Search

Named entity recognition (NER) is one of the most important tasks in natural language processing, which identifies entity boundaries and classifies them into pre-defined categories. In literature, NER systems have been developed for various languages but limited works have been conducted for Vietnamese. This mainly comes from the limitation of available and high-quality annotated data, especially for specific domains such as medicine and healthcare. In this paper, we introduce a new medical NER dataset, named ViMedNER, for recognizing Vietnamese medical entities. Unlike existing works designed for common or too-specific entities, we focus on entity types that can be used in common diagnostic and treatment scenarios, including disease names, the symptoms of the diseases, the cause of the diseases, the diagnostic, and the treatment. These entities facilitate the diagnosis and treatment of doctors for common diseases. Our dataset is collected from four well-known Vietnamese websites that are professional in terms of drag selling and disease diagnostics and annotated by domain experts with high agreement scores. To create benchmark results, strong NER baselines based on pre-trained language models including PhoBERT, XLM-R, ViDeBERTa, ViPubMedDeBERTa, and ViHealthBERT are implemented and evaluated on the dataset. Experiment results show that the performance of XLM-R is consistently better than that of the other pre-trained language models. Furthermore, additional experiments are conducted to explore the behavior of the baselines and the characteristics of our dataset.

One of the first steps in the retinal image preprocessing is cropping the Field of View (FOV) area and scaling it into a template of a predefined size. Fundus cameras of different producers record digital images of the retina of various sizes, and the FOV area containing helpful information can be from 43 to 98% of the image area. For automated analysis of retinal images and detection of DR, it is necessary to segment the FOV region and cut it out from the image. This is important to preserve microaneurysms and small capillaries in the retinal image as much as possible, since neural network methods always reduce the original images to a predefined size. In this paper, we propose a universal method for FOV segmentation based on the ideas of histograms and thresholds. We compared 11 methods for segmenting FOV regions on the four most commonly used retinal image grayscale representations. In total, we compared 35 variants of segmentation and evaluated the obtained results by four functions: Jaccard index, Matthews correlation coefficient (MCC), accuracy and balanced accuracy. All options were tested on 7000 images from nine of the largest databases. The images were generated by 100 different fundus cameras. The following observations have been extracted through extensive comparative experiments namely: 1) segmentation of the FOV area should be performed on the grayscale image obtained from the red channel; 2) for more accurate segmentation, a logarithmic transformation should be applied to the grayscale image; 3) the FOV area mask can be segmented by a global threshold calculated by Otsu’s method; 4) global thresholding based on analysis of histogram peaks does not provide advantages over binarization by Otsu’s method applied to the logarithmic transformation of the image.

This study was conducted to assess the customers’ satisfaction level with solid waste collection service in Salavane city, Salavane province, Laos. The interviewed data from 132 households have been tested and analyzed for the correlations between influencing factors and customers’ satisfaction. Through testing Cronbach's alpha coefficient and KMO and Bartlett test, as well as exploratory factor analysis, from 36 observed variables, the authors reduced to 18 significant observed variables. Multivariate regression analysis was applied to build a model to assess the level of satisfaction with solid waste collection services. The results show that “Responsiveness of workers”, “Responsiveness of facility”, and “Reliability” have a great influence on customer's satisfaction.

This paper introduces a semi-automated approach for the prioritization of software features in medium- to large-sized software projects, considering stakeholders’ satisfaction and dissatisfaction as key criteria for the incorporation of candidate features. Our research acknowledges an inherent asymmetry in stakeholders’ evaluations, between the satisfaction from offering certain features and the dissatisfaction from not offering the same features. Even with systematic, ordinal scale-based prioritization techniques, involved stakeholders may exhibit hesitation and uncertainty in their assessments. Our approach aims to address these challenges by employing the Binary Search Tree prioritization method and leveraging the mathematical framework of Intuitionistic Fuzzy Sets to quantify the uncertainty of stakeholders when expressing assessments on the value of software features. Stakeholders’ rankings, considering satisfaction and dissatisfaction as features prioritization criteria, are mapped into Intuitionistic Fuzzy Numbers, and objective weights are automatically computed. Rankings associated with less hesitation are considered more valuable to determine the final features’ priorities than those rankings with more hesitation, reflecting lower indeterminacy or lack of knowledge from stakeholders. We validate our proposed approach with a case study, illustrating its application, and conduct a comparative analysis with existing software requirements prioritization methods.

Fuzzy inference systems, in general, and complex fuzzy inference systems, in particular, play an increasingly important role in many fields, such as change detection, image classification, recognition problems, etc. Despite being the well-known technique to solve with time series data, the rulebase still has the considered limitation because of the directly affecting the results as well as the processing time of these methods. To overcome this limitation, this study proposes an Adaptive spatial complex inference system that can automatically infer and adapt to the new remotely sensed image. In the proposed model, to predict the image of time t + 1, the system will generate a new rulebase according to this expected image. This new rulebase and the previous Co-Spatial-CFIS+ rulebase are evaluated using a complex fuzzy measure. This measure is built by determining the intersection domain between two rule spaces; this intersection value estimates removing, merging, or adding a newly generated rule into the current rulebase. Finally, a more suitable set of rules is obtained for image prediction. To illustrate the efficiency of the proposed approach, it is applied to the remote sensing cloud image data of the U.S. Navy. Our model evaluated the model’s effectiveness in comparison to the state-of-the-art along studies in detecting changes in remote sensing cloud images. Moreover, the findings of the experiments revealed that the proposed model could improve the change detection results in terms of $R^{2}$ , RMSE, time-consuming, and the number of rules.

In multi-criteria decision making, attribute reduction has attracted the attention of researchers for more than two decades. So far, numerous scientists have proposed algorithms to construct reducts in decision tables. However, most of the suggested algorithms are heuristic which discovers a reduction based on criteria of the attribute set. In fact, studying the properties of reducts to build efficient attribute reduction models is an urgent problem. In this research, we present some properties of reducts in incomplete decision tables by the relational database theory approach. It was found that the properties of reducts in incomplete decision tables are equivalent to properties of the Sperner-systems in the theory of relational database. By studying the properties of the Sperner-systems, the efficient attribute reduction models can be built to improve the efficiency of multi-criteria decision making systems.

English is an indispensable language, especially in the digital age. For students who are not specialized in English vocabulary, understanding effective vocabulary learning strategies becomes crucial, helps increase their chances of being hired, and improves coherence in written and spoken communication. This study investigates the vocabulary learning strategies most and least commonly employed by ESP students. The research involved 59 participants from three majors: business administration, accounting, and tourism. Data collection was carried out through questionnaires and interviews. The findings highlight students' preference for metacognitive strategies and their positive attitude toward technology as a supportive tool for vocabulary acquisition. Additionally, cognitive and memory strategies linked to learned vocabulary were occasionally utilized. The implications of this research extend to teachers, students, and curriculum designers, providing insights for developing appropriate methods to enhance ESP vocabulary learning.

This paper proposed a novel first-order single-valued neutrosophic hesitant fuzzy time series (SVNHFTS) forecasting model. Our aim is to improve the previously proposed neutrosophic time series (NTS) model by incorporating the degree of the hesitancy using single-valued neutrosophic hesitant fuzzy set (SVNHFS) model instead of single-valued neutrosophic set (SVNS). Our paper's novelty is that we incorporate an algorithm that automatically converts the crisp dataset into the neutrosophic set that eliminates the need for experts' input or opinions in determining the membership in each of the partitioned neutrosophic set. We also incorporate Markov Chain algorithm in the de-neutrosophication process to include the weightage of the repeating neutrosophic logical relationships (NLRs). Our paper's significant contribution is to add to the existing body of knowledge related to fuzzy time series (FTS) by developing a new FTS model based on SVNHFS, one of the improved version of fuzzy sets, since this area of research is still relatively underdeveloped. To determine our proposed model's capability, we apply our proposed SVNHFTS model to three real datasets while also comparing the result to the other FTS models based on improved versions of fuzzy sets. Our datasets include benchmark enrollment data of University of Alabama, IDX Composite (Indonesian composite stock index), and MERVAL index (Argentinian composite stock index). The result shows that our proposed SVNHFTS model outperforms most of the other FTS models in terms of AFE and RMSE, especially the previously proposed NTS model.

This article proposes a new method to overcome the sparse data problem of the collaborative filtering models (CF models) by considering the homologous relationship between users or items calculated on contextual attributes when we build the CF models. In the traditional CF models, the results are built only based on data from the user's ratings for items. The results of the proposed models are calculated on two factors: (1) the similar factors based on rating values; (2) the similar factors based on contextual attributes. The findings from the experimentation on two datasets DePaulMovie and InCarMusic, show that the proposed models have higher accuracy than the traditional CF models.

Context and Background:Complex fuzzy theory has a strong practical implication in many real-world applications. Complex Fuzzy Inference System (CFIS) is a powerful technique to overcome the challenges of uncertain, periodic data. However, a question is raised for CFIS: How can we deduce and predict the result in case there is little knowledge about data information and rule base? This is significance because many real applications do not have enough knowledge of rule base for inference so that the performance of systems may be low. Thus, it is necessary to have an approximate reasoning method to represent and derive final results. Motivation: Recently, the Mamdani Complex Fuzzy Inference System (M-CFIS) has been proposed with a specific inference mechanism according to the Mamdani type. A new improvement so-called the Mamdani Complex Fuzzy Inference System with Rule Reduction (M-CFIS-R) has been designed to utilize granular computing with complex similarity measures to reduce the rule base so as to gain better performance in decision-making problems. However in M-CFIS-R, testing data are checked by matching with each rule in the rule base, which leads to a high cost of computational time. Besides, if the testing data contain records that are not inferred by the rule base, the output cannot be generated. This happens in real commerce systems in which the rule base is small at the time of creation and needs to feed with new rules. Methodology: In order to handle those issues, this article first time proposes the Fuzzy Knowledge Graph to represent the rule base in terms of linguistic labels and their relationships according to the rule set. An adjacent matrix of Fuzzy Knowledge Graph is generated for inference. When a record in the Testing dataset is given, it would be fuzzified and labelled. Each component in the record is checked with the Fuzzy Knowledge Graph by the inference mechanism in approximate reasoning called Fast Inference Search Algorithm. Then, we derive the label of the new record by the Max-Min operator. Besides, we also propose four extensions of Mamdani Complex Fuzzy Inference System Rule Reduction including Sugeno Complex Fuzzy Inference Systems, Tsukamoto Complex Fuzzy Inference Systems, Complex Fuzzy Measures and Complex Fuzzy Integrals in M-CFIS-R. Results: The experiments on the UCI Machine Learning datasets show that the proposed method classifies samples as correctly as M-CFIS-R with very lower run time (6.45 times on average). The experiments are performed through many tests via 2 main scenarios. Conclusion: The proposed system has good performance in reducing the computational time of inference with acceptable accuracy. It has ability to work with systems having limited knowledge and rule base.

This paper proposes a multi-criteria decision making method called the neutrosophic data analytic hierarchy process (NDAHP) for the single-valued neutrosophic set (SVNS). This method is an extension of the neutrosophic analytic hierarchy process (NAHP) designed to handle actual datasets which consist of crisp values. The proposed NDAHP method uses an objective weighting mechanism whereas all other existing versions of the AHP, fuzzy AHP, and other fuzzy based AHP method in literature such as the NAHP and picture fuzzy AHP uses a subjective weighting mechanism to arrive at the decision. This makes the proposed NDAHP method effective as the weightage of the criteria which forms the input of the evaluation matrix are determined in an objective manner using actual data collected for the problem, and hence will not change according to the opinions of different decision makers which are subjective. The proposed NDAHP method is applied to a multi-criteria decision making problem related to the ranking of the financial performance of five public listed petrochemical companies trading in the main board of the Kuala Lumpur Stock Exchange (KLSE). Actual dataset of 15 financial indices for the five petrochemical companies for 2017 obtained from Yahoo! Finance was used in this paper. Following this, a brief comparative study is conducted to evaluate the performance of our NDAHP algorithm against the results of other existing SVNS-based decision making methods in the literature. The results are compared against actual results obtained from KLSE. To further verify the rankings obtained through each method, the Spearman and Pearson ranking tests are carried out on each of the decision making methods that are studied. It is proved that NDAHP produces the most accurate results, and this was further verified from the results of the Spearman and Pearson ranking tests.

Assessment of code smell for predicting software change proneness is essential to ensure its significance in the area of software quality. While multiple studies have been conducted in this regard, the number of systems studied and the methods used in this paper are quite different, thus, causing confusion for understanding the best methodology. The objective of this paper is to approve the effect of code smell on the change inclination of a specific class in a product framework. This is the novelty and surplus of this work against the others. Furthermore, this paper aims to validate code smell for predicting class change proneness to find an error in the prediction of change proneness using code smell. Six typical machine learning algorithms (Naive Bayes Classifier, Multilayer Perceptron, LogitBoost, Bagging, Random Forest, and Decision Tree) have been used to predict change proneness using code smell from a set of 8200 Java classes spanning 14 software systems. The experimental results suggest that code smell is indeed a powerful predictor of class change proneness with multilayer perceptron being the most effective technique. The sensitivity and specificity values for all the models are well over 70% with a few exceptions.

Deep learning techniques have gained significant importance among artificial intelligence techniques for any computing applications. Among them, deep convolutional neural networks (DCNNs) is one of the widely used deep learning networks for any practical applications. The accuracy is generally high and the manual feature extraction process is not necessary in these networks. However, the high accuracy is achieved at the cost of huge computational complexity. The complexity in DCNN is mainly due to: 1) increased number of layers between input and output layers and 2) two set of parameters (one set of filter coefficients and another set of weights) in the fully connected network need to be adjusted. In this paper, the second aspect is targeted to reduce the computational complexity of conventional DCNN. Suitable modifications are performed in the training algorithm to reduce the number of parameter adjustments. The weight adjustment process in the fully connected layer is completely eliminated in the proposed modified approach. Instead, a simple assignment process is used to find the weights of this fully connected layer. Thus, the computational complexity is significantly reduced in the proposed approach. The application of modified DCNN is explored in the context of magnetic resonance brain tumor image classification. Abnormal brain tumor images from four different classes are used in this paper. The experimental results show promising results for the proposed approach.

A large community of research has been developed in recent years to analyze social media and social networks, with the aim of understanding, discovering insights, and exploiting the available information. The focus has shifted from conventional polarity classification to contemporary application-oriented fine-grained aspects such as, emotions, sarcasm, stance, rumor, and hate speech detection in the user-generated content. Detecting a sarcastic tone in natural language hinders the performance of sentiment analysis tasks. The majority of the studies on automatic sarcasm detection emphasize on the use of lexical, syntactic, or pragmatic features that are often unequivocally expressed through figurative literary devices such as words, emoticons, and exclamation marks. In this paper, we propose a deep learning model called sAtt-BLSTM convNet that is based on the hybrid of soft attention-based bidirectional long short-term memory (sAtt-BLSTM) and convolution neural network (convNet) applying global vectors for word representation (GLoVe) for building semantic word embeddings. In addition to the feature maps generated by the sAtt-BLSTM, punctuation-based auxiliary features are also merged into the convNet. The robustness of the proposed model is investigated using balanced (tweets from benchmark SemEval 2015 Task 11) and unbalanced (approximately 40000 random tweets using the Sarcasm Detector tool with 15000 sarcastic and 25000 non-sarcastic messages) datasets. An experimental study using the training- and test-set accuracy metrics is performed to compare the proposed deep neural model with convNet, LSTM, and bidirectional LSTM with/without attention and it is observed that the novel sAtt-BLSTM convNet model outperforms others with a superior sarcasm-classification accuracy of 97.87% for the Twitter dataset and 93.71% for the random-tweet dataset.

With the wide applications of wireless sensor networks (WSNs) in various fields, such as environment monitoring, battlefield surveillance, healthcare, and intrusion detection, trust establishment among sensor nodes becomes a vital requirement to improve security, reliability, and successful cooperation. The existing trust management approaches for large-scale WSN are failed due to their low dependability (i.e., cooperation), higher communication, and memory overheads (i.e., resource inefficient). In this paper, we propose a novel and comprehensive trust estimation approach (LTS) for large-scale WSN that employs clustering to improve cooperation, trustworthiness, and security by detecting malicious (faulty or selfish) sensor nodes with reduced resource (memory and power) consumption. The proposed scheme (LTS) operates on two levels, namely, intra-cluster and inter-cluster along with distributed approach and centralized approach, respectively, to make accurate trust decision of sensor nodes with minimum overheads. LTS consists of unique features, such as robust trust estimation function, attack resistant, and efficient trust aggregation at the cluster, head to obtain the global feedback trust value. Data trust along with communication trust plays a significant role to cope with malicious nodes. In LTS, punishment and trust severity can be tuned according to the application requirement, which makes it an innovative LTS. Moreover, dishonest recommendations (outliers) are eliminated before aggregation at the base station by observing the statistical dispersion. The theoretical and mathematical validations along with simulation results exhibit the great performance of our proposed approach in terms of trust evaluation cost, prevention, and detection of malicious nodes as well as communication overhead.

Software maintainability predicts changes or failures that may occur in software after it has been deployed. Since it deals with the degree to which an application may be understood, repaired, or enhanced, it also takes into account the overall cost of the project. In the past, several measures have been taken into account for predicting metrics that influence software maintainability. However, deep learning is yet to be explored for the same. In this paper, we perform deep learning for software maintainability metrics' prediction on a large number of datasets. Unlike the previous research works, we have relied on large datasets from 299 software and subsequently applied various metrics and functions to the same; 29 object-oriented metrics have been considered along with their impact on software maintainability of open source software. Several metrics have been analyzed and descriptive statistics of these metrics have been pointed out. The proposed long short term memory has been evaluated using measures, such as mean absolute error, root mean square error and accuracy. Five machine learning algorithms, namely, ridge regression with variable selection, decision tree, quantile regression forest, support vector machine, and principal component analysis have been applied to the original datasets, as well as, to the refined datasets. It was found that this paper provides results in the form of metrics that may be used in the prediction of software maintenance and the proposed deep learning model outperforms all of the other methods that were considered. Furthermore, the results of experiment affirm the efficiency of the proposed deep learning model for software maintainability prediction.

In recent years, the number of cell phones in society has increased drastically and they are getting popular due to their computational ability and adaptability. Resource provisioning is important, but still remains NP-hard problem in mobile computational grid (MCG). Once the jobs are assigned to the MCG, the main challenge is how to identify the correct resource according to the job's requirement and use them to execute the sub-jobs. The heuristic methods such as Min-Min, Max-Min, and HEFT can be used to select appropriate resources from the MCG that is assigned for job execution. Since the computational nodes are static and mobile in nature, the performance of such heuristics is not as expected. Such heuristics suffers from low throughput and low speedup. The process of localization is used in a wireless sensor network with good results. The proposed model uses heuristics and localization process for optimizing the quality of service parameter localization, normalized speedup, and throughput in MCG, with the concept of grid nodes available in MCG. The observation shows significant improvement in the quality of service parameter localization, normalized speedup, and throughput in MCG. The proposed model HGLA and MIN-MIN, MAX-MIN, and HEFT are compared with respect to localization, speedup, and throughput. The results reveal that the proposed model shows better performance over MIN-MIN, MAX-MIN, and HEFT.

Nowadays, society is growing and crowded, the construction of automatic smart waste sorter machine utilizing the intelligent sensors is important and necessary. To build this system, trash classification from trash images is an important issue in computer vision to be addressed for integrating into sensors. Therefore, this study proposes a robust model using deep neural networks to classify trash automatically which can be applied in smart waste sorter machines. Firstly, we collect the VN-trash dataset that consists of 5904 images belonging to three different classes including Organic, Inorganic and Medical wastes from Vietnam. Next, this study develops a deep neural network model for trash classification named DNN-TC which is an improvement of ResNext model to improve the predictive performance. Finally, the experiments are conducted to compare the performances of DNN-TC and the state-of-the-art methods for trash classification on VN-trash dataset as well as Trashnet dataset to show the effectiveness of the proposed model. The experimental results indicate that DNN-TC yields 94% and 98% in terms of accuracy for Trashnet and VN-trash datasets respectively and thus it outperforms the state-of-the-art methods for trash classification on both experimental datasets.

This paper proposes an integration of two neutrosophic based multi-criteria decision making methods, namely the neutrosophic data analytical hierarchy process (NDAHP) and the Technique of Order Preference by Similarity to Ideal Solution (TOPSIS) with maximizing deviation method, both based on the single-valued neutrosophic set (SVNS) to evaluate the efficiency of general insurance companies in Malaysia. The level of efficiency of insurance companies is a subjective and vague matter, as the efficiency can be further branched into operational efficiency, investment efficiency, underwriting efficiency, and risk management efficiency. Hence relying on entirely objective decision making methods based on crisp data might not address the problem effectively, and therefore fuzzy based decision making methods are highly appropriate to be used in this situation. Our proposed decision making algorithm uses an integrated weighting mechanism that takes into consideration both the objective and subjective weights of the data attributes. The objective weighting mechanism handles the actual datasets that were used which consists of crisp values, whereas the subjective weighing mechanism handles the opinions of the experts in the general insurance industry who were surveyed in this study. This makes the proposed method a more holistic approach to evaluate the efficiency of general insurance companies in Malaysia as previous researches in this area are generally based on the actual datasets without consideration of the opinions and evaluations of the industry experts, or vice-versa. The proposed decision making algorithm is applied on actual datasets of management expenses, net commission, net earned premium and the net investment income for 19 selected general insurance companies in Malaysia over a two-year period from 2016 to 2017. The results obtained are then discussed and the possible reasons for the results are analyzed. A comprehensive comparative study of the results obtained via our proposed method and two other commonly used methods are then presented, analyzed and discussed.

One of the most efficient tools for modeling uncertainty in decision-making problems is the neutrosophic set (NS) and its extensions, such as complex NS (CNS), interval NS (INS), and interval complex NS (ICNS). Linguistic variables have been long recognized as a useful tool in decision-making problems for solving the problem of crisp neutrosophic membership degree. In this paper, we aim to introduce new concepts: single-valued linguistic complex neutrosophic set (SVLCNS-2) and interval linguistic complex neutrosophic set (ILCNS-2) that are more applicable and adjustable to real-world implementation than those of their previous counterparts. Some set-theoretic operations and the operational rules of SVLCNS-2 and ILCNS-2 are designed. Then, gather classifications of the candidate versus criteria, gather the significance weights, gather the weighted rankings of candidates versus criteria and a score function to arrange the candidates are determined. New TOPSIS decision-making procedures in SVLCNS-2 and ICNS-2 are presented and applied to lecturer selection in the case study of the University of Economics and Business, Vietnam National University. The applications demonstrate the usefulness and efficiency of the proposal.

Multicast routing protocols normally depend upon the standard establishment of a multicast tree that needs maintenance of state information by individual nodes. In the case of dynamic networks with burst traffic, between the bursts of data, a long period of silence is expected. The multicast state preservation appends a huge amount of transmission and memory overload. This is no longer suitable for any applications. Therefore, this paper proposes a stateless high power node multicasting method utilizing a group of sink node data, which are implanted in packet headers, to facilitate recipients to fix the finest technique to send data packets in the multicast traffic. In order to eliminate expensive state information of the neighbor table, the HPN multicast protocol utilizes the awareness of the exact positions of sensor nodes. This protocol will be preferably appropriate for multicasting in active networks. The simulation results confirm that HPN multicast affords elevated success rates and little delay exclusive of the trouble of state information.

Mobile Ad-hoc Networks (MANETs) is the network of wireless mobile nodes with self-organizing, dynamic network connectivity without any pre-defined infrastructure for wireless communication. Error-less data broadcasting is the major role in MANET transmission. With the salient feature of dynamic topology and the distributed infrastructure, multipath routing is of great interests in MANETs. Multipath routing methods are dependable on adjacent nodes for finding the shortest path that several data packets are fallen to network traffic. Attention on the adjacent nodes can have the end-to-end delay while broadcasting the data packets into other nodes that finish up being fallen to congestion. It will also reduce network throughput and cause the network optimality problem. In this paper, we propose a new link-disjoint multipath routing method to solve the optimization problem in the real-time network environment. Hence, the proposed method is used to choose the shortest path from multiple paths in MANETs. Simulation results proved that the proposed method performs well in the dynamic network environment.

The world is consuming large amounts of energy in various forms like electric energy and mechanical energy. Since the electrical energy is an important factor for the development of the world, many researchers tried to generate electricity from renewable energy sources collected by sensors in order to overcome the shortage of electrical energy for household appliances and industrial areas. In this paper, we develop Internet-of-Things (IoT) based system to generate electrical energy from multiple sensors for household appliances and industrial areas. Different sensors namely piezoelectric sensor, body heat to electric converter and solar panel are utilized and connected to the power storage circuit for generation of electrical energy. Two different Artificial Intelligence (AI) models such as Artificial Neural Network (ANN), Adaptive Network based Fuzzy Inference System (ANFIS) are utilized for the total power generated from renewable energy resources. Validation is done through the statistical parameters such as Root Mean Square Error (RMSE) and R2 coefficient of correlation. Result outcome from the models shows that ANN performance is better than ANFIS.

Production of electricity from the burning of fossil fuels has caused an increase in the emission of greenhouse gases. In the long run, greenhouse gases cause harm to the environment. To reduce these gases, it is important to accurately forecast electricity production, supply and consumption. Forecasting of electricity consumption is, in particular, useful for minimizing problems of overproduction and oversupply of electricity. This research study focuses on forecasting electricity consumption based on time series data using different artificial intelligence and metaheuristic methods. The aim of the study is to determine which model among the artificial neural network (ANN), adaptive neuro-fuzzy inference system (ANFIS), least squares support vector machines (LSSVMs) and fuzzy time series (FTS) produces the highest level of accuracy in forecasting electricity consumption. The variables considered in this research include the monthly electricity consumption over the years for different countries. The monthly electricity consumption data for seven countries, namely, Norway, Switzerland, Malaysia, Egypt, Algeria, Bulgaria and Kenya, for 10 years were used in this research. The performance of all of the models was evaluated and compared using error metrics such as the root mean squared error (RMSE), average forecasting error (AFE) and performance parameter (PP). The differences in the results obtained via the different methods are analyzed and discussed, and it is shown that the different models performed better for different countries in different forecasting periods. Overall, it was found that the FTS model performed the best for most of the countries studied compared to the other three models. The research results can allow electricity management companies to have better strategic planning when deciding on the optimal levels of electricity production and supply, with the overall aim of preventing surpluses or shortages in the electricity supply.

Precipitation nowcasting is one of the main tasks of weather forecasting that aims to predict rainfall events accurately, even in low-rainfall regions. It has been observed that few studies have been devoted to predicting future radar echo images in a reasonable time using the deep learning approach. In this paper, we propose a novel approach, RainPredRNN, which is the combination of the UNet segmentation model and the PredRNN_v2 deep learning model for precipitation nowcasting with weather radar echo images. By leveraging the abilities of the contracting-expansive path of the UNet model, the number of calculated operations of the RainPredRNN model is significantly reduced. This result consequently offers the benefit of reducing the processing time of the overall model while maintaining reasonable errors in the predicted images. In order to validate the proposed model, we performed experiments on real reflectivity fields collected from the Phadin weather radar station, located at Dien Bien province in Vietnam. Some credible quality metrics, such as the mean absolute error (MAE), the structural similarity index measure (SSIM), and the critical success index (CSI), were used for analyzing the performance of the model. It has been certified that the proposed model has produced improved performance, about 0.43, 0.95, and 0.94 of MAE, SSIM, and CSI, respectively, with only 30% of training time compared to the other methods.

Nowadays, smart farming involves the integration of advanced technologies that incorporate low-cost robots to meet the required knowledge and maintain the health of plants in farming. Technologies like precision agriculture are also used to optimize resources based on the field condition. Internet of Green Things is also one of the technologies to integrate and share the information between people and healthy farm things. Internet of Green Things gives the information like soil moisture, temperature, humidity, and nutrient level by means of respective sensors. Monitoring and information gathering in green houses with the help of robots is a tedious and expensive process. In this connection, information is shared among low-cost robots encouraging data availability of the current state of a plant with other robots. This will emphasize the monitoring of green houses in a well-organized way. In this article, a Flask-based framework through Raspberry Pi is proposed for interoperability among the low-cost ESP8266 robots. Data gathering is performed by smart robots that are accessible through Message Queuing Telemetry Transport subscribes by means of Representational State Transfer Application Programming Interface. A cloud-like database server is provided to stock up the data. The integration of robotics with Internet of Green Things gains more advantage in gathering about spatial information data that are connected with the irrigation. Visualization techniques and perspectives based on Internet of Green Things for precision agriculture in the field of farming are highlighted.

Mobile ad hoc networks (MANETs) are surrounded by tons of different attacks, each with different behavior and aftermaths. One of the serious attacks that affect the normal working of MANETs is DoS attack. A sort of DoS attack is Jellyfish attack, which is quite hard because of its foraging behavior. The Jellyfish attack is regarded as one of the most difficult attack to detect and degrades the overall network performance. In order to combat Jellyfish attack in MANETs, this paper proposes a novel technique called accurate prevention and detection of jelly fish attack detection (APD-JFAD). It is a fusion of authenticated routing-based framework for detecting attacks and support vector machine (SVM). SVM is utilized for learning packet forwarding behavior. The proposed technique chooses trusted nodes in the network for performing routing of packets on the basis of hierarchical trust evaluation property of nodes. The technique is tested using NS-2 simulator against other existing techniques, i.e., ABC, MABC, and AR-AIDF-GFRS algorithms by various parameters such as throughput, PDR, dropped packet ratio, and delay. The results prove that APD-JFAD is highly efficient in Jellyfish attack detection and also performs well as compared to other algorithms.

Flood is one of the deadliest natural hazards worldwide, with the population affected being more than 2 billion between 1998–2017 with a lack of warning systems according to WHO. Especially, flash floods have the potential to generate fatal damages due to their rapid evolution and the limited warning and response time. An effective Early Warning Systems (EWS) could support detection and recognition of flash floods. Information about a flash flood can be mainly provided from observations of hydrology and from satellite images taken before the flash flood happens. Then, predictions from satellite images can be integrated with predictions based on sensors’ information to improve the accuracy of a forecasting system and subsequently trigger warning systems. The existing Deep Learning models such as UNET has been effectively used to segment the flash flood with high performance, but there are no ways to determine the most suitable model architecture with the proper number of layers showing the best performance in the task. In this paper, we propose a novel Deep Learning architecture, namely PSO-UNET, which combines Particle Swarm Optimization (PSO) with UNET to seek the best number of layers and the parameters of layers in the UNET based architecture; thereby improving the performance of flash flood segmentation from satellite images. Since the original UNET has a symmetrical architecture, the evolutionary computation is performed by paying attention to the contracting path and the expanding path is synchronized with the following layers in the contracting path. The UNET convolutional process is performed four times. Indeed, we consider each process as a block of the convolution having two convolutional layers in the original architecture. Training of inputs and hyper-parameters is performed by executing the PSO algorithm. In practice, the value of Dice Coefficient of our proposed model exceeds 79.75% (8.59% higher than that of the original UNET model). Experimental results on various satellite images prove the advantages and superiority of the PSO-UNET approach.

Neutrosophic set is a generalization of classical set, fuzzy set, and intuitionistic fuzzy set by employing a degree of truth (T), a degree of indeterminacy (I), and a degree of falsehood (F) associated with an element of the dataset. One of the most essential problems is studying set-theoretic operators in order to be applied to practical applications. Developing Matlab toolboxes for computing the operational matrices in neutrosophic environments is essential to gain more widely-used of neutrosophic algorithms. In this paper, we propose some computing procedures in Matlab for neutrosophic operational matrices, especially i) computing the single-valued neutrosophic matrix; ii) determining complement of a single-valued neutrosophic matrix; iii) computing max-min-min and min-max-max of two single-valued neutrosophic matrices; v) computing power of a single-valued neutrosophic matrix; vi) computing additional operation and subtraction of two single-valued neutrosophic matrices; and ix) computing transpose of a single-valued neutrosophic matrix. Numerical examples are given to illustrate their applicability.

Abstract Background MicroRNAs (miRNAs) have been shown to play an important role in pathological initiation, progression and maintenance. Because identification in the laboratory of disease-related miRNAs is not straightforward, numerous network-based methods have been developed to predict novel miRNAs in silico. Homogeneous networks (in which every node is a miRNA) based on the targets shared between miRNAs have been widely used to predict their role in disease phenotypes. Although such homogeneous networks can predict potential disease-associated miRNAs, they do not consider the roles of the target genes of the miRNAs. Here, we introduce a novel method based on a heterogeneous network that not only considers miRNAs but also the corresponding target genes in the network model. Results Instead of constructing homogeneous miRNA networks, we built heterogeneous miRNA networks consisting of both miRNAs and their target genes, using databases of known miRNA-target gene interactions. In addition, as recent studies demonstrated reciprocal regulatory relations between miRNAs and their target genes, we considered these heterogeneous miRNA networks to be undirected, assuming mutual miRNA-target interactions. Next, we introduced a novel method (RWRMTN) operating on these mutual heterogeneous miRNA networks to rank candidate disease-related miRNAs using a random walk with restart (RWR) based algorithm. Using both known disease-associated miRNAs and their target genes as seed nodes, the method can identify additional miRNAs involved in the disease phenotype. Experiments indicated that RWRMTN outperformed two existing state-of-the-art methods: RWRMDA, a network-based method that also uses a RWR on homogeneous (rather than heterogeneous) miRNA networks, and RLSMDA, a machine learning-based method. Interestingly, we could relate this performance gain to the emergence of “disease modules” in the heterogeneous miRNA networks used as input for the algorithm. Moreover, we could demonstrate that RWRMTN is stable, performing well when using both experimentally validated and predicted miRNA-target gene interaction data for network construction. Finally, using RWRMTN, we identified 76 novel miRNAs associated with 23 disease phenotypes which were present in a recent database of known disease-miRNA associations. Conclusions Summarizing, using random walks on mutual miRNA-target networks improves the prediction of novel disease-associated miRNAs because of the existence of “disease modules” in these networks.

One of the crucial problems in Industry 4.0 is how to strengthen the performance of mobile communication within mobile ad-hoc networks (MANETs) and mobile computational grids (MCGs). In communication, Industry 4.0 needs dynamic network connectivity with higher amounts of speed and bandwidth. In order to support multiple users for video calling or conferencing with high-speed transmission rates and low packet loss, 4G technology was introduced by the 3G Partnership Program (3GPP). 4G LTE is a type of 4G technology in which LTE stands for Long Term Evolution, followed to achieve 4G speeds. 4G LTE supports multiple users for downlink with higher-order modulation up to 64 quadrature amplitude modulation (QAM). With wide coverage, high reliability and large capacity, LTE networks are widely used in Industry 4.0. However, there are many kinds of equipment with different quality of service (QoS) requirements. In the existing LTE scheduling methods, the scheduler in frequency domain packet scheduling exploits the spatial, frequency, and multi-user diversity to achieve larger MIMO for the required QoS level. On the contrary, time-frequency LTE scheduling pays attention to temporal and utility fairness. It is desirable to have a new solution that combines both the time and frequency domains for real-time applications with fairness among users. In this paper, we propose a channel-aware Integrated Time and Frequency-based Downlink LTE Scheduling (ITFDS) algorithm, which is suitable for both real-time and non-real-time applications. Firstly, it calculates the channel capacity and quality using the channel quality indicator (CQI). Additionally, data broadcasting is maintained by using the dynamic class-based establishment (DCE). In the time domain, we calculate the queue length before transmitting the next packets. In the frequency domain, we use the largest weight delay first (LWDF) scheduling algorithm to allocate resources to all users. All the allocations would be taken placed in the same transmission time interval (TTI). The new method is compared against the largest weighted delay first (LWDF), proportional fair (PF), maximum throughput (MT), and exponential/proportional fair (EXP/PF) methods. Experimental results show that the performance improves by around 12% compared with those other algorithms.

Corona viruses are a large family of viruses that are not only restricted to causing illness in humans but also affect animals such as camels, cattle, cats, and bats, thus affecting a large group of living species. The outbreak of Corona virus in late December 2019 (also known as COVID-19) raised major concerns when the outbreak started getting tremendous. While the first case was discovered in Wuhan, China, it did not take long for the disease to travel across the globe and infect every continent (except Antarctica), killing thousands of people. Since it has become a global concern, different countries have been working toward the treatment and generation of vaccine, leading to different speculations. While some argue that the vaccine may only be a few weeks away, others believe that it may take some time to create the vaccine. Given the increasing number of deaths, the COVID-19 has caused havoc worldwide and is a matter of serious concern. Thus, there is a need to study how the disease has been propagating across continents by numbers as well as by regions. This study incorporates a detailed description of how the COVID-19 outbreak started in China and managed to spread across the globe rapidly. We take into account the COVID-19 outbreak cases (confirmed, recovered, death) in order to make some observations regarding the pandemic. Given the detailed description of the outbreak, this study would be beneficial to certain industries that may be affected by the outbreak in order to take timely precautionary measures in the future. Further, the study lists some industries that have witnessed the impact of the COVID-19 outbreak on a global scale.

Complex fuzzy theory has strong practical background in many important applications, especially in decision-making support systems. Recently, the Mamdani Complex Fuzzy Inference System (M-CFIS) has been introduced as an effective tool for handling events that are not restricted to only values of a given time point but also include all values within certain time intervals (i.e., the phase term). In such decision-making problems, the complex fuzzy theory allows us to observe both the amplitude and phase values of an event, thus resulting in better performance. However, one of the limitations of the existing M-CFIS is the rule base that may be redundant to a specific dataset. In order to handle the problem, we propose a new Mamdani Complex Fuzzy Inference System with Rule Reduction Using Complex Fuzzy Measures in Granular Computing called M-CFIS-R. Several fuzzy similarity measures such as Complex Fuzzy Cosine Similarity Measure (CFCSM), Complex Fuzzy Dice Similarity Measure (CFDSM), and Complex Fuzzy Jaccard Similarity Measure (CFJSM) together with their weighted versions are proposed. Those measures are integrated into the M-CFIS-R system by the idea of granular computing such that only important and dominant rules are being kept in the system. The difference and advantage of M-CFIS-R against M-CFIS is the usage of the training process in which the rule base is repeatedly changed toward the original base set until the performance is better. By doing so, the new rule base in M-CFIS-R would improve the performance of the whole system. Experiments on various decision-making datasets demonstrate that the proposed M-CFIS-R performs better than M-CFIS.

Dynamic multi-criteria decision-making (DMCDM) models have many meaningful applications in real life in which solving indeterminacy of information in DMCDMs strengthens the potential application of DMCDM. This study introduces an extension of dynamic internal-valued neutrosophic sets namely generalized dynamic internal-valued neutrosophic sets. Based on this extension, we develop some operators and a TOPSIS method to deal with the change of both criteria, alternatives, and decision-makers by time. In addition, this study also applies the proposal model to a real application that facilitates ranking students according to attitude-skill-knowledge evaluation model. This application not only illustrates the correctness of the proposed model but also introduces its high potential appliance in the education domain.

In dental diagnosis, recognizing tooth complications quickly from radiology (e.g., X-rays) takes highly experienced medical professionals. By using object detection models and algorithms, this work is much easier and needs less experienced medical practitioners to clear their doubts while diagnosing a medical case. In this paper, we propose a dental defect recognition model by the integration of Adaptive Convolution Neural Network and Bag of Visual Word (BoVW). In this model, BoVW is used to save the features extracted from images. After that, a designed Convolutional Neural Network (CNN) model is used to make quality prediction. To evaluate the proposed model, we collected a dataset of radiography images of 447 patients in Hanoi Medical Hospital, Vietnam, with third molar complications. The results of the model suggest accuracy of 84% ± 4%. This accuracy is comparable to that of experienced dentists and radiologists.

Decision-making activities are prevalent in human life. Many methods have been developed to address real-world decision problems. In some practical situations, decision-makers prefer to provide their evaluations over a set of criteria and weights. However, in many real-world situations, problems include a lack of weight information for the times, criteria, and decision-makers (DMs). To remedy such discrepancies, an optimization model has been proposed to determine the weights of attributes, times, and DMs. A new concept related to the correlation measure and some distance measures for the dynamic interval-valued neutrosophic set (DIVNS) are defined in this paper. An extend Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) method in the interval-valued neutrosophic set with unknown weight information in dynamic neutrosophic environments is developed. Finally, a practical example is discussed to illustrate the feasibility and effectiveness of the proposed method.

Professional selection is a significant task for any organization that aims to select the most appropriate candidates to fill well-defined vacancies up. In the recruitment process, various individual characteristics are involved, such as leadership, analytical skills, independent thinking, innovation, stamina and personality, ambiguity and imprecision. It outlines staff contribution and therefore plays a significant part in human resources administration. Additionally, in the era of the Internet of Things and Big Data (IoTBD), professional selection would face several challenges not only to the safe selection and security but also to make wise and prompt decisions especially in the large-scale candidates and criteria from the Cloud. However, the process of professional selection is often led by experience, which contains vague, ambiguous and uncertain decisions. It is therefore necessary to design an efficient decision-making algorithm, which could be further escalated to IoTBD. In this paper, we propose a new hybrid neutrosophic multi criteria decision making (MCDM) framework that employs a collection of neutrosophic analytical network process (ANP), and order preference by similarity to ideal solution (TOPSIS) under bipolar neutrosophic numbers. The MCDM framework is applied for chief executive officer (CEO) selection in a case study at the Elsewedy Electric Group, Egypt. The proposed approach allows us to assemble individual evaluations of the decision makers and therefore perform accurate personnel selection. The outcomes of the proposed method are compared with those of the related works such as weight sum model (WSM), weight product model (WPM), analytical hierarchy process (AHP), multi-objective optimization based on simple ratio analysis (MOORA) and ANP methods to prove and validate the results.

This paper proposed and verified a new integrated approach based on the iterative super-resolution algorithm and expectation-maximization for face hallucination, which is a process of converting a low-resolution face image to a high-resolution image. The current sparse representation for super resolving generic image patches is not suitable for global face images due to its lower accuracy and time-consumption. To solve this, in the new method, training global face sparse representation was used to reconstruct images with misalignment variations after the local geometric co-occurrence matrix. In the testing phase, we proposed a hybrid method, which is a combination of the sparse global representation and the local linear regression using the Expectation Maximization (EM) algorithm. Therefore, this work recovered the high-resolution image of a corresponding low-resolution image. Experimental validation suggested improvement of the overall accuracy of the proposed method with fast identification of high-resolution face images without misalignment.

The International Roughness Index (IRI) is the one of the most important roughness indexes to quantify road surface roughness. In this paper, we propose a new hybrid approach between adaptive network based fuzzy inference system (ANFIS) and various meta-heuristic optimizations such as the genetic algorithm (GA), particle swarm optimization (PSO), and the firefly algorithm (FA) to develop several hybrid models namely GA based ANGIS (GANFIS), PSO based ANFIS (PSOANFIS), FA based ANFIS (FAANFIS), respectively, for the prediction of the IRI. A benchmark model named artificial neural networks (ANN) was also used to compare with those hybrid models. To do this, a total of 2811 samples in the case study of the north of Vietnam (Northwest region, Northeast region, and the Red River Delta Area) within the scope of management of the DRM-I Department were used to validate the models in terms of various criteria like coefficient of determination (R) and the root mean square error (RMSE). Experimental results affirmed the potentiality and effectiveness of the proposed prediction models whereas the PSOANFIS (RMSE = 0.145 and R = 0.888) is better than the other models named GANFIS (RMSE = 0.155 and R = 0.872), FAANFIS (RMSE = 0.170 and R = 0.849), and ANN (RMSE = 0.186 and R = 0.804). The results of this study are helpful for accurate prediction of the IRI for evaluation of quality of road surface roughness.

The framework of the T-spherical fuzzy set is a recent development in fuzzy set theory that can describe imprecise events using four types of membership grades with no restrictions. The purpose of this manuscript is to point out the limitations of the existing intuitionistic fuzzy Einstein averaging and geometric operators and to develop some improved Einstein aggregation operators. To do so, first some new operational laws were developed for T-spherical fuzzy sets and their properties were investigated. Based on these new operations, two types of Einstein aggregation operators are proposed namely the Einstein interactive averaging aggregation operators and the Einstein interactive geometric aggregation operators. The properties of the newly developed aggregation operators were then investigated and verified. The T-spherical fuzzy aggregation operators were then applied to a multi-attribute decision making (MADM) problem related to the degree of pollution of five major cities in China. Actual datasets sourced from the UCI Machine Learning Repository were used for this purpose. A detailed study was done to determine the most and least polluted city for different perceptions for different situations. Several compliance tests were then outlined to test and verify the accuracy of the results obtained via our proposed decision-making algorithm. It was proved that the results obtained via our proposed decision-making algorithm was fully compliant with all the tests that were outlined, thereby confirming the accuracy of the results obtained via our proposed method.

This paper presents a system dedicated to monitoring the heart activity parameters using Electrocardiography (ECG) mobile devices and a Wearable Heart Monitoring Inductive Sensor (WHMIS) that represents a new method and device, developed by us as an experimental model, used to assess the mechanical activity of the hearth using inductive sensors that are inserted in the fabric of the clothes. Only one inductive sensor is incorporated in the clothes in front of the apex area and it is able to assess the cardiorespiratory activity while in the prior of the art are presented methods that predict sensors arrays which are distributed in more places of the body. The parameters that are assessed are heart data-rate and respiration. The results are considered preliminary in order to prove the feasibility of this method. The main goal of the study is to extract the respiration and the data-rate parameters from the same output signal generated by the inductance-to-number convertor using a proper algorithm. The conceived device is meant to be part of the “wear and forget” equipment dedicated to monitoring the vital signs continuously.

The evolution of multipurpose sensors over the last decades has been investigated with the aim of developing innovative devices with applications in several fields of technology, including in the food industry. The integration of such sensors in food packaging technology has paved the way for intelligent food packaging. These integrated systems are capable of providing reliable information about the quality of the packed products during their storage period. To accomplish this goal, intelligent packs use a variety of sensors suited for monitoring the quality and safety of food products by recording the evolution of parameters like the quantity of pathogen agents, gases, temperature, humidity and storage period. This technology, when combined with IoT, is able to provide a lot more information than conventional food inspection technologies, which are limited to weight, volume, color and aspect inspection. The original system described in this work relies on a simple but effective method of integrated food monitoring, right at the client home, suitable for user prepared vacuum-packed foods. It builds upon the IoT concept and is able to create a network of interconnected devices. By using this approach, we are able to combine actuators and sensing devices also providing a common operating picture (COP) by sharing information over the platforms. More precisely, our system consists of gas, temperature and humidity sensors, which provide the essential information needed for evaluating the quality of the packed product. This information is transmitted wirelessly to a computer system providing an interface where the user can observe the evolution of the product quality over time.

Software defect prediction has been one of the key areas of exploration in the domain of software quality. In this paper, we perform a systematic mapping to analyze all the software defect prediction literature available from 1995 to 2018 using a multi-stage process. A total of 156 studies are selected in the first step, and the final mapping is conducted based on these studies. The ability of a model to learn from data that does not come from the same project or organization will help organizations that do not have sufficient training data or are going to start work on new projects. The findings of this research are useful not only to the software engineering domain, but also to the empirical studies, which mainly focus on symmetry as they provide steps-by-steps solutions for questions raised in the article.

Recently, prediction modelling has become important in data analysis. In this paper, we propose a novel algorithm to analyze the past dataset of crop yields and predict future yields using regression-based approximation of time series fuzzy data. A framework-based algorithm, which we named DAbFP (data algorithm for degree approximation-based fuzzy partitioning), is proposed to forecast wheat yield production with fuzzy time series data. Specifically, time series data were fuzzified by the simple maximum-based generalized mean function. Different cases for prediction values were evaluated based on two-set interval-based partitioning to get accurate results. The novelty of the method lies in its ability to approximate a fuzzy relation for forecasting that provides lesser complexity and higher accuracy in linear, cubic, and quadratic order than the existing methods. A lesser complexity as compared to dynamic data approximation makes it easier to find the suitable de-fuzzification process and obtain accurate predicted values. The proposed algorithm is compared with the latest existing frameworks in terms of mean square error (MSE) and average forecasting error rate (AFER).

In this paper, we design and develop a new class of linear algebraic codes defined as soft linear algebraic codes using soft sets. The advantage of using these codes is that they have the ability to transmit m-distinct messages to m-set of receivers simultaneously. The methods of generating and decoding these new classes of soft linear algebraic codes have been developed. The notion of soft canonical generator matrix, soft canonical parity check matrix, and soft syndrome are defined to aid in construction and decoding of these codes. Error detection and correction of these codes are developed and illustrated by an example.

The vague graph has found its importance as a closer approximation to real life situations. A review of the literature in this area reveals that the edge coloring problem for vague graphs has not been studied until now. Therefore, in this paper, we analyse the concept of vertex and edge coloring on simple vague graphs. Specifically, two new definitions for vague graphs related to the concept of the λ-strong-adjacent and ζ-strong-incident of vague graphs are introduced. We consider the color classes to analyze the coloring on the vertices in vague graphs. The proposed method illustrates the concept of coloring on vague graphs, using the definition of color class, which depends only on the truth membership function. Applications of the proposal in solving practical problems related to traffic flow management and the selection of advertisement spots are mainly discussed.

The Neutrosophic set (NS) has grasped concentration by its ability for handling indeterminate, uncertain, incomplete, and inconsistent information encountered in daily life. Recently, there have been various extensions of the NS, such as single valued neutrosophic sets (SVNSs), Interval neutrosophic sets (INSs), bipolar neutrosophic sets (BNSs), Refined Neutrosophic Sets (RNSs), and triangular fuzzy number neutrosophic set (TFNNs). This paper contains an extended overview of the concept of NS as well as several instances and extensions of this model that have been introduced in the last decade, and have had a significant impact in literature. Theoretical and mathematical properties of NS and their counterparts are discussed in this paper as well. Neutrosophic-set-driven decision making algorithms are also overviewed in detail.

Bankruptcy prediction has been a popular and challenging research topic in both computer science and economics due to its importance to financial institutions, fund managers, lenders, governments, as well as economic stakeholders in recent years. In a bankruptcy dataset, the problem of class imbalance, in which the number of bankruptcy companies is smaller than the number of normal companies, leads to a standard classification algorithm that does not work well. Therefore, this study proposes a cluster-based boosting algorithm as well as a robust framework using the CBoost algorithm and Instance Hardness Threshold (RFCI) for effective bankruptcy prediction of a financial dataset. This framework first resamples the imbalance dataset by the undersampling method using Instance Hardness Threshold (IHT), which is used to remove the noise instances having large IHT value in the majority class. Then, this study proposes a Cluster-based Boosting algorithm, namely CBoost, for dealing with the class imbalance. In this algorithm, the majority class will be clustered into a number of clusters. The distance from each sample to its closest centroid will be used to initialize its weight. This algorithm will perform several iterations for finding weak classifiers and combining them to create a strong classifier. The resample set resulting from the previous module, will be used to train CBoost, which will be used to predict bankruptcy for the validation set. The proposed framework is verified by the Korean bankruptcy dataset (KBD), which has a very small balancing ratio in both the training and the testing phases. The experimental results of this research show that the proposed framework achieves 86.8% in AUC (area under the ROC curve) and outperforms several methods for dealing with the imbalanced data problem for bankruptcy prediction such as GMBoost algorithm, the oversampling-based method using SMOTEENN, and the clustering-based undersampling method for bankruptcy prediction in the experimental dataset.