Considering the increasing importance of Artificial Intelligence in Education (AIEd) and the absence of a comprehensive review on it, this research aims to conduct a comprehensive and systematic review of influential AIEd studies. We analyzed 45 articles in terms of annual distribution, leading journals, institutions, countries/regions, the most frequently used terms, as well as theories and technologies adopted. We also evaluated definitions of AIEd from broad and narrow perspectives and clarified the relationship among AIEd, Educational Data Mining, Computer-Based Education, and Learning Analytics. Results indicated that: 1) there was a continuingly increasing interest in and impact of AIEd research; 2) little work had been conducted to bring deep learning technologies into educational contexts; 3) traditional AI technologies, such as natural language processing were commonly adopted in educational contexts, while more advanced techniques were rarely adopted, 4) there was a lack of studies that both employ AI technologies and engage deeply with educational theories. Findings suggested scholars to 1) seek the potential of applying AI in physical classroom settings; 2) spare efforts to recognize detailed entailment relationships between learners’ answers and the desired conceptual understanding within intelligent tutoring systems; 3) pay more attention to the adoption of advanced deep learning algorithms such as generative adversarial network and deep neural network; 4) seek the potential of NLP in promoting precision or personalized education; 5) combine biomedical detection and imaging technologies such as electroencephalogram, and target at issues regarding learners’ during the learning process; and 6) closely incorporate the application of AI technologies with educational theories.

Application and theory gaps during the rise of Artificial Intelligence in Education

In the large-scale parallel computing environment, resource allocation and energy efficient techniques are required to deliver the quality of services (QoS) and to reduce the operational cost of the system. Because the cost of the energy consumption in the environment is a dominant part of the owner's and user's budget. However, when considering energy efficiency, resource allocation strategies become more difficult, and QoS (i.e., queue time and response time) may violate. This paper therefore is a comparative study on job scheduling in large-scale parallel systems to: (a) minimize the queue time, response time, and energy consumption and (b) maximize the overall system utilization. We compare thirteen job scheduling policies to analyze their behavior. A set of job scheduling policies includes (a) priority-based, (b) first fit, (c) backfilling, and (d) window-based policies. All of the policies are extensively simulated and compared. For the simulation, a real data center workload comprised of 22385 jobs is used. Based on results of their performance, we incorporate energy efficiency in three policies i.e., (1) best result producer, (2) average result producer, and (3) worst result producer. We analyze the (a) queue time, (b) response time, (c) slowdown ratio, and (d) energy consumption to evaluate the policies. Moreover, we present a comprehensive workload characterization for optimizing system's performance and for scheduler design. Major workload characteristics including (a) Narrow, (b) Wide, (c) Short, and (d) Long jobs are characterized for detailed analysis of the schedulers' performance. This study highlights the strengths and weakness of various job scheduling polices and helps to choose an appropriate job scheduling policy in a given scenario.

A comparative study on resource allocation and energy efficient job scheduling strategies in large-scale parallel computing systems

Machine Learning (ML) applications are making a considerable impact on healthcare. ML is a subtype of Artificial Intelligence (AI) technology that aims to improve the speed and accuracy of physicians' work. Countries are currently dealing with an overburdened healthcare system with a shortage of skilled physicians, where AI provides a big hope. The healthcare data can be used gainfully to identify the optimal trial sample, collect more data points, assess ongoing data from trial participants, and eliminate data-based errors. ML-based techniques assist in detecting early indicators of an epidemic or pandemic. This algorithm examines satellite data, news and social media reports, and even video sources to determine whether the sickness will become out of control. Using ML for healthcare can open up a world of possibilities in this field. It frees up healthcare providers' time to focus on patient care rather than searching or entering information. This paper studies ML and its need in healthcare, and then it discusses the associated features and appropriate pillars of ML for healthcare structure. Finally, it identified and discussed the significant applications of ML for healthcare. The applications of this technology in healthcare operations can be tremendously advantageous to the organisation. ML-based tools are used to provide various treatment alternatives and individualised treatments and improve the overall efficiency of hospitals and healthcare systems while lowering the cost of care. Shortly, ML will impact both physicians and hospitals. It will be crucial in developing clinical decision support, illness detection, and personalised treatment approaches to provide the best potential outcomes. 

Significance of machine learning in healthcare: Features, pillars and applications

Abstract The quality of Neural Machine Translation (NMT), as a data-driven approach, massively depends on quantity, quality and relevance of the training dataset. Such approaches have achieved promising results for bilingually high-resource scenarios but are inadequate for low-resource conditions. Generally, the NMT systems learn from millions of words from bilingual training dataset. However, human labeling process is very costly and time consuming. In this paper, we describe a round-trip training approach to bilingual low-resource NMT that takes advantage of monolingual datasets to address training data bottleneck, thus augmenting translation quality. We conduct detailed experiments on English-Spanish as a high-resource language pair as well as Persian-Spanish as a low-resource language pair. Experimental results show that this competitive approach outperforms the baseline systems and improves translation quality.

/pdf/augmenting-neural-machine-translation-through-round-trip-132d97o22g.pdf

Augmenting Neural Machine Translation through Round-Trip Training Approach

Tuberculosis (TB) is an infectious disease that has been a major menace to human health globally, causing millions of deaths yearly. Well-timed diagnosis and treatment are an arch to full recovery of the patient. Computer-aided diagnosis (CAD) has been a hopeful choice for TB diagnosis. Many CAD approaches using machine learning have been applied for TB diagnosis, specific to the artificial intelligence (AI) domain, which has led to the resurgence of AI in the medical field. Deep learning (DL), a major branch of AI, provides bigger room for diagnosing deadly TB disease. This review is focused on the limitations of conventional TB diagnostics and a broad description of various machine learning algorithms and their applications in TB diagnosis. Furthermore, various deep learning methods integrated with other systems such as neuro-fuzzy logic, genetic algorithm, and artificial immune systems are discussed. Finally, multiple state-of-the-art tools such as CAD4TB, Lunit INSIGHT, qXR, and InferRead DR Chest are summarized to view AI-assisted future aspects in TB diagnosis.

/pdf/evolution-of-machine-learning-in-tuberculosis-diagnosis-a-39osbnbp.pdf

Evolution of Machine Learning in Tuberculosis Diagnosis: A Review of Deep Learning-Based Medical Applications

This paper describes the notion of machine learning practices and key technologies for healthcare informatics. We categorize the machine learning techniques applied for Healthcare Informatics into four categories: machine learning types, approaches, learning paradigms and algorithms for healthcare informatics. In this paper, we provide a quick overview of the state-of-the-art, research challenges and future directions, specifically driven to the Tuberculosis disease diagnostics. We highlight the strengths and weaknesses of the machine learning techniques to help the healthcare research community to select the appropriate technique in order to apply in the healthcare domain.

A Review of Machine Learning for Healthcare Informatics Specifically Tuberculosis Disease Diagnostics

This study towards the Map-Matching process that is useful to align a location of Global Positioning System (GPS) of vehicles on the digital road networks. Today’s GPS-enabled vehicles in developed countries generate a big volume of GPS data. On the other hand, the development of new roads in the city enables the road network very complex and difficult to match the vehicles’ location. So therefore, different techniques (i.e., pre-processing techniques) may be applied before the map-matching process is a recent concern of the Intelligent Transport System (ITS) research community. In this paper, we introduce the pre-processing technique; splitting the road network graph and processing the Single Source Shortest Path (SSSP) in synchronize parallel processing in the Hadoop environment. The proposed technique enables the map-matching schemes efficient to align the GPS points on the digital road networks. In the experimental work, the results of the map-matching schemes (i.e., found in the literature review) incorporated with our proposed pre-processing technique shows better performance in aspect to the response time.

/pdf/a-study-of-pre-processing-technique-for-map-matching-schemes-10sovmleeq.pdf

A Study of Pre-Processing Technique for Map-Matching Schemes of GPS-Enabled Vehicles

This paper addresses a preliminary model for self-aware heatstroke early-warning system based on the healthcare internet of things (IoT). Basically, heatstroke is a syndrome caused by human's body overheating, commonly due to lengthy exposure or physical exertion in excessive temperatures. Now-a-days, heatstroke is one of the most critical issues in human health due to global warming. The major goal of this research is to save valuable lives by proposing a self-aware heatstroke early-warning system by applying an advancement of healthcare IoT and machine learning technique. The proposed system is an easy to wear and cost-effective system that even middle class people can afford it. The system will use real-time sensor data obtained from the users in real-time outdoor and indoor experiment. In this system, we use an Arduino prototype which contains three different types of sensors including (a) temperature sensor, (b) pulse sensor and (c) breath sensor. In addition to this, the usage of analytics here can enhance accuracy and real-time capability, allow in-advance detection, and enable personalization.

Towards Self-Aware Heatstroke Early-Warning System Based on Healthcare IoT

With the increasing popularity of cloud computing, datacenters are becoming more important than ever before. A typical datacenter typically consists of a large number of homogeneous or heterogeneous servers connected by networks. Unfortunately, these servers and network equipment are often under-utilized and power hungry. To improve the utilization of hardware resources and make them power efficiency in datacenters, workload characterization and analysis is at the foundation. In this paper, we characterize and analyze the job arriving rate, arriving time, job length, power consumption, and temperature dissipation in a real world datacenter by using statistical methods. From the characterization, we find unique features in the workload can be used to optimize the resource utilization and power consumption of datacenters

A Case Study on Job Scheduling Policy for Workload Characterization and Power Efficiency.

/pdf/taxonomy-on-healthcare-system-based-on-machine-learning-2v2up1vlfm.pdf

Imtiaz Ali Korejo

Papers

A Review of Machine Learning for Healthcare Informatics Specifically Tuberculosis Disease Diagnostics

A Study of Pre-Processing Technique for Map-Matching Schemes of GPS-Enabled Vehicles

Towards Self-Aware Heatstroke Early-Warning System Based on Healthcare IoT

A Case Study on Job Scheduling Policy for Workload Characterization and Power Efficiency.

Taxonomy on Healthcare System Based on Machine Learning