A Gradient Boosted Decision Tree-Based Influencer Prediction in Social Network Analysis

Big Data and Cognitive Computing, Journal Year: 2023, Volume and Issue: 7(1), P. 6 - 6

Published: Jan. 5, 2023

Twitter, Instagram and Facebook are expanding rapidly, reporting on daily news, social activities regional or international actual occurrences. Twitter other platforms have gained popularity because they allow users to submit information, links, photos videos with few restrictions content. As a result of technology advances (“big” data) an increasing trend toward institutionalizing ethics regulation, network analysis (SNA) research is currently confronted serious ethical challenges. A significant percentage human interactions occur networks online. In this instance, content freshness essential, as declines time. Therefore, we investigate how influencer (i.e., posts) generates interactions, measured by the number likes reactions. The Gradient Boosted Decision Tree (GBDT) Chaotic Gradient-Based Optimizer required for estimation (CGBO). Using earlier group develop Influencers Prediction issue in study’s setting SN-created groups. We also provide GBDT-CGBO framework efficient method identifying ability influence future behaviour others. Our contribution based logic, experimentation analytic techniques. goal paper find domain-based influencers using that uses semantic machine learning modules measure predict users’ credibility different domains at times. To solve these problems, will focus co-authorship economic instead online networks. results show our both useful effective. Based test results, model can correctly classify unclear data, which speeds up processing makes it more efficient.

Language: Английский

---

Robust Facial Expression Recognition Using an Evolutionary Algorithm with a Deep Learning Model

Applied Sciences, Journal Year: 2022, Volume and Issue: 13(1), P. 468 - 468

Published: Dec. 29, 2022

The most important component that can express a person’s mental condition is facial expressions. A human communicate around 55% of information non-verbally and the remaining 45% audibly. Automatic expression recognition (FER) has now become challenging task in surveying computers. Applications FER include understanding behavior humans monitoring moods psychological states. It even penetrates other domains—namely, robotics, criminology, smart healthcare systems, entertainment, security holographic images, stress detection, education. This study introduces novel Robust Facial Expression Recognition using an Evolutionary Algorithm with Deep Learning (RFER-EADL) model. RFER-EADL aims to determine various kinds emotions computer vision DL models. Primarily, performs histogram equalization normalize intensity contrast levels images identical persons Next, deep convolutional neural network-based densely connected network (DenseNet-169) model exploited chimp optimization algorithm (COA) as hyperparameter-tuning approach. Finally, teaching learning-based (TLBO) long short-term memory (LSTM) employed for classification. designs COA TLBO algorithms aided optimal parameter selection DenseNet LSTM models, respectively. brief simulation analysis benchmark dataset portrays greater performance compared approaches.

Language: Английский

---

Speech emotion recognition using the novel PEmoNet (Parallel Emotion Network)

Applied Acoustics, Journal Year: 2023, Volume and Issue: 212, P. 109613 - 109613

Published: Aug. 28, 2023

Language: Английский

---

Advanced Speech Emotion Recognition Utilizing optimized Equivariant quantum convolutional neural network for Accurate Emotional State Classification

Knowledge-Based Systems, Journal Year: 2025, Volume and Issue: unknown, P. 113414 - 113414

Published: March 1, 2025

Language: Английский

---

Vocal performance evaluation of the intelligent note recognition method based on deep learning

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: April 22, 2025

This study aims to optimize the ability of note recognition and improve accuracy vocal performance evaluation. Firstly, basic theory music is analyzed. Secondly, convolutional neural network (CNN) in deep learning (DL) selected integrate gated recurrent units for optimization. Moreover, attention mechanism added optimized model implement an intelligent model, results are compared with those common models. Finally, according audio signal classification, a evaluation based on constructed. The under different feature inputs compared. indicate that models show obvious differences F-value, accuracy, precision, recall. mechanism-gated (A-GRCNN) performs best all indicators. Specifically, this model's recall, precision reach 0.961, 0.958, 0.963, 0.970. incorporation multiple can remarkably enhance evaluation, especially combination constant Q Transform features, which most outstanding. improves reliability information processing, promotes application DL technology music, contributes optimizing

Language: Английский

---

A Novel Feature Selection with Hybrid Deep Learning Based Heart Disease Detection and Classification in the e-Healthcare Environment

Computational Intelligence and Neuroscience, Journal Year: 2022, Volume and Issue: 2022, P. 1 - 12

Published: Sept. 28, 2022

With the advancements in data mining, wearables, and cloud computing, online disease diagnosis services have been widely employed e-healthcare environment improved quality of services. The help to reduce death rate by earlier identification diseases. Simultaneously, heart (HD) is a deadly disorder, patient survival depends on early HD. Early HD categorization play key role analysis clinical data. In context e-healthcare, we provide novel feature selection with hybrid deep learning-based detection classification (FSHDL-HDDC) model. two primary preprocessing processes FSHDL-HDDC approach are normalisation replacement missing values. method also necessitates development based elite opposition-based squirrel searchalgorithm (EO-SSA) order determine optimal subset features. Moreover, an attention-based convolutional neural network (ACNN) long short-term memory (LSTM), called (ACNN-LSTM) model, utilized for using medical An extensive experimental study performed ensure performance technique. A detailed comparison reported betterment existing techniques interms different measures. suggested system, FSHDL-HDDC, has reached its maximum level accuracy, which 0.9772.

Language: Английский

---

A review of multimodal-based emotion recognition techniques for cyberbullying detection in online social media platforms

Neural Computing and Applications, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 14, 2024

Language: Английский

---

Heart Disease Prognosis Using D-GRU with Logistic Chaos Honey Badger Optimization in IoMT Framework

Information Technology And Control, Journal Year: 2023, Volume and Issue: 52(2), P. 367 - 380

Published: July 15, 2023

In recent years, heart disease has superseded several other contributory death factors. It is challenging to predict an individual’s risk of acquiring since it requires both expert knowledge and real-world experience. Developing effective method for the prognosis using Internet Medical Things (IoMT) technology in healthcare organizations by collecting sensor data from patients’ bodies, utilizing robust systems, incorporating vast on cardiac disorders alert physicians critical situations a task. Several machine learning-based techniques predicting diagnosing have recently been demonstrated. However, these algorithms cannot effectively handle high-dimensionalinformation due need intelligent framework multiple sources illness. This work proposes unique model prediction based deep learning, Deep Gated Recurrent Units (D-GRU), which combines with Stacked Auto Encoders. A novel optimization algorithm, Logistic Chaos Honey Badger Algorithm, proposed optimal feature selection. Publicly available disease-related datasets collected UCI Repository, Cleveland Database, are used training D-GRU model. The trained further tested gathered sensors IoMT framework. performance compared against learning models existing works literature. outperforms taken comparison andexhibits supremacy accuracy 95.15% diseases.

Language: Английский

---

Predicting the core thermal hydraulic parameters with a gated recurrent unit model based on the soft attention mechanism

Nuclear Engineering and Technology, Journal Year: 2024, Volume and Issue: 56(6), P. 2343 - 2351

Published: March 6, 2024

Accurately predicting the thermal hydraulic parameters of a transient reactor core under different working conditions is first step toward safety. Mass flow rate and temperature are important hydraulics, which have often been modeled as time series prediction problems. This study aims to achieve accurate continuous instantaneous conditions, well test feasibility newly constructed gated recurrent unit (GRU) model based on soft attention mechanism for parameter predictions. Herein, China Experimental Fast Reactor (CEFR) used research object, CEFR 1/2 was taken subject carry out predictive analysis conditions., while subchannel code named SUBCHANFLOW generate thermal-hydraulic parameters. The GRU predict mass core. results show that compared adaptive radial basis function neural network, network produces better results. average relative error less than 0.5 % when size 3, effect within 15 s. 5 10, in subsequent 12 not only shows higher accuracy, but also captures trends dynamic series, useful maintaining safety preventing nuclear power plant accidents. Furthermore, it can provide long-term predictions engineering applications improving

Language: Английский

---

Analyzing emotions in online classes: Unveiling insights through topic modeling, statistical analysis, and random walk techniques

International Journal of Cognitive Computing in Engineering, Journal Year: 2024, Volume and Issue: 5, P. 221 - 236

Published: Jan. 1, 2024

High dropout rates globally perpetuate educational disparities with various underlying causes. Despite numerous strategies to address this issue, more attention should be given understanding and addressing student emotions during classes. This lack of focus adversely affects learner engagement retention rates. While previous studies on online learning have primarily emphasized the effectiveness technology, infrastructure, cognition, motivation, economic benefits, there is still a gap in emotional aspects distance learning. First, study addresses by employing thematic modeling utilizing non-negative matrix factorization (NMF) for emotion recognition through students' deep techniques facial (FER). Second, statistical analysis these findings further augments depth study. Finally, research proposes mathematical model based random walk state transitions. The underscore importance considering environments their significant impact student's academic performance satisfaction. By acknowledging factors, educators can enhance engagement, promote positive emotions, mitigate negative learning, ultimately improve courses.

Language: Английский

---