Future smart cities: requirements, emerging technologies, applications, challenges, and future aspects

Cities, Journal Year: 2022, Volume and Issue: 129, P. 103794 - 103794

Published: June 18, 2022

Language: Английский

---

Hand gesture classification using a novel CNN-crow search algorithm

Complex & Intelligent Systems, Journal Year: 2021, Volume and Issue: 7(4), P. 1855 - 1868

Published: March 13, 2021

Abstract Human–computer interaction (HCI) and related technologies focus on the implementation of interactive computational systems. The studies in HCI emphasize system use, creation new techniques that support user activities, access to information, ensures seamless communication. use artificial intelligence deep learning-based models has been extensive across various domains yielding state-of-the-art results. In present study, a crow search-based convolution neural networks model implemented gesture recognition pertaining domain. hand dataset used study is publicly available one, downloaded from Kaggle. this work, one-hot encoding technique convert categorical data values binary form. This followed by search algorithm (CSA) for selecting optimal hyper-parameters training using networks. irrelevant parameters are eliminated consideration, which contributes towards enhancement accuracy classifying gestures. generates 100 percent testing justifies superiority against traditional models.

Language: Английский

---

Deep Learning for Depression Detection from Textual Data

Electronics, Journal Year: 2022, Volume and Issue: 11(5), P. 676 - 676

Published: Feb. 23, 2022

Depression is a prevalent sickness, spreading worldwide with potentially serious implications. Timely recognition of emotional responses plays pivotal function at present, the profound expansion social media and users internet. Mental illnesses are highly hazardous, stirring more than three hundred million people. Moreover, that why research focused on this subject. With advancements machine learning availability sample data relevant to depression, there possibility developing an early depression diagnostic system, which key lessening number afflicted individuals. This paper proposes productive model by implementing Long-Short Term Memory (LSTM) model, consisting two hidden layers large bias Recurrent Neural Network (RNN) dense layers, predict from text, can be beneficial in protecting individuals mental disorders suicidal affairs. We train RNN textual identify semantics, written content. The proposed framework achieves 99.0% accuracy, higher its counterpart, frequency-based deep models, whereas false positive rate reduced. also compare other models regarding mean accuracy. approach indicates feasibility LSTM achieving exceptional results for emotions numerous subscribers.

Language: Английский

---

An ensemble 1D-CNN-LSTM-GRU model with data augmentation for speech emotion recognition

Expert Systems with Applications, Journal Year: 2023, Volume and Issue: 218, P. 119633 - 119633

Published: Feb. 1, 2023

Language: Английский

---

Challenges and Opportunities of Text-Based Emotion Detection: A Survey

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 18416 - 18450

Published: Jan. 1, 2024

Emotion detection has become an intriguing issue for researchers because of its psychological, social, and commercial significance. People express their feelings directly or indirectly through facial expressions, language, writing, behavior. An emotion tool is a critical practical way recognizing categorizing moods with various applications. Artificial intelligence often used in research to identify emotions. Machine learning deep algorithms produce high-quality solutions diagnosing emotional diseases social media users. Numerous studies survey articles have been published on based textual data. However, most these did not comprehensively address emerging architectures performance analysis detection. This paper provides extensive state-of-the-art systems, techniques, datasets recognition. Another goal this study emphasize the limitations provide up-and-coming directions fill gaps rapidly evolving field. investigated concepts performances different categories models, approaches, methodologies.

Language: Английский

---

ElStream: An Ensemble Learning Approach for Concept Drift Detection in Dynamic Social Big Data Stream Learning

IEEE Access, Journal Year: 2021, Volume and Issue: 9, P. 66408 - 66419

Published: Jan. 1, 2021

With the rapid increase in communication technologies and smart devices, an enormous surge data traffic has been observed.A huge amount of gets generated every second by different applications, users, devices.This generation created need for solutions to analyze change over time unforeseen ways despite resource constraints.These unforeseeable changes underlying distribution streaming are identified as concept drifts.This paper presents a novel approach named ElStream that detects drift using ensemble conventional machine learning techniques both real artificial data.ElStream utilizes majority voting technique making only optimum classifier vote decision.Experiments were conducted evaluate performance proposed approach.According experimental analysis, provides consistent real-world sets.Experiments prove better accuracy 12.49%, 11.98%, 10.06%, 1.2%, 0.33% PokerHand, LED, Random RBF, Electricity, SEA dataset respectively, which is compared previous state-of-the-art studies algorithms.

Language: Английский

---

Identification of malnutrition and prediction of BMI from facial images using real‐time image processing and machine learning

IET Image Processing, Journal Year: 2021, Volume and Issue: 16(3), P. 647 - 658

Published: May 20, 2021

Abstract Human faces contain useful information that can be used in the identification of age, gender, weight etc. Among these biometrics, body mass index (BMI) and are good indicators a healthy person. Motivated by recent health science studies, this work investigates ways to identify malnutrition affected people obese analyzing BMI from facial images proposing regression method based on 50‐layers Residual network architecture. For face detection, Multi‐task Cascaded Convolutional Neural Networks have been employed. A system is created evaluate along with age gender human real‐time images. Malnutrition obesity commonly determined help BMI. In previous works, height, weight, estimation through automatic means predominantly focused full‐body videos humans. The usage for estimating such traits given less importance. order facilitate analysis, dataset cleaned metadata containing about persons gender. Gender‐based analysis performed prediction Finally, an email picture their details sent concerned officer.

Language: Английский

---

Cardiovascular Disease Detection using Ensemble Learning

Computational Intelligence and Neuroscience, Journal Year: 2022, Volume and Issue: 2022, P. 1 - 9

Published: Aug. 16, 2022

One of the most challenging tasks for clinicians is detecting symptoms cardiovascular disease as earlier possible. Many individuals worldwide die each year from disease. Since heart a major concern, it must be dealt with timely. Multiple variables affecting health, such excessive blood pressure, elevated cholesterol, an irregular pulse rate, and many more, make to diagnose cardiac Thus, artificial intelligence can useful in identifying treating diseases early on. This paper proposes ensemble-based approach that uses machine learning (ML) deep (DL) models predict person’s likelihood developing We employ six classification algorithms Models are trained using publicly available dataset cases. use random forest (RF) extract important features. The experiment results demonstrate ML ensemble model achieves best prediction accuracy 88.70%.

Language: Английский

---

Context-aware Emotion Detection from Low-resource Urdu Language Using Deep Neural Network

ACM Transactions on Asian and Low-Resource Language Information Processing, Journal Year: 2022, Volume and Issue: 22(5), P. 1 - 30

Published: April 1, 2022

Emotion detection (ED) plays a vital role in determining individual interest any field. Humans use gestures, facial expressions, and voice pitch choose words to describe their emotions. Significant work has been done detect emotions from the textual data English, French, Chinese, other high-resource languages. However, emotion classification not well studied low-resource languages (i.e., Urdu) due lack of labeled corpora. This article presents publicly available Urdu Nastalique Emotions Dataset ( UNED ) sentences paragraphs annotated with different proposes deep learning (DL)-based technique for classifying corpus. Our corpus six both sentences. We perform extensive experimentation evaluate quality further classify it using machine DL approaches. Experimental results show that developed DL-based model performs better than generic approaches an F1 score 85% on sentence-based 50% paragraph-based

Language: Английский

---

Hypertuned Deep Convolutional Neural Network for Sign Language Recognition

Computational Intelligence and Neuroscience, Journal Year: 2022, Volume and Issue: 2022, P. 1 - 10

Published: April 30, 2022

Sign language plays a pivotal role in the lives of impaired people having speaking and hearing disabilities. They can convey messages using hand gesture movements. American Language (ASL) recognition is challenging due to increasing intra-class similarity high complexity. This paper used deep convolutional neural network for ASL alphabet overcome challenges. presents an approach network. The performance DeepCNN model improves with amount given data; this purpose, we applied data augmentation technique expand size training from existing artificially. According experiments, proposed provides consistent results dataset. Experiments prove that gives better accuracy gain 19.84%, 8.37%, 16.31%, 17.17%, 5.86%, 3.26% as compared various state-of-the-art approaches.

Language: Английский

---