerosis patients, Chinese DNMO patients presented with fewer recurrences, higher occurrence of necrosis, perivascular inflammatory cell infiltration and gitter cells, and a lower occurrence of collagenous hyperplasia.CONCLUSION：There was no difference in DNMO clinical features between Chinese and Caucasian patients. However, the clinical and pathological features of DNMO were different compared with multiple sclerosis in Chinese patients. Results suggested that the characteristics of DNMO in Chinese patients were significantly different than multiple sclerosis.
基金supported by Foundation of NationalNatural Science Foundation of China(81241074,81071946 and 81302040)Natural Science Foundation of Jiangsu Province(BK2012485)+4 种基金Jiangsu Province's Medical Elite Program(RC201148)a Project Funded by the Priority Academic Program Development of Jiangsu Higher Education Institutionsthe Program for Development of Innovative Research Team in the First Affiliated Hospital of NJMUClinical Research Program from Health Ministry of China(Key project 2010to 2012)Scientific Research Program for Public Interests from the Health Ministry of China(No.201202017)
文摘This study sought to analyze the clinical features and prognosis of multiple myeloma with isolated extramedullary relapse and with the absence of systemic progression.The clinical features and outcome were retrospectively analyzed in six multiple myeloma patients.These patients had secretory multiple myeloma at diagnosis.When relapsed,the dissociation between medullary and extramedullary response was detected.The serum or urine monoclonal component was extremely low or absent.The plasma cells in bone marrow were 〈5%.All patients received new targeted therapies（thalidomide or bortezomib） before extramedullary relapse.It is difficult to achieve second remission for them.Even in those showing response,the duration of response was extremely short.The median of overall survival from diagnosis and from extramedullary relapse was 19 months and 6 months,respectively.The overall survival was significantly shorter compared to the patients without extramedullary involvement（84 months,P= 0.001）.These patients exhibited a special and rare relapse pattern.Patients with this relapse pattern were resistant to current therapies,including novel targeted agents and associated with poor prognosis.
文摘Considering that real communication signals corrupted by noise are generally nonstationary, and timefrequency distributions are especially suitable for the analysis of nonstationary signals, time-frequency distributions are introduced for the modulation classification of communication signals： The extracted time-frequency features have good classification information, and they are insensitive to signal to noise ratio （SNR） variation. According to good classification by the correct rate of a neural network classifier, a multilayer perceptron （MLP） classifier with better generalization, as well as, addition of time-frequency features set for classifying six different modulation types has been proposed. Computer simulations show that the MLP classifier outperforms the decision-theoretic classifier at low SNRs, and the classification experiments for real MPSK signals verify engineering significance of the MLP classifier.
基金The National Key Research and Development Program of China:Design and Key Technology Research of Non-metallic Flexible Risers for Deep Sea Mining(2022YFC2803701)The General Program of National Natural Science Foundation of China(52071336,52374022).
文摘Since leaks in high-pressure pipelines transporting crude oil can cause severe economic losses,a reliable leak risk assessment can assist in developing an effective pipeline maintenance plan and avoiding unexpected incidents.The fast and accurate leak detection methods are essential for maintaining pipeline safety in pipeline reliability engineering.Current oil pipeline leakage signals are insufficient for feature extraction,while the training time for traditional leakage prediction models is too long.A new leak detection method is proposed based on time-frequency features and the Genetic Algorithm-Levenberg Marquardt(GA-LM)classification model for predicting the leakage status of oil pipelines.The signal that has been processed is transformed to the time and frequency domain,allowing full expression of the original signal.The traditional Back Propagation(BP)neural network is optimized by the Genetic Algorithm(GA)and Levenberg Marquardt(LM)algorithms.The results show that the recognition effect of a combined feature parameter is superior to that of a single feature parameter.The Accuracy,Precision,Recall,and F1score of the GA-LM model is 95%,93.5%,96.7%,and 95.1%,respectively,which proves that the GA-LM model has a good predictive effect and excellent stability for positive and negative samples.The proposed GA-LM model can obviously reduce training time and improve recognition efficiency.In addition,considering that a large number of samples are required for model training,a wavelet threshold method is proposed to generate sample data with higher reliability.The research results can provide an effective theoretical and technical reference for the leakage risk assessment of the actual oil pipelines.
文摘Objective To analyze the clinical features of the multiple trauma patients combined with spine and spinal cord injuries.Methods A retrospective study was performed in143multiple trauma patients combined with spine and spinal
基金National Natural Science Foundation of China(No.61101202)
文摘Remote sensing image classification is the basis of remote sensing image analysis and understanding.It aims to assign each pixel an object class label.To achieve satisfactory classification accuracy,single feature is not enough.Multiple features are usually integrated in remote sensing image classification.In this paper,a method based on neural network to combine multiple features was proposed.A single network was used to perform the task instead of ensemble of neural networks.A special architecture of network was designed to fit the task.The method effectively avoids the problems in direct conjunction of multiple features.Experiments on Indian93 data set show that the method has obvious advantages over conjunction of features on both recognition rate and training time.
基金The National Natural Science Foundation of China(No.61231002,61273266)the Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD)
文摘In order to improve the performance of speech emotion recognition, a novel feature fusion method is proposed. Based on the global features, the local information of different kinds of features is utilized. Both the global and the local features are combined together. Moreover, the multiple kernel learning method is adopted. The global features and each kind of local feature are respectively associated with a kernel, and all these kernels are added together with different weights to obtain a mixed kernel for nonlinear mapping. In the reproducing kernel Hilbert space, different kinds of emotional features can be easily classified. In the experiments, the popular Berlin dataset is used, and the optimal parameters of the global and the local kernels are determined by cross-validation. After computing using multiple kernel learning, the weights of all the kernels are obtained, which shows that the formant and intensity features play a key role in speech emotion recognition. The classification results show that the recognition rate is 78. 74% by using the global kernel, and it is 81.10% by using the proposed method, which demonstrates the effectiveness of the proposed method.
基金supported by the National Natural Science Foundation of China(Grant No.61973037 and No.61673066).
文摘This paper considers the problem of target and jamming recognition for the pulse Doppler radar fuze(PDRF).To solve the problem,the matched filter outputs of the PDRF under the action of target and jamming are analyzed.Then,the frequency entropy and peak-to-peak ratio are extracted from the matched filter output of the PDRF,and the time-frequency joint feature is constructed.Based on the time-frequency joint feature,the naive Bayesian classifier(NBC)with minimal risk is established for target and jamming recognition.To improve the adaptability of the proposed method in complex environments,an online update process that adaptively modifies the classifier in the duration of the work of the PDRF is proposed.The experiments show that the PDRF can maintain high recognition accuracy when the signal-to-noise ratio(SNR)decreases and the jamming-to-signal ratio(JSR)increases.Moreover,the applicable analysis shows that he ONBCMR method has low computational complexity and can fully meet the real-time requirements of PDRF.
文摘Scene recognition is a popular open problem in the computer vision field.Among lots of methods proposed in recent years,Convolutional Neural Network(CNN)based approaches achieve the best performance in scene recognition.We propose in this paper an advanced feature fusion algorithm using Multiple Convolutional Neural Network(Multi-CNN)for scene recognition.Unlike existing works that usually use individual convolutional neural network,a fusion of multiple different convolutional neural networks is applied for scene recognition.Firstly,we split training images in two directions and apply to three deep CNN model,and then extract features from the last full-connected(FC)layer and probabilistic layer on each model.Finally,feature vectors are fused with different fusion strategies in groups forwarded into SoftMax classifier.Our proposed algorithm is evaluated on three scene datasets for scene recognition.The experimental results demonstrate the effectiveness of proposed algorithm compared with other state-of-art approaches.
基金Supported by the National Natural Science Foundation of China(61133012,61202193,61373108)the Major Projects of the National Social Science Foundation of China(11&ZD189)+1 种基金the Chinese Postdoctoral Science Foundation(2013M540593,2014T70722)the Open Foundation of Shandong Key Laboratory of Language Resource Development and Application
文摘In this paper we propose a multiple feature approach for the normalization task which can map each disorder mention in the text to a unique unified medical language system（UMLS）concept unique identifier（CUI）. We develop a two-step method to acquire a list of candidate CUIs and their associated preferred names using UMLS API and to choose the closest CUI by calculating the similarity between the input disorder mention and each candidate. The similarity calculation step is formulated as a classification problem and multiple features（string features,ranking features,similarity features,and contextual features） are used to normalize the disorder mentions. The results show that the multiple feature approach improves the accuracy of the normalization task from 32.99% to 67.08% compared with the Meta Map baseline.
文摘Objective To investigate the endoscopic and pathological features and the independent risk factors for early esophageal cancer combined with multiple primary cancer.Methods Endoscopic and pathological features of 324 patients diagnosed as having early esophageal cancer from January 2013 to January 2022 in Beijing FriendshipHospital wereretrospectivelycollected.Independent risk factors for early esophageal cancer combined with multiple primary cancer were selected by multivariate logistic regression analysis.Results Among the 324 patients with early esophageal cancer,47(14.51%)patients(29 metachronous and 18 synchronous)had multiple primary cancer.Multivariate logistic regression analysis showed that alcohol drinking≥5 standard drinks/day(OR=6.23,95%CI:2.49-15.57,P<0.001),submucosal layer invasion(0R=2.80,95%Cl:1.07-7.30,P=0.036),lesion location at lower esophagus(0R=4.18,95%CI:1.98-8.97,P<0.001)and multiple lesions in esophagus(0R=3.30,95%CI:1.57-6.92,P=0.002)were independent risk factors for early esophageal cancer combined with multiple primary cancer.Conclusion Alcohol drinking≥5 standard drinks/day,submucosal layer invasion,lower lesions location,and multiple lesions in the esophagus are independent risk factors that are more likely to develop multiple primary cancer in patients with early esophageal cancer.It is recommended to prioritize monitoring patients with these factors,and enhance endoscopic follow-up and assessment.
文摘This paper presents a tool wear monitoring method in drilling process using cutting force signal. The kurtosis coefficient and the energy of a special frequency band of cutting force signals were taken as the signal features of tool wear as well as the mean value and the standard deviation from the time and frequency domain. The relationships between the signal feature and tool wear were discussed; then the vectors constituted of the signal features were input to the artificial neural network for fusion in order to realize intelligent identification of tool wear. The experimental results show that the artificial neural network can realize fusion of multiple features effectively, but the identification precision and the extending ability are not ideal owing to the relationship between the features and the tool wear being fuzzy and not certain.
基金This work was supported by National Natural Science Foundation of China,Nos.62002359 and 61836015the Beijing Advanced Discipline Fund,No.115200S001.
文摘In recent years,simultaneous localization and mapping in dynamic environments(dynamic SLAM)has attracted significant attention from both academia and industry.Some pioneering work on this technique has expanded the potential of robotic applications.Compared to standard SLAM under the static world assumption,dynamic SLAM divides features into static and dynamic categories and leverages each type of feature properly.Therefore,dynamic SLAM can provide more robust localization for intelligent robots that operate in complex dynamic environments.Additionally,to meet the demands of some high-level tasks,dynamic SLAM can be integrated with multiple object tracking.This article presents a survey on dynamic SLAM from the perspective of feature choices.A discussion of the advantages and disadvantages of different visual features is provided in this article.
