Search results
1 – 10 of 234Yizhuo Zhang, Yunfei Zhang, Huiling Yu and Shen Shi
The anomaly detection task for oil and gas pipelines based on acoustic signals faces issues such as background noise coverage, lack of effective features, and small sample sizes…
Abstract
Purpose
The anomaly detection task for oil and gas pipelines based on acoustic signals faces issues such as background noise coverage, lack of effective features, and small sample sizes, resulting in low fault identification accuracy and slow efficiency. The purpose of this paper is to study an accurate and efficient method of pipeline anomaly detection.
Design/methodology/approach
First, to address the impact of background noise on the accuracy of anomaly signals, the adaptive multi-threshold center frequency variational mode decomposition method(AMTCF-VMD) method is used to eliminate strong noise in pipeline signals. Secondly, to address the strong data dependency and loss of local features in the Swin Transformer network, a Hybrid Pyramid ConvNet network with an Agent Attention mechanism is proposed. This compensates for the limitations of CNN’s receptive field and enhances the Swin Transformer’s global contextual feature representation capabilities. Thirdly, to address the sparsity and imbalance of anomaly samples, the SpecAugment and Scaper methods are integrated to enhance the model’s generalization ability.
Findings
In the pipeline anomaly audio and environmental datasets such as ESC-50, the AMTCF-VMD method shows more significant denoising effects compared to wavelet packet decomposition and EMD methods. Additionally, the model achieved 98.7% accuracy on the preprocessed anomaly audio dataset and 99.0% on the ESC-50 dataset.
Originality/value
This paper innovatively proposes and combines the AMTCF-VMD preprocessing method with the Agent-SwinPyramidNet model, addressing noise interference and low accuracy issues in pipeline anomaly detection, and providing strong support for oil and gas pipeline anomaly recognition tasks in high-noise environments.
Details
Keywords
Soha Rawas, Cerine Tafran and Duaa AlSaeed
Accurate diagnosis of brain tumors is crucial for effective treatment and improved patient outcomes. Magnetic resonance imaging (MRI) is a common method for detecting brain…
Abstract
Purpose
Accurate diagnosis of brain tumors is crucial for effective treatment and improved patient outcomes. Magnetic resonance imaging (MRI) is a common method for detecting brain malignancies, but interpreting MRI data can be challenging and time-consuming for healthcare professionals.
Design/methodology/approach
An innovative method is presented that combines deep learning (DL) models with natural language processing (NLP) from ChatGPT to enhance the accuracy of brain tumor detection in MRI scans. The method generates textual descriptions of brain tumor regions, providing clinicians with valuable insights into tumor characteristics for informed decision-making and personalized treatment planning.
Findings
The evaluation of this approach demonstrates promising outcomes, achieving a notable Dice coefficient score of 0.93 for tumor segmentation, outperforming current state-of-the-art methods. Human validation of the generated descriptions confirms their precision and conciseness.
Research limitations/implications
While the method showcased advancements in accuracy and understandability, ongoing research is essential for refining the model and addressing limitations in segmenting smaller or atypical tumors.
Originality/value
These results emphasized the potential of this innovative method in advancing neuroimaging practices and contributing to the effective detection and management of brain tumors.
Details
Keywords
Wenshen Xu, Yifan Zhang, Xinhang Jiang, Jun Lian and Ye Lin
In the field of steel defect detection, the existing detection algorithms struggle to achieve a satisfactory balance between detection accuracy, computational cost and inference…
Abstract
Purpose
In the field of steel defect detection, the existing detection algorithms struggle to achieve a satisfactory balance between detection accuracy, computational cost and inference speed due to the interference from complex background information, the variety of defect types and significant variations in defect morphology. To solve this problem, this paper aims to propose an efficient detector based on multi-scale information extraction (MSI-YOLO), which uses YOLOv8s as the baseline model.
Design/methodology/approach
First, the authors introduce an efficient multi-scale convolution with different-sized convolution kernels, which enables the feature extraction network to accommodate significant variations in defect morphology. Furthermore, the authors introduce the channel prior convolutional attention mechanism, which allows the network to focus on defect areas and ignore complex background interference. Considering the lightweight design and accuracy improvement, the authors introduce a more lightweight feature fusion network (Slim-neck) to improve the fusion effect of feature maps.
Findings
MSI-YOLO achieves 79.9% mean average precision on the public data set Northeastern University (NEU)-DET, with a model size of only 19.0 MB and an frames per second of 62.5. Compared with other state-of-the-art detectors, MSI-YOLO greatly improves the recognition accuracy and has significant advantages in computational cost and inference speed. Additionally, the strong generalization ability of MSI-YOLO is verified on the collected industrial site steel data set.
Originality/value
This paper proposes an efficient steel defect detector with high accuracy, low computational cost, excellent detection speed and strong generalization ability, which is more valuable for practical applications in resource-limited industrial production.
Details
Keywords
S. Punitha and K. Devaki
Predicting student performance is crucial in educational settings to identify and support students who may need additional help or resources. Understanding and predicting student…
Abstract
Purpose
Predicting student performance is crucial in educational settings to identify and support students who may need additional help or resources. Understanding and predicting student performance is essential for educators to provide targeted support and guidance to students. By analyzing various factors like attendance, study habits, grades, and participation, teachers can gain insights into each student’s academic progress. This information helps them tailor their teaching methods to meet the individual needs of students, ensuring a more personalized and effective learning experience. By identifying patterns and trends in student performance, educators can intervene early to address any challenges and help students acrhieve their full potential. However, the complexity of human behavior and learning patterns makes it difficult to accurately forecast how a student will perform. Additionally, the availability and quality of data can vary, impacting the accuracy of predictions. Despite these obstacles, continuous improvement in data collection methods and the development of more robust predictive models can help address these challenges and enhance the accuracy and effectiveness of student performance predictions. However, the scalability of the existing models to different educational settings and student populations can be a hurdle. Ensuring that the models are adaptable and effective across diverse environments is crucial for their widespread use and impact. To implement a student’s performance-based learning recommendation scheme for predicting the student’s capabilities and suggesting better materials like papers, books, videos, and hyperlinks according to their needs. It enhances the performance of higher education.
Design/methodology/approach
Thus, a predictive approach for student achievement is presented using deep learning. At the beginning, the data is accumulated from the standard database. Next, the collected data undergoes a stage where features are carefully selected using the Modified Red Deer Algorithm (MRDA). After that, the selected features are given to the Deep Ensemble Networks (DEnsNet), in which techniques such as Gated Recurrent Unit (GRU), Deep Conditional Random Field (DCRF), and Residual Long Short-Term Memory (Res-LSTM) are utilized for predicting the student performance. In this case, the parameters within the DEnsNet network are finely tuned by the MRDA algorithm. Finally, the results from the DEnsNet network are obtained using a superior method that delivers the final prediction outcome. Following that, the Adaptive Generative Adversarial Network (AGAN) is introduced for recommender systems, with these parameters optimally selected using the MRDA algorithm. Lastly, the method for predicting student performance is evaluated numerically and compared to traditional methods to demonstrate the effectiveness of the proposed approach.
Findings
The accuracy of the developed model is 7.66%, 9.91%, 5.3%, and 3.53% more than HHO-DEnsNet, ROA-DEnsNet, GTO-DEnsNet, and AOA-DEnsNet for dataset-1, and 7.18%, 7.54%, 5.43% and 3% enhanced than HHO-DEnsNet, ROA-DEnsNet, GTO-DEnsNet, and AOA-DEnsNet for dataset-2.
Originality/value
The developed model recommends the appropriate learning materials within a short period to improve student’s learning ability.
Details
Keywords
Zhanglin Peng, Tianci Yin, Xuhui Zhu, Xiaonong Lu and Xiaoyu Li
To predict the price of battery-grade lithium carbonate accurately and provide proper guidance to investors, a method called MFTBGAM is proposed in this study. This method…
Abstract
Purpose
To predict the price of battery-grade lithium carbonate accurately and provide proper guidance to investors, a method called MFTBGAM is proposed in this study. This method integrates textual and numerical information using TCN-BiGRU–Attention.
Design/methodology/approach
The Word2Vec model is initially employed to process the gathered textual data concerning battery-grade lithium carbonate. Subsequently, a dual-channel text-numerical extraction model, integrating TCN and BiGRU, is constructed to extract textual and numerical features separately. Following this, the attention mechanism is applied to extract fusion features from the textual and numerical data. Finally, the market price prediction results for battery-grade lithium carbonate are calculated and outputted using the fully connected layer.
Findings
Experiments in this study are carried out using datasets consisting of news and investor commentary. The findings reveal that the MFTBGAM model exhibits superior performance compared to alternative models, showing its efficacy in precisely forecasting the future market price of battery-grade lithium carbonate.
Research limitations/implications
The dataset analyzed in this study spans from 2020 to 2023, and thus, the forecast results are specifically relevant to this timeframe. Altering the sample data would necessitate repetition of the experimental process, resulting in different outcomes. Furthermore, recognizing that raw data might include noise and irrelevant information, future endeavors will explore efficient data preprocessing techniques to mitigate such issues, thereby enhancing the model’s predictive capabilities in long-term forecasting tasks.
Social implications
The price prediction model serves as a valuable tool for investors in the battery-grade lithium carbonate industry, facilitating informed investment decisions. By using the results of price prediction, investors can discern opportune moments for investment. Moreover, this study utilizes two distinct types of text information – news and investor comments – as independent sources of textual data input. This approach provides investors with a more precise and comprehensive understanding of market dynamics.
Originality/value
We propose a novel price prediction method based on TCN-BiGRU Attention for “text-numerical” information fusion. We separately use two types of textual information, news and investor comments, for prediction to enhance the model's effectiveness and generalization ability. Additionally, we utilize news datasets including both titles and content to improve the accuracy of battery-grade lithium carbonate market price predictions.
Details
Keywords
Yongqing Ma, Yifeng Zheng, Wenjie Zhang, Baoya Wei, Ziqiong Lin, Weiqiang Liu and Zhehan Li
With the development of intelligent technology, deep learning has made significant progress and has been widely used in various fields. Deep learning is data-driven, and its…
Abstract
Purpose
With the development of intelligent technology, deep learning has made significant progress and has been widely used in various fields. Deep learning is data-driven, and its training process requires a large amount of data to improve model performance. However, labeled data is expensive and not readily available.
Design/methodology/approach
To address the above problem, researchers have integrated semi-supervised and deep learning, using a limited number of labeled data and many unlabeled data to train models. In this paper, Generative Adversarial Networks (GANs) are analyzed as an entry point. Firstly, we discuss the current research on GANs in image super-resolution applications, including supervised, unsupervised, and semi-supervised learning approaches. Secondly, based on semi-supervised learning, different optimization methods are introduced as an example of image classification. Eventually, experimental comparisons and analyses of existing semi-supervised optimization methods based on GANs will be performed.
Findings
Following the analysis of the selected studies, we summarize the problems that existed during the research process and propose future research directions.
Originality/value
This paper reviews and analyzes research on generative adversarial networks for image super-resolution and classification from various learning approaches. The comparative analysis of experimental results on current semi-supervised GAN optimizations is performed to provide a reference for further research.
Details
Keywords
Weijiang Wu, Heping Tan and Yifeng Zheng
Community detection is a key factor in analyzing the structural features of complex networks. However, traditional dynamic community detection methods often fail to effectively…
Abstract
Purpose
Community detection is a key factor in analyzing the structural features of complex networks. However, traditional dynamic community detection methods often fail to effectively solve the problems of deep network information loss and computational complexity in hyperbolic space. To address this challenge, a hyperbolic space-based dynamic graph neural network community detection model (HSDCDM) is proposed.
Design/methodology/approach
HSDCDM first projects the node features into the hyperbolic space and then utilizes the hyperbolic graph convolution module on the Poincaré and Lorentz models to realize feature fusion and information transfer. In addition, the parallel optimized temporal memory module ensures fast and accurate capture of time domain information over extended periods. Finally, the community clustering module divides the community structure by combining the node characteristics of the space domain and the time domain. To evaluate the performance of HSDCDM, experiments are conducted on both artificial and real datasets.
Findings
Experimental results on complex networks demonstrate that HSDCDM significantly enhances the quality of community detection in hierarchical networks. It shows an average improvement of 7.29% in NMI and a 9.07% increase in ARI across datasets compared to traditional methods. For complex networks with non-Euclidean geometric structures, the HSDCDM model incorporating hyperbolic geometry can better handle the discontinuity of the metric space, provides a more compact embedding that preserves the data structure, and offers advantages over methods based on Euclidean geometry methods.
Originality/value
This model aggregates the potential information of nodes in space through manifold-preserving distribution mapping and hyperbolic graph topology modules. Moreover, it optimizes the Simple Recurrent Unit (SRU) on the hyperbolic space Lorentz model to effectively extract time series data in hyperbolic space, thereby enhancing computing efficiency by eliminating the reliance on tangent space.
Details
Keywords
Adela Sobotkova, Ross Deans Kristensen-McLachlan, Orla Mallon and Shawn Adrian Ross
This paper provides practical advice for archaeologists and heritage specialists wishing to use ML approaches to identify archaeological features in high-resolution satellite…
Abstract
Purpose
This paper provides practical advice for archaeologists and heritage specialists wishing to use ML approaches to identify archaeological features in high-resolution satellite imagery (or other remotely sensed data sources). We seek to balance the disproportionately optimistic literature related to the application of ML to archaeological prospection through a discussion of limitations, challenges and other difficulties. We further seek to raise awareness among researchers of the time, effort, expertise and resources necessary to implement ML successfully, so that they can make an informed choice between ML and manual inspection approaches.
Design/methodology/approach
Automated object detection has been the holy grail of archaeological remote sensing for the last two decades. Machine learning (ML) models have proven able to detect uniform features across a consistent background, but more variegated imagery remains a challenge. We set out to detect burial mounds in satellite imagery from a diverse landscape in Central Bulgaria using a pre-trained Convolutional Neural Network (CNN) plus additional but low-touch training to improve performance. Training was accomplished using MOUND/NOT MOUND cutouts, and the model assessed arbitrary tiles of the same size from the image. Results were assessed using field data.
Findings
Validation of results against field data showed that self-reported success rates were misleadingly high, and that the model was misidentifying most features. Setting an identification threshold at 60% probability, and noting that we used an approach where the CNN assessed tiles of a fixed size, tile-based false negative rates were 95–96%, false positive rates were 87–95% of tagged tiles, while true positives were only 5–13%. Counterintuitively, the model provided with training data selected for highly visible mounds (rather than all mounds) performed worse. Development of the model, meanwhile, required approximately 135 person-hours of work.
Research limitations/implications
Our attempt to deploy a pre-trained CNN demonstrates the limitations of this approach when it is used to detect varied features of different sizes within a heterogeneous landscape that contains confounding natural and modern features, such as roads, forests and field boundaries. The model has detected incidental features rather than the mounds themselves, making external validation with field data an essential part of CNN workflows. Correcting the model would require refining the training data as well as adopting different approaches to model choice and execution, raising the computational requirements beyond the level of most cultural heritage practitioners.
Practical implications
Improving the pre-trained model’s performance would require considerable time and resources, on top of the time already invested. The degree of manual intervention required – particularly around the subsetting and annotation of training data – is so significant that it raises the question of whether it would be more efficient to identify all of the mounds manually, either through brute-force inspection by experts or by crowdsourcing the analysis to trained – or even untrained – volunteers. Researchers and heritage specialists seeking efficient methods for extracting features from remotely sensed data should weigh the costs and benefits of ML versus manual approaches carefully.
Social implications
Our literature review indicates that use of artificial intelligence (AI) and ML approaches to archaeological prospection have grown exponentially in the past decade, approaching adoption levels associated with “crossing the chasm” from innovators and early adopters to the majority of researchers. The literature itself, however, is overwhelmingly positive, reflecting some combination of publication bias and a rhetoric of unconditional success. This paper presents the failure of a good-faith attempt to utilise these approaches as a counterbalance and cautionary tale to potential adopters of the technology. Early-majority adopters may find ML difficult to implement effectively in real-life scenarios.
Originality/value
Unlike many high-profile reports from well-funded projects, our paper represents a serious but modestly resourced attempt to apply an ML approach to archaeological remote sensing, using techniques like transfer learning that are promoted as solutions to time and cost problems associated with, e.g. annotating and manipulating training data. While the majority of articles uncritically promote ML, or only discuss how challenges were overcome, our paper investigates how – despite reasonable self-reported scores – the model failed to locate the target features when compared to field data. We also present time, expertise and resourcing requirements, a rarity in ML-for-archaeology publications.
Details
Keywords
Zhenghao Liu, Yuxing Qian, Wenlong Lv, Yanbin Fang and Shenglan Liu
Stock prices are subject to the influence of news and social media, and a discernible co-movement pattern exists among multiple stocks. Using a knowledge graph to represent news…
Abstract
Purpose
Stock prices are subject to the influence of news and social media, and a discernible co-movement pattern exists among multiple stocks. Using a knowledge graph to represent news semantics and establish connections between stocks is deemed essential and viable.
Design/methodology/approach
This study presents a knowledge-driven framework for predicting stock prices. The framework integrates relevant stocks with the semantic and emotional characteristics of textual data. The authors construct a stock knowledge graph (SKG) to extract pertinent stock information and use a knowledge graph representation model to capture both the relevant stock features and the semantic features of news articles. Additionally, the authors consider the emotional characteristics of news and investor comments, drawing insights from behavioral finance theory. The authors examined the effectiveness of these features using the combined deep learning model CNN+LSTM+Attention.
Findings
Experimental results demonstrate that the knowledge-driven combined feature model exhibits significantly improved predictive accuracy compared to single-feature models.
Originality/value
The study highlights the value of the SKG in uncovering potential correlations among stocks. Moreover, the knowledge-driven multi-feature fusion stock forecasting model enhances the prediction of stock trends for well-known enterprises, providing valuable guidance for investor decision-making.
Details
Keywords
Srishti Sharma and Mala Saraswat
The purpose of this research study is to improve sentiment analysis (SA) at the aspect level, which is accomplished through two independent goals of aspect term and opinion…
Abstract
Purpose
The purpose of this research study is to improve sentiment analysis (SA) at the aspect level, which is accomplished through two independent goals of aspect term and opinion extraction and subsequent sentiment classification.
Design/methodology/approach
The proposed architecture uses neighborhood and dependency tree-based relations for target opinion extraction, a domain–ontology-based knowledge management system for aspect term extraction, and deep learning techniques for classification.
Findings
The authors use different deep learning architectures to test the proposed approach of both review and aspect levels. It is reported that Vanilla recurrent neural network has an accuracy of 83.22%, long short-term memory (LSTM) is 89.87% accurate, Bi-LSTM is 91.57% accurate, gated recurrent unit is 65.57% accurate and convolutional neural network is 82.33% accurate. For the aspect level analysis, ρaspect comes out to be 0.712 and Δ2aspect is 0.384, indicating a marked improvement over previously reported results.
Originality/value
This study suggests a novel method for aspect-based SA that makes use of deep learning and domain ontologies. The use of domain ontologies allows for enhanced aspect identification, and the use of deep learning algorithms enhances the accuracy of the SA task.
Details