Search results

The purpose of the study is to address the problems of low accuracy and missed detection of occluded pedestrians and small target pedestrians when using the YOLOX general object detection algorithm for pedestrian detection. This study proposes a multi-level fine-grained YOLOX pedestrian detection algorithm.

First, to address the problem of the original YOLOX algorithm in obtaining a single perceptual field for the feature map before feature fusion, this study improves the PAFPN structure by adding the ResCoT module to increase the diversity of the perceptual field of the feature map and divides the pedestrian multi-scale features into finer granularity. Second, for the CSPLayer of the PAFPN, a weight gain-based normalization-based attention module (NAM) is proposed to make the model pay more attention to the context information when extracting pedestrian features and highlight the salient features of pedestrians. Finally, the authors experimentally determined the optimal values for the confidence loss function.

The experimental results show that, compared with the original YOLOX algorithm, the AP of the improved algorithm increased by 2.90%, the Recall increased by 3.57%, and F1 increased by 2% on the pedestrian dataset.

The multi-level fine-grained YOLOX pedestrian detection algorithm can effectively improve the detection of occluded pedestrians and small target pedestrians.

The authors introduce a multi-level fine-grained ResCoT module and a weight gain-based NAM attention module.

This study aims to construct a sentiment series generation method for danmu comments based on deep learning, and explore the features of sentiment series after clustering.

This study consisted of two main parts: danmu comment sentiment series generation and clustering. In the first part, the authors proposed a sentiment classification model based on BERT fine-tuning to quantify danmu comment sentiment polarity. To smooth the sentiment series, they used methods, such as comprehensive weights. In the second part, the shaped-based distance (SBD)-K-shape method was used to cluster the actual collected data.

The filtered sentiment series or curves of the microfilms on the Bilibili website could be divided into four major categories. There is an apparently stable time interval for the first three types of sentiment curves, while the fourth type of sentiment curve shows a clear trend of fluctuation in general. In addition, it was found that “disputed points” or “highlights” are likely to appear at the beginning and the climax of films, resulting in significant changes in the sentiment curves. The clustering results show a significant difference in user participation, with the second type prevailing over others.

Their sentiment classification model based on BERT fine-tuning outperformed the traditional sentiment lexicon method, which provides a reference for using deep learning as well as transfer learning for danmu comment sentiment analysis. The BERT fine-tuning–SBD-K-shape algorithm can weaken the effect of non-regular noise and temporal phase shift of danmu text.

The problem of image retrieval and image description exists in various fields. In this paper, a model of content-based image retrieval and image content extraction based on the KD-Tree structure was proposed.

A Random Forest structure was built to classify the objects on each image on the basis of the balanced multibranch KD-Tree structure. From that purpose, a KD-Tree structure was generated by the Random Forest to retrieve a set of similar images for an input image. A KD-Tree structure is applied to determine a relationship word at leaves to extract the relationship between objects on an input image. An input image content is described based on class names and relationships between objects.

A model of image retrieval and image content extraction was proposed based on the proposed theoretical basis; simultaneously, the experiment was built on multi-object image datasets including Microsoft COCO and Flickr with an average image retrieval precision of 0.9028 and 0.9163, respectively. The experimental results were compared with those of other works on the same image dataset to demonstrate the effectiveness of the proposed method.

A balanced multibranch KD-Tree structure was built to apply to relationship classification on the basis of the original KD-Tree structure. Then, KD-Tree Random Forest was built to improve the classifier performance and retrieve a set of similar images for an input image. Concurrently, the image content was described in the process of combining class names and relationships between objects.

This paper aims to propose a classification method for steel strip surface defects based on a mixed attention mechanism to achieve fast and accurate classification performance. The traditional method of classifying surface defects of hot-rolled steel strips has the problems of low recognition accuracy and low efficiency in the industrial complex production environment.

The authors selected min–max scaling comparison method to filter the training results of multiple network models on the steel strip surface defect data set. Then, the best comprehensive performance model EfficientNet-B0 was refined. Based on this, the authors proposed two mixed attention addition methods, which include squeeze-excitation spatial mixed module and multilayer mixed attention mechanism (MMAM) module, respectively.

With these two methods, the authors achieved 96.72% and 97.70% recognition accuracy on the steel strip data set after data augmentation for adapting to the complex production environment, respectively. Using the transfer learning method, the EfficientNet-B0 based on MMAM obtained 100% recognition accuracy.

This study not only focuses on improving the recognition accuracy of the network model itself but also considers other performance indicators of the network, which are rarely considered by many researchers. The authors further improve the intelligent production technique and address this issue. Both methods proposed in this paper can be applied to embedded equipment, which can effectively improve steel strip factory production efficiency and reduce material and time loss.

Fitness service companies often promote the companies' personal training service by attributing trainers' competent characteristics, qualifications or/and service provision to their effort or talent. This promotion is called performance attribution promotion. Utilizing attribution theory and the theory's adjacent studies, this study investigated whether and why performance attribution promotion affects consumers' service purchase of personal fitness training.

The authors developed the experimental stimuli of performance attribution promotion and validated those through a pretest (N = 200). Using the validated stimuli, the authors conducted an experiment with employing a single factor between-subject design (performance attribution promotion: effort vs talent) based on random assignment (N = 200).

The analysis results revealed that attributing trainers' competent characteristics, qualifications or/and service provision to effort (vs talent) leads to a higher level of service registration intention. Moreover, this effect was mediated by the perceived teaching expertise but not by the perceived teaching trustworthiness.

These findings enrich the literature by illuminating a new mechanism and consequence of performance attribution promotion. The authors' study also extends the marketing studies related to expertise perception by presenting the attribution of visible features as one of the characteristics determining expertise perception. Finally, the authors' findings also have implications for fitness service companies and other stakeholders that seek to effectively leverage trainers' competent outcomes for consumer acquisition.

The growing availability of naturalistic driving datasets (NDDs) presents a valuable opportunity to develop various models for autonomous driving. However, while current NDDs include data on vehicles with and without intended driving behavior changes, they do not explicitly demonstrate a type of data on vehicles that intend to change their driving behavior but do not execute the behaviors because of safety, efficiency, or other factors. This missing data is essential for autonomous driving decisions. This study aims to extract the driving data with implicit intentions to support the development of decision-making models.

According to Bayesian inference, drivers who have the same intended changes likely share similar influencing factors and states. Building on this principle, this study proposes an approach to extract data on vehicles that intended to execute specific behaviors but failed to do so. This is achieved by computing driving similarities between the candidate vehicles and benchmark vehicles with incorporation of the standard similarity metrics, which takes into account information on the surrounding vehicles' location topology and individual vehicle motion states. By doing so, the method enables a more comprehensive analysis of driving behavior and intention.

The proposed method is verified on the Next Generation SIMulation dataset (NGSim), which confirms its ability to reveal similarities between vehicles executing similar behaviors during the decision-making process in nature. The approach is also validated using simulated data, achieving an accuracy of 96.3 per cent in recognizing vehicles with specific driving behavior intentions that are not executed.

This study provides an innovative approach to extract driving data with implicit intentions and offers strong support to develop data-driven decision-making models for autonomous driving. With the support of this approach, the development of autonomous vehicles can capture more real driving experience from human drivers moving towards a safer and more efficient future.

According to the Indian Sign Language Research and Training Centre (ISLRTC), India has approximately 300 certified human interpreters to help people with hearing loss. This paper aims to address the issue of Indian Sign Language (ISL) sentence recognition and translation into semantically equivalent English text in a signer-independent mode.

This study presents an approach that translates ISL sentences into English text using the MobileNetV2 model and Neural Machine Translation (NMT). The authors have created an ISL corpus from the Brown corpus using ISL grammar rules to perform machine translation. The authors’ approach converts ISL videos of the newly created dataset into ISL gloss sequences using the MobileNetV2 model and the recognized ISL gloss sequence is then fed to a machine translation module that generates an English sentence for each ISL sentence.

As per the experimental results, pretrained MobileNetV2 model was proven the best-suited model for the recognition of ISL sentences and NMT provided better results than Statistical Machine Translation (SMT) to convert ISL text into English text. The automatic and human evaluation of the proposed approach yielded accuracies of 83.3 and 86.1%, respectively.

It can be seen that the neural machine translation systems produced translations with repetitions of other translated words, strange translations when the total number of words per sentence is increased and one or more unexpected terms that had no relation to the source text on occasion. The most common type of error is the mistranslation of places, numbers and dates. Although this has little effect on the overall structure of the translated sentence, it indicates that the embedding learned for these few words could be improved.

Sign language recognition and translation is a crucial step toward improving communication between the deaf and the rest of society. Because of the shortage of human interpreters, an alternative approach is desired to help people achieve smooth communication with the Deaf. To motivate research in this field, the authors generated an ISL corpus of 13,720 sentences and a video dataset of 47,880 ISL videos. As there is no public dataset available for ISl videos incorporating signs released by ISLRTC, the authors created a new video dataset and ISL corpus.

This study aims to examine the influence of training and development (TAD), including performance appraisal (PFA), on the performance of microfinance institutions in a developing economy.

A random sampling drew 100 microfinance institutions in Ghana's Greater Accra Region. Then, a purposive sampling approach selected a cross-section of employees in these institutions. Finally, the data were collected from a sample of 367 respondents, such as managers, utilizing a survey questionnaire. Structural equation modeling (SEM) was used to test hypothesized relationships.

The study results indicate that PFA has a statistically significant positive relationship with organizational performance, and this relationship is partially mediated by job satisfaction (JBS). Interestingly, the TAD process does not have a statistically significant positive relationship with organizational performance when JBS is present in the model. In fact, JBS fully mediates the relationship between TAD and organizational performance.

The study is limited to microfinance in tiers two and three in Greater Accra city of Ghana and did not include the entire country. Although the city of Accra provides a generalized representation of the research, which can be replicated, some variables and results may be impacted if other tiers of microfinance organizations are incorporated.

TAD, as well as PFA, enhance the performance of microfinance and can be utilized as tools for competitive advantage in small and medium-sized enterprises (SMEs) (e.g. microfinance institutions). The study accentuates the value of TAD, PFA and JBS in microfinance in a developing country like Ghana.

This is an original study investigating the effect of TAD and PFA practices on the performance of SMEs in a developing country like Ghana. Also, the study analyses JBS as a mediation variable to performance using SEM, which advances the research methodology in this research field.

Defects in concrete surfaces are inevitably recurring during construction, which needs to be checked and accepted during construction and completion. Traditional manual inspection of surface defects requires inspectors to judge, evaluate and make decisions, which requires sufficient experience and is time-consuming and labor-intensive, and the expertise cannot be effectively preserved and transferred. In addition, the evaluation standards of different inspectors are not identical, which may lead to cause discrepancies in inspection results. Although computer vision can achieve defect recognition, there is a gap between the low-level semantics acquired by computer vision and the high-level semantics that humans understand from images. Therefore, computer vision and ontology are combined to achieve intelligent evaluation and decision-making and to bridge the above gap.

Combining ontology and computer vision, this paper establishes an evaluation and decision-making framework for concrete surface quality. By establishing concrete surface quality ontology model and defect identification quantification model, ontology reasoning technology is used to realize concrete surface quality evaluation and decision-making.

Computer vision can identify and quantify defects, obtain low-level image semantics, and ontology can structurally express expert knowledge in the field of defects. This proposed framework can automatically identify and quantify defects, and infer the causes, responsibility, severity and repair methods of defects. Through case analysis of various scenarios, the proposed evaluation and decision-making framework is feasible.

This paper establishes an evaluation and decision-making framework for concrete surface quality, so as to improve the standardization and intelligence of surface defect inspection and potentially provide reusable knowledge for inspecting concrete surface quality. The research results in this paper can be used to detect the concrete surface quality, reduce the subjectivity of evaluation and improve the inspection efficiency. In addition, the proposed framework enriches the application scenarios of ontology and computer vision, and to a certain extent bridges the gap between the image features extracted by computer vision and the information that people obtain from images.

The authors develop a novel forecast combination approach based on the order statistics of individual predictability from panel data forecasts. To this end, the authors define the notion of forecast depth, which provides a ranking among different forecasts based on their normalized forecast errors during the training period. The forecast combination is in the form of a depth-weighted trimmed mean. The authors derive the limiting distribution of the depth-weighted forecast combination, based on which the authors can readily construct prediction intervals. Using this novel forecast combination, the authors predict the national level of new COVID-19 cases in the United States and compare it with other approaches including the ensemble forecast from the Centers for Disease Control and Prevention (CDC). The authors find that the depth-weighted forecast combination yields more accurate and robust predictions compared with other popular forecast combinations and reports much narrower prediction intervals.