Deep Learning Approaches for Cyberbullying Detection and Classification on Social Media

Computational Intelligence and Neuroscience, Journal Year: 2022, Volume and Issue: 2022, P. 1 - 13

Published: June 11, 2022

As a result of the ease with which internet and cell phones can be accessed, online social networks (OSN) media have seen significant increase in popularity recent years. Security privacy, on other hand, are key concerns platforms. On cyberbullying (CB) is serious problem that needs to addressed Known as (CB), it defined repetitive, purposeful, aggressive reaction performed by individuals through use information communication technology (ICT) platforms such platforms, internet, phones. It made up hate messages sent e-mail, chat rooms, accessed computers mobile The detection categorization CB using deep learning (DL) models are, therefore, crucial order combat this trend. Feature subset selection learning-based (FSSDL-CBDC) novel approach for combines feature selection. suggested FSSDL-CBDC technique consists number phases, including preprocessing, selection, classification, among others. Additionally, binary coyote optimization (BCO)-based (BCO-FSS) employed select features will classification performance BCO algorithm. salp swarm algorithm (SSA) used conjunction belief network (DBN), known SSA-DBN model, detect characterize environments. development BCO-FSS highlights originality research. A large simulations were carried out illustrate superior proposed technique. model has exhibited accuracy algorithms, 99.983 % rate. Overall, experimental results revealed beats strategies different aspects.

Language: Английский

---

Machine Learning-Based Anomaly Detection Using K-Mean Array and Sequential Minimal Optimization

Electronics, Journal Year: 2022, Volume and Issue: 11(14), P. 2158 - 2158

Published: July 10, 2022

Recently, artificial intelligence (AI) techniques have been used to describe the characteristics of information, as they help in process data mining (DM) analyze and reveal rules patterns. In DM, anomaly detection is an important area that helps discover hidden behavior within most vulnerable attack. It also detect network intrusion. Algorithms such hybrid K-mean array sequential minimal optimization (SMO) rating can be improve accuracy rate. This paper presents model based on machine learning (ML) technique. ML improves rate, reduces false-positive alarm capable enhancing intrusion classification. study a dataset known security-knowledge discovery (NSL-KDD) lab evaluate proposed technology. cluster SMO were for study, performance was tested, results showed use enhances rate positive besides reducing false alarms achieving high at same time. Moreover, algorithm outperformed recent close work related using similar variables environment by 14.48% decreased probability (FAP) (12%) addition giving higher 97.4%. These outcomes are attributed common providing appropriate number detectors generated with acceptable accurate trivial (FAP). The could considered future systems, where processing real-time highly likely reduced dramatically. justification provide numbers FAP. Given low FAP, it expected reduce time preprocessing compared other algorithms.

Language: Английский

---

Anomaly Detection in 6G Networks Using Machine Learning Methods

Electronics, Journal Year: 2023, Volume and Issue: 12(15), P. 3300 - 3300

Published: July 31, 2023

While the cloudification of networks with a micro-services-oriented design is well-known feature 5G, 6G era closely related to intelligent network orchestration and management. Consequently, artificial intelligence (AI), machine learning (ML), deep (DL) have big part play in paradigm that being imagined. Future end-to-end automation requires proactive threat detection, use clever mitigation strategies, confirmation will be self-sustaining. To strengthen consolidate role AI safeguarding networks, this article explores how may employed security. In order achieve this, novel anomaly detection system for (AD6GNs) based on ensemble (EL) communication was redeveloped study. The first stage EL-ADCN process pre-processing. second selection approach. It applies reimplemented hybrid approach using comparison random forest algorithms (CFS-RF). NB2015, CIC_IDS2017, NSL KDD, CICDDOS2019 are three datasets, each given reduced dimensionality, top subset characteristic determined separately. Hybrid EL techniques used third step find intrusions. average voting methodology as an aggregation method, two classifiers—support vector machines (SVM) forests (RF)—are modified bagging adaboosting, respectively. Testing concept last involves employing classification forms binary multi-class. best experimental results were obtained by applying 30, 35, 40, 40 features datasets: NSL_KDD, UNSW_NB2015, CICDDOS2019. For NSL_KDD dataset, accuracy 99.5% false alarm rate 0.0038; 99.9% UNSW_NB2015 dataset 0.0076; 99.8% CIC_IDS2017 0.0009. However, 99.95426% 0.00113.

Language: Английский

---

Advanced Meta-Heuristic Algorithm Based on Particle Swarm and Al-Biruni Earth Radius Optimization Methods for Oral Cancer Detection

IEEE Access, Journal Year: 2023, Volume and Issue: 11, P. 23681 - 23700

Published: Jan. 1, 2023

Oral cancer is a deadly form of cancerous tumor that widely spread in low and middle-income countries. An early affordable oral diagnosis might be achieved by automating the detection precancerous malignant lesions mouth. There are many research attempts to develop robust machine-learning model can detect from images. However, these still lacking high precision detection. Therefore, this work aims propose new approach capable detecting medical images with higher accuracy. In work, novel based on convolutional neural network (CNN) optimized deep belief (DBN). The design parameters CNN DBN using optimization algorithm, which developed as hybrid Particle Swarm Optimization (PSO) Al-Biruni Earth Radius (BER) algorithms denoted (PSOBER). Using standard biomedical dataset available Kaggle repository, proposed shows promising results outperforming various competing approaches an accuracy 97.35%. addition, set statistical tests, such One-way analysis-of-variance (ANOVA) Wilcoxon signed-rank conducted prove significance stability approach. methodology solid efficient, specialists adopt it. additional larger scale required confirm findings highlight other features utilized for

Language: Английский

---

Statistical normalization methods in microbiome data with application to microbiome cancer research

Gut Microbes, Journal Year: 2023, Volume and Issue: 15(2)

Published: Aug. 25, 2023

Mounting evidence has shown that gut microbiome is associated with various cancers, including gastrointestinal (GI) tract and non-GI cancers. But data have unique characteristics pose major challenges when using standard statistical methods causing results to be invalid or misleading. Thus, analyze data, it not only needs appropriate methods, but also requires normalized prior analysis. Here, we first describe the of in analyzing them (Section 2). Then, provide an overall review on available normalization 16S rRNA shotgun metagenomic along examples their applications cancer research 3). In Section 4, comprehensively investigate how are evaluated. Finally, summarize conclude remarks 5). Altogether, this aims a broad comprehensive view promises examples.

Language: Английский

---

Fused Weighted Federated Deep Extreme Machine Learning Based on Intelligent Lung Cancer Disease Prediction Model for Healthcare 5.0

International Journal of Intelligent Systems, Journal Year: 2023, Volume and Issue: 2023, P. 1 - 14

Published: April 17, 2023

In the era of advancement in information technology and smart healthcare industry 5.0, diagnosis human diseases is still a challenging task. The accurate prediction diseases, especially deadly cancer utmost importance for wellbeing. recent years, global Internet Medical Things (IoMT) has evolved at dizzying pace, from small wristwatch to big aircraft. With this industry, there also rises issue data privacy. To ensure privacy patients’ fast transmission, federated deep extreme learning entangled with edge computing approach considered proposed intelligent system lung disease. Federated machine applied disease system. Furthermore, strengthen model, fused weighted methodology adopted better MATLAB 2020a tool used simulation results. model validation best 5.0. result achieved 97.2%, which than state-of-the-art published methods.

Language: Английский

---

Adaptive Aquila Optimizer with Explainable Artificial Intelligence-Enabled Cancer Diagnosis on Medical Imaging

Cancers, Journal Year: 2023, Volume and Issue: 15(5), P. 1492 - 1492

Published: Feb. 27, 2023

Explainable Artificial Intelligence (XAI) is a branch of AI that mainly focuses on developing systems provide understandable and clear explanations for their decisions. In the context cancer diagnoses medical imaging, an XAI technology uses advanced image analysis methods like deep learning (DL) to make diagnosis analyze images, as well explanation how it arrived at its diagnoses. This includes highlighting specific areas system recognized indicative while also providing data fundamental algorithm decision-making process used. The objective patients doctors with better understanding system's increase transparency trust in method. Therefore, this study develops Adaptive Aquila Optimizer Enabled Cancer Diagnosis (AAOXAI-CD) technique Medical Imaging. proposed AAOXAI-CD intends accomplish effectual colorectal osteosarcoma classification process. To achieve this, initially employs Faster SqueezeNet model feature vector generation. As well, hyperparameter tuning takes place use AAO algorithm. For classification, majority weighted voting ensemble three DL classifiers, namely recurrent neural network (RNN), gated unit (GRU), bidirectional long short-term memory (BiLSTM). Furthermore, combines approach LIME explainability black-box method accurate detection. simulation evaluation methodology can be tested imaging databases, outcomes ensured auspicious outcome than other current approaches.

Language: Английский

---

Empirical Study on Classifiers for Earlier Prediction of COVID-19 Infection Cure and Death Rate in the Indian States

Healthcare, Journal Year: 2022, Volume and Issue: 10(1), P. 85 - 85

Published: Jan. 2, 2022

Machine Learning methods can play a key role in predicting the spread of respiratory infection with help predictive analytics. techniques mine data to better estimate and predict COVID-19 status. A Fine-tuned Ensemble Classification approach for death cure rates patients from using has been proposed different states India. The classification model is applied recent dataset India, performance evaluation various state-of-the-art classifiers performed. forecasted patients' status regions plan resources response care systems. appropriate output class based on extracted input features essential achieve accurate results classifiers. experimental outcome exhibits that Hybrid Model reached maximum F1-score 94% compared Ensembles other like Support Vector Machine, Decision Trees, Gaussian Naïve Bayes 5004 instances through 10-fold cross-validation right class. feasibility automated prediction Indian was demonstrated.

Language: Английский

---

[Retracted] Environmental and Geographical (EG) Image Classification Using FLIM and CNN Algorithms

Contrast Media & Molecular Imaging, Journal Year: 2022, Volume and Issue: 2022(1)

Published: Jan. 1, 2022

Intelligent machines have grown in importance recent years object recognition terms of their ability to envision, comprehend, and reach decisions. There are a lot complicated algorithms that accomplish AI utilities. In addition use the medical industry, these methods wide range other fields, most notably industries, which they can be applied. contrast proposed calculation, calculation is less complex more accurate under certain SNR conditions. deep nervous tissue fine‐tuning discriminator, phantom highlights binding separated as sources; modified direct components used neuronal activation abilities; cross entropy unfortunate abilities. Optimized profound builds periodic for regulatory confirmation corresponding signal.

Language: Английский

---

Grid Search for Predicting Coronary Heart Disease by Tuning Hyper-Parameters

Computer Systems Science and Engineering, Journal Year: 2022, Volume and Issue: 43(2), P. 737 - 749

Published: Jan. 1, 2022

Diagnosing the cardiovascular disease is one of biggest medical difficulties in recent years. Coronary (CHD) a kind heart and blood vascular disease. Predicting this sort cardiac illness leads to more precise decisions for disorders. Implementing Grid Search Optimization (GSO) machine training models therefore useful way forecast sickness as soon possible. The state-of-the-art work tuning hyperparameter together with selection feature by utilizing model search minimize false-negative rate. Three cross-validation approach do required task. Feature Selection based on use statistical correlation matrices multivariate analysis. For Random models, extensive comparison findings are produced retrieval, F1 score, precision measurements. evaluated using metrics kappa statistics that illustrate three models' comparability. study effort focuses optimizing function selection, tweaking hyperparameters improve accuracy prediction examining Framingham datasets random forestry classification. Tuning grid thus decreases erroneous rate achieves global optimization.

Language: Английский

---