Search results

Computer vision for automated analysis of cells and tissues usually include extracting features from images before analyzing such features via various machine learning and machine vision algorithms. The purpose of this work is to explore and demonstrate the ability of a Convolutional Neural Network (CNN) to classify cells pictured via brightfield microscopy without the need of any feature extraction, using a minimum of images, improving work-flows that involve cancer cell identification.

The methodology involved a quantitative measure of the performance of a Convolutional Neural Network in distinguishing between two cancer lines. In their approach, they trained, validated and tested their 6-layer CNN on 1,241 images of MDA-MB-468 and MCF7 breast cancer cell line in an end-to-end fashion, allowing the system to distinguish between the two different cancer cell types.

They obtained a 99% accuracy, providing a foundation for more comprehensive systems.

Value can be found in that systems based on this design can be used to assist cell identification in a variety of contexts, whereas a practical implication can be found that these systems can be deployed to assist biomedical workflows quickly and at low cost. In conclusion, this system demonstrates the potentials of end-to-end learning systems for faster and more accurate automated cell analysis.

The aim of this study is to investigate subject independent emotion recognition capabilities of EEG and peripheral physiological signals namely: electroocoulogram (EOG), electromyography (EMG), electrodermal activity (EDA), temperature, plethysmograph and respiration. The experiments are conducted on both modalities independently and in combination. This study arranges the physiological signals in order based on the prediction accuracy obtained on test data using time and frequency domain features.

DEAP dataset is used in this experiment. Time and frequency domain features of EEG and physiological signals are extracted, followed by correlation-based feature selection. Classifiers namely – Naïve Bayes, logistic regression, linear discriminant analysis, quadratic discriminant analysis, logit boost and stacking are trained on the selected features. Based on the performance of the classifiers on the test set, the best modality for each dimension of emotion is identified.

 The experimental results with EEG as one modality and all physiological signals as another modality indicate that EEG signals are better at arousal prediction compared to physiological signals by 7.18%, while physiological signals are better at valence prediction compared to EEG signals by 3.51%. The valence prediction accuracy of EOG is superior to zygomaticus electromyography (zEMG) and EDA by 1.75% at the cost of higher number of electrodes. This paper concludes that valence can be measured from the eyes (EOG) while arousal can be measured from the changes in blood volume (plethysmograph). The sorted order of physiological signals based on arousal prediction accuracy is plethysmograph, EOG (hEOG + vEOG), vEOG, hEOG, zEMG, tEMG, temperature, EMG (tEMG + zEMG), respiration, EDA, while based on valence prediction accuracy the sorted order is EOG (hEOG + vEOG), EDA, zEMG, hEOG, respiration, tEMG, vEOG, EMG (tEMG + zEMG), temperature and plethysmograph.

Many of the emotion recognition studies in literature are subject dependent and the limited subject independent emotion recognition studies in the literature report an average of leave one subject out (LOSO) validation result as accuracy. The work reported in this paper sets the baseline for subject independent emotion recognition using DEAP dataset by clearly specifying the subjects used in training and test set. In addition, this work specifies the cut-off score used to classify the scale as low or high in arousal and valence dimensions. Generally, statistical features are used for emotion recognition using physiological signals as a modality, whereas in this work, time and frequency domain features of physiological signals and EEG are used. This paper concludes that valence can be identified from EOG while arousal can be predicted from plethysmograph.

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.

The purpose of this study is to examine the state of research into adoption of machine learning systems within the health sector, to identify themes that have been studied and observe the important gaps in the literature that can inform a research agenda going forward.

A systematic literature strategy was utilized to identify and analyze scientific papers between 2012 and 2022. A total of 28 articles were identified and reviewed.

The outcomes reveal that while advances in machine learning have the potential to improve service access and delivery, there have been sporadic growth of literature in this area which is perhaps surprising given the immense potential of machine learning within the health sector. The findings further reveal that themes such as recordkeeping, drugs development and streamlining of treatment have primarily been focused on by the majority of authors in this area.

The search was limited to journal articles published in English, resulting in the exclusion of studies disseminated through alternative channels, such as conferences, and those published in languages other than English. Considering that scholars in developing nations may encounter less difficulty in disseminating their work through alternative channels and that numerous emerging nations employ languages other than English, it is plausible that certain research has been overlooked in the present investigation.

This review provides insights into future research avenues for theory, content and context on adoption of machine learning within the health sector.

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.

Ground Penetrating Radar is a multidisciplinary Nondestructive Evaluation technique that requires knowledge of electromagnetic wave propagation, material properties and antenna theory. Under some circumstances this tool may require auxiliary algorithms to improve the interpretation of the collected data. Detection, location and definition of target’s geometrical and physical properties with a low false alarm rate are the objectives of these signal post-processing methods. Basic approaches are focused in the first two objectives while more robust and complex techniques deal with all objectives at once. This work reviews the use of Artificial Neural Networks and Machine Learning for data interpretation of Ground Penetrating Radar surveys. We show that these computational techniques have progressed GPR forward from locating and testing to imaging and diagnosis approaches.

Decision-making is one of the key technologies for self-driving cars. The high dependency of previously existing methods on human driving data or rules makes it difficult to model policies for different driving situations.

In this research, a probabilistic decision-making method based on the Markov decision process (MDP) is proposed to deduce the optimal maneuver automatically in a two-lane highway scenario without using any human data. The decision-making issues in a traffic environment are formulated as the MDP by defining basic elements including states, actions and basic models. Transition and reward models are defined by using a complete prediction model of the surrounding cars. An optimal policy was deduced using a dynamic programing method and evaluated under a two-dimensional simulation environment.

Results show that, at the given scenario, the self-driving car maintained safety and efficiency with the proposed policy.

This paper presents a framework used to derive a driving policy for self-driving cars without relying on any human driving data or rules modeled by hand.

The paper aims to expand on the works well documented by Joy Boulamwini and Ruha Benjamin by expanding their critique to the African continent. The research aims to assess if algorithmic biases are prevalent in DALL-E 2 and Starry AI. The aim is to help inform better artificial intelligence (AI) systems for future use.

The paper utilised a desktop study for literature and gathered data from Open AI’s DALL-E 2 text-to-image generator and StarryAI text-to-image generator.

The DALL-E 2 significantly underperformed when it was tasked with generating images of “An African Family” as opposed to images of a “Family”. The pictures lacked any conceivable detail as compared to the latter of this comparison. The StarryAI significantly outperformed the DALL-E 2 and rendered visible faces. However, the accuracy of the culture portrayed was poor.

Because of the chosen research approach, the research results may lack generalisability. Therefore, researchers are encouraged to test the proposed propositions further. The implications, however, are that more inclusion is warranted to help address the issue of cultural inaccuracies noted in a few of the paper’s experiments.

The paper is useful for advocates who advocate for algorithmic equality and fairness by highlighting evidence of the implications of systemic-induced algorithmic bias.

The reduction in offensive racism and more socially appropriate AI can be a better product for commercialisation and general use. If AI is trained on diversity, it can lead to better applications in contemporary society.

The paper’s use of DALL-E 2 and Starry AI is an under-researched area, and future studies on this matter are welcome.

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.

This paper proposes a holistic, proactive and adaptive approach to cybersecurity from a service lens, given the continuously evolving cyber-attack techniques, threat and vulnerability landscape that often overshadow existing cybersecurity approaches.

Through an extensive literature review of relevant concepts and analysis of existing cybersecurity frameworks, standards and best practices, a logical argument is made to produce a dynamic end-to-end cybersecurity service system model.

Cyberspace has provided great value for businesses and individuals. The COVID-19 pandemic has significantly motivated the move to cyberspace by organizations. However, the extension to cyberspace comes with additional risks as traditional protection techniques are insufficient and isolated, generally focused on an organization's perimeter with little attention to what is out there. More so, cyberattacks continue to grow in complexity creating overwhelming consequences. Existing cybersecurity approaches and best practices are limited in scope, and implementation strategies, differing in strength and focus, at different levels of granularity. Nevertheless, the need for a proactive, adaptive and responsive cybersecurity solution is recognized.

This paper presents a model that promises proactive, adaptive and responsive end-to-end cybersecurity. The proposed cybersecurity continuity and management model premised on a service system, leveraging on lessons learned from existing solutions, takes a holistic analytical view of service activities from source (service provider) to destination (Customer) to ensure end-to-end security, whether internally (within an organization) or externally.