The adoption and use of learning analytics tools to improve decision making in higher learning institutions: An extension of technology acceptance model.

Learning Analytics Tools (LATs) can be used for informed decision-making regarding teaching strategies and their continuous enhancement. Therefore, LATs must be adopted in higher learning institutions, but several factors hinder its implementation, primarily due to the lack of an implementation model. Therefore, in this study, the focus is directed towards examining LATs adoption in Higher Learning Institutions (HLIs), with emphasis on the determinants of the adoption process. The study mainly aims to design a model of LAT adoption and use it in the above context to improve the institutions' decision-making and accordingly, the study adopted an extended version of Technology Acceptance Model (TAM) as the underpinning theory. Five experts validated the employed survey instrument, and 500 questionnaire copies were distributed through e-mails, from which 275 copies were retrieved from Saudi employees working at public HLIs. Data gathered was exposed to Partial Least Square-Structural Equation Modeling (PLS-SEM) for analysis and to test the proposed conceptual model. Based on the findings, the perceived usefulness of LAT plays a significant role as a determinant of its adoption. Other variables include top management support, financial support, and the government's role in LATs acceptance and adoption among HLIs. The findings also supported the contribution of LAT adoption and acceptance towards making informed decisions and highlighted the need for big data facility and cloud computing ability towards LATs usefulness. The findings have significant implications towards LATs implementation success among HLIs, providing clear insights into the factors that can enhance its adoption and acceptance. They also lay the basis for future studies in the area to validate further the effect of LATs on decision-making among HLIs institutions. Furthermore, the obtained findings are expected to serve as practical implications for policy makers and educational leaders in their objective to implement LAT using a multi-layered method that considers other aspects in addition to the perceptions of the individual user.

Breast Cancer Detection and Prevention Using Machine Learning.

Breast cancer is a common cause of female mortality in developing countries. Early detection and treatment are crucial for successful outcomes. Breast cancer develops from breast cells and is considered a leading cause of death in women. This disease is classified into two subtypes: invasive ductal carcinoma (IDC) and ductal carcinoma in situ (DCIS). The advancements in artificial intelligence (AI) and machine learning (ML) techniques have made it possible to develop more accurate and reliable models for diagnosing and treating this disease. From the literature, it is evident that the incorporation of MRI and convolutional neural networks (CNNs) is helpful in breast cancer detection and prevention. In addition, the detection strategies have shown promise in identifying cancerous cells. The CNN Improvements for Breast Cancer Classification (CNNI-BCC) model helps doctors spot breast cancer using a trained deep learning neural network system to categorize breast cancer subtypes. However, they require significant computing power for imaging methods and preprocessing. Therefore, in this research, we proposed an efficient deep learning model that is capable of recognizing breast cancer in computerized mammograms of varying densities. Our research relied on three distinct modules for feature selection: the removal of low-variance features, univariate feature selection, and recursive feature elimination. The craniocaudally and medial-lateral views of mammograms are incorporated. We tested it with a large dataset of 3002 merged pictures gathered from 1501 individuals who had digital mammography performed between February 2007 and May 2015. In this paper, we applied six different categorization models for the diagnosis of breast cancer, including the random forest (RF), decision tree (DT), k-nearest neighbors (KNN), logistic regression (LR), support vector classifier (SVC), and linear support vector classifier (linear SVC). The simulation results prove that our proposed model is highly efficient, as it requires less computational power and is highly accurate.

An Effective and Lightweight Deep Electrocardiography Arrhythmia Recognition Model Using Novel Special and Native Structural Regularization Techniques on Cardiac Signal.

Recently, cardiac arrhythmia recognition from electrocardiography (ECG) with deep learning approaches is becoming popular in clinical diagnosis systems due to its good prognosis findings, where expert data preprocessing and feature engineering are not usually required. But a lightweight and effective deep model is highly demanded to face the challenges of deploying the model in real-life applications and diagnosis accurately. In this work, two effective and lightweight deep learning models named Deep-SR and Deep-NSR are proposed to recognize ECG beats, which are based on two-dimensional convolution neural networks (2D CNNs) while using different structural regularizations. First, 97720 ECG beats extracted from all records of a benchmark MIT-BIH arrhythmia dataset have been transformed into 2D RGB (red, green, and blue) images that act as the inputs to the proposed 2D CNN models. Then, the optimization of the proposed models is performed through the proper initialization of model layers, on-the-fly augmentation, regularization techniques, Adam optimizer, and weighted random sampler. Finally, the performance of the proposed models is evaluated by a stratified 5-fold cross-validation strategy along with callback features. The obtained overall accuracy of recognizing normal beat and three arrhythmias (V-ventricular ectopic, S-supraventricular ectopic, and F-fusion) based on the Association for the Advancement of Medical Instrumentation (AAMI) is 99.93%, and 99.96% for the proposed Deep-SR model and Deep-NSR model, which demonstrate that the effectiveness of the proposed models has surpassed the state-of-the-art models and also expresses the higher model generalization. The received results with model size suggest that the proposed CNN models especially Deep-NSR could be more useful in wearable devices such as medical vests, bracelets for long-term monitoring of cardiac conditions, and in telemedicine to accurate diagnose the arrhythmia from ECG automatically. As a result, medical costs of patients and work pressure on physicians in medicals and clinics would be reduced effectively.

Novel Decision-Making Techniques in Tripolar Fuzzy Environment with Application: A Case Study of ERP Systems.

The intuitionistic fuzzy set (IFS) and bipolar fuzzy set (BFS) are all effective models to describe ambiguous and incomplete cognitive knowledge with membership, non-membership, negative membership, and hesitancy sections. But in daily life problems, there are some situations where we cannot apply the ordinary models of IFS and BFS, separately. Hence, there is a need to combine both the models of IFS and BFS into a single one. A tripolar fuzzy set (TFS) is a generalization of IFS and BFS. In circumstances where BFS and IFS models cannot be used individually, a tripolar fuzzy model is more dependable and efficient. Further, the IFS and BFS models are reduced to corollaries due to the proposed model of TFS. For this purpose in this article, we first consider some novel operations on tripolar fuzzy information. These operations are formulated on the basis of well-known Dombi T-norm and T-conorm, and the desirable properties are discussed. By applying the Dombi operations, arithmetic and geometric aggregation operators of TFS are proposed, and we introduce the concepts of a TF-Dombi weighted average (TFDWA) operator, a TF-Dombi ordered weighted average (TFDOWA) operator, and a TF-Dombi hybrid weighted (TFDHW) operator and explore their fundamental features including idempotency, boundedness, monotonicity, and others. In the second part, we propose TF-Dombi weighted geometric (TFDWG) operator, TF-Dombi ordered weighted geometric (TFDOWG) operator, and TF-Dombi hybrid geometric (TFDHG) operator. The features and specific cases of the mentioned operators are examined. Enterprise resource planning (ERP) is a management and integration approach that organizations employ to manage and develop many aspects of their operations. The study's primary contribution is to employ TFS to create certain decision-making strategies for the selection of optimal ERP systems. The proposed operators are then used to build several techniques for solving multiattribute decision-making (MADM) issues with TF information. Finally, an example of ERP system selection is investigated to demonstrate that the techniques suggested are trustworthy and realistic.

Internet of Things with Deep Learning-Based Face Recognition Approach for Authentication in Control Medical Systems.

Internet of Things (IoT) with deep learning (DL) is drastically growing and plays a significant role in many applications, including medical and healthcare systems. It can help users in this field get an advantage in terms of enhanced touchless authentication, especially in spreading infectious diseases like coronavirus disease 2019 (COVID-19). Even though there is a number of available security systems, they suffer from one or more of issues, such as identity fraud, loss of keys and passwords, or spreading diseases through touch authentication tools. To overcome these issues, IoT-based intelligent control medical authentication systems using DL models are proposed to enhance the security factor of medical and healthcare places effectively. This work applies IoT with DL models to recognize human faces for authentication in smart control medical systems. We use Raspberry Pi (RPi) because it has low cost and acts as the main controller in this system. The installation of a smart control system using general-purpose input/output (GPIO) pins of RPi also enhanced the antitheft for smart locks, and the RPi is connected to smart doors. For user authentication, a camera module is used to capture the face image and compare them with database images for getting access. The proposed approach performs face detection using the Haar cascade techniques, while for face recognition, the system comprises the following steps. The first step is the facial feature extraction step, which is done using the pretrained CNN models (ResNet-50 and VGG-16) along with linear binary pattern histogram (LBPH) algorithm. The second step is the classification step which can be done using a support vector machine (SVM) classifier. Only classified face as genuine leads to unlock the door; otherwise, the door is locked, and the system sends a notification email to the home/medical place with detected face images and stores the detected person name and time information on the SQL database. The comparative study of this work shows that the approach achieved 99.56% accuracy compared with some different related methods.

An Effective Approach for Human Activity Classification Using Feature Fusion and Machine Learning Methods.

Recent advances in image processing and machine learning methods have greatly enhanced the ability of object classification from images and videos in different applications. Classification of human activities is one of the emerging research areas in the field of computer vision. It can be used in several applications including medical informatics, surveillance, human computer interaction, and task monitoring. In the medical and healthcare field, the classification of patients' activities is important for providing the required information to doctors and physicians for medication reactions and diagnosis. Nowadays, some research approaches to recognize human activity from videos and images have been proposed using machine learning (ML) and soft computational algorithms. However, advanced computer vision methods are still considered promising development directions for developing human activity classification approach from a sequence of video frames. This paper proposes an effective automated approach using feature fusion and ML methods. It consists of five steps, which are the preprocessing, feature extraction, feature selection, feature fusion, and classification steps. Two available public benchmark datasets are utilized to train, validate, and test ML classifiers of the developed approach. The experimental results of this research work show that the accuracies achieved are 99.5% and 99.9% on the first and second datasets, respectively. Compared with many existing related approaches, the proposed approach attained high performance results in terms of sensitivity, accuracy, precision, and specificity evaluation metric.

Gender Identification and Classification of Drosophila melanogaster Flies Using Machine Learning Techniques.

Drosophila melanogaster is an important genetic model organism used extensively in medical and biological studies. About 61% of known human genes have a recognizable match with the genetic code of Drosophila flies, and 50% of fly protein sequences have mammalian analogues. Recently, several investigations have been conducted in Drosophila to study the functions of specific genes exist in the central nervous system, heart, liver, and kidney. The outcomes of the research in Drosophila are also used as a unique tool to study human-related diseases. This article presents a novel automated system to classify the gender of Drosophila flies obtained through microscopic images (ventral view). The proposed system takes an image as input and converts it into grayscale illustration to extract the texture features from the image. Then, machine learning (ML) classifiers such as support vector machines (SVM), Naive Bayes (NB), and K-nearest neighbour (KNN) are used to classify the Drosophila as male or female. The proposed model is evaluated using the real microscopic image dataset, and the results show that the accuracy of the KNN is 90%, which is higher than the accuracy of the SVM classifier.

Analysis of medical diagnosis based on variation co-efficient similarity measures under picture hesitant fuzzy sets and their application.

One of the most dominant and feasible technique is called the PHF setting is exist in the circumstances of fuzzy set theory for handling intricate and vague data in genuine life scenario. The perception of PHF setting is massive universal is compared to these assumptions, who must cope with two or three sorts of data in the shape of singleton element. Under the consideration of the PHF setting, we utilized some SM in the region of the PHF setting are to diagnose the PHFDSM, PHFWDSM, PHFJSM, PHFWJSM, PHFCSM, PHFWCSM, PHFHVSM, PHFWHVSM and demonstrated their flexible parts. Likewise, a lot of examples are exposed under the invented measures based on PHF data in the environment of medical diagnosis to demonstrate the stability and elasticity of the explored works. Finally, the sensitive analysis of the presented works is also implemented and illuminated their graphical structures.

Complex pythagorean fuzzy aggregation operators based on confidence levels and their applications.

The most important influence of this assessment is to analyze some new operational laws based on confidential levels (CLs) for complex Pythagorean fuzzy (CPF) settings. Moreover, to demonstrate the closeness between finite numbers of alternatives, the conception of confidence CPF weighted averaging (CCPFWA), confidence CPF ordered weighted averaging (CCPFOWA), confidence CPF weighted geometric (CCPFWG), and confidence CPF ordered weighted geometric (CCPFOWG) operators are invented. Several significant features of the invented works are also diagnosed. Moreover, to investigate the beneficial optimal from a large number of alternatives, a multi-attribute decision-making (MADM) analysis is analyzed based on CPF data. A lot of examples are demonstrated based on invented works to evaluate the supremacy and ability of the initiated works. For massive convenience, the sensitivity analysis and merits of the identified works are also explored with the help of comparative analysis and they're graphical shown.

Transition Metal-Free Half-Metallicity in Two-Dimensional Gallium Nitride with a Quasi-Flat Band.

Two-dimensional half-metallicity without a transition metal is an attractive attribute for spintronics applications. On the basis of first-principles calculation, we revealed that a two-dimensional gallium nitride (2D-GaN), which was recently synthesized between graphene and SiC or wurtzite GaN substrate, exhibits half-metallicity due to its half-filled quasi-flat band. We found that graphene plays a crucial role in stabilizing a local octahedral structure, whose unusually high density of states due to a flat band leads to a spontaneous phase transition to its half-metallic phase from normal metal. It was also found that its half-metallicity is strongly correlated to the in-plane lattice constants and thus subjected to substrate modification. To investigate the magnetic property, we simplified its magnetic structure with a two-dimensional Heisenberg model and performed Monte Carlo simulation. Our simulation estimated its Curie temperature (TC) to be ∼165 K under a weak external magnetic field, suggesting that transition metal-free 2D-GaN exhibiting p orbital-based half-metallicity can be utilized in future spintronics.

Intelligent Malaysian Sign Language Translation System Using Convolutional-Based Attention Module with Residual Network.

The deaf-mutes population always feels helpless when they are not understood by others and vice versa. This is a big humanitarian problem and needs localised solution. To solve this problem, this study implements a convolutional neural network (CNN), convolutional-based attention module (CBAM) to recognise Malaysian Sign Language (MSL) from images. Two different experiments were conducted for MSL signs, using CBAM-2DResNet (2-Dimensional Residual Network) implementing "Within Blocks" and "Before Classifier" methods. Various metrics such as the accuracy, loss, precision, recall, F1-score, confusion matrix, and training time are recorded to evaluate the models' efficiency. The experimental results showed that CBAM-ResNet models achieved a good performance in MSL signs recognition tasks, with accuracy rates of over 90% through a little of variations. The CBAM-ResNet "Before Classifier" models are more efficient than "Within Blocks" CBAM-ResNet models. Thus, the best trained model of CBAM-2DResNet is chosen to develop a real-time sign recognition system for translating from sign language to text and from text to sign language in an easy way of communication between deaf-mutes and other people. All experiment results indicated that the "Before Classifier" of CBAMResNet models is more efficient in recognising MSL and it is worth for future research.

Temporal Bone Adenoma: A Comprehensive Analysis of Clinical Aspects and Surgical Outcome on a Very Rare Entity.

Objective The aim of this study is to present our experience in dealing with middle ear adenomas (MEAs), very rare tumors of the middle ear. Methods The medical notes of individuals with MEAs treated in tertiary referral; academic settings were retrospectively reviewed. We recorded the presenting symptoms, imaging findings, and pathology results. We additionally examined our surgical outcomes, follow-up period, recurrence, and morbidity. Results We identified four patients with MEAs: two males and two females with an average age of 36.25 years (range = 27-51 years). Despite the detailed imaging studies, including computed tomography and magnetic resonance imaging with intravenous contrast administration, a biopsy was essential in setting the diagnosis. Total surgical resection was achieved in all patients without any recurrence over an average of 6 years (range = 3-10 years). Complete ipsilateral deafness was the commonest surgical morbidity due to footplate infiltration by the tumor. Conclusion Total surgical resection is the treatment of choice in MEAs to minimize the risk for recurrence; this can come with morbidity, mostly sensorineural deafness. Given the very limited literature, long-term follow-up is recommended.

q-Rung Orthopair Fuzzy Rough Einstein Aggregation Information-Based EDAS Method: Applications in Robotic Agrifarming.

The main purpose of this manuscript is to present a novel idea on the q-rung orthopair fuzzy rough set (q-ROFRS) by the hybridized notion of q-ROFRSs and rough sets (RSs) and discuss its basic operations. Furthermore, by utilizing the developed concept, a list of q-ROFR Einstein weighted averaging and geometric aggregation operators are presented which are based on algebraic and Einstein norms. Similarly, some interesting characteristics of these operators are initiated. Moreover, the concept of the entropy and distance measures is presented to utilize the decision makers' unknown weights as well as attributes' weight information. The EDAS (evaluation based on distance from average solution) methodology plays a crucial role in decision-making challenges, especially when the problems of multicriteria group decision-making (MCGDM) include more competing criteria. The core of this study is to develop a decision-making algorithm based on the entropy measure, aggregation information, and EDAS methodology to handle the uncertainty in real-word decision-making problems (DMPs) under q-rung orthopair fuzzy rough information. To show the superiority and applicability of the developed technique, a numerical case study of a real-life DMP in agriculture farming is considered. Findings indicate that the suggested decision-making model is much more efficient and reliable to tackle uncertain information based on q-ROFR information.

Feature selection with ensemble learning for prostate cancer diagnosis from microarray gene expression.

Cancer diagnosis using machine learning algorithms is one of the main topics of research in computer-based medical science. Prostate cancer is considered one of the reasons that are leading to deaths worldwide. Data analysis of gene expression from microarray using machine learning and soft computing algorithms is a useful tool for detecting prostate cancer in medical diagnosis. Even though traditional machine learning methods have been successfully applied for detecting prostate cancer, the large number of attributes with a small sample size of microarray data is still a challenge that limits their ability for effective medical diagnosis. Selecting a subset of relevant features from all features and choosing an appropriate machine learning method can exploit the information of microarray data to improve the accuracy rate of detection. In this paper, we propose to use a correlation feature selection (CFS) method with random committee (RC) ensemble learning to detect prostate cancer from microarray data of gene expression. A set of experiments are conducted on a public benchmark dataset using 10-fold cross-validation technique to evaluate the proposed approach. The experimental results revealed that the proposed approach attains 95.098% accuracy, which is higher than related work methods on the same dataset.

An Efficient Cancer Classification Model Using Microarray and High-Dimensional Data.

Cancer can be considered as one of the leading causes of death widely. One of the most effective tools to be able to handle cancer diagnosis, prognosis, and treatment is by using expression profiling technique which is based on microarray gene. For each data point (sample), gene data expression usually receives tens of thousands of genes. As a result, this data is large-scale, high-dimensional, and highly redundant. The classification of gene expression profiles is considered to be a (NP)-Hard problem. Feature (gene) selection is one of the most effective methods to handle this problem. A hybrid cancer classification approach is presented in this paper, and several machine learning techniques were used in the hybrid model: Pearson's correlation coefficient as a correlation-based feature selector and reducer, a Decision Tree classifier that is easy to interpret and does not require a parameter, and Grid Search CV (cross-validation) to optimize the maximum depth hyperparameter. Seven standard microarray cancer datasets are used to evaluate our model. To identify which features are the most informative and relative using the proposed model, various performance measurements are employed, including classification accuracy, specificity, sensitivity, F1-score, and AUC. The suggested strategy greatly decreases the number of genes required for classification, selects the most informative features, and increases classification accuracy, according to the results.

Conventional to online education during COVID-19 pandemic: Do develop and underdeveloped nations cope alike.

BACKGROUND: Educational institutes around the globe are facing challenges of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Online learning is being carried out to avoid face to face contact in emergency scenarios such as coronavirus infectious disease 2019 (COVID-19) pandemic. Students need to adapt to new roles of learning through information technology to succeed in academics amid COVID-19. OBJECTIVE: However, access and use of online learning resources and its link with satisfaction of students amid COVID-19 are critical to explore. Therefore, in this paper, we aimed to assess and compare the access & use of online learning of Bruneians and Pakistanis amid enforced lockdown using a five-items satisfaction scale underlying existing literature. METHOD: For this, a cross-sectional study was done in the first half of June 2020 after the pandemic situation among 320 students' across Pakistan and Brunei with a pre-defined questionnaire. Data were analyzed with statistical software package for social sciences (SPSS) 2.0. RESULTS: The finding showed that there is a relationship between students' satisfaction and access & use of online learning. Outcomes of the survey suggest that Bruneian are more satisfied (50%) with the use of online learning amid lockdown as compared to Pakistanis (35.9%). Living in the Urban area as compared to a rural area is also a major factor contributing to satisfaction with the access and use of online learning for both Bruneian and Pakistanis. Moreover, previous experience with the use of online learning is observed prevalent among Bruneians (P = .000), while among friends and family is using online learning (P = .000) were encouraging factors contributed to satisfaction with the use of online learning among Pakistanis amid COVID-19. Correlation results suggest that access and use factors of online learning amid COVID-19 were positively associated with satisfaction among both populations amid COVID-19 pandemic. However, Bruneian is more satisfied with internet access (r = 0.437, P < .000) and affordability of gadgets (r = 0.577, P < .000) as compare to Pakistanis (r = 0.176, P < .050) and (r = 0.152, P < .050). CONCLUSION: The study suggested that it is crucial for the government and other policymakers worldwide to address access and use of online learning resources of their populace amid pandemic.

GPS Trajectory Completion Using End-to-End Bidirectional Convolutional Recurrent Encoder-Decoder Architecture with Attention Mechanism.

GPS datasets in the big data regime provide rich contextual information that enable efficient implementation of advanced features such as navigation, tracking, and security in urban computing systems. Understanding the hidden patterns in large amount of GPS data is critically important in ubiquitous computing. The quality of GPS data is the fundamental key problem to produce high quality results. In real world applications, certain GPS trajectories are sparse and incomplete; this increases the complexity of inference algorithms. Few of existing studies have tried to address this problem using complicated algorithms that are based on conventional heuristics; this requires extensive domain knowledge of underlying applications. Our contribution in this paper are two-fold. First, we proposed deep learning based bidirectional convolutional recurrent encoder-decoder architecture to generate the missing points of GPS trajectories over occupancy grid-map. Second, we interfaced attention mechanism between enconder and decoder, that further enhance the performance of our model. We have performed the experiments on widely used Microsoft geolife trajectory dataset, and perform the experiments over multiple level of grid resolutions and multiple lengths of missing GPS segments. Our proposed model achieved better results in terms of average displacement error as compared to the state-of-the-art benchmark methods.

Cutaneous Hyperpigmentation Secondary to High-Dose Tigecycline: A Case Report.

High-dose tigecycline therapy is gaining wide acceptance in treating infections caused by multidrug-resistant bacteria. There are no reports of cutaneous hyperpigmentation with the use of high-dose tigecycline. Here we report a case of a woman who developed reversible cutaneous hyperpigmentation within 48 h of receiving high-dose tigecycline.

Correction: Controlled p-type substitutional doping in large-area monolayer WSe2 crystals grown by chemical vapor deposition.

Correction for 'Controlled p-type substitutional doping in large-area monolayer WSe2 crystals grown by chemical vapor deposition' by Stephen A. Campbell et al., Nanoscale, 2018, 10, 21374-21385.

Controlled p-type substitutional doping in large-area monolayer WSe2 crystals grown by chemical vapor deposition.

Tungsten diselenide (WSe2) is a particularly interesting 2D material due to its p-type conductivity. Here we report a systematic single-step process to optimize crystal size by variation of multiple growth parameters resulting in hexagonal single crystals up to 165 µm wide. We then show that these large single crystals can be controllably in situ doped with the acceptor Niobium (Nb). First principles calculations suggest that substitutional Nb doping of W would yield p-doping with no gap trap states. When used as the active layer of a field effect transistor (FET), doped crystals exhibit conventional p-type behavior, rather than the ambipolar behaviour seen in undoped WSe2 FETs. Nb-doped WSe2 FETs yield a maximum field effect mobility of 116 cm2 V-1 s-1, slightly higher than its undoped counterpart, with an on/off ratio of 106. Doping reduces the contact resistance of WSe2, reaching a minimum value of 0.55 kΩµm in WSe2 FETs. The areal density of holes in Nb-doped WSe2 is approximately double that of undoped WSe2, indicating that Nb doping is working as an effective acceptor. Doping concentration can be controlled over several orders of magnitudes, allowing it to be used to control: FET threshold voltage, FET off-state leakage, and contact resistance.