Classification Ability Research Articles

Application of visual multimedia technology in air transportation information service system

Abstract This paper uses visual multimedia technology to establish a model for civil aviation transportation information services. A training subset is generated with a random forest, and the strength and relevance indicators of the random forest are examined. The generated decision tree is run on the corresponding out-of-bag data to evaluate its classification ability and obtain its weights. The leaf nodes of the decision tree are normalized to calculate the out-of-bag estimation of classification strength to realize the application of visual multimedia technology in the civil aviation transportation information service system. The system scores after application are all 8 and above, and the highest can reach 10. The quality of its service efficiency and level is improved, and passengers traveling by air are satisfied.

Classifying the bacterial taxonomy with its metagenomic data using the deep neural network model

Because of the two sequenced methods stated above, SG and AMP, are being used in different ways, present a deep learning methodology for taxonomic categorization of the metagenomic information which could be utilized for either. To place the suggested pipeline to a trial, 1000 16 S full-length genomes were used to generate either SG or AMP short-reads. Then, to map sequencing as matrices into such a number space, used a k-mer model. Our analysis of the existing approaches revealed several drawbacks, including limited ability to handle complex hierarchical representations of data and suboptimal feature extraction from grid-like structures. To overcome these limitations, we introduce DBNs for feature learning and dimensionality reduction, and CNNs for efficient processing of grid-like metagenomic data. Finally, a training set for every taxon was obtained by training two distinct deep learning constructions, specifically deep belief network (DBN) and convolutional neural network (CNN). This examined the proposed methodology to determine the best factor that determines and compared findings to the classification abilities offered by the RDP classifier, a standard classifier for bacterium identification. These designs outperform using RDP classifiers at every taxonomic level. So, at the genetic level, for example, both CNN and DBN achieved 91.4% accuracy using AMP short-reads, but the RDP classifier achieved 83.9% with the same information. This paper, suggested a classification method for 16 S short-read sequences created on k-mer representations and a deep learning structure, that every taxon creates a classification method. The experimental findings validate the suggested pipelines as a realistic strategy for classifying bacterium samples; as a result, the technique might be included in the most commonly used tools for the metagenomic research. According to the outcomes, it could be utilized to effectively classify either SG or AMP information.

Label-Free Cell Detection of Acute Leukemia Using High-Content Morphological Profiling in Flow

Background: Early diagnosis and prompt initiation of appropriate treatment are critical for improving the prognosis of acute leukemia. Acute leukemia is typically diagnosed through microscopic morphological examination of bone marrow smears and flow cytometric immunophenotyping of bone marrow cells stained with fluorophore-conjugated antibodies. However, these diagnostic processes require trained professionals and are time and resource-intensive. Here, we present a novel diagnostic approach using ghost cytometry (GC), a recently developed high-content flow cytometric approach that leverages machine vision-based, stain-free, high-speed morphological characterization and analysis of cells. Methods: Label-free morphological information of cells was acquired as compressive imaging temporal waveforms. These waveforms were directly analyzed using the support vector machine (SVM) algorithm without computational image production, enabling high-speed and accurate information processing. Conventional flow cytometric data modalities, such as forward-scattering (FSC), backscattering (BSC), and fluorescence signals from biological labeling, were used as ground truth labels to identify and annotate blast and normal cells in bone marrow (BM) based on flow cytometric gating schemes. Subsequently, we trained a leukemia cell classifier using the annotated GC (compressive imaging) waveforms and evaluated its classification ability by comparing the predicted results with the ground truth labels. Finally, we applied the trained classifier to unidentified GC waveforms (a test dataset not used for classifier development) to demonstrate the detection of blast cells in BM based on their morphology, without relying on biological labels. Following this protocol, we first trained and tested a machine classifier using a human leukemia NB-4 cell line spiked into BM from a healthy donor. Next, we trained and tested two classifiers using BM aspirates from patients diagnosed with acute lymphoblastic leukemia (ALL) and acute myeloid leukemia (AML), where CD45 was used as the ground truth marker of leukemic cells. Results: The leukemia cell classifier, developed using a human NB-4 cell line spiked into BM cells from a healthy donor, demonstrated excellent classification accuracy with an ROC-AUC score of 0.9998. The high classification accuracy was reproducible across different spike-in concentrations ranging from 1% to 95%. The classifiers trained using BM cells from patients diagnosed with ALL and AML showed high ROC-AUC scores of 0.986 and 0.941, respectively. When we used the classifiers to evaluate blast cell proportions in test datasets that were not used to develop the classifiers, they were also highly accurate in identifying the percentage of blast cells: 56.8% for ALL with a decision boundary of SVM scores at 0, and 30.4% for AML with a decision boundary of SVM scores at 0.37, when compared to May-Grunwald-Giemsa staining of the same cases by medical technologists at diagnosis (60.0% for ALL and 31.2% for AML). Conclusions: Here, we present a novel diagnostic approach that leverages machine vision-based, stain-free, high-speed morphological characterization and analysis of cells. We demonstrate that the approach can detect leukemic cells from the bone marrow cells of patients diagnosed with ALL and AML, without requiring biological staining. The method presented here holds promise as a rapid, precise, simple, and cost-effective method for the diagnosis of acute leukemia in clinical settings.

High-resolution art recognition of modern packaging design and images based on texture image classification

Abstract First, this paper proposes the EPNN algorithm to recognize the high-resolution art of texture images. Then, a multi-scale multivariate image analysis method for color-textured surface classification is established. Regarding probabilistic neural networks, a differential evolutionary algorithm is proposed to optimize the smoothing parameters of basic probabilistic neural networks. Texture feature extraction involves extracting energy and statistical features of texture images using tree-structured wavelet packet decomposition and statistical-based methods. The image classification is performed by estimating similarity distances and classifying typical feature clusters. The results show that in terms of recognition ability, the proposed EPNN in this paper achieves an average improvement of 0.216 in CCP compared to the LBP method. In terms of classification ability, the proposed multi-scale multivariate image analysis color texture surface classification method in this paper generally achieves more than 10% higher classification ability than LGP in CUReT and Outex texture image libraries.

Research on fault diagnosis of electric submersible pump based on improved convolutional neural network with Bayesian optimization

A conventional intelligent fault diagnosis approach for electric submersible pumps (ESPs) is heavily dependent on manual expertise for feature extraction. Meanwhile, a conventional convolutional neural network (CNN) exhibits an excess of parameters and requires a substantial volume of training samples. In this paper, a fault diagnosis algorithm of ESPs based on a Bayesian optimization-one-dimensional convolutional neural network-support vector machine (BO-1DCNN-SVM) is proposed by combining a 1DCNN with a SVM and using the algorithm BO to tune the improved 1DCNN. First, the method uses the self-extracting feature capability of the 1DCNN to solve the problem that traditional diagnosis methods over-rely on manual experience extraction. Meanwhile, the last layer of the convolutional neural network Softmax layer is replaced by the SVM to effectively process a few sample data. The accuracy and generalization ability of the fault classification of the electric submersible pump are improved. Then, the Bayesian optimization algorithm is used to find the optimal combination of hyperparameters for the improved 1DCNN-SVM model to further improve the prediction performance of the fault diagnosis model. Finally, the experimental results achieved a classification accuracy of 96.64%, which is 5% higher than existing CNN approaches with data samples of similar scale in this paper. The proposed method also proved to be highly accurate and robust in fault diagnosis.

Fault Diagnosis of Centrifugal Fan Based on Grid Search Optimized Voting Weighted KNN

Fan plays the roles of the forced draft fan, induced draft fan, primary air fan, seal fan, and powder exhauster. As an important auxiliary of the fossil-fuel power station, its working environment is harsh. Timely and efficient fault diagnosis can effectively reduce equipment failure and shutdown losses, and improve the efficiency of thermal power generation. K-Nearest Neighbour (KNN) has good classification ability for non-stationary data samples. In response to the shortcomings of the traditional KNN algorithm, this paper constructs a fault diagnosis model based on the voting weighted k-nearest neighbor algorithm. The model constructs a weight voting equation that is negatively correlated with the distance value based on the first k-nearest neighbors and then conducts fault diagnosis based on the voting score. We use grid search to optimize the model and select the k value in the model, and the relationship between the k value and accuracy was verified. The grid search optimization voting weighted k-nearest neighbor is used to diagnose the faults of nine common operating states of centrifugal fans, and the diagnostic accuracy can reach 100%.

Parallel CNN-ELM: A multiclass classification of chest X-ray images to identify seventeen lung diseases including COVID-19.

Numerous epidemic lung diseases such as COVID-19, tuberculosis (TB), and pneumonia have spread over the world, killing millions of people. Medical specialists have experienced challenges in correctly identifying these diseases due to their subtle differences in Chest X-ray images (CXR). To assist the medical experts, this study proposed a computer-aided lung illness identification method based on the CXR images. For the first time, 17 different forms of lung disorders were considered and the study was divided into six trials with each containing two, two, three, four, fourteen, and seventeen different forms of lung disorders. The proposed framework combined robust feature extraction capabilities of a lightweight parallel convolutional neural network (CNN) with the classification abilities of the extreme learning machine algorithm named CNN-ELM. An optimistic accuracy of 90.92% and an area under the curve (AUC) of 96.93% was achieved when 17 classes were classified side by side. It also accurately identified COVID-19 and TB with 99.37% and 99.98% accuracy, respectively, in 0.996 microseconds for a single image. Additionally, the current results also demonstrated that the framework could outperform the existing state-of-the-art (SOTA) models. On top of that, a secondary conclusion drawn from this study was that the prospective framework retained its effectiveness over a range of real-world environments, including balanced-unbalanced or large-small datasets, large multiclass or simple binary class, and high- or low-resolution images. A prototype Android App was also developed to establish the potential of the framework in real-life implementation.

Predicting rock-paper-scissors choices based on single-trial EEG signals.

Decision prediction based on neurophysiological signals is of great application value in many real-life situations, especially in human-AI collaboration or counteraction. Single-trial analysis of electroencephalogram (EEG) signals is a very valuable step in the development of an online decision-prediction system. However, previous EEG-based decision-prediction methods focused mainly on averaged EEG signals of all decision-making trials to predict an individual's general decision tendency (e.g., risk seeking or aversion) over a period rather than on a specific decision response in a single trial. In the present study, we used a rock-paper-scissors game, which is a common multichoice decision-making task, to explore how to predict participants' single-trial choice with EEG signals. Forty participants, comprising 20 females and 20 males, played the game with a computer player for 330 trials. Considering that the decision-making process of this game involves multiple brain regions and neural networks, we proposed a new algorithm named common spatial pattern-attractor metagene (CSP-AM) to extract CSP features from different frequency bands of EEG signals that occurred during decision making. The results showed that a multilayer perceptron classifier achieved an accuracy significantly exceeding the chance level among 88.57% (31 of 35) of participants, verifying the classification ability of CSP features in multichoice decision-making prediction. We believe that the CSP-AM algorithm could be used in the development of proactive AI systems.

DRC-Net Method for Two-dimensional Spectral Classification

Spectral classification plays a crucial role in the analysis of astronomical data. Currently, stellar spectral classification primarily relies on one-dimensional (1D) spectra and necessitates a sufficient signal-to-noise ratio (S/N). However, in cases where the S/N is low, obtaining valuable information becomes impractical. In this paper, we propose a novel model called DRC-Net (Double-branch celestial spectral classification network based on residual mechanisms) for stellar classification, which operates solely on two-dimensional (2D) spectra. The model consists of two branches that use 1D convolutions to reduce the dimensionality of the 2D spectral composed of both blue and red arms. In the following, the features extracted from both branches are fused, and the fused result undergoes further feature extraction before being fed into the classifier for final output generation. The data set is from the Large Sky Area Multi-Object Fiber Spectroscopic Telescope, comprising 15,680 spectra of F, G, and K types. The preprocessing process includes normalization and the early stopping mechanism. The experimental results demonstrate that the proposed DRC-Net achieved remarkable classification precision of 93.0%, 83.5%, and 86.9% for F, G, and K types, respectively, surpassing the performance of 1D spectral classification methods. Furthermore, different S/N intervals are tested to judge the classification ability of DRC-Net. The results reveal that DRC-Net, as a 2D spectral classification model, can deliver superior classification outcomes for the spectra with low S/Ns. These experimental findings not only validate the efficiency of DRC-Net but also confirm the enhanced noise resistance ability exhibited by 2D spectra.

Multimodal fusion sensitive information classification based on mixed attention and CLIP model1

Social network attackers leverage images and text to disseminate sensitive information associated with pornography, politics, and terrorism,causing adverse effects on society.The current sensitive information classification model does not focus on feature fusion between images and text, greatly reducing recognition accuracy.To address this problem, we propose an attentive cross-modal fusion model (ACMF), which utilizes mixed attention mechanism and the Contrastive Language-Image Pre-training model.Specifically, we employ a deep neural network with a mixed attention mechanism as a visual feature extractor. This allows us to progressively extract features at different levels. We combine these visual features with those obtained from a text feature extractor and incorporate image-text frequency domain information at various levels to enable fine-grained modeling. Additionally, we introduce a cyclic attention mechanism and integrate the Contrastive Language-Image Pre-training model to establish stronger connections between modalities, thereby enhancing classification performance.Experimental evaluations conducted on sensitive information datasets collected demonstrate the superiority of our method over other baseline models. The model achieves an accuracy rate of 91.4% and an F1-score of 0.9145. These results validate the effectiveness of the mixed attention mechanism in enhancing the utilization of important features. Furthermore, the effective fusion of text and image features significantly improves the classification ability of the deep neural network.

Stable isotopic fingerprinting of authentic basmati rice from Pakistan

Basmati rice is a popular, high-value aromatic rice which is an easy target for fraudulent activities such as mislabeling and substitution with non-basmati cultivars. Bulk isotope ratio mass spectrometry (IRMS) combined with multivariate analysis was employed to develop a model to identify the geographical origin of rice and authenticate different rice cultivars from Pakistan. ANOVA showed significant statistical differences for δ13C, δ15N, δ2H and δ18O isotopes amongst different basmati and non-basmati rice cultivars. δ2H and δ18O values showed a larger variation between basmati and non-basmati rice cultivars. Multivariate ANOVA showed a significant influence on rice from different regions, cultivars and their stable isotopic values. Regional effects contributed the highest variation for both δ13C and δ15N isotopes (56.6 % and 42.7 %), whereas cultivar type largely contributed to differences in δ2H and δ18O values. Finally, supervised classification models (LDA and PLS-DA) were constructed to assess origin classification ability. The PLS-DA model achieved a higher origin classification accuracy in both training and validation sets (76.7 % and 70.0 %, respectively). In conclusion, isotopic fingerprints along with multivariate statistical analysis showed good potential to characterize rice according to cultivar type and production region. This study provides valuable insights to authenticate Pakistan basmati rice from other non-basmati cultivars, and will be instrumental in developing new tools for industry and regulatory agencies to control fraudulent labeling of basmati rice.

Exploiting local label correlation from sample perspective for multi-label classification via three-way decision theory

In multi-label classification, the expansion of output dimension seriously interferes learning performance, and even fails to build a joint prediction model. In order to restrain the proliferation of multi-label classifier’s hypothesis space, the current works focus on the application of global positive label correlation. However, the “black or white” mechanism ignore other possible forms of label correlation, such as negative or neutral correlation. By introducing the doctrine of the mean, three-way decision (3WD) theory provides a solution for in-depth research on local label correlation, and aims to handle the uncertainty of multi-label learning tasks. In this paper, a novel learning algorithm for multi-label joint classification, namely ML-3WD, is proposed by considering the 3WD label correlation from the perspective of samples. According to the weights of different features on any label, the comprehensive loss of each sample to three action strategies can be measured. Obviously, the 3WD rules for any label variable in multi-label output space is obtained. By aggregating the cutting thresholds between different labels, the division principles of 3WD label correlation are further established. Given any multi-label sample, the local fuzzy membership to co-occurrence or mutual state for label pair is examined based on kernelized fuzzy rough sets. The 3WD local label relevance of each sample is confirmed, that is, positive, negative or neutral. The global application strategy for multi-label classification is utilized to avoid over-fitting induced by local mining strategy. Based on the integral mean of the distribution of 3WD local label relevance in multi-label sample space, two different versions of empirical label relevance are constructed. By constraining the relative position between sub-separation hyperplanes, the 3WD label correlation distribution-based model for multi-label joint classification is designed. The experiment results on fifteen real world multi-label datasets reflect that our algorithm achieves good classification ability and versatility. The impact of core parameters on learning performance is also dissected.

Classification of integers based on residue classes via modern deep learning algorithms

Judging whether an integer can be divided by prime numbers such as 2 or 3 may appear trivial to human beings, but it can be less straightforward for computers. Here, we tested multiple deep learning architectures and feature engineering approaches to classifying integers based on their residues when divided by small prime numbers. We found that the ability of classification critically depends on the feature space. We also evaluated automated machine learning (AutoML) platforms from Amazon, Google, and Microsoft and found that, without appropriately engineered features, they failed on this task. Furthermore, we introduced a method that utilizes linear regression on Fourier series basis vectors and demonstrated its effectiveness. Finally, we evaluated large language models (LLMs) such as GPT-4, GPT-J, LLaMA, and Falcon, and we demonstrated their failures. In conclusion, feature engineering remains an important task to improve performance and increase interpretability of machine learning models, even in the era of AutoML and LLMs.

Bayesian belief network modelling approach for predicting and ranking risk factors for malaria infections among children under 5 years in refugee settlements in Uganda

BackgroundMalaria risk factors at household level are known to be complex, uncertain, stochastic, nonlinear, and multidimensional. The interplay among these factors, makes targeted interventions, and resource allocation for malaria control challenging. However, few studies have demonstrated malaria’s transmission complexity, control, and integrated modelling, with no available evidence on Uganda’s refugee settlements. Using the 2018–2019 Uganda’s Malaria Indicator Survey (UMIS) data, an alternative Bayesian belief network (BBN) modelling approach was used to analyse, predict, rank and illustrate the conceptual reasoning, and complex causal relationships among the risk factors for malaria infections among children under-five in refugee settlements of Uganda.MethodsIn the UMIS, household level information was obtained using standardized questionnaires, and a total of 675 children under 5 years were tested for malaria. From the dataset, a casefile containing malaria test results, demographic, social-economic and environmental information was created. The casefile was divided into a training (80%, n = 540) and testing (20%, n = 135) datasets. The training dataset was used to develop the BBN model following well established guidelines. The testing dataset was used to evaluate model performance.ResultsModel accuracy was 91.11% with an area under the receiver-operating characteristic curve of 0.95. The model’s spherical payoff was 0.91, with the logarithmic, and quadratic losses of 0.36, and 0.16 respectively, indicating a strong predictive, and classification ability of the model. The probability of refugee children testing positive, and negative for malaria was 48.1% and 51.9% respectively. The top ranked malaria risk factors based on the sensitivity analysis included: (1) age of child; (2) roof materials (i.e., thatch roofs); (3) wall materials (i.e., poles with mud and thatch walls); (4) whether children sleep under insecticide-treated nets; 5) type of toilet facility used (i.e., no toilet facility, and pit latrines with slabs); (6) walk time distance to water sources (between 0 and 10 min); (7) drinking water sources (i.e., open water sources, and piped water on premises).ConclusionRanking, rather than the statistical significance of the malaria risk factors, is crucial as an approach to applied research, as it helps stakeholders determine how to allocate resources for targeted malaria interventions within the constraints of limited funding in the refugee settlements.

Leveraging High-Resolution Long-Wave Infrared Hyperspectral Laboratory Imaging Data for Mineral Identification Using Machine Learning Methods

Laboratory-based hyperspectral imaging (HSI) is an optical non-destructive technology used to extract mineralogical information from bedrock drill cores. In the present study, drill core scanning in the long-wave infrared (LWIR; 8000–12,000 nm) wavelength region was used to map the dominant minerals in HSI pixels. Machine learning classification algorithms, including random forest (RF) and support vector machine, have previously been applied to the mineral characterization of drill core hyperspectral data. The objectives of this study are to expand semi-automated mineral mapping by investigating the mapping accuracy, generalization potential, and classification ability of cutting-edge methods, such as various ensemble machine learning algorithms and deep learning semantic segmentation. In the present study, the mapping of quartz, talc, chlorite, and mixtures thereof in HSI data was performed using the ENVINet5 algorithm, which is based on the U-net deep learning network and four decision tree ensemble algorithms, including RF, gradient-boosting decision tree (GBDT), light gradient-boosting machine (LightGBM), AdaBoost, and bagging. Prior to training the classification models, endmember selection was employed using the Sequential Maximum Angle Convex Cone endmember extraction method to prepare the samples used in the model training and evaluation of the classification results. The results show that the GBDT and LightGBM classifiers outperformed the other classification models with overall accuracies of 89.43% and 89.22%, respectively. The results of the other classifiers showed overall accuracies of 87.32%, 87.33%, 82.74%, and 78.32% for RF, bagging, ENVINet5, and AdaBoost, respectively. Therefore, the findings of this study confirm that the ensemble machine learning algorithms are efficient tools to analyze drill core HSI data and map dominant minerals. Moreover, the implementation of deep learning methods for mineral mapping from HSI drill core data should be further explored and adjusted.

Oral cancer detection using convolutional neural network optimized by combined seagull optimization algorithm

Early diagnosis of oral cancer is crucial for improving patient outcomes and saving lives. However, inaccurate and improper diagnosis can hinder effective treatment. This paper presents a novel method for detecting oral cancer using an optimized version of Convolutional Neural Network (CNN). While basic CNNs have been widely used for image classification tasks, the incorporation of the Seagull Optimization Algorithm and Particle Swarm Optimization Algorithm in optimizing the CNN architecture specifically for oral cancer detection is a unique approach that is provided in this study. By combining these algorithms, the proposed method optimizes the CNN's architecture, parameters, and training process specifically for oral cancer detection. This optimization enhances the performance and accuracy of the CNN in identifying cancerous regions in oral images. Unlike previous approaches, our method incorporates advanced image processing techniques, including noise reduction, contrast enhancement, and data augmentation, to enhance the quality of input data extracted from the Oral Cancer (Lips and Tongue) images (OCI) dataset. The optimized CNN architecture uses its ability to learn intricate patterns and features from the enhanced images, enabling more accurate identification of cancerous regions. To evaluate the effectiveness of our approach, we compare it against Textural analysis, FCM, CNN, R-CNN, and ResNet-101 using four measurement indices. Results demonstrate that our proposed CSOA-based CNN system achieves the highest accuracy rate (96.94%) compared to other methods, indicating its superior performance in oral cancer detection. Furthermore, our precision rate of 94.65% and recall rate of 91.60% highlight the model's high correctness and positive classification ability. Finally, our proposed method achieves the highest F1-score (88.55%), emphasizing its superiority over other comparative methods. Through our innovative integration of the Seagull Optimization Algorithm and Particle Swarm Optimization Algorithm with CNN, coupled with advanced image processing techniques, we provide a reliable and effective solution for early detection of oral cancer.

Identification of DNA N4-methylcytosine Sites via Multiview Kernel Sparse Representation Model

Identifying DNA N4-methylcytosine (4mC) sites is of great significance in biological research, such as chromatin structure, DNA stability, DNA-protein interaction and controlling gene expression. However, the traditional sequencing technology to identify 4mC sites is very time-consuming. In order to detect 4mC sites, we develop a multi-view learning method for achieving more effectively via merging multiple feature spaces. Furthermore, we think about whether the multi-view learning method can improve the across species classification ability by fusing data of multiple species. In our study, we propose a multi-view Laplacian kernel sparse representation-based classifier, called MvLapKSRC-HSIC. First, we make use of three feature extraction methods (PSTNP, NCP, DPP) to extract the DNA sequence features. MvLapKSRC-HSIC uses a kernel sparse representation-based classifier with graph regularization. In order to maintain the independence between various views, we add a multi-view regularization term constructed by Hilbert-Schmidt independence criterion (HSIC). In the experiments, MvLapKSRC-HSIC is applied on six datasets, so as to compare with other popular methods in single species and cross-species experiments. All experimental results show that MvLapKSRC-HSIC is superior to other outstanding methods on both single species and cross-species. Importantly, MvLapKSRC-HSIC can identify a series of potential DNA 4mC sites, which have not yet been experimentally evaluate on multiple species and merit further research.

Social Image–Text Sentiment Classification With Cross-Modal Consistency and Knowledge Distillation

Social media sentiment analysis, which aims to evaluate the attitudes of online users based on their posts, has attracted significant research attention due to its successful application in the field of social media monitoring. It is a beneficial way to utilize multimodal information uploaded by users in order to improve sentiment classification ability. However, existing multimodal fusion-based approaches continue to face difficulties due to the issues of between-modality semantic inconsistency and missing modality. To address these issues, we propose a cross-modal consistency modeling-based knowledge distillation framework for image-text sentiment classification of social media data. Specifically, we design a hybrid curriculum learning strategy to measure the semantic consistency of multimodal data, then gradually train all image-text pairs from easy to hard, which can effectively handle the massive amounts of noise caused by inconsistencies between image and text data on social media. Moreover, in order to alleviate the problem of missing images in unimodal posts, we propose a privileged feature distillation method, in which the teacher model additionally considers images as privileged features, to transfer the visual knowledge to the student model, thereby enhancing the accuracy for text sentiment classification. Extensive experiments conducted over three real-world social media datasets demonstrate the effectiveness and superiority of the proposed multimodal sentiment analysis model.

Deep Learning Based Obstacle Awareness from Airborne Optical Sensors

Aviation statistics identify collision with terrain and obstacles as a leading cause of helicopter accidents. Assisting helicopter pilots in detecting the presence of obstacles can greatly mitigate the risk of collisions. However, only a limited number of helicopters in operation have an installed helicopter terrain awareness and warning system (HTAWS), while the cost of active obstacle warning systems remains prohibitive for many civil operators. In this work, we apply machine learning to automate obstacle detection and classification in combination with commercially available airborne optical sensors. While numerous techniques for learning-based object detection have been published in the literature, many of them are data and computation intensive. Our approach seeks to balance the detection and classification accuracy of the method with the size of the training data required and the runtime. Specifically, our approach combines the invariant feature extraction ability of pretrained deep convolutional neural networks (CNNs) and the high-speed training and classification ability of a novel, proprietary frequency-domain support vector machine (SVM) method. We describe our experimental setup comprising the CNN + SVM model and datasets of predefined classes of obstacles—pylons, chimneys, antennas, TV towers, wind turbines, helicopters—synthesized from prerecorded airborne video sequences of low-altitude helicopter flight. We analyze the detection performance using average precision, average recall, and runtime performance metrics on representative test data. Finally, we present a simple architecture for real-time, onboard implementation and discuss the obstacle detection performance of recently concluded flight tests.

Prognostic value of the Walch classification for patients before and after shoulder arthroplasty performed for osteoarthritis with an intact rotator cuff

The Walch classification is commonly utilized by surgeons when determining the treatment of osteoarthritis (OA). However, its utility in prognosticating patient clinical state before and after TSA remains unproven. We assessed the prognostic value of the modified Walch glenoid classification on preoperative clinical state and postoperative clinical and radiographic outcomes in total shoulder arthroplasty (TSA). A prospectively-collected, multi-center database for a single-platform TSA system was queried for patients with rotator cuff-intact OA and minimum 2 year follow-up after anatomic and reverse TSA (aTSA, rTSA). Differences in patient-reported outcome scores (PROMS) [SST, ASES, SPADI, VAS Pain, Shoulder Function score], combined patient-reported and clinical-input scores (Constant, UCLA, SAS), active range of motion (ROM) values (forward elevation [FE], abduction, external rotation [ER], internal rotation [IR], and radiographic outcomes (humeral and glenoid radiolucency line rates, scapula notching rate) were stratified and compared by glenoid deformity type per the Walch classification for aTSA and rTSA cohorts. Comparisons were performed to assess the ability of the Walch classification to predict the preop, postop, and improved state after TSA. 1,008 TSAs were analyzed including 576 aTSA and 432 rTSA. Comparison of outcomes between Walch glenoid types resulted in 15 pairwise comparisons of 12 clinical outcome metrics, yielding 180 total Walch glenoid pairwise comparisons for each clinical state (preoperative, postoperative, improvement). Of the 180 possible pairwise Walch glenoid type / metric comparisons studied for aTSA and rTSA cohorts, <6% and < 2% significantly differed in aTSA and rTSA cohorts, respectively. Significant differences based on Walch type were seen after adjustment for multiple pairwise comparisons in the aTSA cohort for FE and ER preoperatively, the Constant score postoperatively, and for abduction, FE, ER, Constant score, and SAS score for pre- to postoperative improvement. In the rTSA cohort, significant differences were only seen in abduction and Constant score both postoperatively and for pre- to postoperative improvement. There were no statistically significant differences in humeral lucency rate, glenoid lucency rate (aTSA), scapular notching rate (rTSA), complication rates, or revision rates between Walch glenoid types after TSA. Although useful for describing degenerative changes to the glenohumeral joint, we demonstrate a weak association between preoperative glenoid morphology according to the Walch classification and clinical state when evaluating patients undergoing TSA for rotator cuff-intact OA. Alternative glenoid classification systems or predictive models should be considered to provide more precise prognoses for patients undergoing TSA for rotator cuff-intact OA.