Scholarly Publications - Information Systems and Technologies
Permanent URI for this collectionhttps://hdl.handle.net/11693/115493
Browse
Recent Submissions
Item Open Access Precision in vitro propagation by integrating response surface methodology and machine learning for Glossostigma elatinoides (Benth) Hook. F(Springer, 2025-02-13) Özcan, Esra; Ali, Seyid Amjad; Aasim, Muhammad; Atar, Hasan HüseyinOptimization of in vitro organogenesis of Glossostigma elatinoides (Benth) Hook. f. was targeted in this study. The experiment was designed with the help of design of experiment (DOE) of response surface methodology (RSM) model. Murashige and Skoog (MS) basal salt, sucrose, and agar were used as input factors and a total of 15 runs were used for optimization. Results were analyzed by ANOVA and response surface regression analysis (RSRA) followed by prediction and validation via different machine learning (ML) models. Results of ANOVA revealed the impact of different combinations on output parameters. Results of RSRA illustrated the relationship between input and output parameters. Pareto chart analysis showed the significant impact of MS on clump diameter, fresh wt., and dry wt. Normal plot analysis illustrated the positive impact of MS on all output parameters and increased proportionally with MS concentration. Results of heatmap and network analysis also demonstrated the significance of MS on all output parameters. Comparison of ML models depicted the better performance of multilayer perceptron (MLP) model for rooting (R2 = 0.957), fresh wt (R2 = 0.806), and dry wt (R2 = 0.812). Conversely, the support vector regression (SVR) model demonstrated superior prediction for clump diameter (R2 = 0.809). Among the tested models, the SVR model showed the weakest performance, aside from clump diameter, while LightGBM achieved scores close to those of the RF and MLP models across all metrics. The findings clearly indicate that the adopted protocol is well-suited for the effective commercial propagation of the aquatic G. elatinoides plant.Item Open Access Machine learning modeling and response surface methodology driven antioxidant and anticancer activities of chitosan nanoparticle-mediated extracts of Bacopa monnieri(Elsevier BV, 2025-04-23) Bulut, Seyma; Aasim, Muhammad; Emsen, Buğrahan; Ali, Seyid Amjad; Aşkın, Hakan; Karataş, MehmetThis study investigates the potential of chitosan nanoparticles (CNPs) in enhancing the bioavailability and efficacy of Bacopa monnieri extracts, known for their neuroprotective, antioxidant, and anticancer properties. Different concentrations of CNPs were added to the culture medium for in vitro shoot regeneration. Antioxidant activity (DPPH free radical scavenging and $H_2O_2$ removal assays) and cytotoxicity assay (LDH release and XTT viability) were performed. The results demonstrated the highest DPPH radical scavenging activity of 95.60 % at 125 μg/mL CNPs from methanol extract. Whereas, $H_2O_2$ scavenging activity increased with higher extract concentrations, and the maximum was recorded from methanol extract when used at 1000 μg/mL. Cytotoxicity assays revealed a dose-dependent increase in LDH activity and XTT reduction, and water-based extracts demonstrated the strongest cytotoxic effects. IC50 analysis indicated that CNP-enriched methanol and water extracts were significantly more cytotoxic to HeLa cells as compared to ethanol extracts. Response surface regression analysis and ML models confirmed the reliability of the experimental data, with the multilayer perceptron (MLP) model exhibiting the best predictive accuracy, followed by the random forest (RF) model. It can be concluded that CNP enrichment significantly improved the antioxidant and anticancer properties of B. monnieri extracts, highlighting the potential of CNP-based formulations for future studies.Item Open Access Genetic algorithms assisted machine learning algorithms to optimize nano-phytoremediation of cadmium designed by response surface methodology(Taylor and Francis Ltd., 2025-03-07) Bas, Serpil; Aasim, Muhammad; Gumus, Numan Emre; Katırcı, Ramazan; Ali, Seyid Amjad; Karatas, MehmetAdvancements in nanotechnology and artificial intelligence can enhance phytoremediation efficacy, particularly in removing hazardous contaminants like cadmium (Cd). Experiment was conducted by using different concentrations of Cd and titanium dioxide (TiO2) NPs for different time periods, designed by design of experiment of with a total of 20 combinations. Response Surface Regression Analysis was used for data analysis to identify optimal input factors. Results revealed that TiO2 nanoparticles significantly improved the efficiency of phytoremediation by increasing Cd uptake. Cd absorption rates were predicted using machine learning models, and their performance was evaluated using R2 and MSE metrics. Moreover, the Genetic Algorithm (GA) was employed to minimize MSE between predicted and actual Cd absorption values. Ceratophyllum demersum showed an absorption capacity of 99.58%, with a remaining Cd concentration as low as 0.0199 mg/L. The Gaussian Process Regressor (GPR) was the most accurate predictive model with an R2 of 0.99 and MSE of 0.07. The Genetic Algorithm (GA) further optimized the process, identifying optimal NP concentration, Cd concentration, and treatment time. It was concluded that computational models exhibited enhanced Cd absorption due to a synergetic relationship between Cd concentration and treatment time, and absorption efficiency was further enhanced by the supplementation of TiO2 nanoparticles. © 2025 Taylor & Francis Group, LLC.Item Open Access Synergistic application of artificial intelligence and response surface methodology for predicting and enhancing in vitro tuber production of potato (Solanum tuberosum)(Public Library of Science, 2025-07-24) Thinakaran, Rajermani; Korkmaz, Ecenur; Ünver, Başak; Ali, Seyid Amjad; Iqbal, Zeshan; Aasim, MuhammadIn vitro regeneration of potato tubers is highly significant in modern agriculture as it offers efficient propagation, genetic enhancement, and pathogen-free seed production. This study aimed to optimize in vitro tuberization by manipulating key variables, including cultivar, sucrose concentration, and cytokinin-auxin interactions. Results were analyzed by response surface regression analysis (RSRA) of Response Surface Methodology (RSM), followed by data validation and prediction with machine learning (ML) models. Fontana cultivar exhibited superior tuberization performance, with a maximum tuberization rate of 75.6% from Murashige and Skoog (MS) medium supplemented with 90 g/L sucrose, 2 mg/L BAP, and 1 mg/L Indole-3-butyric acid (IBA). Sucrose concentration was the most significant factor for all growth parameters, particularly tuber size and weight. RSRA analysis confirmed the significance of the linear effects of sucrose and BAP on tuberization, while auxins primarily regulated tuber size and weight. Pareto chart analysis highlighted sucrose as the most influential variable for both cultivars. Heatmap and network plot analyses further illustrated strong positive correlations between sucrose, BAP, and tuber formation, whereas auxins exhibited comparatively weaker effects. Results analyzed by Machine learning (ML) models revealed maximum predictive accuracy for tuberization by Random Forest (RF) model with an R2 of 0.379. However, all other models also faced challenges with high error rates, indicating the need for improved feature engineering. This study concludes that optimizing sucrose concentration and BAP levels, combined with selective auxin application, and integration of RSM and AI presents a promising strategy for optimization and potentially improving large-scale commercial production of disease-free potato tubers.Item Open Access Biostimulant effect of seaweed extracts on micropropagation of important ground macrophyte Micranthemum tweediei and data-driven insights using machine learning and response surface regression(Springer Science and Business Media Deutschland GmbH, 2026-01-23) Özcan, Esra; Ali, Seyid Amjad; Asim, Muhammad; Atar, Hasan HüseyinCommercially viable in vitro cultivation of ornamental and aquatic plants depends heavily on the proper use of bio-stimulants that encourage healthy and uniform growth. This study explores the role of two seaweed extracts, Jania rubens and Cystoseira barbata, in promoting in vitro micropropagation of Micranthemum tweediei (Monte Carlo), a widely used aquatic plant. Culture medium was enriched with different concentrations (2.5–20.0%) of J. rubens and C. barbata extracts with 1–4 g L$^{−1}$ Murashige and Skoog (MS) nutrient media. Considering all results, J. rubens extract was more effective than C. barbata in terms of micropropagation and chlorophyll content of M. tweediei. Addition of 5% J. rubens extract to 2 g L$^{−1}$ MS medium (approx. half strength) resulted in a 47% increase in clump diameter (5.18 cm), a 173% increase in rooting rate (92.4%), and a 108% increase in shoot clump fresh weight (3.6 g), and 84%, 115%, and 87% increases in chlorophyll a, b, and total chlorophyll levels, respectively, compared to the control 2 g L$^{−1}$ MS medium without extract. Micropropagation parameters resulting from 4 g L$^{−1}$ MS (approx. full strength) supplemented with J. rubens extract were lower than those obtained from 2 g L$^{−1}$ MS. Unlike J. rubens, C. barbata showed the highest micropropagation when 10% extract was added to 4 g L$^{−1}$ MS nutrient medium, resulting in a clump diameter of 5.11 cm, 42.8% rooting, a fresh clump weight of 7.37 g, and a dry clump weight of 0.59 g. Propagated in vitro plants were easily acclimated to external conditions in aquariums. Results of response surface regression analysis (RSRA) confirmed the results, and MS concentration influenced the plant biomass and chlorophyll contents, whereas seaweed type and concentration regulated the clump diameter and rooting. Application of machine learning models validated and predicted the outcomes precisely. Multi-layer perceptron (MLP) model exhibited superior predictive accuracy for morphological traits, while more predictive accuracy of chlorophyll parameters was attributed to Random Forest (RF) model. This study has shown for the first time that aquatic plants can be micropropagated more successfully and at lower cost by adding seaweed extracts to in vitro nutrient media without the need for growth regulators.Item Open Access Artificial intelligence-driven validation of silver and titanium nanomaterials impact on morpho-chemical potential of industrial hemp (Cannabis sativa L.)(Springer Science and Business Media Deutschland GmbH, 2025-09-12) Akgur, Ozlem; Aasim, Muhammad; Ali, Seyid AmjadThe aim of this research was to assess the effect of titanium nanoparticles (TiO2NPs) and silver nanoparticles (AgNPs) on in vitro seedling emergence, seedling growth, and biochemical parameters of hemp Cv. Narlı. The seeds were introduced to different concentrations (0, 200, 400, 800, 1200, 1600 mg/L) of both nanoparticles, incorporated into the culture medium. The results showed that AgNPs supplementation had a positive effect on shoot length, root length, total length, fresh weight, chlorophyll-a (Chl-a), chlorophyll-b (Chl-b), total carotenoids (Car), and malondialdehyde (MDA). The greatest increase in seedling (%) and shoot:root ratio was recorded from the medium containing TiO2NPs. Furthermore, the supplementation of 800 mg/L AgNPs led to the highest outcomes in terms of root length, total length, and fresh weight. The values for Chl-a, Chl-b, and Car showed no significant variations, reaching their highest points in the medium supplemented with 1600 mg/L NPs. While MDA levels were also not statistically significant and maximum scores were noted at different doses of both NPs. The results were examined by generating a Pareto chart to discern the key influencing factors, and the response optimizer was applied to identify an optimal solution for the combinations of input variables. Finally, the Extreme Gradient Boosting (XGBoost), Random Forest (RF), and Multilayer Perceptron (MLP) based supervised machine learning models were employed to predict and verify the obtained results using three distinct performance criteria. The MLP model, overall, demonstrated superior performance in validation and prediction compared to RF and XGBoost, respectively.Item Open Access Machine learning models for optimization, validation, and prediction of light emitting diodes with kinetin based basal medium for in vitro regeneration of upland cotton (Gossypium hirsutum L.)(BioMed Central Ltd, 2025-05-14) Özkat, Gözde Yalçın; Aasim, Muhammad; Bakhsh, Allah; Ali, Seyid Amjad; Özcan, SebahattinBackground: Plant tissue culture has emerged as a tool for improving cotton propagation and genetics, but recalcitrance nature of cotton makes it difficult to develop in vitro regeneration. Cotton's recalcitrance is influenced by genotype, explant type, and environmental conditions. To overcome these issues, this study uses different machine learning-based predictive models by employing multiple input factors. Cotyledonary node explants of two commercial cotton cultivars (STN-468 and GSN-12) were isolated from 7–8 days old seedlings, preconditioned with 5, 10, and 20 mg·L$^{−1}$ kinetin (KIN) for 10 days. Thereafter, explants were postconditioned on full Murashige and Skoog (MS), ½ MS, ¼ MS, and full MS + 0.05 mg·L$^{−1}$ KIN, cultured in growth room enlightened with red and blue light-emitting diodes (LED) combination. Statistical analysis (analysis of variance, regression analysis) was employed to assess the impact of different treatments on shoot regeneration, with artificial intelligence (AI) models used for confirming the findings. Results: GSN-12 exhibited superior shoot regeneration potential compared with STN-468, with an average of 4.99 shoots per explant versus 3.97. Optimal results were achieved with 5 mg·L$^{−1}$ KIN preconditioning, ¼ MS postconditioning, and 80% red LED, with maximum of 7.75 shoot count for GSN-12 under these conditions; while STN-468 reached 6.00 shoots under the conditions of 10 mg·L$^{−1}$ KIN preconditioning, MS with 0.05 mg·L$^{−1}$ KIN (postconditioning) and 75.0% red LED. Rooting was successfully achieved with naphthalene acetic acid and activated charcoal. Additionally, three different powerful AI-based models, namely, extreme gradient boost (XGBoost), random forest (RF), and the artificial neural network-based multilayer perceptron (MLP) regression models validated the findings. Conclusion: GSN-12 outperformed STN-468 with optimal results from 5 mg·L$^{−1}$KIN + ¼ MS + 80% red LED. Application of machine learning-based prediction models to optimize cotton tissue culture protocols for shoot regeneration is helpful to improve cotton regeneration efficiency.Item Open Access Integrating machine learning and the GGE biplot for identification of climate-suitable grasspea genotypes(Frontiers Research Foundation, 2025-11-21) Barpete, Surendra; Das, Arpita; Parikh, Mangla; Yumnam, Sonika; Aasim, Muhammad; Ali, Seyid Amjad; Singh, Akanksha; Yadav, Ashutosh Kumar; Devate, Narayana Bhat; Kaul, Smita; Bhattacharya, Sudip; Roy, Soumyayan; Gupta, Sanjeev; Kumar, ShivGrasspea is a nutrient-rich food legume crop known for its resilience in the challenging agro-ecosystems. However, information is scanty regarding the recommendation of grasspea genotypes with respect to their suitability for both general and specific adaptations. The primary goal of the study was to delineate stable grasspea genotypes by nullifying the influence of intricate interactions among multiple traits with the environment. Additionally, the study aimed to identify suitable locations within diverse agro-climatic zones in India for future evaluation while also validating and predicting results using machine learning algorithms. From several hundred genotypes developed and tested in station trials at Amlaha, India, a panel of 64 diverse promising grasspea genotypes was identified, and their performance was subsequently assessed through multilocation testing at four diverse locations in India during 2021–2022 using the GGE biplot approach. Mean selection index of each genotype was enumerated considering multi-trait performance for better elucidation of genotype and environment ranking as well as selection of the mega-environment. The findings revealed that the environment was the primary contributor to variation across all studied traits, followed by genotype × environment interactions as the second most influential factor. Genotypes such as FLRP-B54-1-S2, Prateek, 31-GP-F3-S7, 31-GP-F3-S4, FLRP-B38-S5, 48-GP-F3-S3, and BANG-288-S2 were identified as good performers with promising multi-trait performance. Experimental results were validated using multiple performance metrics, with the Random Forest (RF) model of machine learning demonstrating superior predictive accuracy compared to the multilayer perceptron (MLP) model. Regression coefficient (R²) values ranged between 0.558 and 0.947, depending on the output variables. In conclusion, "Prateek," "31-GP-F3-S7," and "48-GP-F3-S3" emerged as the most stable genotypes when considering their combined yield-trait performance. These genotypes can be recommended for widespread commercial cultivation in regions where grasspea cultivation faces challenges of weather extremities.Item Open Access Exploring temporal machine learning approaches for predicting methane discharge in atmospheric studies(Institute of Electrical and Electronics Engineers Inc., 2025-09-24) Zebardast, Sara; Lassem, Nima Kamali; Ali, Seyid AmjadMethane levels in the atmosphere are rising, posing a serious challenge in the fight against climate change. Because methane is a powerful greenhouse gas, being able to accurately forecast its concentration is essential for making smart decisions about climate policy. Traditional ways of monitoring methane rely on direct measurements, which can be expensive and are often limited to certain areas. This study aims to explore how artificial intelligence algorithms (machine learning and deep learning) can help fill the gap. Using time series data from Alberta's methane warehouse, we tested and compared four different models: Random Forest, Extreme Gradient Boosting, Multilayer Perceptron and Temporal Convolutional Networks. We assessed how well each model predicted methane levels over time and how efficiently they handled the data. The findings offer insights into building more affordable and scalable systems for tracking and managing methane emissions, helping support better climate strategies.Item Open Access Coming to terms with the digital natives: understanding the marketing sensitivities of Genzers as hospitality consumers(2024-05-04) Yılmaz, Semih; Collins, Ayşe; Ali, Seyid Amjad; Berezina, K; Nixon, L; Tuomi, AAs "digital natives", GenZ is set apart from previous generations in terms of its online connectedness. Even though this generation is expected to be the prevailing customer base around the world by 2026, there is a noticeable lack of studies on GenZ's consumer characteristics within the hospitality context. This study investigates the marketing-related factors affecting GenZ's accommodation decisions as well as their consumer sensitivities to contemporary constructs such as brand uniqueness, social media presentability, sustainability consciousness, and cancel culture.Item Open Access Capital flows volatility and systemic risk in emerging markets: a case of Türkiye(World Scientific Publishing Co. Pte. Ltd., 2024-04) Ali, Seyid Amjad; Mahmud, Seyid Fahri; Yülek, Murat Ali; Akosman, Fatih FurkanUS sub-prime crisis in 2008–09 led the central banks undertake unconventional monetary policies. In turn, short-term and volatile capital flows into emerging markets surged significantly, reigniting an intense academic debate on the ability of the central banks in EMs to protect their financial markets from external shocks. This paper develops a partially integrated System Dynamics Model to simulate the impact of the capital flows on the dynamics of the nominal exchange rate in Türkiye. The results support the contention that several recent episodes of excessive depreciation of the Turkish Lira as well as the currency crisis of 2018 can be linked to the reversals of stocks of short-term FX liabilities. The model also integrates policy rate sub-module into the main model, allowing responses of the central bank to inflation and exchange rate as a feedback mechanism. The results of the module indicate that external factors may cause the central bank to loose monetary independence in order to maintain financial stability.Item Open Access Synergizing LED technology and hydropriming for intelligent modeling and mathematical expressions to optimize chickpea germination and growth indices(Springer New York LLC, 2024-03-29) Aasim, Muhammad; Akın, Fatma; Ali, Seyid AmjadThe influence of hydropriming and Light Emitting Diodes (LED) on germination and growth indices, followed by optimizing and validation via artificial intelligence-based models was carried out in this research. White LEDs (W-LEDs) were more effective by yielding the most effective growth indices, such as mean germination time (MGT) (1.11 day), coefficient of variation of germination time (CV t ) (20.72%), mean germination rate (MR) (0.81 day-1), uncertainty (U) (0.40 bit), and synchronization (Z values) (0.79); the optimum MGT (1.09 day), CV t (15.97%), MR (0.77 day-1), U (0.32 bit), and Z (0.55) values were found after 2 h of hydropriming, which was responsible for all efficient growth indicators. W-LEDs with 1 h hydropriming proved to be the ideal LED and hydropriming combination. Results on growth indices for in vitro seedlings were completely different from those on germination indices, and the most desirable germination indices were linked to red LEDs (R-LEDs). Whereas 4 h hydropriming was most effective for the post-germination process. Pareto charts, normal plots, contour plots, and surface plots were created to optimize the input variables. Finally, the data were predicted using Arificial Neural Network (ANN) inspired multilayer perceptron (MLP) and machine learning-based random forest (RF) algorithms. For both models, plant height was correlated with maximum R 2 values. Whereas, all output variables had relatively low mean absolute error (MAE), mean square error (MSE), and mean absolute percentage error (MAPE) scores, indicating that both models performed well. The results of this investigation disclosed a link between certain LEDs and hydropriming treatment for in vitro germination indices and plant growth.Item Open Access Phosphate-solubilizing fungus (PSF) - mediated phosphorous solubilization and validation through Artificial intelligence computation(Springer Dordrecht, 2024-11-02) Ölmez, Fatih; Mustafa, Zemran; Türkölmez, Şahimerdan; Bildirici, Aslıhan Esra; Ali, Seyid Amjad; Aasim, MuhammadPhosphate-solubilizing fungus (PSF) strain alaromyces funiculosus was investigated for phosphorus solubilization, utilizing a range of pH levels and phosphate sources, followed by data confirmation through artificial intelligence modeling. T. funiculosus strain was exposed to five different phosphate sources $[Ca_3(PO_4)_2$, $FePO^{4}$, $CaHPO^{4}$, $AlPO^{4}$, and phytin] at different pH levels (4.5, 5.5, 6.5, 7.0, and 7.5). ANOVA, Pareto charts, and normal plots were used for analyzing the data. Artificial intelligence-based multilayer perceptron (MLP), random forest (RF) and extreme gradient boosting (XGBoost) models were used for data validation and prediction. Five-fold more phosphate (P) solubility by T. funiculosus was registered as compared to the control. The maximum soluble P was found at pH 4.5 (318324 ppb) and $CaHPO^{4}$ (444045 ppb). Combination of phytin × 4.5 pH yielded the highest dissolved phosphorus (1537988 ppb), followed by 127458 ppb from the control × 4.5 pH. Pareto chart and normal plot analysis showedthe negative impact of pH (B), pH × F/C (fungus/control) × P-Source (ABC), and F/C (A) factor. Whereas pH × P-Source (AC) and P-Source (C) has positive impact on P solubility. The maximum $R^{2}$ scores showed the order of RF (0.944) > MLP (0.938) > XGBoost (0.899). T. funiculosus strain has a grain potential for sustainable use for different types of phosphate sources. Application AI/ML models based on different performance metrics predicted the validated the attained results. In future research, it is recommended to check the efficacy of developed strategy under field conditions and to check the impact on soil and plant.Item Open Access Evaluating higher education performance via machine learning during disruptive times: a case of applied education in Türkiye(Wiley, 2024-12) Yılmaz, Semih Sait; Collins, Ayşe; Ali, Seyid AmjadIn response to the COVID-19 pandemic, an abrupt wave of digitisation and online migration swept the higher education institutions around the globe. In the aftermath of this digital transformation which endures as the legacy of the pandemic, what lacks in knowledge is how effective the anti-COVID measures were in maintaining quality education. Using machine learning to analyse student grades as a proxy for educational standards, this study investigates and demonstrates the evaluative potential of machine learning (vs. traditional statistics) with respect to not only crisis responses in education but also applied studies such as Information Systems and Tourism. Main implication of this study is the analytical utility of machine learning even when educational data are irregular and small. However, incorporating accurate and meaningful data points into the existing online educational systems is crucial to leverage this utility of machine learning.Item Open Access A unified framework of response surface methodology and coalescing of Firefly with random forest algorithm for enhancing nano-phytoremediation efficiency of chromium via in vitro regenerated aquatic macrophyte coontail (Ceratophyllum demersum L.)(Springer, 2024-06-11) Ali, Seyid Amjad; Gümüş, Numan Emre; Aasim, MuhammadNano-phytoremediation is a novel green technique to remove toxic pollutants from the environment. In vitro regenerated Ceratophyllum demersum (L.) plants were exposed to different concentrations of chromium (Cr) and exposure times in the presence of titania nanoparticles (TiO2NPs). Response surface methodology was used for multiple statistical analyses like regression analysis and optimizing plots. The supplementation of NPs significantly impacted Cr in water and Cr removal (%), whereas NP × exposure time (T) statistically regulated all output parameters. The Firefly metaheuristic algorithm and the random forest (Firefly-RF) machine learning algorithms were coalesced to optimize hyperparameters, aiming to achieve the highest level of accuracy in predicted models. The R2 scores were recorded as 0.956 for Cr in water, 0.987 for Cr in the plant, 0.992 for bioconcentration factor (BCF), and 0.957 for Cr removal through the Firefly-RF model. The findings illustrated superior prediction performance from the random forest models when compared to the response surface methodology. The conclusion is drawn that metal-based nanoparticles (NPs) can effectively be utilized for nano-phytoremediation of heavy metals. This study has uncovered a promising outlook for the utilization of nanoparticles in nano-phytoremediation. This study is expected to pave the way for future research on the topic, facilitating further exploration of various nanoparticles and a thorough evaluation of their potential in aquatic ecosystems.Item Open Access Factors affecting architectural decision-making process and challenges in software projects: an industrial survey(John Wiley & Sons Ltd., 2025-01) Demir, Merve Ö.; Chouseinoglou, Oumout; Tarhan, Ayca K.Software architecture plays a fundamental role in overcoming the challenges of the development process of large-scale and complex software systems. The software architecture of a system is the result of an extensive process in which several stakeholders negotiate issues and solutions, and as a result of this negotiation, a series of architectural decisions are made. This survey study aims to determine the experiences of the software industry experts with respect to architectural decision-making, the factors that are effective in decision-making, and the technical and social problems they encounter. An online questionnaire-based survey was conducted with 101 practitioners. The responses were analyzed qualitatively and quantitatively. Analysis of responses revealed that the majority of the participants prefer to document some or all of the architectural decisions taken and to store these documents in web-based collaboration software. Decisions are usually made by teams of two or three, and discussion-based approaches (brainstorming and consensus) are adopted. In the software architecture decision-making process, “major business impact” is the most challenging situation. Information sharing and keeping track of decisions and decision rationale are areas in need of improvement as identified by most participants. From the participants' feedback and their answers to open-ended questions, we concluded that the software architecture decision-making process has an important role in the industry. Our key findings are that decisions made in the architectural decision-making process are taken by teams and generally all decisions are documented. In projects where decisions are made by a single person, peer pressure is found to be significantly different from pressure in projects where decisions are made by the group. This is an indication that as the number of people in the decision-making process increases, the disagreements also increase.Item Open Access A comparative and practical approach using quantum machine learning (QML) and support vector classifier (SVC) for Light emitting diodes mediated in vitro micropropagation of black mulberry (Morus nigra L.)(Elsevier BV, 2024-03-28) Aasim, Muhammad; Katırcı, Ramazan; Acar, Alpaslan Şevket; Ali, Seyid AmjadIn this study, in vitro regeneration protocol for black mulberry (Morus nigra L.) was optimized using 18 distinct combinations of benzylaminopurine (BAP) with either naphthalene acetic acid (NAA) or Indole butyric acid (IBA). The top two combinations were then utilized to optimize the light intensity given by light-emitting diodes (LEDs). Supplementation of 0.5 mg L-1 BAP and 0.25 mg L-1 IBA with 60 PPFD light intensity yielded a maximum regeneration coefficient (2.53), shoot length (6.01 cm), and number of leaves (10.73). The regenerated plantlets were rooted with IBA under in vitro conditions followed by successful acclimatization of plantlets under greenhouse conditions. The results were further investigated by linking them with an emphasis on improving the Support Vector Classifier (SVC) using quantum computing techniques, and this work embarked on a groundbreaking path to integrate the realms of machine learning (ML) with quantum computing. For this purpose, the traditional Support Vector Classifier (SVC) model was compared with quantum-enhanced algorithms, including SVC with the quantum kernel (SVC Qkernel), SVC with quantum features (SVC Qfeatures), Quantum Support Vector Classifier (QSVC), and the Variational Quantum Circuit (VQC). The quantum-enhanced models showed a range of results, indicating their complex and subtle character, whereas classical SVC performed robustly for multiple metrics. Quantum kernel-based SVC demonstrated an interesting trade-off between recall and precision, indicating its proficiency in processing particular data properties.Item Embargo Zeugodacus fruit flies (Diptera: Tephritidae) host preference analysis by machine learning-based approaches(Elsevier BV, 2024-07) Nazir, N.; Fatima, S.; Aasim, M.; Yaqoob, F.; Mahmood, K.; Ali, Seyid Amjad; Awan, S.I.; ul Haq, I.Detecting the host preference of highly polyphagous and economically significant pest species of fruit flies (Diptera; Tephritidae) is important for identifying their species status, their management in orchards and the international trade of fruits and vegetables. In the current study, three fruit fly species Zeugodacus tau, Z. signata, and Z. cucrbitae, (Diptera: Tephritidae) were evaluated for their oviposition preference among three host fruits: pumpkin, cucumber, and bitter gourd. The investigation was conducted under choice conditions in the laboratory. Fruit fly species and host fruits were used as input/predictive variables whereas, oviposition preference, number of pupae, weight of pupae, adult emergence, and sex ratio were used as output/response variables to test the host preference through an Artificial Neural Network ANN/machine learning (ML) algorithms. ANN-based on a Multi-Layer Perceptron (MLP) model and decision tree-based Random Forest (RF) models were employed. Results revealed that Z. tau preferred pumpkin > cucumber > bitter gourd in order, Z. cucurbitae preferred bitter gourd > pumpkin > cucumber in order and Z. signata also preferred pumpkin but followed by bitter gourd and cucumber for oviposition. The specific host preferences observed in both Z. tau and Z. signata suggest that they may not be distinct species but rather closely related siblings. These findings highlight host preference as a marker for species delimitation. Moreover, the machine learning (ML) tools, provide better prediction in identifying host preference than statistical methods. These results are discussed in the context of the importance of studying host preferences for fruit flies’ species delimitation, their management, and international trade of fruits and vegetables.Item Open Access Development of a web-based decision support nurse care management system: decision support-n-care(Lippincott Williams & Wilkins, 2024-12) Özduyan Kılıç, M.; Korkmaz, F.; Sevgi, Cüneyt; Chouseinoglou, Oumout; Alexander, SusanItem Open Access Artificial intelligence models for validating and predicting the impact of chemical priming of hydrogen peroxide (H2O2) and light emitting diodes on in vitro grown industrial hemp (Cannabis sativa L.)(Springer Dordrecht, 2024-03-25) Aasim, Muhammad; Yildirim, Busra; Say, Ahmet; Ali, Seyid Amjad; Aytac, Selim; Nadeem, Muhammad AzharIndustrial hemp (Cannabis sativa L.) is a highly recalcitrant plant under in vitro conditions that can be overcome by employing external stimuli. Hemp seeds were primed with 2.0-3.0% hydrogen peroxide (H2O2) followed by culture under different Light Emitting Diodes (LEDs) sources. Priming seeds with 2.0% yielded relatively high germination rate, growth, and other biochemical and enzymatic activities. The LED lights exerted a variable impact on Cannabis germination and enzymatic activities. Similarly, variable responses were observed for H2O2 x Blue-LEDs combination. The results were also analyzed by multiple regression analysis, followed by an investigation of the impact of both factors by Pareto chart and normal plots. The results were optimized by contour and surface plots for all parameters. Response surface optimizer optimized 2.0% H2O2 x 918 LUX LEDs for maximum scores of all output parameters. The results were predicted by employing Multilayer Perceptron (MLP), Random Forest (RF), and eXtreme Gradient Boosting (XGBoost) algorithms. Moreover, the validity of these models was assessed by using six different performance metrics. MLP performed better than RF and XGBoost models, considering all six-performance metrics. Despite the differences in scores, the performance indicators for all examined models were quite close to each other. It can easily be concluded that all three models are capable of predicting and validating data for cannabis seeds primed with H2O2 and grown under different LED lights.