Artificial intelligence in higher education: the state of the field

International Journal of Educational Technology in Higher Education, Год журнала: 2023, Номер 20(1)

Опубликована: Апрель 23, 2023

Abstract This systematic review provides unique findings with an up-to-date examination of artificial intelligence (AI) in higher education (HE) from 2016 to 2022. Using PRISMA principles and protocol, 138 articles were identified for a full examination. priori, grounded coding, the data extracted, analyzed, coded. The this study show that 2021 2022, publications rose nearly two three times number previous years. With rapid rise AIEd HE publications, new trends have emerged. research was conducted six seven continents world. trend has shifted US China leading publications. Another is researcher affiliation as prior studies showed lack researchers departments education. now changed be most dominant department. Undergraduate students studied at 72%. Similar other studies, language learning common subject domain. included writing, reading, vocabulary acquisition. In who intended 72% focused on students, 17% instructors, 11% managers. answering overarching question how used HE, coding used. Five usage codes emerged data: (1) Assessment/Evaluation, (2) Predicting, (3) AI Assistant, (4) Intelligent Tutoring System (ITS), (5) Managing Student Learning. revealed gaps literature springboard future researchers, including tools, such Chat GPT.

Язык: Английский

---

Advances in multimodal data fusion in neuroimaging: Overview, challenges, and novel orientation

Information Fusion, Год журнала: 2020, Номер 64, С. 149 - 187

Опубликована: Июль 17, 2020

Язык: Английский

---

Covid-19 classification by FGCNet with deep feature fusion from graph convolutional network and convolutional neural network

Information Fusion, Год журнала: 2020, Номер 67, С. 208 - 229

Опубликована: Окт. 9, 2020

Язык: Английский

---

Improved Breast Cancer Classification Through Combining Graph Convolutional Network and Convolutional Neural Network

Information Processing & Management, Год журнала: 2020, Номер 58(2), С. 102439 - 102439

Опубликована: Дек. 2, 2020

Язык: Английский

---

Applications of deep learning techniques for automated multiple sclerosis detection using magnetic resonance imaging: A review

Computers in Biology and Medicine, Год журнала: 2021, Номер 136, С. 104697 - 104697

Опубликована: Июль 31, 2021

Язык: Английский

---

Time series forecasting of new cases and new deaths rate for COVID-19 using deep learning methods

Results in Physics, Год журнала: 2021, Номер 27, С. 104495 - 104495

Опубликована: Июнь 26, 2021

The first known case of Coronavirus disease 2019 (COVID-19) was identified in December 2019. It has spread worldwide, leading to an ongoing pandemic, imposed restrictions and costs many countries. Predicting the number new cases deaths during this period can be a useful step predicting facilities required future. purpose study is predict rate one, three seven-day ahead next 100 days. motivation for every n days (instead just day) investigation possibility computational cost reduction still achieving reasonable performance. Such scenario may encountered real-time forecasting time series. Six different deep learning methods are examined on data adopted from WHO website. Three LSTM, Convolutional GRU. bidirectional extension then considered each method forecast Australia Iran This novel as it carries out comprehensive evaluation aforementioned their extensions perform prediction COVID-19 death To best our knowledge, that Bi-GRU Bi-Conv-LSTM models used presented form graphs Friedman statistical test. results show have lower errors than other models. A several error metrics compare all models, finally, superiority determined. research could organisations working against determining long-term plans.

Язык: Английский

---

An overview of artificial intelligence techniques for diagnosis of Schizophrenia based on magnetic resonance imaging modalities: Methods, challenges, and future works

Computers in Biology and Medicine, Год журнала: 2022, Номер 146, С. 105554 - 105554

Опубликована: Май 10, 2022

Язык: Английский

---

Automatic Diagnosis of Schizophrenia in EEG Signals Using CNN-LSTM Models

Frontiers in Neuroinformatics, Год журнала: 2021, Номер 15

Опубликована: Ноя. 25, 2021

Schizophrenia (SZ) is a mental disorder whereby due to the secretion of specific chemicals in brain, function some brain regions out balance, leading lack coordination between thoughts, actions, and emotions. This study provides various intelligent deep learning (DL)-based methods for automated SZ diagnosis via electroencephalography (EEG) signals. The obtained results are compared with those conventional methods. To implement proposed methods, dataset Institute Psychiatry Neurology Warsaw, Poland, has been used. First, EEG signals were divided into 25 s time frames then normalized by z -score or norm L2. In classification step, two different approaches considered this was first carried machine e.g., support vector machine, k -nearest neighbors, decision tree, naïve Bayes, random forest, extremely randomized trees, bagging. Various DL models, namely, long short-term memories (LSTMs), one-dimensional convolutional networks (1D-CNNs), 1D-CNN-LSTMs, used following. models implemented activation functions. Among CNN-LSTM architecture had best performance. architecture, ReLU L2-combined normalization model achieved an accuracy percentage 99.25%, better than most former studies field. It worth mentioning that perform all simulations, -fold cross-validation method = 5

Язык: Английский

---

AI in education: A review of personalized learning and educational technology

GSC Advanced Research and Reviews, Год журнала: 2024, Номер 18(2), С. 261 - 271

Опубликована: Фев. 20, 2024

The integration of Artificial Intelligence (AI) in education has ushered a transformative era, redefining traditional teaching and learning methods. This review explores the multifaceted role AI education, with particular focus on personalized educational technology. synergy between promises to address individualized needs, enhance student engagement, optimize outcomes. Personalized learning, enabled by algorithms, tailors experiences unique preferences, pace each student. approach goes beyond one-size-fits-all model, fostering more inclusive effective environment. delves into diverse applications AI-driven ranging from adaptive content delivery real-time feedback intelligent tutoring systems. It analyzes impact these technologies performance, highlighting potential narrow gaps cater styles. Educational technology, powered AI, extends classroom, encompassing online platforms, virtual reality, interactive tools. curriculum development, creation, assessment methods, offering insights how augment experience. Furthermore, examines automating administrative tasks, allowing educators redirect their towards instruction. Challenges ethical considerations associated adoption are also scrutinized. Privacy concerns, algorithmic biases, digital divide discussed, emphasizing importance responsible implementation. underscores need for collaborative efforts among educators, policymakers, technologists establish guidelines ensure equitable distribution AI-enhanced resources. provides comprehensive examination evolving landscape spotlight As symbiosis continues evolve, this synthesis current research trends aims guide future developments, an informed progressive sphere.

Язык: Английский

---

A Comparative Study of YOLOv5 and YOLOv7 Object Detection Algorithms

Deleted Journal, Год журнала: 2023, Номер 2(1), С. 1 - 12

Опубликована: Фев. 8, 2023

This paper presents a comparative analysis of the widely accepted YOLOv5 and latest version YOLO which is YOLOv7. Experiments were carried out by training custom model with both YOLOv7 independently in order to consider one two performs better terms precision, recall, [email protected] [email protected]:0.95. The dataset used experiment for Remote Weapon Station consists 9,779 images containing 21,561 annotations four classes gotten from Google Open Images Dataset, Roboflow Public Dataset locally sourced dataset. are Persons, Handguns, Rifles Knives. experimental results precision score 52.8%, recall value 56.4%, 51.5% [email protected]:0.95 31.5% while that 62.6%, 53.4%, 55.3% 34.2%. It was observed conducted gave result than overall has higher during testing YOLOv5. records 4.0% increase accuracy compared

Язык: Английский

---