Altınbaş University Institutional Repository
Not a member yet
5805 research outputs found
Sort by
SCEN-SCADA Security: An Enhanced Osprey Optimization-Based Cyber Attack Detection Model in Supervisory Control and Data Acquisition System Using Serial Cascaded Ensemble Network
No full textA significant role of Supervisory Control and Data Acquisition (SCADA) systems is to support the operation of the energy system, where Information and Communication Technology (ICT) is utilized to interconnect devices, and this increases the system complexity. The interconnection of SCADA systems increases complexity and the potential for cybersecurity vulnerabilities. In addition, the SCADA networks with legacy devices are affected by inherent cybersecurity deliberation that has provided severe cybersecurity vulnerable points. With the adoption of local-area networks and Internet Protocol (IP)-driven proprietary, malicious or unauthorized user accesses the information from outside sources, and hence, the SCADA systems are weakened by the elaborate attacks. SCADA systems need to deliberate the Denial of Service (DoS) and catastrophic failure and maloperation, which may subsequently compromise the safety and stability of the operations in the power system. Therefore, the pertinent priority in SCADA is to strengthen cybersecurity to guarantee reliable operation, and also, the system stability is governed concerning communications integrity. The smart grid features are used in the conventional machine learning approaches for identifying cyber attacks. Hence, implementing an efficient and accurate cyber attack detection approach with less computational overhead is still a crucial research problem in SCADA. So, a novel and secure model for cyber attack detection in the SCADA system using advanced deep learning techniques together with the heuristic algorithm is executed in this research work. The SCADA data are collected from various power grids. The features from these data are optimally selected and fused with the optimal weights to obtain the weighted optimal features. The weighted optimal feature selection is done using the Enhanced Osprey Optimization Algorithm (EOOA). These optimally selected weighted features are given to the Serial Cascaded Ensemble Network (SCEN) to obtain the final detection output. The developed SCEN is made with the cascading of Autoencoder, Dilated Bidirectional Long Short Term Memory (Bi-LSTM), and Bayesian classifier. The parameters in the SCEN are tuned using the executed IOOA. The final detection of the presence or absence of a cyber attack is evaluated by this SCEN. The performance and the efficiency of the developed framework are confirmed and contrasted by conducting various experiments
Impact of Climate Change on Evaporation in Mosul Dam Reservoir-Iraq
No full textVolume editors : Obaid A.J., Alkhafaji M.A.Water resources in Iraq are considered one of the elements most affected by climate change, especially water bodies, and the loss of water from reservoirs by evaporation is one of the most losses that occur in semi-arid countries. Hence, a study of a subject in this regard is very necessary, so the Mosul Dam reservoir was taken to study the effects of change So we researched this with a detailed analysis of climatic data from 1990-2020. We found the reality of the effect of each climatic element on the evaporation element. We linked five of the climatic elements to one mathematical model to find the value of evaporation from them, and finally we made predictions for some Main climatic elements. The results showed that the reservoir loses about 0.9 billion cubic meters annually through evaporation, and the results of the analysis of evaporation data indicated that its rates were increasing and reached a difference of 13.6% over 30 years, and from the results of the strength of the correlation between the climatic elements with evaporation by the SPSS program, it was found The temperature represents the greatest effect on evaporation in a direct way, then the inverse effect of humidity, and the direct effect of the number of hours of sunshine, and the effect of the rain was inverse of medium intensity, after that a mathematical model of evaporation was made in Mosul Dam Reservoir and its R-square was 95.6%, and the results also showed The storage volume was decreasing during the study years. Due to the great importance of the two elements of temperature and rain, a prediction was made for the data of temperature rates through the SDSM program, and it found that it continues to rise, so about 2050 it will reach an average temperature that is 0.3C0 higher than the average in the year 2023, the data that was predicted for rain recorded a continued decrease in its quantities, as it will be 4.9% less than it is in 2023, and less than about 50% compared to what it was in 1990
Optimum design of liquefied petroleum gas (LPG) composite hybrid and non-hybrid cylinders by genetic algorithm for maximum failure pressure
Get PDFOptimizing the design of composite cylinders is crucial for balancing structural integrity, weight reduction, and cost-effectiveness, especially with the widespread use of fiber-reinforced materials in many engineering applications. This study presents a novel approach using Genetic Algorithms to optimize liquefied petroleum gas (LPG) composite cylinders for maximum failure pressure by MATLAB software. Inspired by natural selection, the Genetic Algorithm efficiently explores design variations, considering different materials and cylinder geometries. The main goal of this study is to find the best ply angle and stacking sequence to maximize failure pressure for hybrid and non-hybrid composite cylinders. The maximum stress and Tsai–Wu criteria are used together to predict failure. The algorithm converges towards an optimal design through iterative generations, evaluated using fitness functions based on classical laminate theory. The results demonstrate the effectiveness of this approach in achieving an optimal design under mechanical and thermal loads. The optimization process exhibits strong sensitivity to the selected failure criterion, with the Tsai-Wu and Maximum Stress theories generating fundamentally different optimal configurations. For example, design I under mechanical loads, the Tsai-Wu failure criterion based GA finds that the optimal solution for carbon epoxy is [-89/-50/56/-50/-51/-503/563/-50/56/-50/57/-502/565/57/-502/56]s. In contrast, for the maximum stress failure criterion based GA, the optimal solution is [512 /-50/512/-502/51/-50/51/-50/522/-502/523/-502/52/-50/51/-503]s. The analysis under combined mechanical and thermal loading highlights significant performance constraints driven by temperature variations, uncovering distinct operational regimes. Within a limited thermal range, several viable stacking sequences are achievable; however, outside this window, only simplified—yet less optimal—designs remain feasible. For example, carbon epoxy, both GA identified that [9026]s is the optimal configuration. Numerical findings provide insights for hybrid and non-hybrid composite cylinders, assessing the best design based on cylinder structural efficiency and the cylinder cost
Support Vector Machines (SVM) in Traffic Prediction for Intelligent Transportation Systems- A comprehension Review
No full textConference name : 7th International Congress on Human-Computer Interaction, Optimization and Robotic Applications, ICHORA 2025
Conference city : Ankara
Conference date : 23 May 2025 - 24 May 2025
Conference code : 209351The Intelligent Transportations System has garnered interest due to rising road safety and effectiveness demands in more interconnected road networks. Traffic prediction is an integral component of ITS and may aid in numerous areas, including road routing and congestion reduction. So, many people in the research community are interested in intelligent transportation systems. Only a few review articles have addressed this topic. This paper presents a comprehensive literature review of support vector machines (SVMs), evaluation, classification, and essential concepts of recent literature sources. It also provides valuable information to transportation application researchers and developers. There is ongoing research into the potential uses of the SVM, a trustworthy and efficient classification method in machine learning. This work has addressed the utilization of the SVM classifier by reviewing several papers. This article summarizes the research on using support vector machines (SVMs) to forecast path obstacles. After a comprehensive analysis and thoughtful topic selection, the findings reveal all the unsolved problems and produce some significant discoveries that could be considered good future research directions
Forecasting of Electrical Energy Consumption Using Hybrid Models of GRU, CNN, LSTM, And ML Regressors
No full textElectricity consumption predictions for a long period are critical in the institutions that distribute the electricity and governmental or private entities that supply the electricity. It guarantees optimum energy utilization and aids in making strategic decisions for improving the energy production quality. This need is especially important in nations like Iraq, which has suffered from energy crises for many years. This study uses daily household electricity consumption data acquired from the Ministry of Electricity in Iraq, namely the Rusafa area of Baghdad, from 2022 to 2024. Weather data for the same years was also included, which contains external weather factors such as temperature, humidity, and solar radiation that directly influence consumption patterns. This paper proposes a hybrid forecasting model that utilizes advanced deep learning architectures LSTM and CNN-based deep learning architectures for forecasting along with an upgraded stacked hybrid model that employs CNN, GRU, Stacked Bi-LSTM, and machine learning regressors, such as XGBoost Regressor, and LightGBM Regressor. These models are being trained to improve accuracy in the forecast and to improve energy acoustic production strategies. The 30 epochs were trained and evaluated on the proposed model using the mean relative absolute error (MAPE) and mean root mean square error (RMSE) to examine the prediction quality. Among all models tested, the best performance was achieved using LightGBM regressor in our hybrid model with MAPE and RMSE of periodic forecasts for the next spilled of time being 0.185155 and 0.094603, respectively. The results show the potential of hybrid modeling techniques for energy forecasts and electricity distribution systems optimization
Maturity Model for Corporate Sector Based on Zero Trust Adoption
No full textThe rapid evolution of cybersecurity threats necessitates the adoption of robust security frameworks. One such approach gaining significant attention is the concept of zero trust, which emphasizes continuous and strong verification, strict access controls and identity management, and well-planned strategy and assessment to mitigate risks. However, organizations often face challenges in effectively implementing and assessing their progress in zero trust adoption. We propose a maturity model for zero trust adoption, designed to assist organizations in evaluating their current security posture, identifying gaps, and developing a roadmap for achieving higher levels of zero trust maturity. The model encompasses various dimensions, including network segmentation, access controls, data protection, and incident response. Additionally, a comprehensive set of self-assessment queries is provided to enable organizations to gauge their progress and identify areas for improvement. Through the utilization of this maturity model and self-assessment framework, organizations can enhance their understanding of zero trust principles, align their security strategies, and prioritize necessary investments to strengthen their overall security posture
Simulation and Optimization of the Antenna Designs for Glucose Biosensing FRET Mechanisms in Endoscopic Capsules
Get PDFAn optimized design of photodetectors and antennas for Förster Resonance Energy Transfer (FRET)-based glucose biosensing in endoscopic capsules is presented. The compact antenna design is tailored for the visible optical frequencies (~526 THz) associated with FRET-based glucose monitoring and integrates structural flexibility to conform to the spatial constraints of endoscopic capsules, such as mechanical bending features. The antenna is embedded in a multimode medium artificial tissue simulating a glucose environment with several layers, providing efficient coupling to the FRET emission signal for glucose sensing. Stable S11 parameters and a maximum gain of 9 dBi are realized by statelier mesh settings, bend adaptation, and cautious SAR constraint handlers. Results of the Specific Absorption Rate (SAR) confirm the limited energy absorption within permissible bounds, confirming its application for biomedical purposes. These results affirm the feasibility of non-invasive glucose measurement in interstitial fluid in this configuration that can be operable through an endoscope with improved sensitivity and functionality
Investigate Schizophrenia Classification Based on EEG Electrode Reduction Using Machine Learning Techniques
Get PDFSchizophrenia is a mental disorder condition that causes patients to become distracted from reality. Over time, the patient loses his cognitive and social abilities to communicate with the outside world. Due to machine learning's strong ability to analyze complicated brain data, it has become an increasingly important tool in recent years. This study considers the brain's neurologic signals in the resting state in two scenarios to classify schizophrenia disease by electroencephalography (EEG). The performed scenarios were to investigate the impact of selecting electrodes randomly (5 electrodes and 8 electrodes) and comparing it with applying the principal component analysis (PCA), utilizing four algorithms to extract features: Fast Fourier Transform (FFT), Approximate Entropy (ApEn), Log Energy Entropy (LogEn), and Shannon Entropy (ShnEn). We used publicly available datasets with 19 EEG channels consisting of two classes, which are schizophrenia and health control, using a one-second epoch window size. We applied a band-pass filter to decompose the EEG signals into five sub-bands. Also, the L2-normalization method has been applied to the derived features, which positively impacted the outcomes. The features were applied to three classifiers named K-nearest neighbor (KNN), support vector machine (SVM), and quadratic discriminant analysis (QDA). From all the scenarios, the five-electrode with random selection showed remarkable results of 99% using the SVM classifier in all evaluation metrics with LogEn+ Bandpass features
Employing Innovative Energy-Saving and Optimization Techniques for A Zero-Energy Consumption Building: A Case Study in Turkey
No full textArticle number : 040020
Volume editors : Albaker B.M., Ali R.M., Kwad A.M.
Conference name : International Research Conference on Engineering and Applied Sciences 2023, IRCEAS 2023
Conference code : 208810This research was guided to identify various vital contributions and beneficial impacts of innovative energy-saving methods and modern energy-efficient approaches to minimize excessive energy consumption in facilities based on other evaluation methods that were not employed greatly or addressed broadly in the current literature, namely MATLAB and Python Simulation processes. To achieve the goal of this article, a case study was considered and analyzed, representing a building in Turkey (240 m2) with significant cooling demands requiring to be optimized and mitigated, helping provide a zero-energy consumption facility that relies only on passive cooling techniques and thermal insulation materials. Simulations and optimization procedures were adopted to explore critical gains of energy-saving mechanisms using Python and MATLAB. According to the numerical research outcomes and simulation work, the research revealed that utilizing modern and practical energy-saving approaches could reduce harmful relative humidity values from 60.4% to 25.1%, corresponding to active prevention of mold, mildew, and microbes. Also, the overall internal temperature declined from 29.8 ºC to 21.3 ºC, and cooling load reduction from 216.8 kW to 99.5 kW, before and after implementing functional energy efficiency solutions, respectively. Furthermore, it was determined that deploying those novel energy-saving technologies, passive cooling and heating, and functional insulation materials would reduce the overall annual budget needed for cooling requirements from 103.1 USD to 49.7 USD. These aspects, in turn, could fulfill beneficial thermal comfort and alleviate the yearly generation of Greenhouse Gas (GHG) emissions and make this facility more ecologically friendly and sustainable
Effect of genetic mutations on outcomes of stem cell transplantation in children with hemophagocytic lymphohistiocytosis
No full textPrimary hemophagocytic lymphohistiocytosis (p-HLH) can be cured with allogeneic haematopoietic stem cell transplantation (allo-HSCT). It remains unclear whether HSCT outcomes are affected by the presence of different genetic mutations. We used data obtained from children who underwent allo-HSCT for HLH to examine the effects of genetic mutations on HSCT outcomes. Data from 153 paediatric patients in 18 paediatric stem cell centres were retrospectively evaluated. Patients were divided into four groups: 1) with PRF1 mutation (n = 46), 2) with UNC13D mutation (n = 38), 3) with STX11/STXBP2 mutation (n = 25) and 4) with Griscelli syndrome type 2/ Chediak–Higashi syndrome (GS2/CHS) diagnosis (n = 44). Statistical analysis showed no difference between the subgroups in terms of engraftment, VOD, acute GVHD, chronic GVHD, TRM, OS and EFS rates. The most important factor affecting OS and EFS in all genetic subgroups was remission status before HSCT. The 5-year EFS values for children with mutations in PRF1, UNC13D, STX11/STXBP2 and GS2/CHS were 71%, 66.6%, 74% and 66.7, respectively (log-rank >0.05). However, with prospective studies covering more patients, and creating different genetic subgroups by performing more detailed genetic analyses, special approaches for different genetic subgroups can be revealed in the future