Frontiers in Artificial Intelligence最新文献

{"title":"Multimodal data integration for oncology in the era of deep neural networks: a review.","authors":"Asim Waqas, Aakash Tripathi, Ravi P Ramachandran, Paul A Stewart, Ghulam Rasool","doi":"10.3389/frai.2024.1408843","DOIUrl":"10.3389/frai.2024.1408843","url":null,"abstract":"<p><p>Cancer research encompasses data across various scales, modalities, and resolutions, from screening and diagnostic imaging to digitized histopathology slides to various types of molecular data and clinical records. The integration of these diverse data types for personalized cancer care and predictive modeling holds the promise of enhancing the accuracy and reliability of cancer screening, diagnosis, and treatment. Traditional analytical methods, which often focus on isolated or unimodal information, fall short of capturing the complex and heterogeneous nature of cancer data. The advent of deep neural networks has spurred the development of sophisticated multimodal data fusion techniques capable of extracting and synthesizing information from disparate sources. Among these, Graph Neural Networks (GNNs) and Transformers have emerged as powerful tools for multimodal learning, demonstrating significant success. This review presents the foundational principles of multimodal learning including oncology data modalities, taxonomy of multimodal learning, and fusion strategies. We delve into the recent advancements in GNNs and Transformers for the fusion of multimodal data in oncology, spotlighting key studies and their pivotal findings. We discuss the unique challenges of multimodal learning, such as data heterogeneity and integration complexities, alongside the opportunities it presents for a more nuanced and comprehensive understanding of cancer. Finally, we present some of the latest comprehensive multimodal pan-cancer data sources. By surveying the landscape of multimodal data integration in oncology, our goal is to underline the transformative potential of multimodal GNNs and Transformers. Through technological advancements and the methodological innovations presented in this review, we aim to chart a course for future research in this promising field. This review may be the first that highlights the current state of multimodal modeling applications in cancer using GNNs and transformers, presents comprehensive multimodal oncology data sources, and sets the stage for multimodal evolution, encouraging further exploration and development in personalized cancer care.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"7 ","pages":"1408843"},"PeriodicalIF":3.0,"publicationDate":"2024-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11308435/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141907822","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Generating rhythm game music with jukebox.","authors":"Nicholas Yan","doi":"10.3389/frai.2024.1296034","DOIUrl":"https://doi.org/10.3389/frai.2024.1296034","url":null,"abstract":"<p><p>Music has always been thought of as a \"human\" endeavor- when praising a piece of music, we emphasize the composer's creativity and the emotions the music invokes. Because music also heavily relies on patterns and repetition in the form of recurring melodic themes and chord progressions, artificial intelligence has increasingly been able to replicate music in a human-like fashion. This research investigated the capabilities of Jukebox, an open-source commercially available neural network, to accurately replicate two genres of music often found in rhythm games, artcore and orchestral. A Google Colab notebook provided the computational resources necessary to sample and extend a total of 16 piano arrangements of both genres. A survey containing selected samples was distributed to a local youth orchestra to gauge people's perceptions of the musicality of AI and human-generated music. Even though humans preferred human-generated music, Jukebox's slightly high rating showed that it was somewhat capable at mimicking the styles of both genres. Despite limitations of Jukebox only using raw audio and a relatively small sample size, it shows promise for the future of AI as a collaborative tool in music production.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"7 ","pages":"1296034"},"PeriodicalIF":3.0,"publicationDate":"2024-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11258020/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141735201","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The privacy-explainability trade-off: unraveling the impacts of differential privacy and federated learning on attribution methods.","authors":"Saifullah Saifullah, Dominique Mercier, Adriano Lucieri, Andreas Dengel, Sheraz Ahmed","doi":"10.3389/frai.2024.1236947","DOIUrl":"10.3389/frai.2024.1236947","url":null,"abstract":"<p><p>Since the advent of deep learning (DL), the field has witnessed a continuous stream of innovations. However, the translation of these advancements into practical applications has not kept pace, particularly in safety-critical domains where artificial intelligence (AI) must meet stringent regulatory and ethical standards. This is underscored by the ongoing research in eXplainable AI (XAI) and privacy-preserving machine learning (PPML), which seek to address some limitations associated with these opaque and data-intensive models. Despite brisk research activity in both fields, little attention has been paid to their interaction. This work is the first to thoroughly investigate the effects of privacy-preserving techniques on explanations generated by common XAI methods for DL models. A detailed experimental analysis is conducted to quantify the impact of private training on the explanations provided by DL models, applied to six image datasets and five time series datasets across various domains. The analysis comprises three privacy techniques, nine XAI methods, and seven model architectures. The findings suggest non-negligible changes in explanations through the implementation of privacy measures. Apart from reporting individual effects of PPML on XAI, the paper gives clear recommendations for the choice of techniques in real applications. By unveiling the interdependencies of these pivotal technologies, this research marks an initial step toward resolving the challenges that hinder the deployment of AI in safety-critical settings.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"7 ","pages":"1236947"},"PeriodicalIF":3.0,"publicationDate":"2024-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11253022/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141634754","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Survival prediction landscape: an in-depth systematic literature review on activities, methods, tools, diseases, and databases.","authors":"Ahtisham Fazeel Abbasi, Muhammad Nabeel Asim, Sheraz Ahmed, Sebastian Vollmer, Andreas Dengel","doi":"10.3389/frai.2024.1428501","DOIUrl":"10.3389/frai.2024.1428501","url":null,"abstract":"<p><p>Survival prediction integrates patient-specific molecular information and clinical signatures to forecast the anticipated time of an event, such as recurrence, death, or disease progression. Survival prediction proves valuable in guiding treatment decisions, optimizing resource allocation, and interventions of precision medicine. The wide range of diseases, the existence of various variants within the same disease, and the reliance on available data necessitate disease-specific computational survival predictors. The widespread adoption of artificial intelligence (AI) methods in crafting survival predictors has undoubtedly revolutionized this field. However, the ever-increasing demand for more sophisticated and effective prediction models necessitates the continued creation of innovative advancements. To catalyze these advancements, it is crucial to bring existing survival predictors knowledge and insights into a centralized platform. The paper in hand thoroughly examines 23 existing review studies and provides a concise overview of their scope and limitations. Focusing on a comprehensive set of 90 most recent survival predictors across 44 diverse diseases, it delves into insights of diverse types of methods that are used in the development of disease-specific predictors. This exhaustive analysis encompasses the utilized data modalities along with a detailed analysis of subsets of clinical features, feature engineering methods, and the specific statistical, machine or deep learning approaches that have been employed. It also provides insights about survival prediction data sources, open-source predictors, and survival prediction frameworks.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"7 ","pages":"1428501"},"PeriodicalIF":3.0,"publicationDate":"2024-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11252047/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141634753","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ArabBert-LSTM: improving Arabic sentiment analysis based on transformer model and Long Short-Term Memory.","authors":"Wael Alosaimi, Hager Saleh, Ali A Hamzah, Nora El-Rashidy, Abdullah Alharb, Ahmed Elaraby, Sherif Mostafa","doi":"10.3389/frai.2024.1408845","DOIUrl":"10.3389/frai.2024.1408845","url":null,"abstract":"<p><p>Sentiment analysis also referred to as opinion mining, plays a significant role in automating the identification of negative, positive, or neutral sentiments expressed in textual data. The proliferation of social networks, review sites, and blogs has rendered these platforms valuable resources for mining opinions. Sentiment analysis finds applications in various domains and languages, including English and Arabic. However, Arabic presents unique challenges due to its complex morphology characterized by inflectional and derivation patterns. To effectively analyze sentiment in Arabic text, sentiment analysis techniques must account for this intricacy. This paper proposes a model designed using the transformer model and deep learning (DL) techniques. The word embedding is represented by Transformer-based Model for Arabic Language Understanding (ArabBert), and then passed to the AraBERT model. The output of AraBERT is subsequently fed into a Long Short-Term Memory (LSTM) model, followed by feedforward neural networks and an output layer. AraBERT is used to capture rich contextual information and LSTM to enhance sequence modeling and retain long-term dependencies within the text data. We compared the proposed model with machine learning (ML) algorithms and DL algorithms, as well as different vectorization techniques: term frequency-inverse document frequency (TF-IDF), ArabBert, Continuous Bag-of-Words (CBOW), and skipGrams using four Arabic benchmark datasets. Through extensive experimentation and evaluation of Arabic sentiment analysis datasets, we showcase the effectiveness of our approach. The results underscore significant improvements in sentiment analysis accuracy, highlighting the potential of leveraging transformer models for Arabic Sentiment Analysis. The outcomes of this research contribute to advancing Arabic sentiment analysis, enabling more accurate and reliable sentiment analysis in Arabic text. The findings reveal that the proposed framework exhibits exceptional performance in sentiment classification, achieving an impressive accuracy rate of over 97%.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"7 ","pages":"1408845"},"PeriodicalIF":3.0,"publicationDate":"2024-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11250580/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141627893","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Editorial: Artificial intelligence education & governance -human enhancive, culturally sensitive and personally adaptive HAI.","authors":"Rajiv Kashyap, Yana Samuel, Linda Weiser Friedman, Jim Samuel","doi":"10.3389/frai.2024.1443386","DOIUrl":"10.3389/frai.2024.1443386","url":null,"abstract":"","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"7 ","pages":"1443386"},"PeriodicalIF":3.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11247171/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141621038","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"HAWKFOG-an enhanced deep learning framework for the Fog-IoT environment.","authors":"R Abirami, Poovammal E","doi":"10.3389/frai.2024.1354742","DOIUrl":"10.3389/frai.2024.1354742","url":null,"abstract":"<p><p>Cardiac disease is considered as the one of the deadliest diseases that constantly increases the globe's mortality rate. Since a lot of expertise is required for an accurate prediction of heart disease, designing an intelligent predictive system for cardiac diseases remains to be complex and tricky. Internet of Things based health regulation systems are a relatively recent technology. In addition, novel Edge and Fog device concepts are presented to advance prediction results. However, the main problem with the current systems is that they are unable to meet the demands of effective diagnosis systems due to their poor prediction capabilities. To overcome this problem, this research proposes a novel framework called HAWKFOGS which innovatively integrates the deep learning for a practical diagnosis of cardiac problems using edge and fog computing devices. The current datasets were gathered from different subjects using IoT devices interfaced with the electrocardiography and blood pressure sensors. The data are then predicted as normal and abnormal using the Logistic Chaos based Harris Hawk Optimized Enhanced Gated Recurrent Neural Networks. The ablation experiments are carried out using IoT nodes interfaced with medical sensors and fog gateways based on Embedded Jetson Nano devices. The suggested algorithm's performance is measured. Additionally, Model Building Time is computed to validate the suggested model's response. Compared to the other algorithms, the suggested model yielded the best results in terms of accuracy (99.7%), precision (99.65%), recall (99.7%), specificity (99.7%). F1-score (99.69%) and used the least amount of Model Building Time (1.16 s) to predict cardiac diseases.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"7 ","pages":"1354742"},"PeriodicalIF":3.0,"publicationDate":"2024-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11239548/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141617200","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"COVLIAS 3.0: cloud-based quantized hybrid UNet3+ deep learning for COVID-19 lesion detection in lung computed tomography.","authors":"Sushant Agarwal, Sanjay Saxena, Alessandro Carriero, Gian Luca Chabert, Gobinath Ravindran, Sudip Paul, John R Laird, Deepak Garg, Mostafa Fatemi, Lopamudra Mohanty, Arun K Dubey, Rajesh Singh, Mostafa M Fouda, Narpinder Singh, Subbaram Naidu, Klaudija Viskovic, Melita Kukuljan, Manudeep K Kalra, Luca Saba, Jasjit S Suri","doi":"10.3389/frai.2024.1304483","DOIUrl":"10.3389/frai.2024.1304483","url":null,"abstract":"<p><strong>Background and novelty: </strong>When RT-PCR is ineffective in early diagnosis and understanding of COVID-19 severity, Computed Tomography (CT) scans are needed for COVID diagnosis, especially in patients having high ground-glass opacities, consolidations, and crazy paving. Radiologists find the manual method for lesion detection in CT very challenging and tedious. Previously solo deep learning (SDL) was tried but they had low to moderate-level performance. This study presents two new cloud-based quantized deep learning UNet3+ hybrid (HDL) models, which incorporated full-scale skip connections to enhance and improve the detections.</p><p><strong>Methodology: </strong>Annotations from expert radiologists were used to train one SDL (UNet3+), and two HDL models, namely, VGG-UNet3+ and ResNet-UNet3+. For accuracy, 5-fold cross-validation protocols, training on 3,500 CT scans, and testing on unseen 500 CT scans were adopted in the cloud framework. Two kinds of loss functions were used: Dice Similarity (DS) and binary cross-entropy (BCE). Performance was evaluated using (i) Area error, (ii) DS, (iii) Jaccard Index, (iii) Bland-Altman, and (iv) Correlation plots.</p><p><strong>Results: </strong>Among the two HDL models, ResNet-UNet3+ was superior to UNet3+ by 17 and 10% for Dice and BCE loss. The models were further compressed using quantization showing a percentage size reduction of 66.76, 36.64, and 46.23%, respectively, for UNet3+, VGG-UNet3+, and ResNet-UNet3+. Its stability and reliability were proved by statistical tests such as the Mann-Whitney, Paired <i>t</i>-Test, Wilcoxon test, and Friedman test all of which had a <i>p</i> < 0.001.</p><p><strong>Conclusion: </strong>Full-scale skip connections of UNet3+ with VGG and ResNet in HDL framework proved the hypothesis showing powerful results improving the detection accuracy of COVID-19.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"7 ","pages":"1304483"},"PeriodicalIF":3.0,"publicationDate":"2024-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11240867/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141617199","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Wearable sensors based on artificial intelligence models for human activity recognition.","authors":"Mohammed Alarfaj, Azzam Al Madini, Ahmed Alsafran, Mohammed Farag, Slim Chtourou, Ahmed Afifi, Ayaz Ahmad, Osama Al Rubayyi, Ali Al Harbi, Mustafa Al Thunaian","doi":"10.3389/frai.2024.1424190","DOIUrl":"10.3389/frai.2024.1424190","url":null,"abstract":"<p><p>Human motion detection technology holds significant potential in medicine, health care, and physical exercise. This study introduces a novel approach to human activity recognition (HAR) using convolutional neural networks (CNNs) designed for individual sensor types to enhance the accuracy and address the challenge of diverse data shapes from accelerometers, gyroscopes, and barometers. Specific CNN models are constructed for each sensor type, enabling them to capture the characteristics of their respective sensors. These adapted CNNs are designed to effectively process varying data shapes and sensor-specific characteristics to accurately classify a wide range of human activities. The late-fusion technique is employed to combine predictions from various models to obtain comprehensive estimates of human activity. The proposed CNN-based approach is compared to a standard support vector machine (SVM) classifier using the one-<i>vs</i>-rest methodology. The late-fusion CNN model showed significantly improved performance, with validation and final test accuracies of 99.35 and 94.83% compared to the conventional SVM classifier at 87.07 and 83.10%, respectively. These findings provide strong evidence that combining multiple sensors and a barometer and utilizing an additional filter algorithm greatly improves the accuracy of identifying different human movement patterns.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"7 ","pages":"1424190"},"PeriodicalIF":3.0,"publicationDate":"2024-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11250658/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141627914","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Editorial: Trends in AI4ESG: AI for sustainable finance and ESG technology.","authors":"Peter Schwendner, Jan-Alexander Posth","doi":"10.3389/frai.2024.1448045","DOIUrl":"https://doi.org/10.3389/frai.2024.1448045","url":null,"abstract":"","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"7 ","pages":"1448045"},"PeriodicalIF":3.0,"publicationDate":"2024-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11231417/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141564670","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}