SUST Journal Systems (Sudan Univ. of Science and Technology)
Not a member yet
189 research outputs found
Sort by
بناء موارد أساسية لتحليل الآراء والمشاعر الواردة في التعليقات باللغة العربية
No full textالمستخلص - نهدف من هذه الورقة إبراز خطوات بناء بعض الموارد اللسانية التي من شأنها أن توظف في بناء البرمجيات والتطبيقات الخاصة بتحليل الآراء والمشاعر الواردة في المواقع ثم تقييمها، من بين الموارد التي قمنا ببنائها معجم متخصص يضم كلمات تستعمل في إبداء الآراء والتعبير عن المشاعر، ثم لائحة حروف المعاني التي تؤثر في تغيير توجيه التعابير العربية، بالإضافة إلى المدونة المعتمدة في اختبار برمجيات تحليل الآراء والمشاعر. وللتمكن من بناء الموارد السابقة الذكر، فقد ركزنا في البداية على المنهج الوصفي لرصد متطلبات بناء نظم تحليل الآراء والمشاعر، كما اعتمدنا على المنهج اليدوي والمنهج الآلي في إعداد كل من المعجم، ولائحة الحروف، والمدونة، فتمكنا من تشكيل معجم قارب 21453 مدخل معجمي، وإعداد لائحة ضمت 9784 حرفا، وجمع ما يقارب 100630 وسم منها %25 يدويا
A Big Bang – Big Crunch Type-2 Fuzzy Logic Based System for Fraud-Detection in the Sudanese Financial Sector
No full textABSTRACT– Improved fraud detection systems are vital tools for the evolution of the Sudanese banking sector where the traditional fraud detection models are incapable of overcoming the emerging, innovative and new attacks that threaten large financial institutions. Hence, there is a need for accurate and transparent techniques which can automatically detect fraud with high speed and identify its causes and common patterns. Many of the Artificial Intelligence (AI) techniques are effective and provide good predictive models. Nevertheless, they are considered as black-box models. On the other hand, the white box models are easy to understand and analyze, but result in a large number of rules, besides having many parameters in each rule. In this paper, we present a novel system based on the Big Bang–Big Crunch optimization (BB–BC) approach, which is combined with type-2 Fuzzy Logic Systems to result in a small set of short IF-Then rules for the fraud detection within the Sudanese banking sector. The proposed system uses real-world dataset from Balad Bank – Sudan, which contains 803,386 transactions with 107 fraud transactions. Hence, the positive class (frauds) rate is 0.0133% of all transactions. The experimental results demonstrate that the performance of proposed system is effective in tuning the parameters of the rule base and membership functions of the Type-2 FLSs (T2FLSs) to improve the accuracy, where the proposed T2FLSs outperformed the Type-1 FLSs (T1FLSs) counterpart, as well as each rule can be simply explainable. Therefore, this can be very helpful for the Sudanese banks to start tracking the fraud cases
Determination of Typical Flexural Reinforcement Area in Negative Region of Composite Beam
Get PDFABSTRACT- Continuous steel beams with reinforced concrete slabs on their top are more economical and effective than classic RC beam models (Reinforcement concrete beams). Also, they are favorite in architectural designs due to their less heights, large spans and ideal resistance to deflection. However, they suffer from several undesirable structural defects, such as local buckling or lateral torsional buckling, so it is necessary to conduct more research and studies on their flexural behavior. In this paper, a mathematical model is prepared and suggested to simulates several experimental samples of continuous composite beam sections using the ANSYS 14 program, then comparing the analytical results with numerical experimental curves (load - deflection) to adjust the validity and accuracy of this suggested mathematical model. Typical reinforcement area value and corresponding resisting bending moment were also determined using this mathematical model for several experimental samples. Furthermore, theoretical formulas have been derived to determine the typical reinforcement area and corresponding bending moment of composite section in negative region, and compare the results of these formulas with the analytical results from numerical model and with values proposed by the codes. Finally, several user-friendly design curves were developed to help in computing the typical reinforcement area values for the composite section within the negative area for continuous steel beam of symmetric flanges. Among the most important results reached, is that reinforcement area ratio is not a fixed ratio but rather related to the properties of the steel and composite section and that it is not advisable to use reinforcement quantities greater than the typical value
Estimating Daily Evaporation in Syrian Coast Using Gene Expression Programming and Adaptive Neuro-Fuzzy Inference System
No full textABSTRACT-The evaporation is one of the basic components of the hydrologic cycle. It is necessary to accurately estimate it for the development and management of water resources, it affects the amount of runoff, the capacity of surface reservoirs, and the plant's need for water, and it requires knowledge of many climatic variables. Although, there are many empirical formulas available for evaporation estimate, but their performances are not all satisfactory due to the complicated nature of the evaporation process. Therefore, the aim of this research is to evaluate the accuracy of Gene Expression Programming (GEP) and Adaptive Neuro-Fuzzy Inference System (ANFIS) for estimating daily evaporation in the Syrian coast, and compare their results with the results of the Ivanov equation. For this, we built GEP and ANFIS models using available climate data, taken from five climatic stations spread over the studied entire area and located at different heights. The statistical parameters used to evaluate the accuracy of the models were: Root Mean Squared Error (RMSE) and correlation coefficient (R). Comparative results showed that GEP is better than ANFIS for estimating pan evaporation. Both models outperformed the Ivanov equation. the model which including temperature, relative humidity, solar radiation and elevation is the best for estimating daily evaporation in the Syrian coast, where the values of RMSE and R for the test group in GEP and ANFIS models were respectively (0.55mm / day), R = 0.94, (0.7mm/ day), R = 0.92
Seepage Sensitivity Analysis through a Homogeneous Dam within the Unsaturated Soil Zone
No full textSeepage through earth dams is affected by the soils characteristics that form them, which are characterized by the difference in time and place by the influence of various factors such as climatic factors and soil moisture variations because of changes in the storage level in the reservoir in front of the dam. Therefore, the possible randomness of these parameters that reflect the characteristics of the soils must be taken and their effect evaluated to ensure the survival of seepage is minimal. This research comes as a continuation of the study applied to several types of soils to find out the effect of the variation of some of their parameters on seepage through earth dams, and by following a new method that observes the unsaturated zone above the seepage line in earthen dams, which provides the best result to simulate the actual situation of any engineering facility (Where it is assumed with average constant values in previous researches to simplify the solution, but they are not constant in the actual case). The aim of the research is to analyze the sensitivity of the steady state seepage for the variation of the hydraulic conductivity, residual water content and saturated water content in a typical homogeneous earth dam, by building a mathematical model with the Seep/W program after writing a program code in c# for the used equations (van Genuchten model to determine the hydraulic conductivity parameter of unsaturated soil, and the van Genuchten to determine the water content). That allows generating random values for those parameters based on their statistical properties from previous research. The Monte Carlo technique was adopted to solve a very large number of simulations (5500 models), and a deterministic model for comparison was also built. The research showed that the variability of all parameters of the studied soil, gravely sand, did not affect the seepage, and the ability to rely on its fixed average values instead of random models, as the highest percentage of difference from the deterministic model was 0.1565%, which is a very small amount that can be neglected
Computer Software Development (Galal-M-RP) for Concrete Pavement Analysis and Design
Get PDFA computer expert system has been developed for structural design of rigid pavements entitled Galal-Muram Rigid Pavement (Galal-M-RP). The developed software program is a design package as well as educational and training tool. The user is assisted to select design inputs by a systematic rule-based expert. These rules are intended to determine AASHTO recommended values. These values are shown on the screen along with a brief explanation during the design process. Screens and various group boxes assist the user in selecting the design inputs. A sensitivity analysis option allows the user to confirm the required precision of the design inputs. The results obtained from this software were evaluated and compared to the manual design case study of Omdurman ring road, as well as with other design examples. They include examples by Huang; AASHO 1993 Guide and Kici, A. and Tigdemir, M. in 2017 applying user friendly software, in addition to lecture notes by Drakos in 2009 at University of Florida. Comparisons were found excellent with differences in pavement thickness ranging between 0.1 and 0.9 cm. Concrete pavement design software Galal-M-RP supersedes conventional design methods regarding errors and difficulties in addition to saving significant time.
Keywords: Visua
Enhancement of the Injection Grade Polypropylene using Extrusion Grade Polypropylene and Calcium Carbonate
Get PDFthe invention provides for study properties of polypropylene (injection grade) / polypropylene (extrusion grade) blend filled with calcium carbonates. In four formulations of PP(Injection grade)/PP(Extrusion grade)) viz. 95/5, 90/10, 85/15 and 80/20 in ratio of weight percentage were prepared for injection molding machine. This PP(Injection grade)/PP(Extrusion grade) (80/20) blend was selected and investigated at different three fractions of calcium carbonate. The mechanical properties such as tensile strength and elongation test were investigated. The rheological properties such as melt flow index (MFI) and melt density were evaluated. The results indicated that incorporate calcium carbonate increase the (MFI), melt density and elongation decreased while increase the tensile strength. It was obtained that increase calcium carbonate content into PP(Injection grade)/PP(Extrusion grade) blends will increase the density. Taking into consideration, it was concluded that, the optimum composition provided the good mechanical, rheological properties and density is PP(Injection grade)/PP(Extrusion grade)/Calcium carbonate (80/20/22.5) wt%
Citizen Adoption of Digital-Government whistleblowing system initiatives in Ethiopian: A validation of the Technology Acceptance Model (TAM) in Whistleblowing Systems success
Get PDFDigital Government whistleblower initiative has been applied in governmental organizations of Ethiopia to tackle unlawful activities in public services. This study explores how the Technology Acceptance Model (TAM) and Digital Government whistleblower initiative would positively impact the Ethiopian government, despite the cultural differences within the country. This study developed a successful model of the Ethiopian Digital Government whistleblower system to assist Ethiopians with more efficient and cost-effective whistleblowing operations. Data was collected using a survey applied to a sample of 554 citizens and data analysis involved linear regression statistical technique (SPSS). The results showed that the core constructs of the TAM have strong influences on user-intention towards Digital Government whistleblowing system. Also, information quality and whistleblowing system quality were the significant determinants of the perceived usefulness of whistleblowing services. In addition, findings suggest that whistleblowing system quality is a factor that influences their behavior toward the use of Digital Government whistleblower syste
Modeling of mortality rate of heterotrophic bacteria due to chromium in waste stabilization pond
Get PDFBacteria play an important role in oxidation and stabilization of organic and inorganic matter
in wastewater treatment plant. This paper presents the development of mathematical model to study the
effect of chromium on heterotrophic bacteria in waste stabilization pond. The governing equation of the
model is based on the Haldane equation. The model developed reflects the mortality rate of heterotrophic
bacteria at variable pH and concentration of chromium. To verify the computed results a series of laboratory
experiments has been carried out, the predicted mortality rate was obtained from these models and compared
with experimental data. The correlation coefficient R2 was 0.87
Petrophysical Study and Formation Evaluation of Jake Reservoir, Block 6, Muglad Basin, Sudan
Get PDFThe study area (Jake oilfield) is located on the Western Escarpment of the Fula Subbasin of the Muglad Basin, which is bounded by the latitudes 11°20' and 11°36′ N and longitudes 28°
30′ and 29° 36′ E. This oilfield has been structurally subdivided into three main structures of Jake,
Jake Central and Jake South. The goal of this study is to identify and to interpret the reservoir quality
and properties (lithology, porosity, shale volume, and water saturation) and then to detremine sand
continuity of Bentiu formation, to achieve this goal in successful way the information and data of
three wells (Jake South -2, Jake South -3, Jake South -15) were made available, then the evaluation of
the given data has been processed using the interactive petrophysic software (IP 3.6) version. The
wireline logging and mud logging data had been carefully evaluated during the process of the data
application, and data quality was thought to be good. Eventually, the results obtained using the shaly
sand evaluation techniques, were in better agreement with core and test data. For the Reservoir and
shale identification the most useful indicator was obtained from the behavior of the density and
neutron logs. The neutron – density cross plot is the best method for lithology identification. Density
– Neutron cross plot values had been used to identify the pure matrix and/related porosity, v-shale,
porosity and water saturation models had been done and full interpreted from the initial results cut off
parameters also determined and multi targets prospects of all wells had been marked, beside netreservoir and net-pay had been obtained successfully.In Jake South -2 (the maximum net pay
thickness for Bentiu reservoirs is 48.2m and the minimum thickness is 3.66m, the average effective
porosity is 17%, and the average water saturation is 48%), in Jake South -3 (the maximum net pay
thickness for Bentiu reservoirs is 4.72m), the average porosity is 22%, and average water saturation is
86%). Hence in Jake South -15 (the maximum net pay thickness for Bentiu reservoirs is 28.12m, the
minimum thickness is 4.5m, the average porosity is 18% and the average water saturation is 33%)