Universitas Ahmad Dahlan Journal
Not a member yet
5744 research outputs found
Sort by
Analisis Perbandingan Model Regresi Logistik Dan Probit Dengan K-Fold Cross Validation Dalam Mengidentifikasi Faktor Signifikan Pada Penyakit Diabetes Melitus
Full text linkStatistika adalah cabang matematika yang berkaitan dengan pengumpulan, analisis, interpretasi, presentasi, dan organisasi data. Statistika digunakan dalam berbagai disiplin ilmu untuk membuat keputusan berdasarkan data. Terdapat dua jenis utama statistika, yaitu statistika deskriptif dan statistika inferensial. Salah satu metode statistika inferensial yang biasa digunakan adalah Analisis Regresi Logistik dan Regresi Probit. Regresi Logistik dan Regresi Probit merupakan teknik dalam statistika inferensial yang digunakan untuk menemukan hubungan di antara variabel prediktor dan variabel respons yang bersifat dikotomus (memiliki dua kategori) atau polikotomus (memiliki lebih dari dua kategori). Regresi logistik menggunakan fungsi distribusi kumulatif dari distribusi logistik sedangkan Regresi Probit menggunakan fungsi distribusi kumulatif dari distribusi normal. Tujuan dari penelitian ini adalah mengetahui model terbaik antara model logit dan model probit berdasarkan validasi model menggunakan k-fold cross validation. Data yang digunakan adalah data sekunder tentang prediksi diabetes yang tersedia dalam Kaggle. Berdasarkan hasil yang diterapkan pada data tersebut didapatkan faktor faktor yang berpengaruh signifikan terhadap penyakit diabetes adalah jenis kelamin, usia, riwayat hipertensi, riwayat penyakit jantung, riwayat merokok, BMI, kadar HbA1c, dan kadar gula darah. Hasil perbandingan model didapatkan dari rata-rata akurasi yang sama menggunakan k-fold cross validation untuk model logit dan probit yaitu sebesar 93.7%. Perbandingan ini diperkuat dengan empat kriteria dalam pemilihan model terbaik yaitu AIC, Pseudo-R2, AUC, Logloss keakuratan klasifikasi, dan uji kesesuaian model (Goodness of fit). Secara keseluruhan dapat disimpulkan bahwa model probit lebih baik daripada model logit dalam kasus data tersebut.
ABSTRACT
Statistics is a discipline of mathematics concerned with the collection, analysis, interpretation, presentation, and organization of data. Statistics is used in various disciplines to make decisions based on data. There are two general types of statistics, descriptive statistics and inferential statistics. One of the commonly used inferential statistical methods is Logistic Regression Analysis and Probit Regression. Logistic regression and Probit regression are techniques in inferential statistics used to find the relationship between predictor variables and response variables that are dichotomous (have two categories) or polycotomous (have more than two categories). Logistic regression uses the cumulative distribution function of the logistic distribution while Probit regression uses the cumulative distribution function of the normal distribution. The purpose of this study is to determine the best model between the Logistic Regression model and the Probit Regression model based on model validation using k-fold cross validation. The data used is secondary data on diabetes prediction available in Kaggle. Based on the results applied to the data, the factors that have a significant effect on diabetes are gender, age, history of hypertension, history of heart disease, smoking history, BMI, HbA1c levels, and blood sugar levels. The results of the model comparison showed the same average accuracy using k-fold cross validation for logistic regression and probit regression models, which was 93.7%. This comparison is supported by four criteria in selecting the best model, namely AIC, Pseudo-R2, AUC, Logloss, classification accuracy, and goodness of fit test. Overall, it can be concluded that the Probit Regression model is better than the Logistic Regression model in the case of these data
Nanoparticle formulation of ethanolic extract of Syzygium polyanthum leaf using chitosan and cross-linking method
Full text linkSyzygium polyanthum (bay leaves) is widely used in Indonesia and has been shown to have pharmacological activity, such as antihyperlipidemia. The nanoparticle is a delivery system that enhances therapy effectiveness, minimizes side effects, and ensures safety. Therefore, this study aimed to improve the antihyperlipidemic efficacy of Syzygium polyanthum extract by formulating it into nanoparticles. The polymer that is used in this nanoparticle formulation is chitosan, while the cross-linking agent that is used is sodium tripolyphosphate. Three formulations have been developed, each with different stirring times after crosslinking: F1 (20 minutes), F2 (90 minutes), and F3 (150 minutes). At the same time, nanoparticles produced were examined for particle size, ζ potential, polydispersity index, entrapment efficiency, and release study. Syzygium polyanthum extract is abundant in secondary metabolites, including alkaloids, flavonoids, saponins, triterpenoids, tannins, and quinones. The particle size data for F1, F2, and F3 were 257±6.68 nm, 232±2.54 nm, and 303±1.3 nm respectively, while the polydispersity index ranged from 0.242 to 0.383. The entrapment efficiency represented by quercetin, used to assess the extracted content of the nanoparticles, yielded results between 39.59% and 67.48%. A release study of nanoparticle Syzygium polyanthum (nanoparticle SP) showed that the extract represented by quercetin can be released from the system is 64-82% in 120 min. The ζ potential measurement in F2 indicated a value of 30.9±0.416 mV, suggesting that the nanoparticle SP formed possesses excellent stability. Among the formulas studied, F2 emerged as the most promising due to its combination of factors such as the smallest size, favorable polydispersity index, high entrapment efficiency, and desirable release profile values. All of the formula has the potential to provide a good therapeutic effect, such as antihyperlipidemia but it needs to be proven by further studies
Assessment of medication-related liver and kidney impairment in admitted patients in Depok, Indonesia: an observational study employing the Naranjo algorithm
Full text linkLiver and kidney impairment caused by medications represents serious side effects that may extend hospital stays and increase the risk of patient death. Implementing strategies to recognize, document, and analyze cases of patient harm related to drug use is crucial for medicines optimization. This study aimed to evaluate the prevalence of medication-related liver and kidney impairment among hospitalized patients, while also identifying the specific medication categories implicated. A retrospective review of patient records was conducted at Universitas Indonesia Hospital (Depok, Indonesia), focusing on adult patients diagnosed with liver or kidney impairment during their 2021 hospital admission. The Naranjo algorithm was applied to assess the likelihood that these injuries were caused by medications. Among the 4,273 admitted patients, it was found that 1.01% experienced medication-related liver impairment (MRLI), while 0.77% experienced medication-related kidney impairment (MRKI). The most common medications associated with liver impairment were antibiotics (31.58%), cardiovascular medications (24.21%), pain relievers (14.74%), anti-ulcer medications (11.58%), antiviral medications (8.42%), antiemetics (8.42%), and antidiabetic medications (1.05%). In contrast, kidney disease was primarily linked to diuretics (29.76%), antibiotics (21.43%), ACE inhibitors/ARBs (21.43%), antiviral medications (9.52%), and NSAIDs (7.14%). Importantly, there was no statistically significant correlation between the occurrence of MRLI or MRKI and factors such as gender, age, body mass index (BMI), or the presence of other health conditions (p > 0.05). These findings underscore the need for heightened awareness regarding the potential for medication-related impairments in hospitalized patients and suggest that careful monitoring of medication use is essential to mitigate these risks
Malware Classification and Detection using Variations of Machine Learning Algorithm Models
Full text linkMalware attacks are attacks carried out by an attacker by sending malicious codes to various files or even many packages and servers. Therefore, reliable network operations are a factor that needs to be considered to prevent attacks as early as possible in order to avoid more severe system damage. Types of attacks can be Ping of Death, flooding, remote-controlled attacks, UDP flooding, and Smurf Attacks. Attack data was obtained from the ClaMP dataset, which has an unbalanced data set, and has very high noise, so it is necessary to analyze data packets in network logs and optimize feature extraction which is then analyzed statistically with machine learning algorithms. The purpose of the study is to detect, classify malware attacks using a variety of ML Algorithm models such as SVM, KNN and Neural Network and testing detection performance. The research stage starts from pre-Processing, extraction, feature selection and classification processes and performance testing. Training and testing data in the study used a mixed model, namely data division, split model and cross validation. The results of the study concluded that the best algorithm for detecting malware packages is the Neural Network for the Feature Combination category with an accuracy rate of 96.91%, Recall of 97.35% and Precision of 96.78%. So that the study can have implications for cyber experts to be able to prevent malware attacks early. While further research requires a special algorithm to improve malware attack detection, in addition to KNN, SVM and Neural Network. And another research challenge is to focus on feature extraction techniques on datasets that have unbalanced or varied features with the Natural Language Processing (NLP) approach. So this research can be used as a reference for researchers who are conducting research in the same field
Prediction of Purchase Volume Coffee Shops in Surabaya Using Catboost with Leave-One-Out Cross Validation
Full text linkIndonesia's coffee consumption grew from 265,000 tons in 2015 to 294,000 tons in 2020. Averaging 2% annual growth with a projected 368,000 tons by 2024. One of the coffee businesses is coffee shops, Coffee shop businesses often struggle to attract customers quickly, risking low purchase volume within their first five years. In their first year, challenges include management, company size, service quality, and customer preferences. This study adopts a quantitative approach and new solutions to develop a purchase prediction application based on machine learning and strategy to enhance purchase volumes for three coffee shops in Surabaya. It utilizes CatBoost, with LightGBM as a comparison, across multiple coffee shop locations. LOOCV (Leave-One-Out Cross-Validation) is used in this model to address research limitations, such as data overfitting and biases, while enhancing evaluation accuracy. As a result, the study established CatBoost as the superior model for purchase prediction, providing insights and practical applications in business forecasting. The Catboost model achieved an MAE of 0.91 and MAPE of 15%, outperforming LightGBM’s MAE of 1.13 and MAPE of 18%. These results confirmed CatBoost’s effectiveness for the coffee shop industry with good accuracy. This research also contributes to helping coffee shop owners in Surabaya understand market characteristics, such as the most profitable coffee types and high-customer-density locations. Additionally, it aids in optimizing purchase volume to leverage profit by developing new strategies based on prediction result. In conclusion, CatBoost accurately predicts purchase volume, helping coffee shops identify target markets and refine strategies based on customer preferences
Development of animal structure practicum e-module on canva
Full text linkThis research explores innovation in learning through the integration of information technology, particularly e-modules for teaching animal structure laboratories using Canva. Using an R&D approach with the 4-D development model, the study involved 3 validators and 17 students at Lancang Kuning University. Data were analyzed descriptively qualitatively and quantitatively, indicating high levels of validity for subject matter, language, and media experts. Student responses to the e-module were also very positive. The research findings indicate that the Animal Structure Laboratory E-Module created with Canva is highly valid and suitable for use in learning, reinforcing the use of technology in an educational context
Does the Integrated Learning Course Affect Openness Traits in Students?
Full text linkThis study investigates the impact of integrated learning courses on the development of the openness personality trait among students enrolled in the Elementary School Teacher Education program at the University of Nusantara PGRI Kediri. Adopting a comparative quantitative design, the research compared the openness levels of students who had participated in integrated learning courses with those who had not. Openness was measured using the International Personality Item Pool (IPIP)-BFM-50, focusing on 10 specific indicators. The validity of the items was confirmed through Pearson product-moment correlation (p < .05), and the scale demonstrated acceptable internal consistency (Cronbach’s alpha = .714). Data analysis confirmed the assumptions of normality and homogeneity. Results revealed that students exposed to the integrated learning course scored significantly higher on openness (t(79) = 3.064, p = .003, Cohen’s d = .681), indicating a moderate to large effect size. The study concludes that integrated learning effectively fosters openness—an essential trait for adaptability and cognitive flexibility in 21st-century education. It recommends the broader integration of such courses into teacher education curricula. For future research, a mixed-methods approach is suggested to better understand the underlying processes through which integrated learning influences personality development.
Keywords: Integrated learning, openness trait, big five facto
Understanding Premarital Sexual Behavior: A Qualitative Case Study among Male and Female College Students
Full text linkYoung individuals frequently engage in intimate relationships, specifically premarital sex, which is categorized as unsafe sexual behavior. Numerous studies have highlighted the premarital sexual behavior of females, who face greater risks compared to their male counterparts. Understanding how gender differences influence this behavior is crucial for developing targeted strategies to mitigate the potential negative consequences among young people. A qualitative case study was conducted to examine the premarital sexual behavior of students in Province X and to identify the factors influencing it. Six participants—three male and three female students—were selected through purposive snowball sampling. After providing consent for private interviews, qualitative in-depth discussions were carried out. The results from thematic analysis revealed eleven key themes related to their premarital sexual behavior and six themes associated with influencing factors. Males reported engaging in their first sexual intercourse at an earlier age during adolescence, while females tended to do so slightly later, in early adulthood. Notably, males expressed feelings of guilty pleasure regarding their premarital sexual activities, whereas females shared unpleasant experiences stemming from a lack of assertiveness in declining sexual advances from their partners. They also reported facing judgmental attitudes from healthcare workers during medical checkups. Similarities found included having multiple sexual partners, neglecting reproductive health, and feeling a disconnection from their religious beliefs. The implications of the study are discussed further
Linking AKHLAK Culture to Engagement: The Mediating Role of Corporate Reputation
Full text linkThis study investigates the mediating role of corporate reputation in the relationship between the AKHLAK work culture and work engagement among 270 employees at PT X in Medan. Utilizing a quantitative approach and Structural Equation Modeling–Partial Least Squares (SEM-PLS) analysis, the results indicate that: (1) the AKHLAK culture significantly enhances work engagement (β = 0.494, p < 0.05); (2) the AKHLAK culture positively influences corporate reputation (β = 0.640, p < 0.05); (3) corporate reputation has a significant positive effect on work engagement (β = 0.328, p < 0.05); and (4) corporate reputation partially mediates the relationship between AKHLAK culture and work engagement (β = 0.210, p < 0.05). Theoretically, this study contributes to the expansion of the Job Demands–Resources (JD-R) Model and Social Identity Theory by positioning corporate reputation as a novel mediating variable. Practically, the findings emphasize the strategic importance of integrating AKHLAK values with corporate reputation-building efforts to enhance employee engagement and organizational competitiveness. These insights offer actionable guidance for Indonesian state-owned enterprises (SOEs) aiming to align cultural initiatives with broader reputational goals, thereby strengthening both internal morale and external stakeholder perception.
Keywords: work culture AKHLAK, corporate reputation, work engagemen
Psychometric Properties of the Rosenberg Self-Esteem Scale: A Specific Application to People with Diabetes Mellitus
Full text linkSelf-esteem is a critical psychological component for individuals living with diabetes mellitus, especially in supporting effective self-management behaviors. Accordingly, the use of a self-esteem assessment instrument with robust psychometric qualities is essential to support effective self-management among individuals with diabetes mellitus. This study aims to evaluate the psychometric characteristics of the Rosenberg Self-Esteem Scale by estimating its construct validity through confirmatory factor analysis and assessing reliability using McDonald's omega. One hundred and twenty individuals diagnosed with diabetes mellitus, receiving care at primary health centers in Yogyakarta City, participated in this study. Data were collected using the Rosenberg Self-Esteem Scale. The estimation of validity and reliability was conducted using the JAMOVI software. Results show nine items of the Rosenberg Self-Esteem Scale demonstrate acceptable validity and reliability for measuring self-esteem among patients with diabetes mellitus. Consequently, the scale may be appropriately applied in diabetes management at primary health care settings