Search

This study proposes a new metaheuristic algorithm called sand cat swarm optimization (SCSO) which mimics the sand cat behavior that tries to survive in nature. These cats are able to detect low frequencies below 2 kHz and also have an incredible ability to dig for prey. The proposed algorithm, inspired by these two features, consists of two main phases (search and attack). This algorithm controls the transitions in the exploration and exploitation phases in a balanced manner and performed well in finding good solutions with fewer parameters and operations. It is carried out by finding the direction and speed of the appropriate movements with the defined adaptive strategy. The SCSO algorithm is tested with 20 well-known along with modern 10 complex test functions of CEC2019 benchmark functions and the obtained results are also compared with famous metaheuristic algorithms. According to the results, the algorithm that found the best solution in 63.3% of the test functions is SCSO. Moreover, the SCSO algorithm is applied to seven challenging engineering design problems such as welded beam design, tension/compression spring design, pressure vessel design, piston lever, speed reducer design, three-bar truss design, and cantilever beam design. The obtained results show that the SCSO performs successfully on convergence rate and in locating all or most of the local/global optima and outperforms other compared methods. WOS:000780842800001

The Sand Cat Swarm Optimization (SCSO) algorithm is a recently introduced metaheuristic with balanced behavior in the exploration and exploitation phases. However, it is not fast in convergence and may not be successful in finding the global optima, especially for complex problems since it starts the exploitation phase late. Moreover, the performance of SCSO is also affected by incorrect position as it depends on the location of the global optimum. Therefore, this study proposes a new method for the SCSO algorithm with a multidisciplinary principle inspired by the Political (Parliamentary) system, which is named PSCSO. The suggested algorithm increases the chances of finding the global solution by randomly choosing positions between the position of the candidate's best solution available so far and the current position during the exploitation phase. In this regard, a new coefficient is defined that affects the exploration and exploitation phases. In addition, a new mathematical model is introduced to use in the exploitation phase. The performance of the PSCSO algorithm is analyzed on a total of 41 benchmark functions from CEC2015, 2017, and 2019. In addition, its performance is evaluated in four classical engineering problems. The proposed algorithm is compared with the SCSO, Stochastic variation and Elite collaboration in SCSO (SE-SCSO), Hybrid SCSO (HSCSO), Parliamentary Optimization Algorithm (POA), and Arithmetic Optimization Algorithm (AOA) algorithms, which have been proposed in recent years. The ob-tained results depict that the PSCSO algorithm performs better or equivalently to the compared optimization algorithms. WOS:000926264400001 Q1

Purpose Efficient resource utilization in wireless sensor networks is an important issue. Clustering structure has an important effect on the efficient use of energy, which is one of the most critical resources. However, it is extremely vital to choose efficient and suitable cluster head (CH) elements in these structures to harness their benefits. Selecting appropriate CHs and finding optimal coefficients for each parameter of a relevant fitness function in CHs election is a non-deterministic polynomial-time (NP-hard) problem that requires additional processing. Therefore, the purpose of this paper is to propose efficient solutions to achieve the main goal by addressing the related issues. Design/methodology/approach This paper draws inspiration from three metaheuristic-based algorithms; gray wolf optimizer (GWO), incremental GWO and expanded GWO. These methods perform various complex processes very efficiently and much faster. They consist of cluster setup and data transmission phases. The first phase focuses on clusters formation and CHs election, and the second phase tries to find routes for data transmission. The CH selection is obtained using a new fitness function. This function focuses on four parameters, i.e. energy of each node, energy of its neighbors, number of neighbors and its distance from the base station. Findings The results obtained from the proposed methods have been compared with HEEL, EESTDC, iABC and NR-LEACH algorithms and are found to be successful using various analysis parameters. Particularly, I-HEELEx-GWO method has provided the best results. Originality/value This paper proposes three new methods to elect optimal CH that prolong the networks lifetime, save energy, improve overhead along with packet delivery ratio.

Efficient and collision-free pathfinding, between source and destination locations for multi-Unmanned Aerial Vehicles (UAVs), in a predefined environment is an important topic in 3D Path planning methods. Since path planning is a Non-deterministic Polynomial-time (NP-hard) problem, metaheuristic approaches can be applied to find a suitable solution. In this study, two efficient 3D path planning methods, which are inspired by Incremental Grey Wolf Optimization (I-GWO) and Expanded Grey Wolf Optimization (Ex-GWO), are proposed to solve the problem of determining the optimal path for UAVs with minimum cost and low execution time. The proposed methods have been simulated using two different maps with three UAVs with diverse sets of starting and ending points. The proposed methods have been analyzed in three parameters (optimal path costs, time and complexity, and convergence curve) by varying population sizes as well as iteration numbers. They are compared with well-known different variations of grey wolf algorithms (GWO, mGWO, EGWO, and RWGWO). According to path cost results of the defined case studies in this study, the I-GWO-based proposed path planning method (PPI-GWO) outperformed the best with %36.11. In the other analysis parameters, this method also achieved the highest success compared to the other five methods. WOS:000682214900003 Q2

Background Colorectal cancer (CRC) is the third most frequent kind of cancer globally, making it a significant public health problem. This project aims to construct a network to uncover potential biomarkers for diagnostic reasons, prospective EDCs for preventative applications, and potential drugs for therapeutic purposes in early-stage CRC. Results To this end, we identified driver genes linked with early-stage colorectal cancer and used the R package WGCNA to design a co-expression network. Following that, modules were chosen, and possible biomarkers were identified using the Cytoscape software and the TCGA database. Then, using the comptox database, we identified probable EDCs and created an EDC-GENE network. Finally, we introduced EDCs with a high degree of risk. The drug-gene network was then reconstructed to find viable therapies for colorectal cancer in its early stages. The co-expression network was constructed using the 1108 driver Genes’ mRNA expression values of 70 early-stage CRC and 12 healthy control samples. The clustering results show that the overlapping gene set is divided into 27 modules. Our study identified five modules (indicated in dark green, dark orange, light cyan, royal blue, and purple) according to the average linkage hierarchical clustering and Zsummary less than 2. Then we find 17 high degree genes of these modules as potential biomarkers for diagnostic issues. Moreover, we explored 25 possible high degrees of Endocrine Disrupting Chemicals that affect the main genes of each module for preventing purposes. Finally, we identified 27 potential high degree drugs that affect the primary genes of each module as treating aims. Then, these biomarkers, EDCs, and drugs that may be tested as a basis for future research were introduced. Conclusions This research aimed to identify potential biomarkers for diagnostic purposes, prospective EDCs for prevention, and potential therapeutic agents in colorectal cancer in its early stages. These biomarkers, EDCs, and medications will aid in diagnosing, preventing, and treating colorectal cancer in its early stages.

Background: In the current generation, infertility is one of the leading reasons for relationship problems. Infertility is defined as having active intercourse without the use of birth control pills on a yearly basis not resulting in zygote development and fertilization. Methods: In the current study, genes associated to male infertility were collected, and then a PPI network was reconstructed. Next, four protein modules were discovered from the reconstructed PPI network. Afterwards, for every protein module a mRNA-miRNA interaction sub-network was drawn. Finally, based on the degree and importance of these genes, modules were introduced as the main markers of male infertility, followed by naming some drugs involved in the disease.Results: Based on PPI network analysis, five genes including TP53, ESR1, PIK3CA, BRAF, and HIF1A are introduced as key candidates in male infertility disorder. Further, hsa-miR-92a-3p, hsa-miR-16-5p, hsa-miR-21-5p, hsa-miR-335-5p, and hsa-miR-106b-5p are probably highlighted among miRNAs. Finally, a drug-gene interaction network was remade for male infertility, and CISPLATIN, DOXORUBICIN, FLUOROURACIL, DOCETAXEL, and PACLITAXEL were found to be the most potent chemotherapy drugs in inducing the illness. Conclusions: According to the findings, it is recommended that young couples, who are having chemotherapy and children, use lower risk treatments rather than the listed medicines as much as possible in their treatment. Given that the steps were computational, it is suggested that these genes and miRNAs be realistically investigated in the laboratory in future research, and it is preferable to offer alternative low-risk medicines in other studies.

WOS:000533233700005 In wireless sensor networks, some resources such as memory and energy are limited. In recent years, there has been an increasing interest in improving network lifetime. Node energy plays an important role in the network lifetime. Along with this remarkable growth in wireless sensor networks, however, there is an increasing concern over network lifetime. The principal purpose of this study is to develop an understanding of the effects of other parameters on selecting a cluster head. The methodological approach taken in this study is a mixed methodology typically based on the node's energy. The authors have operated four parameters to select the cluster head: Node energy, the energy of the node's neighbours, number of hops and number of links to neighbours. Each of these parameters has an impact in selecting the cluster head. They accurately observed hop size, energy of each sensor node, average energy of sensor neighbours, links to sensor nodes (HEEL) has better improvements in comparison of Node ranked Low Energy Adaptive Clustering Hierarchy (Nr-LEACH), Modified Low Energy Adaptive Clustering Hierarchy (ModLEACH), Low Energy Adaptive Clustering Hierarchy-B (LEACH-B), Low Energy Adaptive Clustering Hierarchy (LEACH), Power-Efficient Gathering in Sensor Information System (PEGASIS), energy-aware clustering scheme with transmission power control for sensor networks (EACLE) and hybrid energy efficient distributed clustering (HEED) algorithms in possible case of network lifetime and throughput.

The node deployment problem is a non-deterministic polynomial time (NP-hard). This study proposes a new and efficient method to solve this problem without the need for predefined circumstances about the environments independent of terrain. The proposed method is based on a metaheuristic algorithm and mimics the grey wolf optimizer (GWO) algorithm. In this study, we also suggested an enhanced version of the GWO algorithm to work adaptively in such problems and named it Mutant-GWO (MuGWO). Also, the suggested model ensures connectivity by generating topology graphs and potentially supports data transmission mechanisms. Therefore, the proposed method based on MuGWO can enhance resources utilization, such as reducing the number of nodes, by maximizing the coverage rate and maintaining the connectivity. While most studies assume classical rectangle uniform environments, this study also focuses on custom (environment-aware) maps in line with the importance and requirements of the real world. The motivation of supporting custom maps by this study is that environments can consist of custom shapes with prioritized and critical areas. In this way, environment awareness halts the deployment of nodes in undesired regions and averts resource waste. Besides, novel multi-purpose fitness functions of the proposed method satisfy a convenient approach to calculate costs instead of using complicated processes. Accordingly, this method is suitable for large-scale networks thanks to the capability of the distributed architecture and the metaheuristic-based approach. This study justifies the improvements in the suggested model by presenting comparisons with a Deterministic Grid-based approach and the Original GWO. Moreover, this method outperforms the fruit fly optimization algorithm, bat algorithm (BA), Optimized BA, harmony search, and improved dynamic deployment technique based on genetic algorithm methods in declared scenarios in literature, considering the results of simulations. WOS:000857798800002 Q2

The performance of a model in machine learning problems highly depends on the dataset and training algorithms. Choosing the right training algorithm can change the tale of a model. While some algorithms have a great performance in some datasets, they may fall into trouble in other datasets. Moreover, by adjusting hyperparameters of an algorithm, which controls the training processes, the performance can be improved. This study contributes a method to tune hyperparameters of machine learning algorithms using Grey Wolf Optimization (GWO) and Genetic algorithm (GA) metaheuristics. Also, 11 different algorithms including Averaged Perceptron, FastTree, FastForest, Light Gradient Boost Machine (LGBM), Limited memory Broyden Fletcher Goldfarb Shanno algorithm Maximum Entropy (LbfgsMxEnt), Linear Support Vector Machine (LinearSVM), and a Deep Neural Network (DNN) including four architectures are employed on 11 datasets in different biological, biomedical, and nature categories such as molecular interactions, cancer, clinical diagnosis, behavior related predictions, RGB images of human skin, and X-rays images of Covid19 and cardiomegaly patients. Our results show that in all trials, the performance of the training phases is improved. Also, GWO demonstrates a better performance with a p-value of 2.6E-5. Moreover, in most experiment cases of this study, the metaheuristic methods demonstrate better performance and faster convergence than Exhaustive Grid Search (EGS). The proposed method just receives a dataset as an input and suggests the best-explored algorithm with related arguments. So, it is appropriate for datasets with unknown distribution, machine learning algorithms with complex behavior, or users who are not experts in analytical statistics and data science algorithms. © 2022 Elsevier Ltd

Despite the rapid improvement in mobile devices, overall gradual growth in the ubiquitous computing field, the wide applicability, more usefulness of location based services in general and indoor navigation. The Global Positioning System (GPS) has undergone tremendous improvement since the 1900s and it, indeed is considered one of the most successful navigation systems known to date. However, it is still inefficient for sufficiently accurate positioning in both indoor environments and environments with many tall buildings such as skyscrapers since such buildings block or interfere with its signal transmissions. In particular, building a sufficiently accurate, efficient and relatively cheap indoor navigation system in a GPS-free environment is still a challenging task with a lot of tradeoffs and constraints to put into consideration. In this paper, a simple yet robust, low-cost, context-aware user-interactive, user-friendly hybrid of fingerprinting and dead reckoning indoor navigation system suitable for both the visually and the physically disabled as well that takes advantage of the results yielded by sensor fusion is proposed. The presented system is also designed to allow for efficient evacuation of users in cases of emergences. The prototype is made majorly of the following parts; user tracking, optimal, context-aware and dynamic route calculation and planning and dynamic route representation with an upper bound of 2m and an average of 0.8-1.3m accuracy. All that is required from the user is a smart phone without installation of extra hardware.

Voluntary or compulsory immigration of people to other regions or countries for different reasons can lead to social, cultural, and economic problems. In recent years, especially the rate of forced migration has increased and it is sometimes chosen as a last resort for social mobilization. Scientists and governments who have gathered data on migration for years have recently realized that Artificial Intelligence (AI) and Machine Learning (ML) methods are important in analyzing this data and developing utility models and systems. It has been gradually understood that these new technologies are very important in recent years, but studies have either only been done in the field of social sciences or only in the field of engineering. In this study, a comprehensive interdisciplinary study covering both dimensions is prepared. In this study, a machine learning-based model is presented by making a multidisciplinary study and exemplifying the Lake Urmia case study. The proposed method can be used in the decision-making process in the migration management. In our study, is proposed a model using three different algorithms (Support Vector Machine (SVM), Random Forest (RF), and K-Nearest Neighbors (KNN)). According to the results, the SVM-based model outperforms others in accuracy and validations. The trained model of SVM has a success rate on mean accuracy as near to 86% with 4,00E-02 standard deviation rate. SVM ranked first and this method was followed by RF and KNN methods, respectively. In this context, this model can make forward-looking predictions and, like an expert system, can guide the relevant researchers and even state or form ideas according to the results obtained from it.

Today, the outbreak of the coronavirus has become a major global crisis and has affected many countries. One of the consequences of the spread of this virus is the creation of social panic and rapid changes in people's lifestyles, which the social networks are noticing. The impact of social media, which plays an effective role even in people's lifestyles, is being examined in the Covid-19 Pandemic. The purpose of this paper is to investigate the role of social networks in lifestyle changes in the coronavirus pandemic period. The present research is quantitative in terms of approach and in terms of type and nature, it is a descriptive survey. The data collection tool was assumed to be the Twitter social network. A total of 100.000 cases have been investigated based on the support vector machine (SVM) method and its results have been compared with decision tree and naive Bayes methods. Data processing is done using Python software. The trained model of SVM has a success rate on accuracy as near to 97% and also has 92% in the F1 score. The results show that social networks have about a 30% effect on lifestyle changes and stress during the pandemic periods. In order to form logical and desirable behaviors instead of dramatic behaviors such as fear and social stress in the use of social networks, social agents have their priority in organizing information and knowledge and informing the target community about the constructive and harmful cases of these networks and place different social roles and activities in society. Accordingly, providing the right news and information through trusted and responsible channels and platforms can play an important role in the proper management of society.

Modern time microwave stages require low power consumption, low size, low-noise amplifier (LNA) designs with high-performance measures. These demands need a single transistor LNA design, which is a challenging multi-objective, multi-dimensional optimization problem that requires solving objectives with non-linear feasible design target space, that can only be achieved by optimally selecting the source (Z(S)) and load (Z(L)) terminations. Meta-heuristic algorithms (MHAs) have been extensively used as a search and optimization method in many problems in the field of science, commerce, and engineering. Since feasible design target space (FDTS) of an LNA transistor (NE3511S02 biased at VDS = 2 V and IDS = 7 mA) is a multi-objective multi-variable optimization problem the MHA can be considered as a suitable choice. Three different types of grey wolf variants inspired algorithms had been applied to the LNA FDTS problem to obtain the optimal source and load terminations that satisfies the required performance measures of the aimed LNA design. Furthermore, the obtained results are justified via the use of the Electromagnetic Simulator tool AWR. As a result, an efficient optimization method for optimal determination of Z(S) and Z(L) terminations of a high-performance LNA design had been achieved. WOS:000672272500002 Q4

RNA-protein interactions of a virus play a major role in the replication of RNA viruses. The replication and transcription of these viruses take place in the cytoplasm of the host cell; hence, there is a probability for the host RNA-viral protein and viral RNA-host protein interactions. The current study applies a high-throughput computational approach, including feature extraction and machine learning methods, to predict the affinity of protein sequences of ten viruses to three categories of RNA sequences. These categories include RNAs involved in the protein-RNA complexes stored in the RCSB database, the human miRNAs deposited at the mirBase database, and the lncRNA deposited in the LNCipedia database. The results show that evolution not only tries to conserve key viral proteins involved in the replication and transcription but also prunes their interaction capability. These proteins with specific interactions do not perturb the host cell through undesired interactions. On the other hand, the hypermutation rate of NSP3 is related to its affinity to host cell RNAs. The Gene Ontology (GO) analysis of the miRNA with affiliation to NSP3 suggests that these miRNAs show strongly significantly enriched GO terms related to the known symptoms of COVID-19. Docking and MD simulation study of the obtained miRNA through high-throughput analysis suggest a non-coding RNA (an RNA antitoxin, ToxI) as a natural aptamer drug candidate for NSP5 inhibition. Finally, a significant interplay of the host RNA-viral protein in the host cell can disrupt the host cell's system by influencing the RNA-dependent processes of the host cells, such as a differential expression in RNA. Furthermore, our results are useful to identify the side effects of mRNA-based vaccines, many of which are caused by the off-label interactions with the human lncRNAs., Graphical abstract Image 1

Three-dimensional path planning for autonomous robots is a prevalent problem in mobile robotics. This paper presents three novel versions of a hybrid method designed to assist in planning such paths for these robots. In this paper, an improvement on Rapidly exploring Random Tree (RRT) algorithm, namely Adapted-RRT, is presented that uses three well-known metaheuristic algorithms, namely Grey Wolf Optimization (GWO), Incremental Grey Wolf Optimization (I-GWO), and Expanded Grey Wolf Optimization (Ex-GWO)). RRT variants, using these algorithms, are named Adapted-RRTGWO, Adapted-RRTI-GWO, and Adapted-RRTEx-GWO. The most significant shortcoming of the methods in the original sampling-based algorithm is their inability in finding the optimal paths. On the other hand, the metaheuristic-based algorithms are disadvantaged as they demand a predetermined knowledge of intermediate stations. This study is novel in that it uses the advantages of sampling and metaheuristic methods while eliminating their shortcomings. In these methods, two important operations (length and direction of each movement) are defined that play an important role in selecting the next stations and generating an optimal path. They try to find solutions close to the optima without collision, while providing comparatively efficient execution time and space complexities. The proposed methods have been simulated employing four different maps for three unmanned aerial vehicles, with diverse sets of starting and ending points. The results have been compared among a total of 11 algorithms. The comparison of results shows that the proposed path planning methods generally outperform various algorithms, namely BPIB-RRT*, tGSRT, GWO, I-GWO, Ex-GWO, PSO, Improved BA, and WOA. The simulation results are analysed in terms of optimal path costs, execution time, and convergence rate. WOS:000659898800002 Q1

Reverse engineering is used for extracting and understanding software architecture models from source code when the source code is the only available software product. Software module clustering is a reverse engineering method which decomposes software modules into several clusters (subsystems) by using module dependency graph. Finding the best clusters for the modules of software is a multi-objective and NP-hard problem; maximizing the cohesion among the modules, minimizing the coupling among different clusters, and maximizing the software modularization quality are considered as the main objectives of software module clustering. Some of these objectives, such as cohesion and coupling, are in contradiction with each other. Simultaneous improvement of all clustering objectives (cohesion, coupling, modularization quality, size, and number of clusters) is the main goal of this study. In this paper, by capitalizing on multi objective genetic algorithm and a new combination of objective functions, we proposed a homogeneous method, namely, Savalan, for clustering software modules. The proposed method generates high-quality clusters with strong cohesion within clusters and weak connections between clusters for the input source code. The results of conducted experiments on the 14 benchmark programs indicate that simultaneous improvement of all clustering objectives is the main merit of this method. According to the experimental results, the proposed algorithm was able to outperform the previous multi objective methods. WOS:000720303600001 2-s2.0-85119450766 Q3

Design and development of legged robots that can navigate effectively and autonomously in a wide range of environments is a challenging problem. At that point it should be noted that nature inspired optimization techniques have been widely studied for autonomous navigation of legged robots. In this study the framework constructed for six-legged walking behavior generation using genetic algorithms is presented and simulation results on Unity are discussed. © 2020 IEEE.

Feature extraction is one of the most important preprocessing steps in predicting the interactions between RNAs and proteins by applying machine learning approaches. Despite many efforts in this area, still, no suitable structural feature extraction tool has been designed. Therefore, an online toolbox, named RPINBASE which can be applied to different scopes of biological applications, is introduced in this paper. This toolbox employs efficient nested queries that enhance the speed of the requests and produces desired features in the form of positive and negative samples. To show the capabilities of the proposed toolbox, the developed toolbox was investigated in the aptamer design problem, and the obtained results are discussed. RPINBASE is an online toolbox and is accessible at http://rpinbase.com.

Today one of the biggest expense items of the enterprises is raw material and stock amounts. Therefore, proper inventory management is very important for the profitability of the enterprises. Products that are not purchased on time cause interruptions in production and products left over because the expiration date has passed will also cause losses for businesses. Therefore, proper inventory management is critical for profit / loss situations of businesses. In this paper we presented a model to predict the demand of certain stock items by using a regression model. Our model can analysis and computer the prediction results on agiven dataset. We evaluate our model on sample dataset and provide the analysis as well calculations over the existing inventory. Accurate analysis of stock consumption enables accurate estimation of the amount of stock to be consumed in the future. Accurate forecasting of stock consumption helps to take corrective steps in decision making. That is, it only allows you to buy in sufficient quantity when necessary. These stages are critical for economic stock management. For this reason, robust and adaptable approaches that can provide models ensure that stock consumption can be managed properly. It is difficult to find previously written sources on estimating the direction of stock movements. One of the most important reasons for this is the lack of incentive to make such studies in the academic literature. As a result, articles written about the subject and the work done have been limited, the results have not reached the reproducible level.

WOS: 000440119900050 In recent years, studies have been conducted on systems based on wireless sensor networks for the detection of animal behaviors. These systems can offer significant information on how to increase the production and animals' health. They consist of low-cost sensor nodes with limited resources. One of the critical resources is the power emit. These systems have an energy problem especially in outdoor environments same as other wireless sensor-based systems. ZigBee-based RF modules are used for data transmissions in these systems. Hence, they have limited battery and memory. To fulfill the requirements of power reduction, this paper proposes a technique based on time-driven systems for controlling the transmission rate of ZigBee-based RF modules based on data aggregation and sleep/wake-up methods. Data aggregation is done in many cases. However, the sleep/wake-up method is related to animal behavior because it may cause changes in the network topology. The proposed system is implemented on cows and the results show that the proposed system can help to achieve a significant reduction in power consumption of wireless sensor networks and improve the lifetime. In additional, it can offer and help to liable of animals in monitoring the health of their animals.

In recent years, the process of learning creatures is converted to one of the new research area. These researches are divided into two general categories that one of them is based on proposing a solution and learning based methodology to any machines. Learning is defined as changes made in the performance of a system based on experiences. The most prominent features of learning-based systems are that they improve themselves over time. Therefore, learning based machines have a big role in these systems. However, they are not very productive in some application and research areas such as smart real time systems especially. In this paper is proposed a new approach based on reinforcement learning technique that has three versions in order to implementation in different areas. It behaviors based on reward and penalty model. The effectiveness of these interactions with the environment is evaluated by the maximum (minimum) of the number of rewards (penalty) taken from the environment. The main advantage of the reinforcement learning over other learning methods is the need for no information from the environment (except amplification signal). The other learning methods as supervised or unsupervised are not appropriate to these problems. In this method, each agent decides the next its actions based on current k-actions instead of one action. The three versions are simple, sequential and unstructured linear learning methods so they evaluated in different possibilities to get the appropriate responses. Depending on the needs of any system, they can be used. The mode of convergence of actions in the proposed automaton (machine) in six different scenarios is examined.

This paper utilises flags to decrease the drag around a short finite circular cylinder. Wall-adapted large eddy simulation and two-way fluid–structure interaction methods were applied to re...

This paper introduces three hybrid algorithms that help in solving global optimization problems using reinforcement learning along with metaheuristic methods. Using the algorithms presented, the search agents try to find a global optimum avoiding the local optima trap. Compared to the classical metaheuristic approaches, the proposed algorithms display higher success in finding new areas as well as exhibiting a more balanced performance while in the exploration and exploitation phases. The algorithms employ reinforcement agents to select an environment based on predefined actions and tasks. A reward and penalty system is used by the agents to discover the environment, done dynamically without following a predetermined model or method. The study makes use of Q-Learning method in all three metaheuristic algorithms, so-called RL I−GWO , RL Ex−GWO , and RL WOA algorithms, so as to check and control exploration and exploitation with Q-Table. The Q-Table values guide the search agents of the metaheuristic algorithms to select between the exploration and exploitation phases. A control mechanism is used to get the reward and penalty values for each action. The algorithms presented in this paper are simulated over 30 benchmark functions from CEC 2014, 2015 and the results obtained are compared with well-known metaheuristic and hybrid algorithms (GWO, RL GWO , I-GWO, Ex-GWO, and WOA). The proposed methods have also been applied to the inverse kinematics of the robot arms problem. The results of the used algorithms demonstrate that RL WOA provides better solutions for relevant problems.

IoT (Internet of Things) ya da diğer adıyla Nesnelerin İnterneti kavramı,internete bağlanan ve diğer cihazlarla iletişimde olan her nesneyikapsamaktadır. Artık hayatımızın bir parçası haline gelecek otonom araçlar,akıllı buzdolabılar, akıllı çamaşır makineleri, akıllı tost makineleri, akıllısaatler gibi birçok IoT cihazı birbiriyle farklı kablosuz ağ teknolojilerini kullanarakhaberleşebilirler. IoT cihazların birçok kritik alanda kullanılmasıylabirlikte IoT güveniğine karşı yapılan saldırılar artmıştır. Bu saldırılar IoT katmanlarına yapılarak veri gizliliği,veri bütünlüğü, veri tazeliği, veri erişilebilirliği, kimlik doğrulama gibikriterler ihlal edilebilmektedir. Bu saldırıları önlemek amacıyla birçokgüvenlik çözümü önerilmiştir, fakat sınırlı enerji, kısıtlı batarya süresi, zayıf işlemci gücü vesınırlı hafıza gibi sınırlamalardan dolayı düşük güçlü IoT cihazlar üzerinde gelenekselgüvenlik yöntemlerinin uygulanması mümkün değildir. Bu çalışmada, IoTcihazların güvenliğini tehdit eden saldırılar incelenerek, ağ katmanlarına göredetaylı şekilde sınıflandırılmış ve savunmateknikleri önerilmiştir., Internet of Things (IoT)covers every object that connects to the Internet and communicates with otherdevices. Many IoT devices, such as autonomous vehicles, smart refrigerators,smart washing machines, smart toasters, smart watches that can become part ofour lives and they can communicate with each other using different wirelessnetwork technologies. Because of using IoT devices in many critical areas,attacks against IoT security have increased. By making these attacks on IoTlayers, criteria such as data privacy, data integrity, data freshness, dataaccessibility and authentication can be violated. Some security solutions have beenproposed to prevent these attacks, but it is not possible to apply traditionalsecurity methods on low-power IoT devices due to some constraints such aslimited energy, limited battery time, limited computational power and limitedmemory. In this paper, attacks that threaten the security of IoT devices areexamined and classified according to network layers and defense techniques areproposed.

Abstract Background The RNA-protein interactions play crucial roles in the biological processes. Recent developments to clarify RNA and protein structural features have the urgent need for designing various databases, related to the specificity and the mechanism of the underlying interactions between a protein and an RNA molecule. The majority of these databases have focused on RNAs or proteins macromolecules independently, and they do not have the capability to run integrated queries on the RNA-protein complex. Theses existing databases have a linear query structure. Furthermore, they only focus on interacting (positive) samples and they do not contain non-interacting (negative) samples. Results We developed a Database for RNA-Protein Interaction Network Analysis and Aptamer Design (RPINaptaBASE). RPINaptaBASE has a nested query approach that enables users to apply nonlinear query analysis. The query engine module contains a wide range of features related to RNA and protein sequences and secondary structure elements of these macromolecules, which are helpful to generate custom datasets, especially for machine learning approaches. In this version, more than 175 features were calculated and available to users. It provides a web interface with download management services allowing users to generate desired datasets of unique RNA or protein sequences in independent lists. Furthermore; the web service empowers users to create artificial datasets of positive and negative samples from RNA-protein complexes. In order to present negative samples, the idea of distinguishing protein sequences by their clans and families was employed to efficiently generate non-interacting pairs. Conclusion This database prepares a user-friendly platform to study RNA-protein interactions. It also provides an important simplified contribution to the oligonucleotide-aptamer design process using machine learning algorithms. RPINaptaBASE is freely available at http://rpinbase.com

Wireless sensor networks have gained the attention of researchers from various fields due to increased applicability. This has thus led to rapid development in the field. However, these networks still suffer from various challenges and limitations. These range from computation and processing power and available energy to mention but a few. These problems are even much more pronounced in some areas of the field such as real-time Internet of Things-based applications. In this study, a dynamic protocol that efficiently utilizes the available resources is proposed. The protocol employs five developed algorithms that aid the data transmission, neighbor, and optimal path finding processes. The protocol can be utilized in, but not limited to, real-time large-data streaming applications. The protocol is implemented on sensor nodes that are custom made by our research team. In this article, a structure that enables the sensor devices to communicate with each other over their local network or Internet as required in order to preserve the available resources is defined. Both theoretical and experimental result analyses of the entire protocol in general and individual algorithms are also performed. © The Author(s) 2019.