Search

Nowadays, there has been a rapidly increasing number of scientific submissions in multiple research domains. A large number of journals have various acceptance rates, impact factors, and rankings in different publishers. It becomes time-consuming for many researchers to select the most suitable journal to submit their work with the highest acceptance rate. A paper submission recommendation system is more critical for the research community and publishers as it gives scientists another support to complete their submission conveniently. This paper investigates the submission recommendation system for two main research topics: computer science and applied mathematics. Unlike the previous works (Wang et al., 2018; Son et al., 2020) that extract TF–IDF and statistical features as well as utilize numerous machine learning algorithms (logistics regression and multiple perceptrons) for building the recommendation engine, we present an efficient paper submission recommendation algorithm by using different bidirectional transformer encoders and the Mixture of Transformer Encoders technique. We compare the performance between our methodology and other approaches by one dataset from Wang et al. (2018) with 14012 papers in computer science and another dataset collected by us with 223,782 articles in 178 Springer applied mathematics journals in terms of top K accuracy (K = 1 , 3 , 5 , 10). The experimental results show that our proposed method extensively outperforms other state-of-the-art techniques with a significant margin in all top K accuracy for both two datasets. We publish all datasets collected and our implementation codes for further references. 1 1 https://github.com/BinhMisfit/PSRMTE. • Bidirectional transformer encoders can improve the performance of the paper submission recommendation system. • The Mixture of Transformer Encoders framework shows the efficiency in the paper submission recommendation problem. • Proposed techniques can surpass other recent techniques on two datasets related. [ABSTRACT FROM AUTHOR]

• A novel SMO inspired by mimicking behavior to solve optimization problems is presented. • SMO includes a mimic operator to simulate search in the response space. • SMO does not require control operator respect to other Meta heuristic methods. • SMO solve optimization problems with minimum population size. • SMO is compared with 14 well-known and state of the art optimization algorithms. Increase in complexity of real world problems has provided an area to explore efficient methods to solve computer science problems. Meta-heuristic methods based on evolutionary computations and swarm intelligence are instances of techniques inspired by nature. This paper presents a novel social mimic optimization (SMO) algorithm inspired by mimicking behavior to solve optimization problems. The proposed algorithm is evaluated using 23 test functions. Obtained results are compared with 14 known optimization algorithms including Whale optimization algorithm (WOA), Grasshopper optimization algorithm (GOA), Particle Swarm Optimization (PSO), Stochastic fractal search (SFS), Grey Wolf Optimizer (GWO), Optics Inspired Optimization (OIO), League Championship Algorithm (LCA), Wind Driven Optimization (WDO), Harmony search (HS), Firefly Algorithm (FA), Artificial Bee Colony (ABC), Biogeography Based Optimization (BBO), Bat Algorithm (BA), and Teaching Learning Based Optimization (TLBO). Obtained results indicate higher capability of the SMO algorithm in solving high-dimensional decision variables. Furthermore, SMO is used to solve two classic engineering design problems. Three important features of SMO are simple implementation, solving optimization problems with minimum population size and not requiring control parameters. Results of various evaluations show superiority of the proposed method in finding the optimal solution with minimum function evaluations. This superiority is achieved based on reducing number of initial population. The proposed method can be applied to applications like automatic evolution of robotics, automatic control of machines and innovation of machines in finding better solutions with less cost. [ABSTRACT FROM AUTHOR]

• Fileless malware has no signature because it does not leverage executable files. • We suggest a memory-based approach for detecting and analyzing fileless malware. • This proposed method offers useful insight for the experts working in this field. • The proposed methodʼs applicability was demonstrated using a real case study sample. The rapid advancements in cyber-attack strategies are in parallel with the measures for detection, analysis, and prevention. Attackers have recently developed fileless malware that can simply bypass existing security mechanisms. Researchers publish reports to help discover fileless malware and to better understand the threatʼs scope to counteract it. However, with the lack of studies on fileless malware regarding the classification and the scale of the threat, they have not been thoroughly analyzed. As a result, in this research, we explored the most recent advancements in fileless malware prevention and detection and highlighted future research challenges. We also propose an analytical approach based on the attack strategies and attributes of the selected sample. Our method simplifies feature extraction and reduces processing load. Furthermore, compared to the static analysis we do not need for decompression and unpacking for the analysis. We applied the proposed method on a real case example. It has been seen that information about fileless malware detection, working mechanism, attack method and attacker named "Kovter" can be accessed. Our approach is advantageous and can be applied as a new technique for fileless malware detection to protect systems from cyber threats. This paper also presents an insight to the fileless malware threat and provides a basic review of the methods and techniques used in the detection and analysis of fileless malware attacks. [ABSTRACT FROM AUTHOR]

Remediation actions are performed in scenarios in which consequences of a problem should be promptly mitigated when its cause takes too long to be addressed or is unknown. Such scenarios are recurrent in the real world, including in the context of computer science. Existing approaches that address these scenarios are application-specific. Nevertheless, the reasoning about remediation actions as well as cause identification and resolution, in order to address problems permanently, can be abstracted in such a way that they can be incorporated to autonomous software components, often referred to as agents. They can thus autonomously deal with these scenarios, which we refer to as critical cause-effect situations . In this paper, we propose a domain-independent extension to the belief-desire-intention (BDI) architecture that provides such agents with this automated reasoning. Our work provides an extensible solution to this recurrent problem-solving strategy and allows agents to flexibly deal with resource-constrained scenarios. This solution removes the need for manually implementing the coordination of actions performed by agents, using causal models to capture the knowledge required to carry out this task. Therefore, it not only allows the development of systems with remediative behaviour, but also enables the reduction of development effort by means of a reusable infrastructure that can be used in several different domains. Our approach was evaluated based on an existing solution in the network resilience domain, which showed that our extended agent can autonomously address a network challenge, with a reduction in the development effort and no impact in agent performance. [ABSTRACT FROM AUTHOR]

Activity recognition has been a hot topic for decades, from the scientific research to the development of off-the-shelf commercial products. Since people perform the activities differently, to avoid overfitting, building a general model with activity data of various users is required before the deployment for personal use. However, annotating a large amount of activity data is expensive and time-consuming. In this paper, we build a general model for activity recognition with a limited amount of labelled data. We combine Latent Dirichlet Allocation (LDA) and AdaBoost to jointly train a general activity model with partially labelled data. After that, when AdaBoost is used for online prediction, we combine it with graphical models (such as HMM and CRF) to exploit the temporal information in human activities to smooth out the accidental misclassifications. Experiments with publicly available datasets show that we are able to obtain the accuracy of more than 90% with 1% labelled data. [ABSTRACT FROM AUTHOR]

Many real-world networks have a topological structure characterized by cohesive groups of vertices. To perform the task of identifying such subsets of vertices, community detection in networks has aroused the interest of researchers and practitioners alike. In spite of the existence of various efficient community detection algorithms in the literature, most of them uses global information about the network, not applicable to distributed networks. This paper proposes a genetic-based algorithm to detect communities in directed networks based on local information to generate the offspring. The major difference between the proposed strategy and those found in the literature is the way of exploiting target regions of interest in the solution space. This step is directly influenced by the crossover operator that depends largely on the individual representation. In the introduced strategy, GA-LP, the individual is locally stored in the vertices as labels, what brings more flexibility in the system to be adapted to address applications that involve, for example, dynamic networks. In computational experiments, the proposed strategy showed an outstanding performance, being fast, achieving the best results on average in the networks tested. [ABSTRACT FROM AUTHOR]

• A comprehensive survey/review paper on computer-aided diagnosis (CAD) in medicine of 251 publications. • Referenced publications had to pass criteria to determine subject relevance and quality of publication. • It bridges a crucial gap that currently exists in the literature regarding an overview of CAD systems in medicine. • It provides a venue for people with different backgrounds to understand pertinent aspects in medicine and in computer science. • Provides a foundation for accelerating research in this vital field in the interface of medicine and computer science. Computer-aided diagnosis (CAD) in medicine is the result of a large amount of effort expended in the interface of medicine and computer science. As some CAD systems in medicine try to emulate the diagnostic decision-making process of medical experts, they can be considered as expert systems in medicine. Furthermore, CAD systems in medicine may process clinical data that can be complex and/or massive in size. They do so in order to infer new knowledge from data and use that knowledge to improve their diagnostic performance over time. Therefore, such systems can also be viewed as intelligent systems because they use a feedback mechanism to improve their performance over time. The main aim of the literature survey described in this paper is to provide a comprehensive overview of past and current CAD developments. This survey/review can be of significant value to researchers and professionals in medicine and computer science. There are already some reviews about specific aspects of CAD in medicine. However, this paper focuses on the entire spectrum of the capabilities of CAD systems in medicine. It also identifies the key developments that have led to today's state-of-the-art in this area. It presents an extensive and systematic literature review of CAD in medicine, based on 251 carefully selected publications. While medicine and computer science have advanced dramatically in recent years, each area has also become profoundly more complex. This paper advocates that in order to further develop and improve CAD, it is required to have well-coordinated work among researchers and professionals in these two constituent fields. Finally, this survey helps to highlight areas where there are opportunities to make significant new contributions. This may profoundly impact future research in medicine and in select areas of computer science. [ABSTRACT FROM AUTHOR]

A detailed and extensive empirical study of empty prediction of multi-label classification is conducted in this paper and to the best of our knowledge this work is the first empirical study of this problem. Total 8 state of the art multi-label classification methods, BR, CC, CLR, HOMER, RAkEL, ECC, MLkNN, and BRkNN, are compared on 11 datasets. The empirical results clearly answer the two research questions, (1) whether empty prediction problems happen in commonly used state of the art multi-label classification methods and what their empty prediction rates (EPR) on different test sets are and (2) what multi-label classification methods are with overall highest/lowest EPRs. Specifically, it is empirically shown that every method considered all made empty predictions on different datasets. In addition, several thresholding methods which in theory can solve empty prediction are compared. The clear answers to the two research questions and the experimental findings are the main contributions of this work to multi-label classification. [ABSTRACT FROM AUTHOR]

In this paper we describe a tool that can be effectively used to evaluate student learning outcomes using concept maps and Markov chain analysis. The main purpose of this tool is to advance the use of artificial intelligence techniques by using concept maps and Markov chains in evaluating a student’s understanding of a particular topic of study using concept maps. The method used in the tool makes use of XML parsing to perform the required evaluation. For the purpose of experimenting this tool we have taken into consideration concept maps developed by students enrolled in two different courses in Computer Science. The result of this experimentation is also discussed. [ABSTRACT FROM AUTHOR]

QUALIFLEX (QUALItative FLEXible multiple criteria method) is a very useful outranking method to deal simultaneously with the cardinal and ordinal information in decision making process. The purpose of this paper is to develop a hesitant fuzzy QUALIFLEX with a signed distance-based comparison method for handling multi-criteria decision-making problems in which both the assessments of alternatives on criteria and the weights of criteria are expressed by hesitant fuzzy elements (HFEs). We propose a novel concept of hesitancy index for the HFE to measure the degree of hesitancy of the decision-maker or the decision organization. By taking their hesitancy indices into account, we present a signed distance-based method to compare the magnitude of HFEs. Using the signed distance-based comparison approach, we define the concordance/discordance index, the weighted concordance/discordance index and the comprehensive concordance/discordance index. By investigating all possible permutations of alternatives with respect to the level of concordance/discordance of the complete preference order, the optimal ranking orders of alternatives can be obtained. An application study of the proposed method on green supplier selection is conducted. The study indicates that the proposed method does not require the complicated computation procedures but still yields a reasonable and credible solution. [ABSTRACT FROM AUTHOR]