Search results

Diagnosing brain tumors is a process that demands a significant amount of time and is heavily dependent on the proficiency and accumulated knowledge of radiologists. Over the traditional methods, deep learning approaches have gained popularity in automating the diagnosis of brain tumors, offering the potential for more accurate and efficient results. Notably, attention-based models have emerged as an advanced, dynamically refining and amplifying model feature to further elevate diagnostic capabilities. However, the specific impact of using channel, spatial or combined attention methods of the convolutional block attention module (CBAM) for brain tumor classification has not been fully investigated.

To selectively emphasize relevant features while suppressing noise, ResNet50 coupled with the CBAM (ResNet50-CBAM) was used for the classification of brain tumors in this research.

The ResNet50-CBAM outperformed existing deep learning classification methods like convolutional neural network (CNN), ResNet-CBAM achieved a superior performance of 99.43%, 99.01%, 98.7% and 99.25% in accuracy, recall, precision and AUC, respectively, when compared to the existing classification methods using the same dataset.

Since ResNet-CBAM fusion can capture the spatial context while enhancing feature representation, it can be integrated into the brain classification software platforms for physicians toward enhanced clinical decision-making and improved brain tumor classification.

This research has not been published anywhere else.

Surface roughness has a serious impact on the fatigue strength, wear resistance and life of mechanical products. Realizing the evolution of surface quality through theoretical modeling takes a lot of effort. To predict the surface roughness of milling processing, this paper aims to construct a neural network based on deep learning and data augmentation.

This study proposes a method consisting of three steps. Firstly, the machine tool multisource data acquisition platform is established, which combines sensor monitoring with machine tool communication to collect processing signals. Secondly, the feature parameters are extracted to reduce the interference and improve the model generalization ability. Thirdly, for different expectations, the parameters of the deep belief network (DBN) model are optimized by the tent-SSA algorithm to achieve more accurate roughness classification and regression prediction.

The adaptive synthetic sampling (ADASYN) algorithm can improve the classification prediction accuracy of DBN from 80.67% to 94.23%. After the DBN parameters were optimized by Tent-SSA, the roughness prediction accuracy was significantly improved. For the classification model, the prediction accuracy is improved by 5.77% based on ADASYN optimization. For regression models, different objective functions can be set according to production requirements, such as root-mean-square error (RMSE) or MaxAE, and the error is reduced by more than 40% compared to the original model.

A roughness prediction model based on multiple monitoring signals is proposed, which reduces the dependence on the acquisition of environmental variables and enhances the model's applicability. Furthermore, with the ADASYN algorithm, the Tent-SSA intelligent optimization algorithm is introduced to optimize the hyperparameters of the DBN model and improve the optimization performance.

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.

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.

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.

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.

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.

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.

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.

This study aims to introduce a new methodology for generating synthetic images for facility management purposes. The method starts by leveraging the existing 3D open-source BIM models and using them inside a graphic engine to produce a photorealistic representation of indoor spaces enriched with facility-related objects. The virtual environment creates several images by changing lighting conditions, camera poses or material. Moreover, the created images are labeled and ready to be trained in the model.

This paper focuses on the challenges characterizing object detection models to enrich digital twins with facility management-related information. The automatic detection of small objects, such as sockets, power plugs, etc., requires big, labeled data sets that are costly and time-consuming to create. This study proposes a solution based on existing 3D BIM models to produce quick and automatically labeled synthetic images.

The paper presents a conceptual model for creating synthetic images to increase the performance in training object detection models for facility management. The results show that virtually generated images, rather than an alternative to real images, are a powerful tool for integrating existing data sets. In other words, while a base of real images is still needed, introducing synthetic images helps augment the model’s performance and robustness in covering different types of objects.

This study introduced the first pipeline for creating synthetic images for facility management. Moreover, this paper validates this pipeline by proposing a case study where the performance of object detection models trained on real data or a combination of real and synthetic images are compared.

Perception has been identified as the main cause underlying most autonomous vehicle related accidents. As the key technology in perception, deep learning (DL) based computer vision models are generally considered to be black boxes due to poor interpretability. These have exacerbated user distrust and further forestalled their widespread deployment in practical usage. This paper aims to develop explainable DL models for autonomous driving by jointly predicting potential driving actions with corresponding explanations. The explainable DL models can not only boost user trust in autonomy but also serve as a diagnostic approach to identify any model deficiencies or limitations during the system development phase.

This paper proposes an explainable end-to-end autonomous driving system based on “Transformer,” a state-of-the-art self-attention (SA) based model. The model maps visual features from images collected by onboard cameras to guide potential driving actions with corresponding explanations, and aims to achieve soft attention over the image’s global features.

The results demonstrate the efficacy of the proposed model as it exhibits superior performance (in terms of correct prediction of actions and explanations) compared to the benchmark model by a significant margin with much lower computational cost on a public data set (BDD-OIA). From the ablation studies, the proposed SA module also outperforms other attention mechanisms in feature fusion and can generate meaningful representations for downstream prediction.

In the contexts of situational awareness and driver assistance, the proposed model can perform as a driving alarm system for both human-driven vehicles and autonomous vehicles because it is capable of quickly understanding/characterizing the environment and identifying any infeasible driving actions. In addition, the extra explanation head of the proposed model provides an extra channel for sanity checks to guarantee that the model learns the ideal causal relationships. This provision is critical in the development of autonomous systems.

In this research, the authors demonstrate the advantage of reinforcement learning (RL) based intrusion detection systems (IDS) to solve very complex problems (e.g. selecting input features, considering scarce resources and constrains) that cannot be solved by classical machine learning. The authors include a comparative study to build intrusion detection based on statistical machine learning and representational learning, using knowledge discovery in databases (KDD) Cup99 and Installation Support Center of Expertise (ISCX) 2012.

The methodology applies a data analytics approach, consisting of data exploration and machine learning model training and evaluation. To build a network-based intrusion detection system, the authors apply dueling double deep Q-networks architecture enabled with costly features, k-nearest neighbors (K-NN), support-vector machines (SVM) and convolution neural networks (CNN).

Machine learning-based intrusion detection are trained on historical datasets which lead to model drift and lack of generalization whereas RL is trained with data collected through interactions. RL is bound to learn from its interactions with a stochastic environment in the absence of a training dataset whereas supervised learning simply learns from collected data and require less computational resources.

All machine learning models have achieved high accuracy values and performance. One potential reason is that both datasets are simulated, and not realistic. It was not clear whether a validation was ever performed to show that data were collected from real network traffics.

The study provides guidelines to implement IDS with classical supervised learning, deep learning and RL.

The research applied the dueling double deep Q-networks architecture enabled with costly features to build network-based intrusion detection from network traffics. This research presents a comparative study of reinforcement-based instruction detection with counterparts built with statistical and representational machine learning.

Sarcasm is a linguistic expression that usually carries the opposite meaning of what is being said by words, thus making it difficult for machines to discover the actual meaning. It is mainly distinguished by the inflection with which it is spoken, with an undercurrent of irony, and is largely dependent on context, which makes it a difficult task for computational analysis. Moreover, sarcasm expresses negative sentiments using positive words, allowing it to easily confuse sentiment analysis models. This paper aims to demonstrate the task of sarcasm detection using the approach of machine and deep learning.

For the purpose of sarcasm detection, machine and deep learning models were used on a data set consisting of 1.3 million social media comments, including both sarcastic and non-sarcastic comments. The data set was pre-processed using natural language processing methods, and additional features were extracted and analysed. Several machine learning models, including logistic regression, ridge regression, linear support vector and support vector machines, along with two deep learning models based on bidirectional long short-term memory and one bidirectional encoder representations from transformers (BERT)-based model, were implemented, evaluated and compared.

The performance of machine and deep learning models was compared in the task of sarcasm detection, and possible ways of improvement were discussed. Deep learning models showed more promise, performance-wise, for this type of task. Specifically, a state-of-the-art model in natural language processing, namely, BERT-based model, outperformed other machine and deep learning models.

This study compared the performance of the various machine and deep learning models in the task of sarcasm detection using the data set of 1.3 million comments from social media.

This paper aims to propose an enhanced densely dehazing network to suit railway scenes’ features and improve the visual quality degraded by haze and fog.

It is an end-to-end network based on DenseNet. The authors design enhanced dense blocks and fuse them in a pyramid pooling module for visual data’s local and global features. Multiple ablation studies have been conducted to show the effects of each module proposed in this paper.

The authors have compared dehazed results on real hazy images and railway hazy images of state-of-the-art dehazing networks with the dehazed results in data quality. Finally, an object-detection test is taken to judge the edge information preservation after haze removal. All results demonstrate that the proposed dehazing network performs better under railway scenes in detail.

This study provides a new method for image enhancing in the railway monitoring system.

Recently, deep learning (DL) has been widely applied in various aspects of human endeavors. However, studies have shown that DL models may also be a primary cause of data leakage, which raises new data privacy concerns. Membership inference attacks (MIAs) are prominent threats to user privacy from DL model training data, as attackers investigate whether specific data samples exist in the training data of a target model. Therefore, the aim of this study is to develop a method for defending against MIAs and protecting data privacy.

One possible solution is to propose an MIA defense method that involves adjusting the model’s output by mapping the output to a distribution with equal probability density. This approach effectively preserves the accuracy of classification predictions while simultaneously preventing attackers from identifying the training data.

Experiments demonstrate that the proposed defense method is effective in reducing the classification accuracy of MIAs to below 50%. Because MIAs are viewed as a binary classification model, the proposed method effectively prevents privacy leakage and improves data privacy protection.

The method is only designed to defend against MIA in black-box classification models.

The proposed MIA defense method is effective and has a low cost. Therefore, the method enables us to protect data privacy without incurring significant additional expenses.

The recent innovations of Industry 4.0 have made it possible to easily collect data related to a production environment. In this context, information about industrial equipment – gathered by proper sensors – can be profitably used for supporting predictive maintenance (PdM) through the application of data-driven analytics based on artificial intelligence (AI) techniques. Although deep learning (DL) approaches have proven to be a quite effective solutions to the problem, one of the open research challenges remains – the design of PdM methods that are computationally efficient, and most importantly, applicable in real-world internet of things (IoT) scenarios, where they are required to be executable directly on the limited devices’ hardware.

In this paper, the authors propose a DL approach for PdM task, which is based on a particular and very efficient architecture. The major novelty behind the proposed framework is to leverage a multi-head attention (MHA) mechanism to obtain both high results in terms of remaining useful life (RUL) estimation and low memory model storage requirements, providing the basis for a possible implementation directly on the equipment hardware.

The achieved experimental results on the NASA dataset show how the authors’ approach outperforms in terms of effectiveness and efficiency the majority of the most diffused state-of-the-art techniques.

A comparison of the spatial and temporal complexity with a typical long-short term memory (LSTM) model and the state-of-the-art approaches was also done on the NASA dataset. Despite the authors’ approach achieving similar effectiveness results with respect to other approaches, it has a significantly smaller number of parameters, a smaller storage volume and lower training time.

The proposed approach aims to find a compromise between effectiveness and efficiency, which is crucial in the industrial domain in which it is important to maximize the link between performance attained and resources allocated. The overall accuracy performances are also on par with the finest methods described in the literature.

The proposed approach allows satisfying the requirements of modern embedded AI applications (reliability, low power consumption, etc.), finding a compromise between efficiency and effectiveness.