Bilgisayar Mühendisliği Bölümü Yayın Koleksiyonu
Bu koleksiyon için kalıcı URI
Güncel Gönderiler
Öğe Analysis of cyber security knowledge gaps based on cyber security body of knowledge (Sep, 10.1007/s10639-022-11261-8, 2022)(Springer, 2022) Catal, Cagatay; Ozcan, Alper; Donmez, Emrah; Kaşif, AhmetThe correct affiliation of Emrah Donmez is "Department of Software Engineering, Bandirma Onyedi Eylul University, Balikesir, Turkey".The original version has been corrected.Öğe Adaptation of the Four Levels of Test Maturity Model Integration with Agile and Risk-Based Test Techniques(MDPI, 2022) Unudulmaz, Ahmet; Cingiz, Mustafa Özgür; Kalipsiz, OyaMany projects that progress with failure, processes managed erroneously, failure to deliver products and projects on time, excessive increases taking place in costs, and an inability to analyze customer requests correctly pave the way for the use of agile processes in software development methods and cause the importance of test processes to increase day by day. In particular, the inability to properly handle testing processes and risks with time and cost pressures, the differentiation of software development methods between projects, the failure to integrate risk management, and risk analysis studies, conducted within a company/institution, with software development methods also complicates this situation. It is recommended to use agile process methods and test maturity model integration (TMMI), with risk-based testing techniques and user scenario testing techniques, to eliminate such problems. In this study, agile process transformation of a company, operating in factory automation systems in the field of industry, was followed for two and a half years. This study has been prepared to close the gap in the literature on the integration of TMMI level 2, TMMI level 3, and TMMI level 4 with SAFE methodology and agile processes. Our research has been conducted upon the use of all TMMI level sub-steps with both agile process practices and some test practices (risk-based testing techniques, user scenario testing techniques). TMMI coverage percentages have been determined as 92.85% based on TMMI level 2, 92.9% based on TMMI level 3, and 100% based on TMMI level 4. In addition, agile process adaptation metrics and their measurements between project versions will be shown, and their contribution to quality will be mentioned.Öğe Analysis of cyber security knowledge gaps based on cyber security body of knowledge(Springer, 2023) Catal, Cagatay; Ozcan, Alper; Donmez, Emrah; Kaşif, AhmetDue to the increasing number of cyber incidents and overwhelming skills shortage, it is required to evaluate the knowledge gap between cyber security education and industrial needs. As such, the objective of this study is to identify the knowledge gaps in cyber security graduates who join the cyber security workforce. We designed and performed an opinion survey by using the Cyber Security Knowledge Areas (KAs) specified in the Cyber Security Body of Knowledge (CyBOK) that comprises 19 KAs. Our data was gathered from practitioners who work in cyber security organizations. The knowledge gap was measured and evaluated by acknowledging the assumption for employing sequent data as nominal data and improved it by deploying chi-squared test. Analyses demonstrate that there is a gap that can be utilized to enhance the quality of education. According to acquired final results, three key KAs with the highest knowledge gap are Web and Mobile Security, Security Operations and Incident Management. Also, Cyber-Physical Systems (CPS), Software Lifecycles, and Vulnerabilities are the knowledge areas with largest difference in perception of importance between less and more experienced personnel. We discuss several suggestions to improve the cyber security curriculum in order to minimize the knowledge gaps. There is an expanding demand for executive cyber security personnel in industry. High-quality university education is required to improve the qualification of upcoming workforce. The capability and capacity of the national cyber security workforce is crucial for nations and security organizations. A wide range of skills, namely technical skills, implementation skills, management skills, and soft skills are required in new cyber security graduates. The use of each CyBOK KA in the industry was measured in response to the extent of learning in university environments. This is the first study conducted in this field, it is considered that this research can inspire the way for further researches.Öğe A Firewall Policy Anomaly Detection Framework for Reliable Network Security(IEE, 2021) Togay, Cengiz; Kaşif, Ahmet; Catal, Cagatay; Tekinerdogan, BedirOne of the key challenges in computer networks is network security. For securing the network, various solutions have been proposed, including network security protocols and firewalls. In the case of so-called packet-filtering firewalls, policy rules are implemented to monitor changes to the network and preserve the required security level. Due to the dramatic increase of devices, however, and herewith the rapid increase of the size of the policy rules, firewall policy anomalies occur more frequently. This requires careful implementation of the policy rules to ensure cost-efficient solutions for anomaly detection to support network security. In this study, we present an anomaly detection framework for detecting intrafirewall policy anomaly rules. The framework supports the simulation of packets through the firewall ruleset for validating and enhancing the security level of the network. The framework is validated using four different types of firewall policy anomalies. Experimental results demonstrate that the framework is effective and efficient in detecting firewall policy anomalies.Öğe The Investigation of the Success of Different Machine Learning Methods in Breast Cancer Diagnosis(Düzce Üniversitesi, 2021) Ates, Ibrahim; Bilgin, Turgay TugayObjective: The aim of this study is to identify cancer earlier in life using machine learning methods. Methods: For this purpose, the Wisconsin Diagnostic Breast Cancer dataset was classified using Naive Bayes, decision trees, artificial neural networks algorithms and comparison of these machine learning methods was made. KNIME Analytics Platform was used for applications. Before the classification process, the dataset was preprocessed. After the preprocessing stage, three different classifier methods were applied to the dataset. Accuracy, sensitivity, specificity and confusion matrices were used to measure the success of the methods. Results: The results show that Naive Bayes and artificial neural network methods classify tumors with 96.5% accuracy. The success of the decision tree method in classification was 92.6%. Conclusions: The machine learning algorithms can be used successfully in breast cancer diagnosis to determine whether the tumors are malign or benign.Öğe A New Approach to Minimize Memory Requirements of Frequent Subgraph Mining Algorithms(Gazi Universitesi, 2021) Bilgin, Turgay TugayFrequent subgraph mining (FSM) is a subsection of graph mining domain which is extensively used for graph classification and graph clustering purposes. Over the past decade, many efficient FSM algorithms have been developed. The improvements generally focus on reducing time complexity by changing the algorithm structure or using parallel programming techniques. FSM algorithms have another problem to solve, which is the high memory consumption. In this study, a new approach called Predictive Dynamic Sized Structure Packing (PDSSP) have been proposed to minimize the memory requirement of FSM algorithms. Proposed approach redesigns the internal data structures of FSM algorithms without any algorithmic modifications. PDSSP has two contributions. The first one is the Dynamic Sized Integer Type (ds_Int) which is a newly designed unsigned integer data type. The second contribution is "Data Structure packaging" component that uses a data structure packing technique which changes the behaviour of the compiler. A number of experiments have been conducted to examine the effectiveness and efficiency of the PDSSP approach by embedding it into two state-of-art algorithms called gSpan and Gaston. Proposed implementation have been compared to the official one. Almost all results show that the proposed implementation consumes less memory on each support level. As a result, PDSSP extensions can save memory and the peak memory usage may decrease up to 38% depending on the dataset.Öğe Securing Internet of Things Networks with Gateways and Multi-SSID Technology(Institute of Electrical and Electronics Engineers Inc., 2021) Kaşif, Ahmet; Toğay, Cengiz; Levi, AlbertThe Internet of Things (IoT) technology has entered our lives with industry and smart home technologies, and today it has started to be used in fields such as health, finance, transportation, energy and space research. Existing security solutions for IoT devices with limited hardware capacity do not provide integrated protection. In this study, it is aimed to increase the security of the IoT devices in the local network and the confidentiality of the data produced within the system by supporting the multiple SSID feature of the routers with the controller application placed on the gateway. Wireless communication security and packet transmission performance at the physical, network and application layers of the proposed architecture have been tested in real world conditions. Another contribution of the presented study is to limit the communication of devices with other devices in their own networks and with the external network in the light of the information defined by the manufacturer on a device basis. The results show that the proposed system offers a secure and performance efficient solution for protecting IoT environments in the local network.Öğe Novel Approach to Minimize the Memory Requirements of Frequent Subgraph Mining Techniques(John Wiley and Sons Inc, 2021) Bilgin, Turgay Tugay; Murat, OğuzFrequent subgraph mining (FSM) is a subset of the graph mining domain that is extensively used for graph classification and clustering. Over the past decade, many efficient FSM algorithms have been developed with improvements generally focused on reducing the time complexity by changing the algorithm structure or using parallel programming techniques. FSM algorithms also require high memory consumption, which is another problem that should be solved. In this paper, we propose a new approach called Predictive dynamic sized structure packing (PDSSP) to minimize the memory needs of FSM algorithms. Our approach redesigns the internal data structures of FSM algorithms without making algorithmic modifications. PDSSP offers two contributions. The first is the Dynamic Sized Integer Type, a newly designed unsigned integer data type, and the second is a data structure packing technique to change the behavior of the compiler. We examined the effectiveness and efficiency of the PDSSP approach by experimentally embedding it into two state-of-the-art algorithms, gSpan and Gaston. We compared our implementations to the performance of the originals. Nearly all results show that our proposed implementation consumes less memory at each support level, suggesting that PDSSP extensions could save memory, with peak memory usage decreasing up to 38% depending on the dataset.Öğe Clustered mobile data collection in WSNs: An energy-delay trade-off(Turkiye Klinikleri, 2021) Şentürk, İzzet FatihWireless sensor networks enable monitoring remote areas with limited human intervention. However, the network connectivity between sensor nodes and the base station (BS) may not be always possible due to the limited transmission range of the nodes. In such a case, one or more mobile data collectors (MDCs) can be employed to visit nodes for data collection. If multiple MDCs are available, it is desirable to minimize the energy cost of mobility while distributing the cost among the MDCs in a fair manner. Despite availability of various clustering algorithms, there is no single fits all clustering solution when different requirements and performance metrics are considered. Depending on the available wireless communication technology, the MDCs may or may not be required to visit the BS to forward the collected data. This paper considers both cases and suggests clustering algorithms for various performance metrics including the energy consumption and the maximum travel time.Öğe Energy load forecasting using a dual-stage attention-based recurrent neural network(MDPI, 2021) Ozcan A.; Catal C.; Kaşif, AhmetProviding a stable, low-price, and safe supply of energy to end-users is a challenging task. The energy service providers are affected by several events such as weather, volatility, and special events. As such, the prediction of these events and having a time window for taking preventive measures are crucial for service providers. Electrical load forecasting can be modeled as a time series prediction problem. One solution is to capture spatial correlations, spatial-temporal relations, and time-dependency of such temporal networks in the time series. Previously, different machine learning methods have been used for time series prediction tasks; however, there is still a need for new research to improve the performance of short-term load forecasting models. In this article, we propose a novel deep learning model to predict electric load consumption using Dual-Stage Attention-Based Recurrent Neural Networks in which the attention mechanism is used in both encoder and decoder stages. The encoder attention layer identifies important features from the input vector, whereas the decoder attention layer is used to overcome the limitations of using a fixed context vector and provides a much longer memory capacity. The proposed model improves the performance for short-term load forecasting (STLF) in terms of the Mean Absolute Error (MAE) and Root Mean Squared Errors (RMSE) scores. To evaluate the predictive performance of the proposed model, the UCI household electric power consumption (HEPC) dataset has been used during the experiments. Experimental results demonstrate that the proposed approach outperforms the previously adopted techniques.Öğe A new parallel processing architecture for accelerating image encryption based on chaos(Elsevier Ltd, 2021) Yavuz, ErdemThis study introduces a novel parallel processing architecture for accelerating image encryption based on chaos. In the proposed architecture, whole image data is split into partitions of particular size to create separate encryption threads. As the proposed cryptosystem employs several identical chaotic ciphers running concurrently and independently to process the partitions, it greatly leverages the degree of parallelism to some extent. A powerful output mixing logic based on an additional chaotic function, and simple exclusive-OR and shift operations is innovatively incorporated to ensure inter-partition diffusion. Since there is no dependency on previous data bytes in the introduced logic, blending operations applied on the outputs of independent encryption threads can be concurrently executed by exploiting loop-level parallelism to the extent allowed by data processing units available. The number of blending operations that should be carried out for an image is kept proportional to the partition size which also directly determines the number of separate encryption threads created. In order to measure encryption/decryption runtimes, the proposed architecture has been tested on two different multi-core CPUs, namely 4-core and 8-core. The obtained results show that the proposed cryptosystem parallelising sequential operations by introducing a multi-threaded encryption architecture is much faster than the base cipher and most of the other state-of-the-art algorithms. Having successfully passed various security tests, the proposed cryptosystem manifests its robustness against cryptographic attacks, and hence become evident that it is efficient for secure transmission.Öğe Web Proxy Log Data Mining System for Clustering Users and Search Keywords(2017) Bilgin, Turgay Tugay; Aytekin, Mustafa KorayIn this study, Internet users were clustered by the search keywords which they type into search bars of search engines. Our proposed software is called UQCS (User Queries Clustering System) and it is developed to demonstrate the efficiency of our hypothesis. UQCS co-operates with the Strehl’s relationship based clustering toolkit and performs segmentation on users based on the keywords they use for searching the web. Internet Proxy server logs were parsed and query strings were extracted from the search engine URL’s and the resulting IP-Term matrix was converted into a similarity matrix using Euclidean, Jaccard, Cosine Distance and Pearson Correlation Distance metrics. K- Means and graph-based OPOSSUM algorithm were used to perform clustering on the similarity matrices. Results were illustrated by using CLUSION visualization toolkit.Öğe A Steiner Zone Approach for Mobile Data Collection in Partitioned Wireless Sensor Networks(2020) Şentürk, İzzet FatihWireless sensor networks (WSNs) typically operate in harsh environmental conditions. Hardware constraints and external damage from inhospitable surroundings leave the nodes susceptible to node failures. Depending on the damage scale, the network can be subject to partitioning which segments the network into multiple isolated connected components. A prompt reactive approach to restore network connectivity is to employ a mobile data collector (MDC) that visits and collects data from partitions periodically. Availability of the wireless data communication through multi-hop routing in a partitioned network complicates designating the shortest possible route for data collection. This paper regards the mentioned data collection problem as the Close-enough Traveling Salesman Problem (CETSP) and employs Steiner zone approach to designate respective data collection points for corresponding partitions. We have assessed the proposed approach in terms of the number of points visited for data collection and the total travel distance of the MDC. Obtained results indicate that the proposed approach can reduce the number of data collection points up to 67% and total travel distance up to 42%.Öğe Meme Kanseri Teşhisi İçin Yeni Bir Skor Füzyon Yaklaşımı(2019) Yavuz, Erdem; Eyüpoğlu, CanMeme kanseri tüm dünyada yaygın bir hastalık olması sebebiyle hastalığın erken teşhisi, hastaların bu hastalıktan tamamen kurtulabilmeleri açısından kritik öneme sahiptir. Hastalığın teşhisini kolaylaştırmak için tıp doktorları bilgisayar destekli uzman sistemlerden yararlanabilmektedir. Bu çalışmada meme kanseri veri örneklerini iyi huylu veya kötü huylu sınıflarına ayırmak için genel regresyon sinir ağı (Generalized Regression Neural Network-GRNN) ve ileri beslemeli sinir ağı (Feed Forward Neural Network-FFNN) temelli bir skor füzyon yöntemi önerilmiştir. Önerilen yöntem Wisconsin Teşhis Meme Kanseri (Wisconsin Diagnostic Breast Cancer-WDBC) veri seti üzerinde test edilmiştir. Bu iki temel ağın ve önerilen yöntemin kullanışlılığı incelenmiş ve performans sonuçları karşılaştırmalı olarak sunulmuştur. Önerilen yöntem sınıflandırma doğruluğu bakımından literatürde WDBC veri setini kullanarak yapılan mevcut çalışmalar ile kıyaslanmıştır. Elde edilen deneysel sonuçlar önerilen yöntemin, meme kanseri teşhisi için umut vadettiğini ve tıp uzmanlarının hastalığa ilişkin karar vermelerinde yardımcı bir araç olarak kullanılabileceğini göstermektedir.Öğe Performing similarity analysis on organic farming crop data of Turkish Cities(Institute of Electrical and Electronics Engineers Inc., 2020) Kaşif, Ahmet; Ortaç, Gizem; Ibis, E.; Bilgin, Turgay TugayOrganic crop production is an important technique which can help increase the quality and throughput of food production. In this study, similarity analysis of organic farming crop data of Turkish cities has been performed. The dataset has been collected from the web site of Turkish Ministry of Agriculture and Forestry. Some pre-processing techniques have been applied. Dynamic Time Warping distance has been used as a similarity metric. Results show that Dynamic Time Warping similarity is suitable for similarity detection of organic crop production. © 2020 IEEE.Öğe Intrinsic evaluation of word embeddings for Turkish(Association for Computing Machinery, 2020) Agun, Hayri Volkan; Yilmazel, O.Word embeddings are evaluated through intrinsic and extrinsic tests. Similarity and analogy test are mainly preferred for intrinsic evaluation and natural language processing tasks such as named entity recognition and question answering are prefferred for extrinsic evaluation. Although there are various intrinsic evaluation datasets for English, the datasets for Turkish are very limited and measuring the degree of similarity and relatedness between words without specifying the type of semantic relation. In this paper, we propose an intrinsic evaluation dataset for evaluating different semantic relations other than a synonym, antonym, hypernym, and meronym as well as morphological relations of individual Turkish words. Moreover, we benchmark three publicly available word-embedding models on the proposed dataset and discuss agglutinative characteristics of the Turkish language for language modeling. © 2020 ACM.Öğe An Electronic Control Unit for Erythrocyte Sedimentation Rate Test Device(Institute of Electrical and Electronics Engineers Inc., 2020) Sanver, U.; Yavuz, ErdemErythrocyte sedimentation rate test device, which is expensive as a commercial product, is a commonly used tools in the biomedical field. In this study, a low-cost and effective electronic control unit for erythrocyte sedimentation device was designed and implemented. This microcontroller-based control system manages the circular tray, where blood tubes stay on, for measuring sedimentation level using image processing technique. In order to manage the tray, control unit drives a stepper motor via switching components. Necessary information was transferred to computer via serial port communication in order to display to users. The position of circular tray is sensed for aligning camera and tubes. The measurement number data are taken to microcontroller from RFID Cards using RFID Transceiver. The unit controls also the amount of ambient light in the measurement area. The temperature level of device is measured using temperature sensor and step down by switching on a fan when necessary. © 2020 IEEE.Öğe Topological and biological assessment of gene networks using miRNA-target gene data(Institute of Electrical and Electronics Engineers Inc., 2019) Cingiz, Mustafa Özgür; Diri, B.In recent years, different biological data sets obtained by the next generation sequencing techniques have enhanced the analysis of the underlying molecular interactions of diseases. In our study we apply ARNetMiT, C3NET, WGCNA and ARACNE algorithms on microRNA-Target gene datasets to infer gene coexpression networks of breast, prostate, colon and pancreatic cancers. Gene coexpression networks are evaluated according to their topological and biological features. WGCNA based gene coexpression networks fits to scale free network topology more than other gene coexpression networks. In biological assessment there is no obvious difference found between gene coexpression networks which derived from different algorithms. © 2019 IEEE.Öğe A Prescient Recovery Approach for Disjoint MSNs(Ieee, 2017) Şentürk, İzzet FatihIn Mobile Sensor Networks (MSNs), limited transmission range of the sensor nodes requires nodes to collaborate with each other in order to send their data to the Base Station (BS) which acts as a gateway between the network and the remote user. However, nodes may fail arbitrarily due to battery depletion, hardware malfunction, or an external damage. Such failures may partition the network into multiple disjoint segments isolated from the rest of the network. To restore network connectivity, network topology can be restructured by employing node mobility. However, mobility incurs excessive energy consumption and must be limited to avoid further failures and extend the network lifetime. In this paper, we present a distributed mobility-based approach to restore network connectivity while minimizing the movement cost as well as the number of nodes to be relocated. While determining the movement target, we consider the former locations of the upstream nodes but designate an alternative spot for movement to avoid possible risks caused the failure and to minimize the movement cost. The experiment results indicate that the proposed approach outperforms the approaches currently used in terms of total movement distance, maximum movement distance and the number of relocated nodes.Öğe Deployment Algorithms to Simulate Large-scale Node Failures in Wireless Sensor Networks(Ieee, 2018) Şentürk, İzzet FatihWireless sensor networks (WSNs) enable monitoring surrounding physical phenomena in inhospitable environments through employing low-power sensor nodes with limited transmission range. A less resource-restricted base station (BS) provides long-range wireless communication to connect the network with the remote user. Within the network, nodes form a multi-hop network to reach the BS. However, some of the nodes may fail arbitrarily and impair the network connectivity. Depending on the network topology and the damage scale, network can be divided into disjoint subsets where some of the nodes are isolated from the rest of the network. Consequently, data collected in remote partitions cannot be delivered to the BS and the coverage drops drastically. Such failures can be tolerated with one of the existing connectivity restoration algorithms. However, despite abundance of self-configuring fault-tolerance schemes, research on the relationship between the deployment scheme and the recovery cost is limited. This paper presents three different node deployment schemes to simulate large-scale node failures which lead to partitioning. We have also investigated the impact of deployment schemes on the cost of recovery.
