Bibliographic Records
Epilepsy is one of the most frequent neurological illnesses caused by epileptic seizures and the second most prevalent neurological ailment after stroke, affecting millions of people worldwide. People with epileptic disease are considered a category of people with disabilities. It significantly impairs a person’s capacity to perform daily tasks, especially those requiring focusing or remembering. Electroencephalogram (EEG) signals are commonly used to diagnose people with epilepsy. However, it is tedious, time-consuming, and subjected to human errors. Several machine learning techniques have been applied to recognize epilepsy previously, but they have some limitations. This study proposes a deep neural network (DNN) machine learning model to determine the existing limitations of previous studies by improving the recognition efficiency of epileptic disease. A public dataset is used in this study and classified into training and testing sets. Experiments were performed to evaluate the DNN model with different dataset classification ratios (80:20), (70:30), (60:40), and (50:50) for training and testing, respectively. Results were evaluated by using different performance metrics including validations, and comparison processes that allow the assessment of the model’s effectiveness. The experimental results showed that the overall efficiency of the proposed model is the highest compared with previous works, with an accuracy rate of 97%. Thus, this study is more accurate and efficient than the existing seizure detection approaches. DNN model has great potential for recognizing epileptic patient activity using a numerical EEG dataset offering a data-driven approach to improve the accuracy and reliability of seizure detection systems for the betterment of patient care and management of epilepsy. Copyright © 2024 Khurshid, Wahid, Ali, Gumaei, Alzanin and Mosleh.
Breast cancer (BC) is a major global health concern. Detecting BC at an early stage gives more treatment options and can help avoid more aggressive treatments. The use of machine learning (ML) in BC prediction offers significant potential for improving the accuracy and speed of diagnosis, personalizing treatment, and identifying high-risk patients. However, there are significant challenges associated with the use of ML, including the need for high-quality data and more flexible models with optimal parameters to achieve high efficiency. In this paper, we propose an optimized framework based on multi-stage data exploration. This framework is designed to provide a comprehensive approach to data exploration, ensuring that the data is well-prepared for ML. In addition, the framework includes dynamic ensemble-based classifiers, which combine multiple independent classifiers to improve accuracy and mitigate the risk of overfitting in conjunction with the cross-validation techniques. These classifiers are optimized using Bayesian hyperparameter tuning, which involves selecting the optimal values for the various hyperparameters of the model. This approach can significantly improve the prediction accuracy of the resulting model. The study evaluates the framework using the publicly available Wisconsin Diagnostic Breast Cancer (WDBC) dataset and compares our results with other state-of-the-art models. The experimental results show that the best result is 100% for accuracy and recall with hyperparameters of (Ensemble Method = AdaBoost, Number of learners = 322, learning rate = 0.9350, and the Maximum number of splits = 1). The highest performance has been achieved with the proposed framework compared with the other models in terms of accuracy (mean = 99.35%, best = 100%, worst = 98.7%, and Standard Deviation = 0.325). The framework can potentially improve the accuracy and efficiency of BC prediction, ultimately leading to better outcomes for patients. © (2024), (Research Institute of Intelligent Computer Systems). All rights reserved.
Test automation is crucial for agile software projects to enable frequent delivery of working software with cost and time and minimal bugs. However, selecting the right automated testing tool is considered challenging due to the wide range of such existing tools. Additionally, the challenges occur clearly due to several issues such as the programming code language, the categorization of the developed system, and the tester’s knowledge and skills. This paper aims to address this gap by proposing an evaluation framework for comparing and classifying the existing automated testing tools used in agile projects. The framework is developed based on an extensive literature review of existing agile testing methodologies and common commercial automation testing techniques. The key criteria for tool evaluation are identified to cover the main testing objective aspects such as test design support, testing interfaces, reporting capabilities, etc. These criteria are considered the core methodology for this study used to analyze and compare the popular open-source and commercial tools. The proposed evaluation framework provides agile practitioners with guidelines to assist in selecting the appropriate tools based on their specific project needs such as budget, timelines, and technical expertise. This study is considered a comparative evaluation of existing agile testing tools to highlight their key strengths and limitations. The findings of this study categorized the testing tools based on the interface, code, design, and report features. This research contributes to assisting the project developer and tester in selecting suitable tools for the adoption of automated testing tools in their agile software projects. It also identifies the direction for future work, such as integrations with modern development methodologies and technologies. © 2024 IEEE.
Yemeni Sign Language (YSL) is a vital communication means for the deaf-muted Yemen community. The deaf-mute community in Yemen faces communication obstacles due to limited access to several environments such as education, work, and social activities. In addition, there are no datasets available for Yemeni sign language. This study is designed to overcome some of the current limitations of Yemeni Sign Language by extending a new dataset for the Yemeni Sign Language dataset and investigating the efficiency of recent transfer learning approaches for YSL recognition. This study compared the effectiveness of transfer learning techniques in the context of YSL recognition. Deep learning models adopted are AlexNet, ResNet152V2, Swin Transformer, InceptionV3, and Xception. These models were selected due to their performance reported by previous research within a diverse computer vision task. The new dataset was constructed with 24,245 sign images collected manually with specific criteria to obtain 32 different sign labels. A preprocessing for sign images was applied to improve the recognition process of the YSL sign. CNN models are customized using transfer learning and fine-tuning strategies for experimental purposes. Experiment results showed a remarkable accuracy rate for Swin Transformer, AlexNet, InceptionV3, ResNet152V2, and Xception models as 99.0%, 99.0%, 98,0%, 98.0%, and 99.0%, respectively. The study result showed that The Xception model obtained the highest training accuracy rate, and the AlexNet and Swin transformer models obtained the highest testing accuracy rate. In conclusion, the outcomes contribute to developing a robust and accessible YSL recognition system to prompt effective communication and inclusivity for the deaf-muted community in Yemen. © 2024 IEEE.
Sign language is widely used to facilitate the communication process between deaf people and their surrounding environment. Sign language, like most other languages, is considered a complex language which cannot be mastered easily. Thus, technology can be used as an assistive tool to solve the difficulties and challenges that deaf people face during interactions with society. In this study, an automatic bidirectional translation framework for Arabic Sign Language (ArSL) is designed to assist both deaf and ordinary people to communicate and express themselves easily. Two main modules were intended to translate Arabic sign images into text by utilizing different transfer learning models and to translate the input text into Arabic sign images. A prototype was implemented based on the proposed framework by using several pre-trained convolutional neural network (CNN)-based deep learning models, including the DenseNet121, ResNet152, MobileNetV2, Xception, InceptionV3, NASNetLarge, VGG19, and VGG16 models. A fuzzy string matching score method, as a novel concept, was employed to translate the input text from ordinary people into appropriate sign language images. The dataset was constructed with specific criteria to obtain 7030 images for 14 classes captured from both deaf and ordinary people locally. The prototype was developed to conduct the experiments on the collected ArSL dataset using the utilized CNN deep learning models. The experimental results were evaluated using standard measurement metrics such as accuracy, precision, recall, and F1-score. The performance and efficiency of the ArSL prototype were assessed using a test set of an 80:20 splitting procedure, obtaining accuracy results from the highest to the lowest rates with average classification time in seconds for each utilized model, including (VGG16, 98.65%, 72.5), (MobileNetV2, 98.51%, 100.19), (VGG19, 98.22%, 77.16), (DenseNet121, 98.15%, 80.44), (Xception, 96.44%, 72.54), (NASNetLarge, 96.23%, 84.96), (InceptionV3, 94.31%, 76.98), and (ResNet152, 47.23%, 98.51). The fuzzy matching score is mathematically validated by computing the distance between the input and associative dictionary words. The study results showed the prototype’s ability to successfully translate Arabic sign images into Arabic text and vice versa, with the highest accuracy. This study proves the ability to develop a robust and efficient real-time bidirectional ArSL translation system using deep learning models and the fuzzy string matching score method. © 2024 by the authors.
Breast cancer is a primary cause of cancer-associated mortality among women globally, and early detection and personalized treatment are critical for improving patient outcomes. In this study, we propose an optimal framework for predicting breast cancer patient survivability using the GentleBoost algorithm and Bayesian optimization. The proposed framework combines the strengths of the GentleBoost algorithm, which is a powerful machine-learning algorithm for classification, and Bayesian optimization, which is a powerful optimization technique for hyperparameter tuning. We evaluated the proposed framework using the publicly available breast cancer dataset provided by The Surveillance, Epidemiology, and End Results (SEER) program and compared its performance with several popular single algorithms, including support vector machine (SVM), artificial neural network (ANN), and knearest neighbors (KNN). The experimental results demonstrate that the proposed framework outperforms these methods in terms of accuracy (mean= 95.16%, best = 95.35, worst = 95.1%, and SD = 0.008). The values of precision, recall, and f1-score of the best experiment were 92.3 %, 98.2 %, and 95.2 %, respectively, with hyperparameters of (number of learners = 246, learning rate = 0.0011, and maximum number of splits = 1240). The proposed framework has the potential to improve breast cancer patient survival predictions and personalized treatment plans, leading to the improved patient outcomes and reduced healthcare costs. © (2023), (Research Institute of Intelligent Computer Systems). All Rights Reserved.
Face recognition is a subfield of artificial intelligence science that uses different biometric features of human faces to recognize people. Face recognition systems are widely used due to highly achieved recognition accuracy reaching almost 99.73%. However, there are several challenges and limitations existing especially for real-time face recognitions. Some of these challenges occurred during the global outbreak of the COVID-19 pandemic in December 2019. In this paper, a transfer learning approach proposes to overcome the challenges of masked face recognition by using a pre-trained deep convolution neural network (DCNN) model. The modified version of the CASIA dataset with generated synthetic masks dataset is used for evaluating the proposed model. The results of evaluation metrics were promises where the overall model accuracy rate reaches 93%. Thus, the proposed model showed the ability of DCNN model to recognize masked face images efficiently. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.
Breast cancer (BC) is a major health concern affecting women worldwide, and early detection is crucial for effective treatment and improved survival rates. In this study, we propose a novel BC prediction framework based on iterative optimization with Bayesian hyperparameter tuning applied to the Wisconsin Diagnostic Breast Cancer (WDBC) and Surveillance, Epidemiology, and End Results (SEER) datasets. Our approach employs various Machine Learning (ML) algorithms, including tree-based, support vector machine (SVM)-based, K-nearest neighbor (KNN)-based, tree-based ensemble, and artificial neural network (ANN)-based ML models. The results demonstrated that the optimized models generally outperformed their non-optimized counterparts. Notably, the optimized AdaBoost model achieved a remarkable performance with 100% accuracy, precision, recall, and F1-score on the WDBC dataset. The optimized GentleBoost model exhibited a high performance of 95.3% accuracy, 97.4% precision, 93.1% recall, 95.2% F1-score, and 0.99 area under the curve (AUC) on the SEER dataset. These findings highlight the potential of our proposed framework for enhancing BC prediction accuracy and robustness, paving the way for future research and clinical application. © 2023 IEEE.
Breast cancer (BC) is a critical public health concern, and the development of accurate prediction models is crucial for early detection. However, predicting BC using imbalanced datasets poses challenges for achieving accurate predictions. This study aims to enhance the performance of BC prediction models by employing the Synthetic Minority Over-sampling Technique (SMOTE) to address the imbalance in the target class of the dataset. Two approaches are employed to evaluate the models: the first approach utilizes the original Breast Cancer Coimbra Dataset (BCCD), while the second approach utilizes SMOTE to balance the target class in the BCCD. The results of the performance comparison between the two approaches demonstrate that the utilization of SMOTE significantly improves the performance of the BC prediction models. For instance, the Fine Tree, Coarse Tree, and Medium Tree models achieved accuracy rates of 60.9%, 52.2%, and 60.9%, respectively, with the SMOTE implementation. The Quadratic SVM and Cubic SVM models achieved accuracy rates of 73.9% with SMOTE. The Fine Gaussian SVM model achieved accuracy rates of 65.2 % and 80% without and with SMOTE, respectively. Similarly, the Coarse Gaussian SVM model achieved accuracy rates of 52.2% and 60% without and with SMOTE, respectively. The Medium KNN and Weighted KNN models both achieved accuracy rates of 73.9% without SMOTE and 76% with SMOTE. Furthermore, Bagged Trees achieved accuracy rates of 69.6% without SMOTE and 80% with SMOTE, while Subspace Discriminant achieved accuracy rates of 73.9% without SMOTE and 80% with SMOTE. The Optimized LogitBoost model achieved accuracy rates of 73.9% without SMOTE and 88% with SMOTE, and AdaBoost using Bayesian Optimization achieved accuracy rates of 52.2% without SMOTE and 76% with SMOTE. This study demonstrated that implementing SMOTE to balance the dataset leads to improved accuracy in BC prediction models. © 2023 IEEE.
Developing an electronic voting system that meets the practical needs of administrators has been a difficult task for a long time. Now, blockchain technologies solve this problem by providing a distributed ledger with immutable, encrypted, and secure transactions. Distributed ledger technologies are an interesting technological leap in the field of data innovation, transparency, and trustability. In public blockchain, distributed ledger technology is widely used. The blockchain technology can be used in an almost infinite number of ways to benefit from sharing economies. The purpose of this study is to assess how blockchain may be utilized to build electronic voting systems that can be used as a service. The purpose of electronic voting systems is explained in this article, as are the technological and legal limitations of employing blockchain as a service. Then, using blockchain as a foundation, we propose a new electronic voting system that fixes the flaws we observed. In general, this paper evaluates the capabilities of distributed ledger technologies by depicting a contextual investigation in order to fine-tune the process of political election decisions and employing a blockchain-based application that improves security and lowers the cost of conducting nationwide elections. © 2022 Ch Anwar ul Hassan et al.
A personalized recommender system is broadly accepted as a helpful tool to handle the information overload issue while recommending a related piece of information. This work proposes a hybrid personalized recommender system based on affinity propagation (AP), namely, APHPRS. Affinity propagation is a semisupervised machine learning algorithm used to cluster items based on similarities among them. In our approach, we first calculate the cluster quality and density and then combine their outputs to generate a new ranking score among clusters for the personalized recommendation. In the first phase, user preferences are collected and normalized as items rating matrix. This generated matrix is then clustered offline using affinity propagation and kept in a database for future recommendations. In the second phase, online recommendations are generated by applying the offline model. Negative Euclidian similarity and the quality of clusters are used together to select the best clusters for recommendations. The proposed APHPRS system alleviates problems such as sparsity and cold-start problems. The use of affinity propagation and the hybrid recommendation technique used in the proposed approach helps in improving results against sparsity. Experiments reveal that the proposed APHPRS performs better than most of the existing recommender systems. © 2022 Iqbal Qasim et al.
Prostate Cancer (PCa) is considered as one of the widely cancer diseases affect men around the globe. Research found about 16.67% of men affects by PCa in their life specially after 40 ages. Studies reported that one of every six men are suffering from Prostate Cancer approximately. The traditional methods of PCa diagnosis are considered a tedious process and subjected to human errors. Therefore, research tried to develop an efficient diagnostic technique for early detection of PCa which can make a great clinical treatment impact. This paper presents an intelligent system for automated the process of detecting prostate cancer by using MRI images with convolution neural network approaches. Five pre-trained transfer-learning models are used here including: Inception-v3, Inception-v4, Inception-Resent-v2, Xception, and PolyNet. The dataset consisted of 1524 prostate MRIs, which were divided into three parts: 1067 MRI for training, 304 MRI for validation, and 153 MRI for test purposes. Initially, the dimension of MRI images was resized to reduce the complexity and computation processing. Then, the training phase conducted by forwarding MRI images into transfer learning models individually for feature extractions and PCa classification. The transfer learning models were used to classify MRI prostate images into two sets: positive (significant) and negative (nonsignificant) results. Finally, experiments were conducted to evaluate the pre-trained models using both validation and testing datasets. The experimental results showed a robust and high accuracy recognition rate of detecting PCa for each model where Inception-v3 = 98.69, Inception-v4= 96.73%, Inception-Resent-v2= 96.73%, Xception=95.42%, and PolyNet=99.34%. We found here the ability of proposed transfer learning models to detect prostate cancer using MRI images successfully with a high accuracy recognition rate. © 2022 IEEE.
In the domains of computational and applied mathematics, soft computing, fuzzy logic, and machine learning (ML) are well-known research areas. ML is one of the computational intelligence aspects that may address diverse difficulties in a wide range of applications and systems when it comes to exploitation of historical data. Predicting medical insurance costs using ML approaches is still a problem in the healthcare industry that requires investigation and improvement. Using a series of machine learning algorithms, this study provides a computational intelligence approach for predicting healthcare insurance costs. The proposed research approach uses Linear Regression, Support Vector Regression, Ridge Regressor, Stochastic Gradient Boosting, XGBoost, Decision Tree, Random Forest Regressor, Multiple Linear Regression, and k-Nearest Neighbors A medical insurance cost dataset is acquired from the KAGGLE repository for this purpose, and machine learning methods are used to show how different regression models can forecast insurance costs and to compare the models’ accuracy. The results shows that the Stochastic Gradient Boosting (SGB) model outperforms the others with a cross-validation value of 0.0.858 and RMSE value of 0.340 and gives 86% accuracy. Copyright © 2021 Ch. Anwar ul Hassan et al.
The strenuous mining and arduous discovery of the concealed community structure in complex networks has received tremendous attention by the research community and is a trending domain in the multifaceted network as it not only reveals details about the hierarchical structure of multifaceted network but also assists in better understanding of the core functions of the network and subsequently information recommendation. The bipartite networks belong to the multifaceted network whose nodes can be divided into a dissimilar node-set so that no edges assist between the vertices. Even though the discovery of communities in one-mode network is briefly studied, community detection in bipartite networks is not studied. In this paper, we propose a novel Rider-Harris Hawks Optimization (RHHO) algorithm for community detection in a bipartite network through node similarity. The proposed RHHO is developed by the integration of the Rider Optimization (RO) algorithm with the Harris Hawks Optimization (HHO) algorithm. Moreover, a new evaluation metric, i.e., h-Tversky Index (h-TI), is also proposed for computing node similarity and fitness is newly devised considering modularity. The goal of modularity is to quantify the goodness of a specific division of network to evaluate the accuracy of the proposed community detection. The quantitative assessment of the proposed approach, as well as thorough comparative evaluation, was meticulously conducted in terms of fitness and modularity over the citation networks datasets (cit-HepPh and cit-HepTh) and bipartite network datasets (Movie Lens 100 K and American Revolution datasets). The performance was analyzed for 250 iterations of the simulation experiments. Experimental results have shown that the proposed method demonstrated a maximal fitness of 0.74353 and maximal modularity of 0.77433, outperforming the state-of-the-art approaches, including h-index-based link prediction, such as Multiagent Genetic Algorithm (MAGA), Genetic Algorithm (GA), Memetic Algorithm for Community Detection in Bipartite Networks (MATMCD-BN), and HHO. © 2021 Bader Fahad Alkhamees et al.
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.
Planar graphs play an effective role in many practical applications where the crossing of edges becomes problematic. This paper aims to investigate the complex q-rung orthopair fuzzy (CQROF) planar graphs (CQROFPGs). In a CQROFPG, the nodes and edges are based on complex QROF information that represents the uncertain knowledge in the range of unit circles in terms of complex numbers. The motivation in discussing such a topic is the wide flexibility of QROF information in the expression of uncertain knowledge compared to intuitionistic and Pythagorean fuzzy settings. We discussed the complex QROF graphs (CQROFGs), complex QROF multigraphs (CQROFMGs), and related terms followed by examples. Furthermore, the notion of strength and planarity index (PI) of the CQROFPGs is defined and exemplified followed by a study of strong and weak edges. We further defined the notion of complex QROF face (CQROFF) and complex QROF dual graph (CQROFDG) and exemplified these concepts. A study of isomorphism, coweak and weak isomorphism, is set up, and some results relating to the CQROFPG and isomorphisms are explored using examples. Furthermore, the problem of short circuits that results due to crossing is discussed because of the proposed study where an algorithm based on complex QROF (CQROF) information is presented for reducing the crossing in networks. Some advantages of the projected study over the previous study are observed, and some future study is predicted. © 2021 Abrar Hussain et al.
Linear Diophantine uncertain linguistic set (LDULS) is a modified variety of the fuzzy set (FS) to manage problematic and inconsistent information in actual life troubles. LDULS covers the grade of truth, grade of falsity, and their reference parameters with the uncertain linguistic term (ULT) with a rule 0≤αAMGuAMGx+βANGvAMGx≤1, where 0≤αAMG+βANG≤1. In this study, the principle of LDULS and their useful laws are elaborated. Additionally, the power Einstein (PE) aggregation operator (AO) is a conventional sort of AO utilized in innovative decision-making troubles, which is effective to aggregate the family of numerical elements. To determine the interrelationship between any numbers of arguments, we elaborate the linear Diophantine uncertain linguistic PE averaging (LDULPEA), linear Diophantine uncertain linguistic PE weighted averaging (LDULPEWA), linear Diophantine uncertain linguistic PE geometric (LDULPEG), and linear Diophantine uncertain linguistic PE weighted geometric (LDULPEWG) operators; then, we discuss their useful results. Conclusively, a decision-making methodology is utilized for the multiattribute decision-making (MADM) dilemma with elaborated information. A sensible illustration is specified to demonstrate the accessibility and rewards of the intended technique by comparison with certain prevailing techniques. The intended AOs are additional comprehensive than the prevailing ones to exploit the ambiguous and inaccurate knowledge. Numerous remaining operators are chosen as individual incidents of the suggested one. Ultimately, the supremacy and advantages of the elaborated operators are also discussed with the help of the geometrical form to show the validity and consistency of explored operators. © 2021 Tahir Mahmood et al.
voting process is a democratic practice that has been used over the years as a primary method used by people in democratic countries to express their opinions on issues and discussions that concern them. This paper seeks to facilitate and protect the voting process by making an online voting system for elections and referendums connected with voting devices. The IoT and Blockchain have been used with this system to ensure that users’ data are protected from theft and prevent eavesdropping or vote tampering to guarantee the integrity of the voting. The blockchain encrypts votes in order to protect every vote from forgery. This system is not directed to governments only, but to all governmental and private agencies. For example, governments can establish referendums or elections, and anyone who has reached the legal age and has a voting card issued by the government will be able to vote, thus we get rid of the traditional methods and dispense with ballot boxes, standing in long queues and delay counting the votes that cost governments a lot of time, effort and money. Also, any institution or private corporation that wishes to conduct polls and questionnaires or to conduct a specific study in order to collect opinions from people of society can simply use this system to reach them. The system assists the concerned authorities in obtaining results quickly without delay, taking into account the differences in voting process between government and private organizations. © 2021 IEEE.
Malaria is globally known as one of the most prevalent diseases that kill thousands of people every year. Plasmodium parasites are the product of malaria disease that infects the red blood cells of humans. These parasites are transmitted by a female mosquito class that is known as anopheles. The diagnostic process of malaria involves isolation and manual counts in microscopic bloodstreams of parasitized cells by medical practitioners. In large-scale screening, Malaria diagnostic accuracy is largely affected because of resource unavailability. In this paper, we proposed an intelligent diagnosis system using advanced techniques based on a deep learning algorithm precisely AlexNet pre-trained model. As the bright side of machine learning techniques, CNN has greatly led to numerous image recognition activities. This method shows encouraging results. In terms of accuracy, the proposed model achieved 97.33% in the validation phase. Therefore, in some places where there are no medical services, this approach can be widely used for diagnosing parasitized cells. © 2021 IEEE.
Biosensor is a means to transmit some physical phenomena, like body temperature, pulse, respiratory rate, electroencephalogram (EEG), electrocardiogram (ECG), and blood pressure. Such transmission is performed via Wireless Medical Sensor Network (WMSN) while diagnosing patients remotely through Internet-of-Medical-Things (IoMT). The sensitive data transmitted through WMSN from IoMT over an insecure channel is vulnerable to several threats and needs proper attention to be secured from adversaries. In contrast to addressing the security of all associated entities involving patient monitoring in the healthcare system or ensuring the integrity, authorization, and nonrepudiation of information over the communication line, no one can guarantee its security without a robust authentication protocol. Therefore, we have proposed a lightweight and robust authentication scheme for the network-enabled healthcare devices (IoMT) that mitigate all the identified weaknesses posed in the recent literature. The proposed protocol’s security has been analyzed formally using BAN logic and ProVerif2.02 and informally using pragmatic illustration. Simultaneously, at the end of the paper, the performance analysis result shows a delicate balance of security with performance that is often missing in the current protocols. © 2021 Saeed Ullah Jan et al.
The structure of q-rung orthopair fuzzy sets (q-ROFSs) is a generalization of fuzzy sets (FSs), intuitionistic FSs (IFSs), and Pythagorean FSs (PFSs). The notion of q-ROFSs has the proficiency of coping with uncertainty without any restrictions. In addition, the structure of q-ROFSs can effectively cope with the situations involving dual opinions without any restrictions, instead of dealing with only single opinion or dual opinions under certain restrictions. In clustering problems, the correlation coefficients are worthwhile because they provide the degree of similarity or correlation between two elements or sets. The theme of this study is to formulate the correlation coefficients for q-ROFSs that are basically the generalization of correlation coefficients of IFSs and PFSs. Moreover, an application of these correlation coefficients to a clustering problem is proposed. Also, an analysis of the outcomes is carried out. Furthermore, a comparison is carried out among the correlation coefficients for q-ROFSs and the existing ones. Finally, the downsides of the existing works and benefits of the correlation coefficients for q-ROFSs are discussed. © 2021 Huma Bashir et al.
This paper aims to propose a new methodology for spherical cubic fuzzy (SCF) multicriteria decision-making (MCDM) utilizing the TOPSIS method that uses incomplete weight information. At first, the maximum deviation model is suggested to determine the criteria of weight values. An MCDM methodology is introduced using SCF information, based on the proposed method. Also, to validate the effectiveness of the proposed information, a numerical example is given. Finally, a comprehensive and structured analysis of existing work in comparison with previous work is given. © 2021 Tehreem et al.
Self-expression and understanding people language are among the most important things to be considered. Deaf and dumb is a group of that they facing difficulty to express themselves and communicate with others. This group of people is trying to communicate with others using ‘sign language’. This study is design to enhance the communication channel between these people with their society using technology. A prototype system was design to translate the Yemeni sign language into text. Deep learning algorithms included in the system using convolutional neural network (CNN) with various transfer Learning models. System evaluation is used torch and tensorflow libraries as training and testing dataset of Yemeni sign language. Accuracy comparison results obtained among various models included in this study such as Visual Geometry Group (VGG16), Residential Energy Services Network (ResNet), Google Network (GoogleNet), and Densely Connected Convolutional Network (DenseNet). We found that the accuracy results obtained for each model were (ConveNet = 98.66%), (Sequential CNN= 98.34%), (GoogleNet = 98.36%), (Vgg16 = 90, 46%), (DenseNet = 99.65%), and the best result was (ResNet152 = 99.78%). This study showed the ability of technology to enhance the communication methods between deaf and their society with a suitable translation accuracy. © 2021 IEEE.
Background. This study assesses the feasibility of using machine learning methods such as Random Forests (RF), Artificial Neural Networks (ANN), Support Vector Regression (SVR) and Self-Organizing Feature Maps (SOM) to identify and determine factors associated with hypertensive patients’ adherence levels. Hypertension is the medical term for systolic and diastolic blood pressure higher than 140/90mmHg.Aconventional medication adherence scale was used to identify patients’ adherence to their prescribed medication. Using machine learning applications to predict precise numeric adherence scores in hypertensive patients has not yet been reported in the literature. Methods. Data from 160 hypertensive patients from a tertiary hospital in Kuala Lumpur, Malaysia, were used in this study. Variables were ranked based on their sig- nificance to adherence levels using the RF variable importance method. The backward elimination method was then performed using RF to obtain the variables significantly associated with the patients’ adherence levels. RF, SVR and ANN models were developed to predict adherence using the identified significant variables. Visualizations of the relationships between hypertensive patients’ adherence levels and variables were generated using SOM. Result. Machine learning models constructed using the selected variables reported RMSE values of 1.42 for ANN, 1.53 for RF, and 1.55 for SVR. The accuracy of the dichotomised scores, calculated based on a percentage of correctly identified adherence values, was used as an additional model performance measure, resulting in accuracies of 65% (ANN), 78% (RF) and 79% (SVR), respectively. The Wilcoxon signed ranked test reported that there was no significant difference between the predictions of the machine learning models and the actual scores. The significant variables identified from the RF variable importance method were educational level, marital status, General Overuse, monthly income, and Specific Concern. Conclusion. This study suggests an effective alternative to conventional methods in identifying the key variables to understand hypertensive patients’ adherence levels. This can be used as a tool to educate patients on the importance of medication in managing hypertension. Copyright © 2020 Aziz et al.
Manual counting of nuclei cells from histological images is considered tedious process, time-consuming and subjected to human errors. Therefore, automated the process of nuclei cells counting is become important and necessary for effective analyzing of histological images. Current systems and approaches of nuclei cells counting are based on color or grayscale images leading to inaccurate results and have several limitations. In this paper, we propose a novel accurate approach for automatic nuclei cells counting using effective image processing methods. The new techniques are designed based on image thresholding method, morphological image processing operations, and connected component algorithm. The new approach was evaluated experimentally on 37 images of a public data set of 100 histological images. The experimental results demonstrated that the approach achieved a high accuracy up to 89.5% compared with previous works. We concluded the effectiveness of the proposed approach for automatic counting of nuclei cells from histological images.
This article reviews bioimaging techniques for biological and medical specimens in bioimage informatics. The wealth of information generated from bioimages requires a proper method and guidelines to transfer this information into useful knowledge. Advancement in imaging technologies generates quantitative measurements from images that enhance knowledge and understanding of biological phenomena. From this arises the need of bioimage informatics. Bioimage informatics techniques translate image data into valuable biological information. Bioimage informatics techniques that are important include acquisition, processing, segmentation, feature and extraction, analysis, and data mining. Bioimage informatics research is heading towards automated invention of models of biological systems and machine learning methods. © 2019 Elsevier Inc. All rights reserved.
In this study, we examined the lower limb fracture healing time in children using random forest (RF) and Self Organizing feature Maps (SOM) methods. The study sample was obtained from the pediatric orthopedic unit in University Malaya Medical Centre. Radiographs of long bones of lower limb fractures involving the femur, tibia and fibula from children ages 0–12 years, with ages recorded from the date and time of initial injury. Inputs assessment extracted from radiographic images included the following features: type of fracture, angulation of the fracture, contact area percentage of the fracture, age, gender, bone type, type of fracture, and number of bone involved. RF is initially used to rank the most important variables that effecting bone healing time. Then, SOM was applied for analysis of the relationship between the selected variables with fracture healing time. Due to the limitation of available dataset, leave one out technique was applied to enhance the reliability of RF. Results showed that age and contact area percentage of fracture were identified as the most important variables in explaining the fracture healing time. RF and SOM applications have not been reported in the field of pediatric orthopedics. We concluded that the combination of RF and SOM techniques can be used to assist in the analysis of pediatric fracture healing time efficiently. © 2017
Ficus is one of the largest genera in plant kingdom reaching to about 1000 species worldwide. While taxonomic keys are available for identifying most species of Ficus, it is very difficult and time consuming for interpretation by a nonprofessional thus requires highly trained taxonomists. The purpose of the current study is to develop an efficient baseline automated system, using image processing with pattern recognition approach, to identify three species of Ficus, which have similar leaf morphology. Leaf images from three different Ficus species namely F. benjamina, F. pellucidopunctata and F. sumatrana were selected. A total of 54 leaf image samples were used in this study. Three main steps that are image pre-processing, feature extraction and recognition were carried out to develop the proposed system. Artificial neural network (ANN) and support vector machine (SVM) were the implemented recognition models. Evaluation results showed the ability of the proposed system to recognize leaf images with an accuracy of 83.3%. However, the ANN model performed slightly better using the AUC evaluation criteria. The system developed in the current study is able to classify the selected Ficus species with acceptable accuracy. © 2018 The Author(s).
In this study we examined the lower limb fracture in children and classified the healing time using supervised and unsupervised artificial neural network (ANN). Radiographs of long bones from 2009 to 2011 of lower limb fractures involving the femur, tibia and fibula from children ages 0 to 13 years, with ages recorded from the date and time of initial injury was obtained from the pediatric orthopedic unit in University Malaya Medical Centre. ANNs was developed using the following input: type of fracture, angulation of the fracture, displacement of the fracture, contact area of the fracture and age. Fracture healing time was classified into two classes that is less than 12 weeks which represent normal healing time in lower limb fractures and more than 12 weeks which could indicate a delayed union. This research was designed to evaluate the classification accuracy of two ANN methods (SOM, and MLP) on pediatric fracture healing. Standard feed-forward, back-propagation neural network with three layers was used in this study. The less sensitive variables were eliminated using the backward elimination method, and the ANN network was retrained again with minimum variables. Accuracy rate, area under the curve (AUC), and root mean square errors (RMSE) are the main criteria used to evaluate the ANN model results. We found that the best ANN model results was obtained when all input variables were used with overall accuracy percentage of 80%, with RMSE value of 0.34, and AUC value of 0.8. We concluded here that the ANN model in this study can be used to classify pediatric fracture healing time, however extra efforts are required to adapt the ANN model well by using its full potential features to improve the ANN performance especially in the pediatric orthopedic application. © Springer International Publishing Switzerland 2016.
In this study, we provide historical accounts with an overview of essential research on model-checking development tools. This study has two main objectives; first, it is intended to investigate whether model checking still an active area; second, to classify existing model-checking tools by providing an illustration of each dimension scope, an analysis of similarities and differences among them, and a prediction of the future direction of typical model-checking tools. We found that existing model-checking tools show significant effects in automated system testing and verification. We also found that system testing and verification are still active areas of research. Current model-checking tools work efficiently on limited environment, and a lot of work need to perform for verifying the functional and nonfunctional attributes of complex systems. Despite the limitations of existing model-checking tools, universal model-checking tools can probably be developed if a good framework is established to fulfill the requirements of fully automated tools. © Springer International Publishing Switzerland 2016.
Background: Cephalometric analysis and measurements of skull parameters using X-Ray images plays an important role in predicating and monitoring orthodontic treatment. Manual analysis and measurements of cephalometric is considered tedious, time consuming, and subjected to human errors. Several cephalometric systems have been developed to automate the cephalometric procedure; however, no clear insights have been reported about reliability, performance, and usability of those systems. This study utilizes some techniques to evaluate reliability, performance, and usability metric using SUS methods of the developed cephalometric system which has not been reported in previous studies. Methods: In this study a novel system named Ceph-X is developed to computerize the manual tasks of orthodontics during cephalometric measurements. Ceph-X is developed by using image processing techniques with three main models: enhancements X-ray image model, locating landmark model, and computation model. Ceph-X was then evaluated by using X-ray images of 30 subjects (male and female) obtained from University of Malaya hospital. Three orthodontics specialists were involved in the evaluation of accuracy to avoid intra examiner error, and performance for Ceph-X, and 20 orthodontics specialists were involved in the evaluation of the usability, and user satisfaction for Ceph-X by using the SUS approach. Results: Statistical analysis for the comparison between the manual and automatic cephalometric approaches showed that Ceph-X achieved a great accuracy approximately 96.6%, with an acceptable errors variation approximately less than 0.5mm, and 1°. Results showed that Ceph-X increased the specialist performance, and minimized the processing time to obtain cephalometric measurements of human skull. Furthermore, SUS analysis approach showed that Ceph-X has an excellent usability user’s feedback. Conclusions: The Ceph-X has proved its reliability, performance, and usability to be used by orthodontists for the analysis, diagnosis, and treatment of cephalometric. © 2016 The Author(s).
There are world efforts to make technology act with education field for better learning achievements. Technology tries to replace the traditional learning environments, media, and activities into digital age. However, slow progress has been achieved to transfer the note taking activities into digital era. In this study, we explored current note taking tools which developed to bridge the gap between paper-based and technology-based notes. We tried to identify key specific problems and challenges that prevent note taking from existing in the digital age. This study is providing extensive investigation with systematic analysis about the impacts of current note taking tools in learning to identify constrains and limitations of typical note taking systems. Unfortunately, we agreed with similar previous studies that current tools are still inadequate and inefficient to be used for replacing the traditional note taking due to several issues. We found that developing a successful note taking applications is challenges because of four main issues, complexity, technology learning dilemma, integrity, and inefficiency issues. This study discusses the main implications to shape the future of digital notes. © Springer International Publishing Switzerland 2016.
Maintenance and monitoring of aquatic systems such lakes, reservoirs and river involves properly documented, valid, and comprehensible data archives. However, aquatic data are collected and kept separately, creating difficulties in data integration. For effective aquatic data management it is important to have databases metadata that have been validated. This study aims to discuss framework for aquatic data warehouse system using web services for sharing database components using standard format and common data exchange method to foster easier data integration and exchange. The key features of the data warehouse comprises of graphical user interface (GUI) developed using ASP.Net. XML to represent metadata for data exchange and transfer, Darwin Core for formatting ecological and biological data management for data exchange protocol in this study. ©2006-2015 Asian Research Publishing Network (ARPN).
Temporal patterns in ecological data can be visualized and communicated effectively through graphical means. The aim of this study was to develop a data prediction and visualization system based on historical data and thematic map technology to visualize forecast temporal ecological changes. The visualization system consists of prediction and data visualization modules. The prediction module is developed using a hybrid evolutionary algorithm (HEA) to classify and predict noisy ecological data. The visualization module is developed using Dotnet Framework 2.0 to implement thematic cartography for volume visualization. The visualization system is evaluated by its capability in representing the output data on a map, and by predicting the abundance of Chlorophyta based on other water quality parameters. Rules for predicting Chlorophyta abundance had a success rate of almost 90%. The integration of computational data mining using HEA and visualization using thematic maps promises practical solutions and better techniques for forecasting temporal ecological changes, especially when data sets have complex relationships without clear distinction between various variables. © 2015 Taylor & Francis.
Freshwater algae can be used as indicators to monitor freshwater ecosystem condition. Algae react quickly and predictably to a broad range of pollutants. Thus they provide early signals of worsening environment. This study was carried out to develop a computer-based image processing technique to automatically detect, recognize, and identify algae genera from the divisions Bacillariophyta, Chlorophyta and Cyanobacteria in Putrajaya Lake. Literature shows that most automated analyses and identification of algae images were limited to only one type of algae. Automated identification system for tropical freshwater algae is even non-existent and this study is partly to fill this gap. The development of the automated freshwater algae detection system involved image preprocessing, segmentation, feature extraction and classification by using Artificial neural networks (ANN). Image preprocessing was used to improve contrast and remove noise. Image segmentation using canny edge detection algorithm was then carried out on binary image to detect the algae and its boundaries. Feature extraction process was applied to extract specific feature parameters from algae image to obtain some shape and texture features of selected algae such as shape, area, perimeter, minor and major axes, and finally Fourier spectrum with principal component analysis (PCA) was applied to extract some of algae feature texture. Artificial neural network (ANN) is used to classify algae images based on the extracted features. Feed-forward multilayer perceptron network was initialized with back propagation error algorithm, and trained with extracted database features of algae image samples. System’s accuracy rate was obtained by comparing the results between the manual and automated classifying methods. The developed system was able to identify 93 images of selected freshwater algae genera from a total of 100 tested images which yielded accuracy rate of 93%. This study demonstrated application of automated algae recognition of five genera of freshwater algae. The result indicated that MLP is sufficient, and can be used for classification of freshwater algae. However for future studies, application of support vector machine (SVM) and radial basis function (RBF) should be considered for better classifying as the number of algae species studied increases.
Computerized cephalometric information enhance clinical and research studies by making the information accessible, consistent, and statistically valid in comparative studies. Image processing technique was used widely to solve many problems in medical images. This study has developed a new system to computerize the manual process of cephalometric. The system has contained three modules to perform cephalometric analysis and measurements. The filtering module was developed to enhance the contrast of x-ray images; the locating landmark module was developed to identify the interest points in x-ray images manually; and the measurement module was developed to perform angular and linear measurements of cephalometric. The filters make x-ray image clearer that landmark points can be easily identified. The developed system has reduced the processing time for obtaining results of cephalometric measurements for more than 10 times of the manual methods. . The results showed a great accuracy between manual and automatic methods using this system. © 2008 IEEE.