Mekelle Institute of Technology

Permanent URI for this communityhttps://repository.mu.edu.et/handle/123456789/53

Browse

Now showing 1 - 20 of 44

CRIME PATTERN DETECTION USING DATA MINING TECHNIQUES: CASE OF SHIRE TOWN POLICE OFFICE
(Mekelle University, 2025-01-24) TEKLAY LEMA
Shire Town Police Office is not using any technology based system to make analysis of criminals’ activities to understand trends of previous years’ crimes and to identify the prevalent crime patterns occurred. This problem is not impacted only for the Shire Town Police Office but also for the region and the country. This research investigates the potential of data mining tools and techniques in developing models for crime pattern analysis to support the crime detection activities at the Shire Town Police Office-Tigray-Ethiopia. Out of more than 10,000 offenders’ record the researcher used only 9967 offenders’ recordS and 11 attributes data for this research. Utilizing clustering and classification algorithms, specifically K-means for clustering, J48 Decision Tree and NaïveBayes for classification, the research analyzes real offenders' data collected from the Shire Town police office. The results demonstrate that the J48 Decision Tree model, achieving an accuracy of 97.48% with 119 Number of Leaves and 157 Size of the tree, outperforms other models in detecting crime patterns based on the criteria that classifiers evaluated. Based on the findings of the J48 Decision Tree one sample is listed like: if the occurred crime type is at 2007 e.c, offenders who are grouped in the age group of Age2 (20 up to 32 years old), their Educational status is illiterate, and the crime occurred time is AM, then 109 offenders (97.32% of them) are classified as Male. There are 112 records. From which 3 records (2.67% of them) are incorrectly classified. This study highlights the significance of data mining in transforming raw crime data into actionable insights, thereby facilitating more effective decision-making in law enforcement. The findings emphasize the necessity of implementing modern data mining techniques to improve crime management strategies, ultimately contributing to enhanced public safety in the region.
CRIME PATTERN DETECTION USING DATA MINING TECHNIQUES: CASE OF SHIRE TOWN POLICE OFFICE A
(Mekelle University, 2025-01-24) TEKLAY LEMA
Shire Town Police Office is not using any technology based system to make analysis of criminals’ activities to understand trends of previous years’ crimes and to identify the prevalent crime patterns occurred. This problem is not impacted only for the Shire Town Police Office but also for the region and the country. This research investigates the potential of data mining tools and techniques in developing models for crime pattern analysis to support the crime detection activities at the Shire Town Police Office-Tigray-Ethiopia. Out of more than 10,000 offenders’ record the researcher used only 9967 offenders’ recordS and 11 attributes data for this research. Utilizing clustering and classification algorithms, specifically K-means for clustering, J48 Decision Tree and NaïveBayes for classification, the research analyzes real offenders' data collected from the Shire Town police office. The results demonstrate that the J48 Decision Tree model, achieving an accuracy of 97.48% with 119 Number of Leaves and 157 Size of the tree, outperforms other models in detecting crime patterns based on the criteria that classifiers evaluated. Based on the findings of the J48 Decision Tree one sample is listed like: if the occurred crime type is at 2007 e.c, offenders who are grouped in the age group of Age2 (20 up to 32 years old), their Educational status is illiterate, and the crime occurred time is AM, then 109 offenders (97.32% of them) are classified as Male. There are 112 records. From which 3 records (2.67% of them) are incorrectly classified. This study highlights the significance of data mining in transforming raw crime data into actionable insights, thereby facilitating more effective decision-making in law enforcement. The findings emphasize the necessity of implementing modern data mining techniques to improve crime management strategies, ultimately contributing to enhanced public safety in the region.
Evaluation of Aframomum corrorima Seed Extracts and Their Green Synthesized Silver Nanoparticles for Their Antioxidant, Antibacterial, and Wound Healing Activities
(Mekelle University, 2025-04-28) Rahel Sisay Werede
The emergence and spread of multidrug-resistant bacteria pose a significant medical challenge today. This research aimed to evaluate the antioxidant, antibacterial, and wound-healing activities of Aframomum corrorima seed extracts and their green-synthesized silver nanoparticles (AgNPs). Seeds of A. corrorima, collected from Hawassa, were ground into powder, macerated with ethanol, methanol, and water, and extracted using the Soxhlet extraction method. The qualitative phytochemical profile of the A. corrorima seed extracts was evaluated. AgNPs were synthesized from the A. corrorima extracts, and their properties were analyzed using UV-Vis and FTIR spectroscopies, Scanning electron microscopy, and X-ray diffraction. The three extracts and the AgNPs were tested against E. coli, P. aeruginosa, and S. aureus. The wound-healing potential of the extracts, formulations, and the AgNPs was evaluated using a mice model. The antioxidant capacities of the seeds and AgNPs were also assessed. Phytochemical analysis revealed flavonoids, tannins, glycosides, phenols, saponins, and quinones, with no detectable proteins. The methanol extract showed the highest antioxidant activity (IC50 23.38 ± 0.86 mg/ml), but AgNPs exhibited significantly greater potency (IC50 4.41 ± 0.025 mg/ml). AgNPs characterization confirmed nanoscale synthesis. Antibacterial assays demonstrated that AgNPs, seed extracts, and their formulations effectively inhibited E. coli, S. aureus, and P. aeruginosa, surpassing controls. AgNPs were most effective against S. aureus, and synergistic combinations enhanced antibacterial activity. Toxicity tests confirmed the safety of extracts and AgNPs in mice. Wound-healing studies in mice showed that seed extract, AgNPs, and their formulation significantly accelerated wound contraction compared to controls and nitrofurazone. The formulation improved healing by 11% over standard ointment. AgNPs and extracts displayed wound-healing comparable to nitrofurazone. This research highlights the potential of A. corrorima seed extracts and AgNPs as safe and effective sources of antioxidants, antibacterial agents, and wound-healing therapeutics, offering alternatives for multidrug- resistant bacterial infections and wound management.
Isolation and characterization of Lactic Acid Bacteria from raw cow milk and evaluation of their probiotic potential
(Mekelle University, 2025-04-28) Goiteom Senay Niguse
Cow milk is a rich source of lactic acid bacteria (LAB), a group of gram-positive bacteria with diverse applications in dairy, food, feed, and health. Despite this, the probiotic potential of LAB from cow milk remains under-researched. Therefore, the current study aimed to isolate and characterize LAB from raw cow milk and evaluate their probiotic potential. This study involved the isolation of LAB, followed by characterization of their morphology, various biochemical tests, and physiological properties. The LABs were evaluated for their potency and safety as probiotics, and finally, their potential use as starter cultures in yogurt formation was examined. Twenty-three (23) pure bacterial isolates were obtained from seven cow milk samples. Morphologically, eight isolates were cocci (35%), six were rods or bacilli (26%), and nine were coccobacilli (39%). Among these, nine (9) gram-positive and catalase negative isolates were selected for further investigation. These isolates were citrate-negative, non-motile, and indole- negative. All were TSIA-positive, with seven being homo-fermentative and two (M5 and M9) hetero-fermentative. Isolates M1, M2, M3, M4, M5, M6, M7, and M9 demonstrated salt tolerance at 1%, 4%, and 6% NaCl concentrations. Isolates M3 and M4 exhibited acid tolerance, growing at pH levels of 2, 4, 6, and 6.5. Isolates M1, M2, M3, M5, M6, M7, and M9 showed resistance to temperatures ranging from 15°C to 45°C. Isolates M2, M3, M5, M6, M7, M8, and M9 displayed tolerance to 0.4% and 0.6% phenol concentrations. None of the nine LAB isolates exhibited hemolytic activity. However, they showed varying degrees of antibacterial activity and displayed both susceptibility and resistance to antibiotics. Six isolates (67%) performed well as starter cultures for yogurt (riguo) production. The LAB isolates were tentatively grouped under the genera Lactobacillus, Enterococcus, and Leuconostoc. Overall, the isolated LAB from cow milk represents a potential source of probiotics. These LABs could serve as starter cultures in the dairy and food industries and may be developed into commercially viable probiotic products. Further studies, including molecular identification and characterization, are necessary to determine their specific strains.
Therapeutic Potential of Impatiens tinctoria Tuber Extract and Its Green Synthesized Silver Nanoparticles against Trichophyton mentagrophytes
(Mekelle University, 2025-05-21) Meron Mengistu
Dermatophyte infections and antifungal resistance pose a global health challenge, particularly in developing countries, where existing treatments often fail and cause recurrence and side effects. This study evaluated the antioxidant and antifungal properties of Impatiens tinctoria tuber extract and its green-synthesized silver nanoparticles (AgNPs) against Trichophyton mentagrophytes. Tuber extracts were obtained using aqueous, ethanolic, and methanolic solvents, and their phytochemical constituents were analyzed. AgNPs were synthesized using an aqueous extract under optimized conditions (pH 9, 0.1:1 extract-to-AgNO₃ ratio, 5 mM AgNO₃, 45-minute reaction time, and 60°C), with maximum UV-Vis absorbance at 419 nm and an SPR peak at 425 nm confirming formation. AgNPs were characterized via UV–Vis, FTIR, XRD, and SEM, revealing a face-centered cubic crystalline structure with an average crystallite size of 9.28 nm and predominantly spherical morphology. Antioxidant activity was assessed using the DPPH radical scavenging assay, with ethanol extract showing the highest capacity (IC50 = 48.18 ± 1.40 µg/mL), followed by methanol (125.66 ± 1.45 µg/mL) and aqueous (163.70 ± 1.02 µg/mL) extracts. Biosynthesized AgNPs exhibited dose-dependent activity (IC50 = 148.56 ± 0.74 µg/mL), surpassing the aqueous extract but remaining lower than ethanol and methanol extracts. Ethanol extract showed the strongest in vitro antidermatophytic activity against T. mentagrophytes, surpassing terbinafine (inhibition zone: 36.3 ± 1.15 mm at 100 mg/mL). Methanol extract exhibited significant inhibition, while aqueous extract had the lowest effect. AgNPs demonstrated antifungal efficacy, increasing with concentration but remaining less potent than terbinafine. A formulation combining ethanol extract and AgNPs (Formulation 2) significantly enhanced antidermatophytic activity in vitro, while in vivo studies on mice showed faster recovery and complete healing, outperforming individual treatments and proving comparable to terbinafine. Acute oral and dermal toxicity studies confirmed that the ethanol extract, AgNPs, and their formulation were non-toxic at 2000 mg/kg, with no observed toxicity or mortality. These findings suggest that I. tinctoria tuber extract and its green-synthesized AgNPs hold promising potential as alternative therapeutic agents for dermatophytosis treatment
Isolation and Characterization of Engine Oil-Degrading Bacteria from Contaminated Soil at Garage Centers in Mekelle
(Mekelle University, 2025-06-20) Yohannes Tsegay Teklay
The release of engine oil by Mekelle mechanical workshops causes significant environmental pollution; bioremediation is an effective cleanup strategy. This study investigates the isolation and characterization of engine oil-degrading bacteria from contaminated soil at garage centers in Mekelle. Soil and water samples from ten garage centers in Mekelle were collected and analyzed for physicochemical properties. Bacteria were isolated using serial dilution and identified by morphological and biochemical characteristics. To assess the oil degradation ability, bacterial isolates were cultured on Bushnell-Haas agar with engine oil and incubated at 37°C for 14 days. Moreover, the isolates were evaluated for biosurfactant production, heavy metals and salt tolerance, antibiotic susceptibility, as well as for compatibility. Results showed the pH level of the soil ranging from 4.7 ± 0.2 to 6.6 ± 0.2, with temperatures between 25 ± 3.27°C and 34 ± 0.0°C. The isolates were identified as Pseudomonas aeruginosa, Bacillus cereus, Staphylococcus aureus, Acinetobacter baumannii, Bacillus pumilus, and Bacillus megaterium. B. pumilus (98.9 ± 91.6%) showed the highest oil degradation rate in soil followed by A. baumannii (98.7 ± 80%). Whereas, B. megaterium (96.9 ± 92.8%), B. cereus (96.7 ± 88.2%), and P. aeruginosa (96.5 ± 84.6%) showed the highest biodegradation rate in water. However, B. megaterium (98.9 ± 88.8%) achieved a high degradation rate in media. The highest biosurfactant was produced by P. aeruginosa, A. baumannii, and B. cereus. S. aureus and A. baumannii exhibit broad tolerance to all tested heavy metals. P. aeruginosa, B. megaterium, B. cereus, and B. pumilus exhibit significant salt tolerance. Moreover, the antibiotic sensitivity testing reveals that P. aeruginosa, A. baumannii, and B. megaterium are promising candidates for bioremediation due to their susceptibility to effective antibiotics, while strains like B. cereus, S. aureus, and B. pumilus exhibit intermediate as well as multidrug resistance, necessitating careful antibiotic selection. So, from the results obtained, bacterial isolates could be the most effective for the bioremediation of oil spills.
Screening and Identification of Potential Dye-Degrading Bacteria from Maa Garment Effluen
(Mekelle University, 2025-06-21) Berihu Zenawi
The textile industry is a major contributor to water pollution, releasing effluents containing 10% - 15% unused dyes. These, dyes are resistant to biodegradation because their complex aromatic structures pose significant threats to aquatic ecosystems and human health. This study aimed to isolate, screen, and identify potential dye-degrading bacteria from the effluents of the Maa Garment and Textile Factory. Physicochemical parameters, including pH, temperature, total suspended solids (TSS), total dissolved solids (TDS), biological oxygen demand (BOD), and chemical oxygen demand (COD), were analyzed. Bacterial isolates were cultivated in dyecontaining media, and their decolorization efficiency was evaluated using spectrophotometry under varying conditions: temperatures (25°C, 30°C, 37°C, and 40°C), pH levels (5, 7, and 9), and dye concentrations (50, 100, and 150 mg/L). The collected samples exhibited pH levels ranging from 7.2 to 7.5 and the temperature varied significantly, with one sample reaching 38°C. A total of 16 bacterial isolates were screened for their decolorization capabilities under varying conditions of temperature, pH, and dye concentration. The results indicated that optimal decolorization occurred at 37°C and pH 7, particularly at a dye concentration of 50 mg/L. Under these conditions, the Pseudomonas aeruginosae isolates H5P, C2P, and C4P achieved 90% decolorization of reactive dyes. There were statistically significant differences (p < 0.001) among all environmental factors tested. These findings suggest that the isolated bacterial strains have considerable potential for the bioremediation of textile wastewater. This biological approach represents an environmentally sustainable and cost-effective alternative to conventional treatment methods. Further field trials and studies involving a broader range of dyes are recommended to validate their application in real-world wastewater treatment systems
IMAGE PROCESSING AND DEEP LEARNING BASED CLASSIFICATION OF COFFEE LEAF DISEASE
(Mekelle University, 2025-07-24) NETSANET ADUGNA
Coffee leaf diseases are a major threat to coffee production in Ethiopia and worldwide. Early detection and treatment of diseases are essential to prevent crop losses. Convolutional neural networks (CNNs) are a powerful machine learning technique that can be used for image classification. In this research report, we explore the use of CNNs for coffee leaf disease identification. We show that CNNs can be used to achieve high accuracy on this task, even with a relatively small dataset. We also show that AlexNet is a good choice for the base architecture of CNNs for coffee leaf disease identification. The approach is based on AlexNet architecture, and it achieved an accuracy of 97.5% on a dataset of 12600 coffee leaf images. Our research has several implications for the use of CNNs for coffee leaf disease identification. First, it suggests that CNNs are a promising new approach for this task. Second, it suggests that AlexNet is a good choice for the base architecture of CNNs for this task. Third, it suggests that the use of larger datasets can further improve the accuracy of CNNs for this task. Our research also has several limitations. First, our dataset was relatively small. This means that the models we trained may not be able to generalize well to new data. Second, we only evaluated our models on a single type of coffee leaf disease. It is possible that the models would not perform as well on other types of coffee leaf diseases. Despite these limitations, our research provides a good foundation for future research on the use of CNNs for coffee leaf disease identification. We believe that CNNs have the potential to revolutionize the way that coffee leaf diseases are identified and managed.
APPLICATION OF DATA MINING TECHNIQUES FO R CUSTOMER SEGMENTATIONS AND PREDICTION: CASE SINKE BANK, ASSELA BRANCH
(Mekelle University, 2025-07-24) MOHAMMED IRE
Identifying customers who are more likely to respond positively to a product or service offering is an important issue in business decision-making. In customer identification, data mining has been widely used to predict potential customers for various products and services. The main goal of this thesis is to develop a model that classifies customers for Sinke Bank. Since there were no predefined classes describing the bank’s customers, the researcher applied clustering techniques to determine an appropriate number of customer segments. Subsequently, a predictive model was developed to identify potential customers, achieving an accuracy of 99%. For modeling purposes, data was collected from the institution’s head office. Because irrelevant features can negatively affect model performance, data preprocessing was conducted to identify the most relevant inputs. Various data mining techniques and algorithms were applied throughout the modeling process to address related challenges effectively. The K-means clustering algorithm was used to segment customer records into groups with similar characteristics. Different parameters were tested before identifying a segmentation that made sound business sense. The J48 decision tree algorithm was then used for classification. In addition to attributes identified by domain experts as highly influential for customer segmentation, the loan amount attribute was found to have a significant impact. Overall, the findings of this study are encouraging and demonstrate the potential application of data mining solutions in the banking industry, particularly in customer segmentation and prediction for Sinke Bank Corporation.
ENHANCING BANKING SERVICES THROUGH DATA MINING: A CASE STUDY OF WUKRO CITY , TIGRAY REGION.
(Mekelle University, 2025-07-24) ABRHALEY KORKOS
Banking services play a crucial role in supporting economic development and financial inclusion by providing essential products such as savings, loans, fund transfers, mobile banking, and customer support. However, in developing regions like Wukro City, Tigray, banks face persistent challenges in delivering efficient, reliable, and customer-oriented services. These challenges include long service times, limited personalization, weak customer relationship management, and gaps in decision-making processes. To address these issues, this study explores how data mining models can be applied to enhance banking services, thereby improving service quality, customer satisfaction, and operational efficiency. The research employed a mixed-methods approach, integrating both quantitative and qualitative techniques. Survey data were collected from banking customers and employees to identify service gaps and customer expectations. Quantitative data were analyzed using WEKA software to develop predictive. The qualitative data, gathered through interviews and focus group discussions, provided contextual insights into customer experiences and perceptions of banking services in Wukro City. The findings revealed that data mining models can significantly enhance banking services by enabling banks to segment customers effectively, predict loan repayment behaviors, identify cross-selling opportunities, and detect service inefficiencies. The study also highlighted that customer satisfaction is closely linked with digital service adoption, personalized banking products, and reduced waiting times. Furthermore, the results suggest that integrating data-driven decision-making into banking operations can strengthen competitiveness and trust in the local financial sector. This research contributes to the growing field of technology-driven financial services by demonstrating the applicability of data mining in a developing regional context. For Wukro City banks, the study provides a practical framework to adopt data mining techniques in order to deliver more customer-focused, efficient, and innovative services. Ultimately, the study concludes that leveraging data mining not only enhances banking performance but also supports broader financial inclusion and sustainable economic development in the Tigray region.
FACTORS INFLUENCING ICT ADOPTION IN SECONDARY SCHOOLS: A CASE STUDY OF SECONDARY SCHOOLS IN WEREDA KEYH TEKLI, CENTRAL ZONE, TIGRAY REGION, ETHIOPIA
(Mekelle University, 2025-07-24) Weldegerges Gebru
The advent of Information and Communication Technology (ICT) has opened up tremendous opportunity and challenges in our quest for meeting the global demands of globalization and economic development. The purpose of this study was to determine factors that influence ICT adoption in secondary schools in wereda keyh tekli central zone of Tigray Region Ethiopia the specific objectives were as follows, To determine the influence of in-service support offered to teachers on adoption of ICT in teaching and learning in secondary schools in wereda keyh tekli to identify the influence of teachers‟ attitudes towards adoption of ICT in teaching and learning in secondary schools wereda keyh tekli and to examine if subject area is influences the adoption of ICT in teaching and learning in wereda keyh tekli.), which is used in studying individual’s technology adoption. This study adopted a descriptive methodology design where by quantitative tools and qualitative tools were used to collect data. The target populations of this study were 1156students and 4 public secondary schools, 7teachers and 7principalsand vice principals in wereda keyh tekli. The study used a sample of 2 secondary schools, 3 teachers and 297studentsselected using lottery system that means simple random sampling, 4principals(2directors and2vice directors)and supevisor selected by purposive sampling. Questionnaires were used to collect data from students and interview questionnaires also collected from teachers, principals and supervisors; Quantities data was analyzed using descriptive statistics. The findings from different data sets were synchronized during the presentation and discussion. From the foregoing, Study found out that adoption of ICT was a major In luence on teaching and learning in secondary schools, which was a clear indication that schools appreciated the role of ICT in education. However, there were a small number of respondents who felt that ICT had no major influence on teaching and learning. It is essential to note that the respondents only differed on the degree of influence of ICT on teaching and learning. The study found out that secondary schools offered different kinds of support to their teachers, especially those who have adopted ICT in their teaching and learning. There was a relatively even distribution in terms of area of support by schools to the teachers who have adopted ICT in teaching. The study revealed that the teacher’s attitude influenced their levels of adoption of ICT as a tool in teaching and learning. The study found out that thescience oriented subjects were most compatible in terms of curriculum with ICT adoption. The main conclusion from the study was that from the findings, the study found that adoption of ICT influences teaching and learning positively to secondary schools. Teachers were also supported in adopting ICT as a tool in teaching and learning. Teacher’s attitude influences their adoption of ICT where by their attitude is determined by their education levels. The use of ICT as a tool in subject’s areas was determined by the subject’s content and the study concluded academic performance followed by full ICT infrastructure were compatible with ICT. The study recommends that the institutions alongside the ministry of Education should find a way to increase the time period of class lesson with reliable resource materials. This will increase the teacher/ student exposure to the technology thus improves on the learning and teaching rate. The institutions environment should be designed to accommodate ICT. Infrastructure such as laboratories should be equipped well than the current status to be able to aaccommodate more number of students.
A predictive Modeling Framework for Identifying Key Factors Influencing Students’ Academic Performance in Secondary Schools Using Machine Learning
(Mekelle University, 2025-08) Solomon Tsegay
This study develops a predictive modeling framework to identify key factors influencing student academic performance in public secondary schools. Using a dataset comprising socio-economic, demographic, and academic variables, three machine learning algorithms like Linear Regression, Random Forest, and XGBoost were evaluated. Feature selection was conducted using Linear Regression coefficients, Random Forest importance, and XGBoost importance to extract the most impactful predictors. The models were assessed using Root Mean Squared Error (RMSE) and the coefficient of determination (R²). Results indicate that the XGBoost feature selection combined with Linear Regression yielded the highest performance (RMSE = 40.182, R² = 0.331), demonstrating improved predictive accuracy compared to other combinations. The findings highlight the significance of factors such as study hours, attendance rate, teacher quality, and assignment completion in determining student outcomes. This research contributes to data-driven educational decision-making, enabling stakeholders to target interventions more effectively. Recommendations for policy, practice, and future research are also provided
EFFECTS OF INFORMATION AND COMMUNICATION TECHNOLOGY ON STUDENTS’ LEARNING: A CASE OF SHIRE SECONDARY SCHOOL
(Mekelle University, 2025-08-19) AbdelWASIE ADEM
The study investigated the effect of ICT on students‟ learning by taking the case of shire Secondary school. It sought to establish the relationship between ICT and students‟ learning particularly looking at the availability, accessibility and user-ability of the ICT resources in shire secondary school. The rapid advancement of Information and Communication Technology (ICT) has transformed various sectors, particularly education. This thesis investigates the effects of ICT on students’ learning outcomes at Shire Secondary School in Northwestern Tigray. The study aims to evaluate how the integration of ICT in educational practices influences academic performance, student engagement, and overall learning experiences of students. The study was prompted due to the persistent report that students in shire secondary school are getting difficulties in their studies due to limited access and use of ICT resources. It was conducted through cross-sectional survey design; data was collected during the month of March 2017 using questionnaires, interview techniques from a sample of 265 respondents out of a parent population of 3114. In verifying the hypotheses, the researcher used Pearson correlation analysis method to find out whether students‟ learning was linearly correlated with ICT. The study established that the availability of ICT resources in the school is still very much wanting and very inadequate for the students to use. Because of the limited number of functional computers and the computer laboratory, accessibility is timetabled. It was found out that training was mainly limited to introduction to basic concepts of information technology, some application programs notably MS office suit and internet; contextual training of students on how to use ICT in learning was not in practice. The researcher concluded that availability, accessibility and user-ability of ICT resources significantly affect students learning in shire secondary school. Based on the above, the researcher recommends that there is need for the school to invest more in computers and related technology. Access to ICT tools should not be limited only in labs and library but expanded through establishment of ICT resource Centre. ICT training should not be limited to MS Office suites but rather aim at training students with the contextual skills to use ICT for their learning. The rapid advancement of Information and Communication Technology (ICT) has transformed various sectors, particularly education. This thesis investigates the effects of ICT on students’ learning outcomes at Shire Secondary School in Northwestern Tigray. The study aims to evaluate how the integration of ICT in educational practices influences academic performance, student engagement, and overall learning experiences of students.
ASSESSING THE IMPACT OF SOCIAL MEDIA MARKETING ON CONSUMERS' BRAND AWARENESS
(Mekelle University, 2025-08-24) ADDISSIE MINUYELET
Facebook, Twitter, LinkedIn, You Tube and Google+ are major Social media stages have changed the way companies advertise their items and administrations. The reason of this research has been to see at how social media can make brand mindfulness and it’s utilized in Ethiopia. This ponder is of an exploratory and graphic nature whose essential objective is to supply knowledge into a modern showcasing marvel. A combination of both quantitative and subjective strategy was utilized. It has been conceivable to pull back essential and auxiliary information by conducting an internet survey and expert interview conjointly by alluding related literary works separately. A combination of organized questioner study survey and organized meet is conducted to gather the desired data. Both essential and auxiliary strategies were utilized to assemble data to achieve best conceivable result of the research’s exertion. The finding of this research shows that most customers pay attention to notices suggested and shared by companions and contacts on social media systems instead of the coordinate data given or notice campaign made by companies. Suggestion of others which is known as electronic word of mouth is considered as the foremost reliable source of data to impact consumers’ discernment almost items and administrations and half of the shoppers purchase items based on the data they secure from social media systems. By the by, they are confronting a few challenges which prevent the smooth application of social media showcasing campaign. In any case, most neighborhood companies utilize other conventional shapes of limited time channels most such as TV and radio notices. The utilize of social media showcasing these days is getting to be exceptionally prevalent worldwide and it has changed the relationship between clients and commerce and this impact will continuously proceed to advance in Ethiopia as modern media implants the culture and society. Subsequently, the inquire about recommended that neighborhood companies ought to utilize social media arrange to present their brands with gigantic reach, perpetual communication conceivable outcomes and with an awfully restricted advancement taken a toll and get the conceivable openings of abusing the brand building potential through the wealthiest and quickest communication shape accessible. Be that as it may, Social Media as a frame of promoting will show an entirety unused stage challenges.
Design and Implementation of Big Data Analytics Framework at Abyssinia Bank: A Case Study in the Oromia Special Zone, Amhara Region
(Mekelle University, 2025-08-24) Bayew Girma
The Ethiopian banking industry is one of the fastest growing in the economy, Abyssinia Bank is one of the first banks in Ethiopia and it is among the top list of banks in the country. Big data analytics (BDA) has become an increasingly popular topic over the years amongst academics and practitioners alike. Big data, which is an important part of BDA, was originally defined with three Vs, being volume, velocity and variety. The rapid emergence of big data presents significant opportunities for organizations to enhance decision-making processes through data driven insights. This thesis explores the design and implementation of a big data analytics framework at Abyssinia Bank, focusing on its application in the Oromia Special Zone of the Amhara Region. This study aims to identify specific use cases where big data analytics can improve operational efficiency, customer service, and strategic decision-making. Through a mixed-methods approach that incorporates quantitative analysis of existing data and qualitative interviews with key stakeholders, this research will contribute to a deeper understanding of how big data can transform banking practices in emerging markets.
DEVELOPING PREDICTIVE DATA MINING MODEL FOR GRADE 11TH STUDENT PERFORMANCE: IN-CASE OF ELU WOREDA SECONDARY SCHOOL
(Mekelle University, 2025-08-24) BEDADA DEMTEW
Education is a key factor for achieving continuing economic progress. Many students are getting less in their result for many reasons. More academic institutes now store massive student educational and related data. A large number of students will enter every year. So, the demanding growth of data in education sectors continues. Handling and analyzing such a high amount of raw data manually for performance evaluation creates dissatisfaction, boring and unsuccessful. Manually handling and evaluating such a big amount of data for performance evaluation leads to discontent, boredom, and failure. To put it another way, traditional methodologies are overly complex and difficult to analyze and evaluate. To solve such kind’s issues, we use a data mining technique, which is a set of machine learning algorithms, to examine the data .In other words automated discovery of previously unknown, valid, novel, useful, and understandable patterns in school databases. The study's major goal is to use data mining to create a predictive model for student academic performance in Oromia National Region State's South West Shoa zone Elu woreda Teji Senior Secondary School and Asgori secondary schools. This can greatly was support policymakers, planners, and education providers working on the control of student performance. The methodology used for this research will a hybrid six-step CRISP Knowledge Discovery Process. The essential data would be gathered from a school data ware house created specifically for student result purposes, would be collected from 2011 to 2016 E.C. The researcher used three popular data mining algorithms (J48 Decision Trees, Random forest and Naive Bayes Classifier) to develop the predictive model using a larger dataset (4000 cases). The researcher used 10-fold cross-validation and percentage split test mode for data mining algorithms of the three predictive models for performance comparison purposes. The results indicated that the J48 Decision tree with10-foldcross-validation mode and Random Forest with 85% split testis the better predictor due to the nature of data which is categorical for which this two algorithm is better. Both algorithm (the J48 Decision tree with10-foldcross-validation mode and Random Forest with 85% split test) has 100% accuracy on the given school dataset and Naïve Bayes came out to be the second with an accuracy of 97.5%
An Assessment of the Role and Challenges of Information Technology in TVET Institutions: A Case Study of Mekelle, Tigray
(Mekelle University, 2025-08-24) Berhe Gebreyohans
This thesis examines the role of Information Technology (IT) in enhancing the effectiveness of Technical and Vocational Education and Training (TVET) institutions in Mekelle, Tigray, while identifying the challenges faced in integrating these technologies. As Ethiopia's economy undergoes rapid transformation, the need for a skilled workforce equipped with modern competencies becomes increasingly critical. This study employs a mixed-methods approach, combining qualitative interviews and quantitative surveys to gather comprehensive data from educators, students, and administrators across various TVET institutions. The findings reveal that the integration of IT significantly enhances pedagogical practices, promotes equitable access to educational resources, and prepares students for Industry 4.0 competencies. However, challenges such as inadequate infrastructure, limited digital literacy, insufficient funding, and resistance to change hinder effective implementation. The research highlights the urgent need for targeted policies and investments to address these barriers, including improved training for educators and enhanced access to technology. By situating the findings within the broader context of vocational education in Ethiopia, this study contributes to the academic literature on IT integration and offers actionable insights for policymakers and educational leaders. Ultimately, the research underscores the importance of leveraging IT to improve educational outcomes and align TVET programs with the dynamic needs of the labor market, thereby fostering economic growth and social equity in the region.
LEVERAGING INTERNET OF THINGS (IOT) TO ENHANCE TRAFFIC MANAGEMENT SYSTEMS IN MEKELLE CITY
(Mekelle University, 2025-08-24) HAFTAMU HAILU
Rapid urbanization and motorization in Mekelle City have created significant traffic management challenges, including recurrent congestion, road safety concerns, and inefficient manual control systems. Conventional traffic management approaches, which rely on fixed signal timing and limited real-time monitoring, have proven inadequate in addressing these issues. This study investigates the potential of leveraging the Internet of Things (IoT) to enhance traffic management systems in Mekelle City. A mixed-methods research design was employed, combining surveys, interviews, and simulation experiments. Primary data were collected from 102 road users and key stakeholders such as traffic police and urban planners, while secondary data were obtained from government reports and existing literature. A synthetic simulation was conducted to compare the performance of traditional fixed-time traffic signals with IoT-enabled adaptive signal control. The results demonstrate that the IoT-adaptive control strategy significantly reduces average queue length and vehicle delay while increasing throughput compared to the baseline fixed-time model. Specifically, average delays decreased by over 13 seconds per vehicle, while overall throughput improved. Survey findings further revealed strong public support for IoT-based traffic monitoring and violation detection systems, though opinions were divided on broader integration with cloud-based platforms and navigation services. The study concludes that IoT-enabled adaptive traffic management systems offer a feasible and impactful solution for Mekelle City, capable of improving mobility, reducing environmental impacts, and enhancing commuter safety. However, challenges remain, including infrastructure readiness, cost implications, and the need for comprehensive policy support. The research recommends a pilot deployment at major intersections, followed by phased city-wide implementation, integration with public transport systems, and further microscopic simulation using locally calibrated data. This work contributes to the growing field of smart city research in low-resource settings by providing an evidence-based framework for IoT-driven traffic management in Ethiopia
SATELLITE IMAGE BASED URBAN CHANGE DETECTION: THE CASE OF HAWZIEN TOWN IN NORTHERN ETHIOPIA
(Mekelle University, 2025-08-24) KIBROM HAIALY
Information on Land use/Land-cover change is imperative to local, regional and wide-range planning, decision making and ecosystem monitoring. Such planning and management activities are seriously vulnerable to blunders due to the deficiency of reliable and timely information on dynamics of land cover /land-use change. Thus, it is indispensable to study urban changes to evaluate what has changed and to predict future changes of growth and expansion. So far, minimal effort has been applied in Hawzien to precisely and accurately track the land use/land cover and urban changes using widely and commonly used satellite images. Therefore it is necessary to device a model that can automatically detect changes given satellite images of different points in time. Such automated systems will assist to identify, monitor and predict the growth and expansion of urban development This study presents the methods and results of pixel-based, object based and feature based change detection algorithms to spot changes in urban areas between two specific time periods using Land sat images. The implemented model classifies developed areas of different densities as well as undeveloped lands that are likely to be degraded by close proximity to development. This tool can also analyze land cover data for multiple time periods for a given city. For each time period, two maps are generated showing the density classes of the built-up area and the undeveloped land degraded by proximity to the built-up area. A prototype that automatically detects changes that happened between 1986 and 2000 in Hawzien city is implemented. This prototype was developed using Remote sense and has an ability to be integrated into ArcGIS. An easy to use graphical user interface is also developed using Microsoft visual studio 2010 to assist users with minimal or no skills of using ArcGIS. The result of the work shows that combination of feature based, object based and pixel-based Change detection methods exploiting spatial metrics and texture measurements is a potential new avenue to extract detailed urban land-use information from high or medium resolution satellite imagery. Managers, policy makers and planners could use this data as a decision-support tool. The model was evaluated by professional users on its learn ability and efficiency. The results show that the model has a capability of extracting urban change information with few modifications required. The overall feeling of users towards using the model is found to be 86.67%.
Impacts of Socio-economic and Political Factors on the Implementation of IT Education in Embasneyti Wereda Secondary Schools
(Mekelle University, 2025-08-24) Kidane Hailemariam
The objective of this study was to investigate impacts of socio-economic and political factors on the implementation of IT education in Embaseneyti Wereda Secondary Schools. A descriptive survey design with mixed methodology was employed to conduct the study. Data were collected from 70 respondents who were selected using simple random sampling technique from Embaseneyti Secondary School and Getachew Weldu Secondary Schools. Data were collected using questionnaire and interview. Data collected via close-ended questions were analyzed using frequency and percentage using the SPSS version 21. Qualitative method was employed to analyze data gathered through semi-structured interview and open-ended questionnaire. Three research questions were formulated to assess the impacts of socio-economic and political factors in the implementation of IT education in secondary schools. Accordingly, it was found out that socio-economic and political factors had severe negative impact in the implementation of IT education in the secondary schools of Embaseneyti Wereda in central zone of Tigrai. In addition, the schools didn’t have basic computer infrastructure and internet facilities. It was also found out that students’ socio-economic background had great impact on the implementation of IT education in the school as they didn’t have access to technologies and internet service. Since the school’s budget source was limited to its own income generating effort and community contribution, the schools struggled to fulfill the IT infrastructure. Political factors also hugely affected the school as the previous war between the Tigrai Regional government and the federal government of Ethiopia destroyed the basic IT infrastructure the school had. The political tensions also resulted in limited emphasis on the fulfillment of IT infrastructure. Therefore, the researcher recommended coordinated effort by the regional education bureau, woreda education office and the ministry of education to fulfill IT infrastructure in secondary schools and to train professional IT teachers.