Browsing by Author "Li J"
Now showing 1 - 6 of 6
Results Per Page
Sort Options
- ItemA multi-label classification model for full slice brain computerised tomography image(BioMed Central Ltd, 2020-11-18) Li J; Fu G; Chen Y; Li P; Liu B; Pei Y; Feng HBACKGROUND: Screening of the brain computerised tomography (CT) images is a primary method currently used for initial detection of patients with brain trauma or other conditions. In recent years, deep learning technique has shown remarkable advantages in the clinical practice. Researchers have attempted to use deep learning methods to detect brain diseases from CT images. Methods often used to detect diseases choose images with visible lesions from full-slice brain CT scans, which need to be labelled by doctors. This is an inaccurate method because doctors detect brain disease from a full sequence scan of CT images and one patient may have multiple concurrent conditions in practice. The method cannot take into account the dependencies between the slices and the causal relationships among various brain diseases. Moreover, labelling images slice by slice spends much time and expense. Detecting multiple diseases from full slice brain CT images is, therefore, an important research subject with practical implications. RESULTS: In this paper, we propose a model called the slice dependencies learning model (SDLM). It learns image features from a series of variable length brain CT images and slice dependencies between different slices in a set of images to predict abnormalities. The model is necessary to only label the disease reflected in the full-slice brain scan. We use the CQ500 dataset to evaluate our proposed model, which contains 1194 full sets of CT scans from a total of 491 subjects. Each set of data from one subject contains scans with one to eight different slice thicknesses and various diseases that are captured in a range of 30 to 396 slices in a set. The evaluation results present that the precision is 67.57%, the recall is 61.04%, the F1 score is 0.6412, and the areas under the receiver operating characteristic curves (AUCs) is 0.8934. CONCLUSION: The proposed model is a new architecture that uses a full-slice brain CT scan for multi-label classification, unlike the traditional methods which only classify the brain images at the slice level. It has great potential for application to multi-label detection problems, especially with regard to the brain CT images.
- ItemCaring for the last 3%: Telehealth potential and broadband implications for remote Australia(CSIRO, 2012-11-20) Dods S; Freyne J; Alem L; Nepal S; Li J; Jang-Jaccard JAustralians living in remote regions of our nation live with far poorer health outcomes than those in our regional and urban areas. The gaps in health service availability and outcomes between people in urban areas and those in remote parts of our country are well known. Telehealth, the provision of health related services at a distance using technology assisted communications, offers a means to narrow this gap by improving the level and diversity of services in remote areas.
- ItemComparison of algorithms for road surface temperature prediction(Emerald Publishing Limited, 2018-12-13) Liu B; Shen L; You H; Dong Y; Li J; Li YPurpose: The influence of road surface temperature (RST) on vehicles is becoming more and more obvious. Accurate predication of RST is distinctly meaningful. At present, however, the prediction accuracy of RST is not satisfied with physical methods or statistical learning methods. To find an effective prediction method, this paper selects five representative algorithms to predict the road surface temperature separately. Design/methodology/approach: Multiple linear regressions, least absolute shrinkage and selection operator, random forest and gradient boosting regression tree (GBRT) and neural network are chosen to be representative predictors. Findings: The experimental results show that for temperature data set of this experiment, the prediction effect of GBRT in the ensemble algorithm is the best compared with the other four algorithms. Originality/value: This paper compares different kinds of machine learning algorithms, observes the road surface temperature data from different angles, and finds the most suitable prediction method.
- ItemDL-PPI: a method on prediction of sequenced protein-protein interaction based on deep learning(BioMed Central Ltd, 2023-12) Wu J; Liu B; Zhang J; Wang Z; Li JPURPOSE: Sequenced Protein-Protein Interaction (PPI) prediction represents a pivotal area of study in biology, playing a crucial role in elucidating the mechanistic underpinnings of diseases and facilitating the design of novel therapeutic interventions. Conventional methods for extracting features through experimental processes have proven to be both costly and exceedingly complex. In light of these challenges, the scientific community has turned to computational approaches, particularly those grounded in deep learning methodologies. Despite the progress achieved by current deep learning technologies, their effectiveness diminishes when applied to larger, unfamiliar datasets. RESULTS: In this study, the paper introduces a novel deep learning framework, termed DL-PPI, for predicting PPIs based on sequence data. The proposed framework comprises two key components aimed at improving the accuracy of feature extraction from individual protein sequences and capturing relationships between proteins in unfamiliar datasets. 1. Protein Node Feature Extraction Module: To enhance the accuracy of feature extraction from individual protein sequences and facilitate the understanding of relationships between proteins in unknown datasets, the paper devised a novel protein node feature extraction module utilizing the Inception method. This module efficiently captures relevant patterns and representations within protein sequences, enabling more informative feature extraction. 2. Feature-Relational Reasoning Network (FRN): In the Global Feature Extraction module of our model, the paper developed a novel FRN that leveraged Graph Neural Networks to determine interactions between pairs of input proteins. The FRN effectively captures the underlying relational information between proteins, contributing to improved PPI predictions. DL-PPI framework demonstrates state-of-the-art performance in the realm of sequence-based PPI prediction.
- ItemInvestigating the Determinants of Big Data Analytics Adoption in Decision Making: An Empirical Study in New Zealand, China, and Vietnam(Association for Information Systems, 2022-06-28) Yu J; Taskin N; Nguyen CP; Li J; Pauleen DJBackground: As a breakthrough technology, big data provides an opportunity for organizations to acquire business value and enhance competitiveness. Many companies have listed big data analytics (BDA) as one of their top priorities. However, research shows that managers are still reluctant to change their work patterns to utilize this new technology. In addition, the empirical evidence on what determines their adoption of BDA in management decision making is still rare. Method: To more broadly understand the determinants affecting managers’ actual use of BDA in decision making, a survey was conducted on a sample of 363 respondents from New Zealand, China, and Vietnam who work in different managerial roles. The dual process theory, the technology–organization–environment framework, and the key associated demographic characteristics are integrated to form the theoretical foundation to study the internal and external factors influencing the adoption. Results: The findings illustrate that the common essential factors across countries linking BDA in decision making are technology readiness, data quality, managers’ and organizational knowledge related to BDA, and organizational expectations. The factors that are more situation-dependent and evident in one or two countries’ results are managers’ predilection toward valuing intuition and experience over analytics and organizational size. Conclusion: The findings enrich the current literature and provide implications for practitioners on how they can improve the adoption process of this new technology.
- ItemPrediction of seasonal population dynamics of Grapholita molesta (Busck) and Adoxophyes orana (Fischer von Röslerstamm) in peach orchards using sex pheromone trap and degree-days and its implications in pest management(2023-10-04) Ma A; Zhang H; Ran H; Yang X; J Hao J; Zhang J; Li H; Yu Z; Wang X; He X; Li JThe successful management of lepidopteran moths in orchards usually depends on the precise forecast of adult activity. However, the seasonal phenology of moths varies between crop cultivars and years, making it difficult to schedule the control measures. Here, we monitored male flight activity of oriental fruit moth Grapholita molesta and summer fruit tortrix moth Adoxophyes orana by using sex pheromone traps in peach orchards of three different cultivars for three successive years. We developed a logistic multiple-peaks model to fit data and then calculated degree-days (DD) required for male activity and neonate emergency. Results show that G. molesta and A. orana males had 4–5 and 3 flight peaks per year, respectively. The seasonal phenology of G. molesta or A. orana was quite stable with an identical timing of each flight peak between cultivars in a year. The flight activity was usually higher in the second and third peaks for both moths, with a higher cumulative number of G. molesta males captured than that of A. orana. Compared to A. orana, G. molesta emerged early in spring and required lower degree-days to reach the subsequent flight peaks and for neonate emergency. Our results suggest that to decline the possibility of outbreaks of moths during the growing seasons, pheromone traps should be scheduled in April with a cumulative DD between 49.6 and 207.1 for G. molesta and in mid-May–early June with a cumulative DD between 450.4 and 866.7 for A. orana, aiming to trap the newly emerged male adults or disrupting female mating success of overwintered moths in orchards. Based on the thermal requirement for egg hatching (i.e., 79.4 DD for G. molesta and 90.0 DD for A. orana), insecticide treatments would be applied in late-April–early May and late May–early June to reduce the field population density of neonates of G. molesta and A. orana, respectively, to reduce fruit damage in orchards. Furthermore, pheromone traps set up in late July–early August (573.8–1025.2 DD) for G. molesta and in mid-September (1539.7–1788.9 DD) for A. orana may suppress overwintering populations and thus decrease pest infestation in next year.