DPHFM: A Deep Parallel Hybrid Fusion Model for Disaster Tweet Classification on Twitter Data DOI Creative Commons
Dasari Siva Krishna,

Gorla Srinivas,

Prasad Reddy P.V.G.D.

и другие.

Research Square (Research Square), Год журнала: 2023, Номер unknown

Опубликована: Авг. 9, 2023

Abstract In recent years, disaster tweet classification has garnered significant attention in natural language processing (NLP) due to its potential aid response and emergency management. The goal of is automate the identification informative tweets containing information related various types disasters, such as floods, earthquakes, wildfires, more. This task plays a crucial role real-time monitoring, situational awareness, timely coordination during situations. this context, we propose deep parallel hybrid fusion model (DPHFM) that combines features extracted from Convolutional Neural Networks (CNNs) Bidirectional Long Short-Term Memory (Bi-LSTM) base learners. learners are combined using mechanism, resulting then reconstructed supplied meta-learner input for making predictions. DPHFM trained on datasets, crisisMMD, which consists seven events. was thoroughly evaluated metrics, demonstrating an average performance improvement 90–96%. Furthermore, proposed model's surpassed other state-of-the-art models, showcasing learning techniques.

Язык: Английский

A multigrained preference analysis method for product iterative design incorporating AI-generated review detection DOI Creative Commons
Zhaojing Su, Mei Yang, Qijie Zhai

и другие.

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Янв. 20, 2025

Online reviews significantly influence consumer purchasing decisions and serve as a vital reference for product improvement. With the surge of generative artificial intelligence (AI) technologies such ChatGPT, some merchants might exploit them to fabricate deceptive positive reviews, competitors may also negative opinions consumers designers. Attention must be paid trustworthiness online reviews. In addition, expressed by users are limited, design details hidden behind affect usage experience. Therefore, on basis integrated AI-generated review detection, multigrained user preference analysis method is proposed in this work. The utilizes pre-trained language models designs an authenticity detection model Subsequently, attribute-grained considered text-filling problem uses text-infilling objective domain-adaptive pretraining, facilitating knowledge transfer. On feature selection algorithm, calculation importance features introducing random idea. analyzes preferences at granularity attributes features, enabling targeted cost control optimization development guiding decisions. Rigorous comparative few-shot experiments substantiate superiority method.

Язык: Английский

Процитировано

1
A knowledge graph for crop diseases and pests in China DOI Creative Commons
Rongen Yan, Ping An,

Xianghao Meng

и другие.

Scientific Data, Год журнала: 2025, Номер 12(1)

Опубликована: Фев. 6, 2025

Abstract A standardized representation and sharing of crop disease pest data is crucial for enhancing yields, especially in China, which features vast cultivation areas complex agricultural ecosystems. knowledge graph diseases pests, acting as a repository entities relationships, conceptually achieving unified management. However, there currently lack graphs specifically designed this field. In paper, we propose CropDP-KG, pests leverages natural language processing techniques to analyze from the Chinese image-text database. CropDP-KG covers relevant information on featuring 8 primary such diseases, symptoms, crops, organized into 7 relationships occurrence locations, affected parts suitable temperature. total, it includes 13,840 21,961 relationships. case studies presented research, also show versatile application CropDP, namely service system, have released its codebase under an open-source license. The content paper provides guide users build their own graphs, aiming help them effectively reuse extend they create.

Язык: Английский

Процитировано

1
Applications of Long Short-Term Memory (LSTM) Networks in Polymeric Sciences: A Review DOI Open Access
Ivan Malashin, В С Тынченко, Andrei Gantimurov

и другие.

Polymers, Год журнала: 2024, Номер 16(18), С. 2607 - 2607

Опубликована: Сен. 14, 2024

This review explores the application of Long Short-Term Memory (LSTM) networks, a specialized type recurrent neural network (RNN), in field polymeric sciences. LSTM networks have shown notable effectiveness modeling sequential data and predicting time-series outcomes, which are essential for understanding complex molecular structures dynamic processes polymers. delves into use models polymer properties, monitoring polymerization processes, evaluating degradation mechanical performance Additionally, it addresses challenges related to availability interpretability. Through various case studies comparative analyses, demonstrates different science applications. Future directions also discussed, with an emphasis on real-time applications need interdisciplinary collaboration. The goal this is connect advanced machine learning (ML) techniques science, thereby promoting innovation improving predictive capabilities field.

Язык: Английский

Процитировано

7
A Deep Parallel Hybrid Fusion Model for disaster tweet classification on Twitter data DOI Creative Commons
Dasari Siva Krishna,

Gorla Srinivas,

P. V. G. D. Prasad Reddy

и другие.

Decision Analytics Journal, Год журнала: 2024, Номер 11, С. 100453 - 100453

Опубликована: Март 29, 2024

Disaster tweet classification has gained significant attention in natural language processing (NLP) due to its potential aid disaster response and emergency management. The goal of is automate the identification informative tweets containing information related various types disasters, such as floods, earthquakes, wildfires, more. This task plays a crucial role real-time monitoring, situational awareness, timely coordination during situations. In this context, we propose Deep Parallel Hybrid Fusion Model (DPHFM) that combines features from Convolutional Neural Networks (CNNs) Bidirectional Long Short-Term Memory (Bi-LSTM) base learners. extracted these learners are combined using fusion mechanism then reconstructed for input meta-learner making predictions. DPHFM trained on datasets, crisisMMD, which consists seven events. model underwent thorough evaluation metrics, demonstrating an average performance improvement 90% 96%. Furthermore, proposed model's surpassed other state-of-the-art models, showcasing deep learning techniques.

Язык: Английский

Процитировано

6
An Ensemble Approach to Question Classification: Integrating Electra Transformer, GloVe, and LSTM DOI Open Access
Sanad Aburass, Osama Dorgham,

Maha Abu Rumman

и другие.

International Journal of Advanced Computer Science and Applications, Год журнала: 2024, Номер 15(1)

Опубликована: Янв. 1, 2024

Natural Language Processing (NLP) has emerged as a critical technology for understanding and generating human language, with applications including machine translation, sentiment analysis, and, most importantly, question classification. As subfield of NLP, classification focuses on determining the type information being sought, which is an important step downstream such answering systems. This study introduces innovative ensemble approach to that combines strengths Electra, GloVe, LSTM models. After tried thoroughly well-known TREC dataset, model shows combining these different technologies can produce better outcomes. For complex Electra uses transformers; GloVe global vector representations word-level meaning; models long-term relationships through sequence learning. Our strong effective way solve hard problem by mixing parts in smart way. The method works because it got 80% accuracy score test dataset when was compared like BERT, RoBERTa, DistilBERT.

Язык: Английский

Процитировано

5
Artificial Intelligence in Personalized Medicine for Head and Neck Cancer: Optimizing Prescriptions and Treatment Planning DOI
Karthikeyan Elumalai, Sivaneswari Srinivasan

Deleted Journal, Год журнала: 2025, Номер unknown

Опубликована: Март 27, 2025

Язык: Английский

Процитировано

0
Vision Transformers in Medical Imaging: a Comprehensive Review of Advancements and Applications Across Multiple Diseases DOI
Sanad Aburass, Osama Dorgham, Jamil Al Shaqsi

и другие.

Deleted Journal, Год журнала: 2025, Номер unknown

Опубликована: Март 31, 2025

The rapid advancement of artificial intelligence techniques, particularly deep learning, has transformed medical imaging. This paper presents a comprehensive review recent research that leverage vision transformer (ViT) models for image classification across various disciplines. fields focus include breast cancer, skin lesions, magnetic resonance imaging brain tumors, lung diseases, retinal and eye analysis, COVID-19, heart colon disorders, diabetic retinopathy, kidney lymph node bone analysis. Each work is critically analyzed interpreted with respect to its performance, data preprocessing methodologies, model architecture, transfer learning interpretability, identified challenges. Our findings suggest ViT shows promising results in the domain, often outperforming traditional convolutional neural networks (CNN). A overview presented form figures tables summarizing key from each field. provides critical insights into current state using highlights potential future directions this rapidly evolving area.

Язык: Английский

Процитировано

0
Augmentation and Classification of Requests in Moroccan Dialect to Improve Quality of Public Service: A Comparative Study of Algorithms DOI Creative Commons
Hajar Zaidani, Rim Koulali, Abderrahim Maizate

и другие.

Future Internet, Год журнала: 2025, Номер 17(4), С. 176 - 176

Опубликована: Апрель 17, 2025

Moroccan Law 55.19 aims to streamline administrative procedures, fostering trust between citizens and public administrations. To implement this law effectively enhance service quality, it is essential use the dialect involve a wide range of people by leveraging Natural Language Processing (NLP) techniques customized its specific linguistic characteristics. It worth noting that presents unique landscape, marked coexistence multiple texts. Though has emerged as preferred medium communication on social media, reaching audiences, perceived difficulty comprehension remains unaddressed. This article introduces new approach addressing these challenges. First, we compiled processed dataset requests for administration documents, employing augmentation technique size diversity. Second, conducted text classification experiments using various machine learning algorithms, ranging from traditional methods advanced large language models (LLMs), categorize into three classes. The results indicate promising outcomes, with an accuracy more than 80% LLMs. Finally, propose chatbot system architecture deploying most efficient algorithm. solution also contains voice assistant can contribute inclusion illiterate people. concludes outlining potential avenues future research.

Язык: Английский

Процитировано

0
Advancements and implications of artificial intelligence for early detection, diagnosis and tailored treatment of cancer DOI
Sonia Chadha, Sayali Mukherjee, Somali Sanyal

и другие.

Seminars in Oncology, Год журнала: 2025, Номер 52(3), С. 152349 - 152349

Опубликована: Май 8, 2025

Язык: Английский

Процитировано

0
Genome language modeling (GLM): a beginner’s cheat sheet DOI Creative Commons
Navya Tyagi,

Naima Vahab,

Sonika Tyagi

и другие.

Biology Methods and Protocols, Год журнала: 2025, Номер 10(1)

Опубликована: Янв. 1, 2025

Abstract Integrating genomics with diverse data modalities has the potential to revolutionize personalized medicine. However, this integration poses significant challenges due fundamental differences in types and structures. The vast size of genome necessitates transformation into a condensed representation containing key biomarkers relevant features ensure interoperability other modalities. This commentary explores both conventional state-of-the-art approaches language modeling (GLM), focus on representing extracting meaningful from genomic sequences. We latest trends applying techniques sequence data, treating it as text modality. Effective feature extraction is essential enabling machine learning models effectively analyze large datasets, particularly within multimodal frameworks. first provide step-by-step guide various preprocessing tokenization techniques. Then we explore methods for tokens using frequency, embedding, neural network-based approaches. In end, discuss (ML) applications genomics, focusing classification, regression, processing algorithms, integration. Additionally, role GLM functional annotation, emphasizing how advanced ML models, such Bidirectional encoder representations transformers, enhance interpretation data. To best our knowledge, compile end-to-end analytic convert complex biologically interpretable information GLM, thereby facilitating development novel data-driven hypotheses.

Язык: Английский

Процитировано

0