Search

In IoT environment applications generate continuous non-stationary data streams with in-built problems of concept drift and class imbalance which cause classifier performance degradation. The imbalanced data affects the classifier during concept detection and concept adaptation. In general, for concept detection, a separate mechanism is added in parallel with the classifier to detect the concept drift called a drift detector. For concept adaptation, the classifier updates itself or trains a new classifier to replace the older one. In case, the data stream faces a class imbalance issue, the classifier may not properly adapt to the latest concept. In this survey, we study how the existing work addresses the issues of class imbalance and concept drift while learning from nonstationary data streams. We further highlight the limitation of existing work and challenges caused by other factors of class imbalance along with concept drift in data stream classification. Results of our survey found that, out of 1110 studies, by using our inclusion and exclusion criteria, we were able to narrow the pool of articles down to 35 that directly addressed our study objectives. The study found that issues such as multiple concept drift types, dynamic class imbalance ratio, and multi-class imbalance in presence of concept drift are still open for further research. We also observed that, while major research efforts have been dedicated to resolving concept drift and class imbalance, not much attention has been given to with-in-class imbalance, rear examples, and borderline instances when they exist with concept drift in multi-class data. This paper concludes with some suggested future directions. [ABSTRACT FROM AUTHOR]

Prediction of machine failure is challenging as the dataset is often imbalanced with a low failure rate. The common approach to handle classification involving imbalanced data is to balance the data using a sampling approach such as random undersampling, random oversampling, or Synthetic Minority Oversampling Technique (SMOTE) algorithms. This paper compared the classification performance of three popular classifiers (Logistic Regression, Gaussian Naïve Bayes, and Support Vector Machine) in predicting machine failure in the Oil and Gas industry. The original machine failure dataset consists of 20,473 hourly data and is imbalanced with 19945 (97%) ‘non-failure’ and 528 (3%) ‘failure data’. The three independent variables to predict machine failure were pressure indicator, flow indicator, and level indicator. The accuracy of the classifiers is very high and close to 100%, but the sensitivity of all classifiers using the original dataset was close to zero. The performance of the three classifiers was then evaluated for data with different imbalance rates (10% to 50%) generated from the original data using SMOTE, SMOTE-Support Vector Machine (SMOTE-SVM) and SMOTEEdited Nearest Neighbour (SMOTE-ENN). The classifiers were evaluated based on improvement in sensitivity and F-measure. Results showed that the sensitivity of all classifiers increases as the imbalance rate increases. SVM with radial basis function (RBF) kernel has the highest sensitivity when data is balanced (50:50) using SMOTE (Sensitivitytest = 0.5686, Ftest = 0.6927) compared to Naïve Bayes (Sensitivitytest = 0.4033, Ftest = 0.6218) and Logistic Regression (Sensitivitytest = 0.4194, Ftest = 0.621). Overall, the Gaussian Naïve Bayes model consistently improves sensitivity and F-measure as the imbalance ratio increases, but the sensitivity is below 50%. The classifiers performed better when data was balanced using SMOTE-SVM compared to SMOTE and SMOTE-ENN. [ABSTRACT FROM AUTHOR]

Featured Application: The industrial sensor-based application generates continuous non-stationary data streams which change over time. By analyzing the performance of existing change detection methods, the selection of the best performing method can be achieved for application in an industrial environment to early detect the fault or unusual change and to reduce the maintenance cost. The performance of machine learning models diminishes while predicting the Remaining Useful Life (RUL) of the equipment or fault prediction due to the issue of concept drift. This issue is aggravated when the problem setting comprises multi-class imbalanced data. The existing drift detection methods are designed to detect certain drifts in specific scenarios. For example, the drift detector designed for binary class data may not produce satisfactory results for applications that generate multi-class data. Similarly, the drift detection method designed for the detection of sudden drift may struggle with detecting incremental drift. Therefore, in this experimental investigation, we seek to investigate the performance of the existing drift detection methods on multi-class imbalanced data streams with different drift types. For this reason, this study simulated the streams with various forms of concept drift and the multi-class imbalance problem to test the existing drift detection methods. The findings of current study will aid in the selection of drift detection methods for use in developing solutions for real-time industrial applications that encounter similar issues. The results revealed that among the compared methods, DDM produced the best average F1 score. The results also indicate that the multi-class imbalance causes the false alarm rate to increase for most of the drift detection methods. [ABSTRACT FROM AUTHOR]

The Vehicle Routing Problem (VRP) and its variants are found in many fields, especially logistics. In this study, we introduced an adaptive method to a complex VRP. It combines multi-objective optimization and several forms of VRPs with practical requirements for an urban shipment system. The optimizer needs to consider terrain and traffic conditions. The proposed model also considers customers' expectations and shipper considerations as goals, and a common goal such as transportation cost. We offered compromise programming to approach the multi-objective problem by decomposing the original multi-objective problem into a minimized distance-based problem. We designed a hybrid version of the genetic algorithm with the local search algorithm to solve the proposed problem. We evaluated the effectiveness of the proposed algorithm with the Tabu Search algorithm and the original genetic algorithm on the tested dataset. The results show that our method is an effective decision-making tool for the multi-objective VRP and an effective solver for the new variation of VRP. [ABSTRACT FROM AUTHOR]

The scheduling process that aims to assign tasks tomembers is a difficult job in project management. It plays a prerequisite role in determining the project's quality and sometimes winning the bidding process. This study aims to propose an approach based on multi-objective combinatorial optimization to do this automatically. The generated schedule directs the project to be completed with the shortest critical path, at the minimum cost, while maintaining its quality. There are several real-world business constraints related to human resources, the similarity of the tasks added to the optimizationmodel, and the literature's traditional rules. To support the decision-maker to evaluate different decision strategies, we use compromise programming to transform multiobjective optimization (MOP) into a single-objective problem. We designed a genetic algorithm scheme to solve the transformed problem. The proposed method allows the incorporation of the model as a navigator for search agents in the optimal solution search process by transferring the objective function to the agents' fitness function. The optimizer can effectively find compromise solutions even if the user may or may not assign a priority to particular objectives. These are achieved through a combination of nonpreference and preference approaches. The experimental results show that the proposed method worked well on the tested dataset. [ABSTRACT FROM AUTHOR]

Examination timetabling is one of 3 critical timetabling jobs besides enrollment timetabling and teaching assignment. After a semester, scheduling examinations is not always an easy job in education management, especially for many data. The timetabling problem is an optimization and Np-hard problem. In this study, we build a multi-objective optimizer to create exam schedules for more than 2500 students. Our model aims to optimize the material costs while ensuring the dignity of the exam and students' convenience while considering the design of the rooms, the time requirement of each exam, which involves rules and policy constraints. We propose a programmatic compromise to approach the maximum target optimization model and solve it using the Genetic Algorithm. The results show the effective of the introduced algorithm. [ABSTRACT FROM AUTHOR]

Skin cancers are increasing at an alarming rate, and detection in the early stages is essential for advanced treatment. The current segmentation methods have limited labeling ability to the ground truth images due to the numerous noisy expert annotations present in the datasets. The precise boundary segmentation is essential to correctly locate and diagnose the various skin lesions. In this work, the lesion segmentation method is proposed as a Markov decision process. It is solved by training an agent to segment the region using a deep reinforcement-learning algorithm. Our method is similar to the delineation of a region of interest by the physicians. The agent follows a set of serial actions for the region delineation, and the action space is defined as a set of continuous action parameters. The segmentation model learns in continuous action space using the deep deterministic policy gradient algorithm. The proposed method enables continuous improvement in performance as we proceed from coarse segmentation results to finer results. Finally, our proposed model is evaluated on the International Skin Imaging Collaboration (ISIC) 2017 image dataset, Human against Machine (HAM10000), and PH2 dataset. On the ISIC 2017 dataset, the algorithm achieves an accuracy of 96.33% for the naevus cases, 95.39% for the melanoma cases, and 94.27% for the seborrheic keratosis cases. The other metrics are evaluated on these datasets and rank higher when compared with the current state-of-the-art lesion segmentation algorithms. [ABSTRACT FROM AUTHOR]

Sensor network-based home automation systems are familiar over the recent decades. Incorporating the benefits of the sensor network, energy management systems (EMS), is introduced to benefit end-user through periodic information sharing and remote access. WSN opted for energy harvesters to reduce the maintenance costs and maximize the lifetime of network. It is a perfect match for wireless devices and WSNs. Energy management system designed for effective use of harvested energy. Wireless sensor networks (WSN) coupled with EMS and grid-based applications serve as a support for smart home appliances. The integrated system architectures are cost effective and are energy harvesting that is profitable for end-user applications. Identifying optimal devices and defining an energy management policy are a tedious task as the devices are interfaced through different application support. This manuscript proposes a reward-based energy harvesting (REH) approach for identifying reliable devices in order to frame minimal-allocation energy for its operation. The rewards for the devices are estimated through observations carried out using reinforced learning that determines the operation state of the device. The reward function is computed using a variant function evaluated using the enduring energy and storage metrics of a device. Unlike the other learning methods, this approach operates in variable communication interval retaining the reward from the previous history of the devices. With a distributed WSN support and recursive knowledge of the sensor devices, REH is intended to improve the energy conservation rate with lesser retransmissions. The curtailed number of retransmissions minimizes delay with more preferable ideal devices in a home management system. The performance of the proposed REH is evaluated through simulations considering the following metrics: end-to-end delay, energy utilization, packets forwarded, expected TTL and number of retransmissions. [ABSTRACT FROM AUTHOR]

Various factors should be considered in the modeling of DWC of repairable systems or products, including system structure, component failure processes, discounting methods, and the warranty policy itself. This paper presents discounted warranty cost (DWC) models for repairable series systems subject to Gamma and Mixed Exponential Failure Laws. In particular, a policy on a free repair warranty and a policy on a pro-rata guarantee are being studied. The impact of repair actions on the failure times of the components is assumed to be minimal, hence NHPPs is used to describe the failure processes. This paper considers two types of discounting methods: a continuous discount function and a discrete discount function. Expressions for both the expected value and the variance of DWC are obtained for Gamma and Mixed Exponential Failure Laws. The WRD was calculated for Gamma Failure Laws under application section. Further extension of this research is provided in the conclusion section. [ABSTRACT FROM AUTHOR]

An optimized design of a fuzzy logic system can be regarded as setting of different parameters of the system automatically. For a single parameter, there may exist multiple feasible values. Consequently, with the increase in number of parameters, the complexity of a system increases. Type 2 fuzzy logic system has more parameters than the type 1 fuzzy logic system and is therefore much more complex than its counterpart. This paper proposes optimal parameters for an extreme learning machine-based interval type 2 fuzzy logic system to learn its best configuration. Extreme learning machine (ELM) is utilized to tune the consequent parameters of the interval type 2 fuzzy logic system (IT2FLS). A disadvantage of ELM is the random generation of its hidden neuron that causes additional uncertainty, in both approximation and learning. In order to overcome this limitation in an ELM-based IT2FLS, artificial bee colony optimization algorithm is utilized to obtain its antecedent parts parameters. The simulation results verified better performance of the proposed IT2FLS over other models with the benchmark data sets. [ABSTRACT FROM AUTHOR]

Abstract: Ineffective software team composition has become recognized as a prominent aspect of software project failures. Reports from results extracted from different theoretical personality models have produced contradicting fits, validity challenges, and missing guidance during software development personnel selection. It is also believed that the technique/s used while developing a model can impact the overall results. Thus, this study aims to (1) discover an effective classification technique to solve the problem and (2) develop a model for composition of the software development team. The model developed was composed of 3 predictors: team role, personality types, and gender variables; it also contained 1 outcome: team performance variable. The techniques used for model development were logistic regression, decision tree, and rough sets theory (RST). Higher prediction accuracy and reduced pattern complexity were the 2 parameters for selecting the effective technique. Based on the results, the Johnson algorithm (JA) of RST appeared to be an effective technique for a team composition model. The study has proposed a set of 24 decision rules for finding effective team members. These rules involve gender classification to highlight the appropriate personality profile for software developers. In the end, this study concludes that selecting an appropriate classification technique is one of the most important factors in developing effective models. [ABSTRACT FROM AUTHOR]

The fast growing demand of software has caused numerous challenges for software developers to produces quality software within deadlines. The main purpose of this research article was to find the suitable personality type combinations of programmer with team-leaders and programmers by gender classification in software development teams. Myers-Briggs Type Indicator (MBTI) was applied to measure the personality types of the study participants. In order to find the possible combination of personality types between team-leader and programmer, this study applied Genetic Algorithm (GA) and Johnson's Algorithm (JA) on data. Results emanated from training experiments were validated with Standard Voting (SV), Voting with Object tracking, and Naïve Bayes classification techniques based on prediction accuracy. Basically, two types of decision rules were formed: rules without gender classification of programmer but they only discussed the personality types of team-leader and programmer. Whereas, the second type of rules were composed of team-leader, programmer personality types, and gender of programmer. It was found that extrovert (E) trait programmers can be suitable with E trait team-leaders. In the same way, male programmer can work in a good way with male leaders or other way around for females. At the end, there were only certain personality types appeared to be effective in mixed gender teams. [ABSTRACT FROM AUTHOR]

A plethora of research has been carried out to explore the key importance of team roles and personality types in software development. What types of personality are handy and beneficial for an ideal and effective teamwork is still a question for the researchers and practitioners. This study has combined the past claims of personality preferences for programmer role so that researchers and practitioners can easily access the literature. In order to achieve the study objective, Kitchenham guidelines were followed to design and implement the review protocol. The whole review focused to find the effective personality preferences of programmer role from different experimental settings: individuals-andteams and academic-and-industry. Additionally, only those studies were selected that used Myers-Briggs type indicator (MBTI) personality test. The results of this study were divided into three categories based on the obtained personality preferences: strongly appeared, weakly appeared, and disappeared. For example, it was strongly observed in the results that combination of intuitive (N) and feeling (F) traits is not a suitable personality choice for programmer role. The conclusion of this study can be drawn with the statement that personality based software development research needs serious attention to fill the wide gaps. There are numerous ambiguities for practitioners if they intend to put these studies into use. [ABSTRACT FROM AUTHOR]

The production of software and their effectiveness have become the prerequisite for the development of various sectors of the world. Persistent demand for the software, feasible and effective in nature to address the clients' demand have levitated the interest amongst researchers to determine the factors that idealize the software development team since an adept and compatible team members, in terms of personality, are likely to ensure the success of software. In this regard, personality clashes have been attributed as the prominent factors of all to the failure of the software. Although copious research studies have been carried out in the past to suggest ideal and compatible personalities for making an ideal software development team, it is regret to add that the findings of these studies have rather enhanced the gravity of the problem for giving different suggestions for composing an ideal team for software development. To lessen such confusion, this study aims to propose solution for personality-based team composition by executing the different ranges of the programmer's role based on Myer Brig Type Indicator (MBTI) pairs. This method supposedly allows the researchers to reach the suitable conclusion by thorough investigation of all traits of personality for programmer role. In order to attain the best solution, student population was involved to develop the software projects in teams. The experiments were divided into two segments: defining balancing benchmark and validating the benchmark. In outcomes, this study proposed different ranges of personality traits based on gender classification for software programmers. [ABSTRACT FROM AUTHOR]

Researchers are finding their way to solve the chaotic and uncertain problems using the extensions of classical fuzzy model. At present Interval Type-2 Fuzzy logic Systems (IT2-FLS) are extensively used after the thriving exploitation of Type-2 FLS. Fuzzy time series models have been used for forecasting stock and FOREX indexes, enrollments, temperature, disease diagnosing and weather. In this paper an integrated fuzzy time series model based on ARIMA and IT2-FLS is presented. The propose model will use ARIMA to select appropriate coefficients from the observed dataset. IT2-FLS is utilized here for forecasting the result with more accuracy and certainty. [ABSTRACT FROM AUTHOR]

In this paper, we present a solution for autonomous agent navigation in unknown virtual environments. A new decision making method using fuzzy logic is proposed. The objective is to solve behaviour conflicts in behaviour-based architectures. Two main problems have been identified: how to decide which behaviour should be activated at each instant; and how to combine the results from different behaviours into one action. The method uses fuzzy _-levels to compute behaviour weights for each behaviour and the final action is selected using the Hurwicz criterion. The experimental results show that the autonomous virtual agent had successfully navigated various virtual environments. The results show the virtual agent required less decision making which means more reliable decisions had been generated and redundant decisions had been reduced. The qualities of the path produced are reasonably smooth, short and clear of collision. [ABSTRACT FROM AUTHOR]

The problem of scheduling is an area that has attracted a lot of attention from researchers for many years. Its goal is to optimize resources in the system. The lecturer's assigning task is an example of the timetabling problem, a class of scheduling. This study introduces a mathematical model to assign constrained tasks (the time and required skills) to university lecturers. Our model is capable of generating a calendar that maximizes faculty expectations. The formulated problem is in the form of a multi-objective problem that requires the trade-off between two or more conflicting objectives to indicate the optimal solution. We use the compromise programming approach to the multi-objective problem to solve this. We then proposed the new version of the Genetic Algorithm to solve the introduced model. Finally, we tested the model and algorithm with real scheduling data, including 139 sections of 17 subjects to 27 lecturers in 10 timeslots. Finally, a web application supports the decision-maker to visualize and manipulate the obtained results. [ABSTRACT FROM AUTHOR]

We can find solutions to the team selection problem in many different areas. The problem solver needs to scan across a large array of available solutions during their search. This problem belongs to a class of combinatorial and NP-Hard problems that requires an efficient search algorithm to maintain the quality of solutions and a reasonable execution time. The team selection problem has become more complicated in order to achieve multiple goals in its decision-making process. This study introduces a multiple cross-functional team (CFT) selection model with different skill requirements for candidates who meet the maximum required skills in both deep and wide aspects. We introduced a method that combines a compromise programming (CP) approach and metaheuristic algorithms, including the genetic algorithm (GA) and ant colony optimization (ACO), to solve the proposed optimization problem. We compared the developed algorithms with the MIQP-CPLEX solver on 500 programming contestants with 37 skills and several randomized distribution datasets. Our experimental results show that the proposed algorithms outperformed CPLEX across several assessment aspects, including solution quality and execution time. The developed method also demonstrated the effectiveness of the multi-criteria decision-making process when compared with the multi-objective evolutionary algorithm (MOEA)., Competing Interests: The authors declare there are no competing interests., (©2022 Ngo et al.)