Publication Search

The increasing complexity and scale of modern network traffic driven by IoT and cloud-based infrastructures have made accurate intrusion detection a critical challenge. Conventional network intrusion detection systems (NIDS) and many deep learning–based approaches struggle to reliably detect minority and stealthy attacks due to severe class imbalance and limited discrimination of subtle traffic patterns. To address these limitations, this study proposes a hybrid CNN–RBF–Attention framework for network intrusion detection. The proposed model integrates three complementary components: (i) a convolutional neural network for hierarchical feature extraction from network flow data, (ii) a radial basis function (RBF) network for localized nonlinear classification using prototype-based decision regions, and (iii) an attention mechanism that adaptively weights RBF activations to emphasize discriminative traffic patterns. SMOTE is applied exclusively to the training data to mitigate class imbalance. The framework is evaluated on the widely used CICIDS2017 and CICIDS2018 benchmark datasets in both binary and multiclass settings, using recall, precision, F1-score, confusion matrices, and ROC analysis. Experimental results demonstrate that the proposed hybrid model consistently outperforms standalone CNN and RBF baselines, particularly in terms of recall and F1-score. On the CICIDS2018 dataset, the model achieves 99.81% accuracy and 99.81% F1-score in binary classification, and 99.54% accuracy and 99.54% F1-score in multiclass classification. On CICIDS2017, it achieves 98.12% accuracy and 98.12% F1-score in binary classification, and 98.92% accuracy and 98.92% F1-score in multiclass classification. Confusion matrix and ROC analyses further show strong class separability and reliable performance in low–false-positive-rate regions, which is critical for real-world IDS deployment. These results confirm that combining deep hierarchical feature learning, localized prototype-based classification, and attention-guided refinement yields a robust, operationally reliable intrusion detection framework for highly imbalanced network environments.

Career selection is an important process for students at Darussalam Gontor University (UNIDA) because it influences their academic development and future employment. However, many UNIDA students experience difficulties in determining suitable careers due to a lack of understanding of their psychological characteristics. This study aims to build a Decision Support System (DSS) for career recommendations for UNIDA students based on psychological test results using the Simple Additive Weighting (SAW) method. The psychological data used are non-clinical test results collected through a structured questionnaire from six respondents and converted into numerical scores. The research stages include determining criteria and weights, compiling a decision matrix, normalization process, calculating preference values, and ranking career alternatives using SAW. The career alternatives used consist of academics, corporate professionals, entrepreneurs, managers, and social/public services. The results show that the managerial career alternative obtained the highest preference value of 0.861, followed by entrepreneurs at 0.824, corporate professionals at 0.778, social/public services at 0.737, and academics at 0.703. These findings demonstrate that the SAW method is capable of providing objective and systematic career recommendations based on the psychological profiles of UNIDA students. This research is expected to assist UNIDA students and academics in making more informed career decisions tailored to individual characteristics

Freshwater fish diseases significantly affect aquaculture productivity and economic sustainability, while accurate visual classification remains challenging due to interclass similarity and image variability. This study presents a comparative evaluation of three deep learning architectures—DenseNet201, ResNet50, and EfficientNetV2-S—using a stepwise optimization strategy combined with Gradient-weighted Class Activation Mapping (Grad-CAM) for freshwater fish disease classification. Models were trained through three phases: baseline, optimized, and fine-tuned. Performance was evaluated using accuracy, precision, recall, F1 score, Matthews correlation coefficient (MCC), Cohen’s kappa, and per-class ROC–AUC. Results show consistent performance improvement across all architectures, with EfficientNetV2-S achieving the highest accuracy (97.14%), followed by ResNet50 (96.11%) and DenseNet201 (94.40%). High ROC–AUC values (>0.98) indicate strong discriminative capability. Grad-CAM analysis confirms that all optimized models focus on biologically relevant lesion regions, enhancing model transparency and reliability.

The white shrimp (Litopenaeus vannamei) is one of the popular marine shrimp species in aquaculture due to its adaptability to various environmental conditions, including a wide range of salinity, and its omnivorous feeding behavior. This study aims to determine the effect of different combinations of stocking density and salinity on the growth rate and post larval survival of vaname shrimp (Litopenaeus vannamei). The research was conducted using factorial planning based on two factors namely stocking density (3, 6, and 9ekor/L) and salinity (15 ppt and 25 ppt). Parameters measured included daily growth rate, absolute weight, survival rate, feed utilization efficiency, and feed conversion ratio (FCR). Water quality observations were also made during the study period including temperature, pH, dissolved oxygen, salinity, and total ammonia. The results showed that the combination of stocking density of 3 fish/L with salinity of 25 ppt gave the best results with a daily growth rate of 0,00664 gram and a survival rate of 86%. This treatment also produced the best feed utilization efficiency of 0.87 and the best FCR value of 1.27, indicating the most efficient use of feed. Water quality parameters during the study were within the appropriate range to support the growth of vanamei shrimp.

Vaname shrimp (Litopenaeus vannamei) has a fast growth rate, good tolerance to a wide range of salinity and temperature, and resistance to several common shrimp diseases. Vaname shrimp has an efficient feed conversion making it more economical to cultivate, and its international market demand is high. The research method used four treatments of fermented soybean meal doses, namely 0% (control), 15%, 25%, and 35%, each with 3 replications. The feed was formulated using Pearson’s Square method targeting 35% protein, and the soybean meal was fermented using tempe yeast method. The observed parameters included daily growth rate (%), absolute weight gain (grams), survival rate (%), feed utilization efficiency (FUE), and feed conversion ratio (FCR). The results showed that the treatment with 25% fermented soybean meal dose gave the best results with a daily growth rate of 6.42%, absolute weight gain of 0.22 grams, survival rate of 90.66%, and the highest feed utilization efficiency of 0.66.

Best graduate selection is crucial for academic achievement and contributes to the accreditation value of the institution. Instituto Profissional de Canossa (IPDC) is a higher education institution founded by the Canossian Sisters in Timor-Leste. To improve the effectiveness of assessment and decision-making processes, an information system is needed to assist in selecting the best graduates based on multiple criteria. This research develops a web-based Decision Support System (DSS) using the Multi-Attribute Utility Theory (MAUT) method. MAUT is a multi-criteria decision-making method that evaluates alternatives based on their utility scores across several criteria. The study uses four main criteria: attendance, academic performance, ethics, and discipline. The system is implemented as a web application for universal access. The MAUT calculation results provide valid and accurate recommendations for the best graduates. System testing showed that the application successfully ranked candidates based on defined weights and criteria, providing objective and consistent selection results.

Nutritional status plays an important role in shaping body image among adolescents, particularly female adolescents who experience rapid physical and psychosocial changes. Adolescents with nutritional problems are more likely to feel dissatisfied withitheiribody shape, whichimay lead to unhealthy behaviors such as strict dieting or excessive eating to gain weight. Thisistudy aimed toianalyze theirelationship betweeninutritional statusiand bodyiimage amongifemale adolescentsiat SMK Negeri 1 Palu. This research employedia quantitativeiapproachiwith aicross-sectionalidesign. Aitotal ofi169 femaleistudentsiwere selected using stratified random sampling. Body image data were collected using the Body Self Relation Questionnaire–Appearance Scale, while nutritional status was assessed using Body Mass Index for Age (BMI-for-Age) and Height for Age (HFA). Data were analyzed using the Spearman Rank correlation test. The results indicated that there was no significant relationship between nutritional status based on BMI-for-Age and body image, with a p-value of 0.329. Similarly, no significant relationship was found between Height-for-Age and body image among female adolescents, with a p-value of 0.892. Most respondents were aged 16–17 years, had a negative body image perception, normal BMI-for-Age nutritional status, and normal Height-for-Age category. These findings suggest that body image among female adolescents is not solely influenced by nutritional status but may also be affected by other psychosocial and environmental factors. Therefore, future research is recommended to apply a cohort study design and explore other determinants of body image, such as social media exposure, peer influence, and infectious diseases, to provide a more comprehensive understanding of factors affecting adolescent body image.

The increasing demand for housing in tropical regions requires building materials that are fast to apply, environmentally friendly, and resilient to extreme climate conditions as well as disaster risks. Conventional interlocking bricks are often chosen for their ease of construction, yet they still face challenges such as moisture and early cracking. This study proposes the innovation of the Hybrid Living Green Brick, a combination of lightweight bricks made from rice husk ash and fly ash waste (FRCB) with a biological layer of cyanobacteria. FRCB improves compressive strength by approximately 30% with the addition of 5% rice husk ash, achieving 65 kg/cm², thereby meeting Class 50 requirements (≥50 kg/cm²) according to SNI-15-2094-2000. The incorporation of 3% cyanobacteria provides an additional though not significant strength improvement, while still within the Class 50 category. It also reduces brick weight by 4.3%, with further optimization potential through cyanobacteria integration, and lowers carbon emissions from the firing process. Cyanobacteria induce the formation of CaCO₃ layers that seal pores, reduce water absorption by an average of 10%, and provide self-healing properties for microcracks. Preliminary observations indicate that FRCB offers stable mechanical performance, while biological activity was observed on the 7th day with the formation of pale-white mineral layers continuing until the 28th day. This hybrid innovation shows potential to support sustainable and disaster-resilient tropical construction by combining the mechanical strength of waste-based materials with the biological durability of cyanobacteria against extreme climates. Despite challenges related to moisture control and production standardization, the Hybrid Living Green Brick concept opens new pathways for developing environmentally friendly construction materials that are more adaptive to disaster-prone tropical conditions.

Diuretic resistance is a serious complication in heart failure patients associated with increased morbidity and mortality. Tolvaptan, a vasopressin V2 receptor antagonist, offers an alternative therapeutic mechanism through aquaresis. This study aims to evaluate the effectiveness and safety of tolvaptan in heart failure patients with diuretic resistance. A retrospective cohort study was conducted on 58 hospitalized patients with NYHA III-IV heart failure and diuretic resistance (urine output <1000 mL/day despite furosemide use ≥80 mg/day) who received tolvaptan 7.5-15 mg/day for 7 days. Variables measured included weight change, urine output, serum sodium, and kidney function. The results showed a significant increase in daily urine output from 820±230 mL to 2180±520 mL (p<0.001), along with an average weight loss of 3.4±1.1 kg (p<0.001). Hypernatremia (>145 mEq/L) occurred in 8.6% of patients. In conclusion, tolvaptan is effective in improving diuresis and reducing congestion in heart failure patients with diuretic resistance, although the risk of hypernatremia should be monitored.

Data from the 2020 LFSP (Long Form Population Census) recorded a maternal mortality ratio of 189 per 100,000 live births, while the infant mortality rate was recorded at 16.85 per 1,000 live births. The causes of maternal mortality were hemorrhage, preeclampsia/eclampsia, infection, prolonged labor, and miscarriage. Meanwhile, the majority of infant deaths were due to low birth weight, asphyxia, and infection at birth. Stunting remains a particular concern in Tegal City. Various measures have been taken, and the stunting rate has decreased to around 13.8% according to data from early 2025. This PKM is expected to increase public knowledge on caring for pregnant women, women in labor, postpartum women, and newborns, as well as preventing stunting in children, thereby reducing maternal and infant mortality rates. The methods used in this activity include health education and outreach with a promotive and preventive approach, targeting pregnant women and mothers with infants and toddlers. Community service was held on Wednesday, December 17, 2025, from 8:30 a.m. to 12:00 p.m. at the Boegenvil Health Center in Cabawan Village, Tegal City, with 53 participants. The results of this activity showed an increase in the level of knowledge of the participants, from 11 people with a good level of knowledge to 41 people after receiving counseling, with 3 participants still having a low level of knowledge.

Hypertension, a global health issue, is increasingly prevalent and significantly contributes to morbidity and mortality. It often coexists with obesity, a key risk factor for hypertension and vascular complications. The combination of hypertension and obesity leads to metabolic changes, chronic inflammation, and oxidative stress that damage retinal blood vessels, directly affecting visual acuity. This literature review examines the relationship between hypertension, obesity, and visual acuity, analyzing 20 articles published between 2021 and 2025, sourced from PubMed, Google Scholar, and ScienceDirect. The study found a significant association between hypertension and obesity with decreased visual acuity. Obesity not only serves as a comorbidity but also as a mediator, worsening hypertension's effects through mechanisms like insulin resistance and endothelial dysfunction. Longitudinal studies indicate that visual impairment is progressive, while cross-sectional studies highlight its high prevalence in hypertensive obese populations. The review emphasizes the need for routine eye exams, blood pressure control, and weight management as preventive measures. In conclusion, hypertension and obesity together significantly increase the risk of visual impairment, necessitating a multidisciplinary approach to care and promoting preventive strategies to preserve eye health and enhance patients' quality of life.

Malnutrition and stunting among children under five remain major public health challenges in developing countries, including Indonesia. These conditions are associated with increased morbidity, mortality, impaired cognitive development, and reduced productivity in adulthood. Stunting reflects chronic nutritional deficiencies, while severe malnutrition indicates acute or prolonged inadequate nutrient intake, often exacerbated by infections, poor caregiving practices, and unfavorable socioeconomic conditions. This case report aims to describe the clinical condition, contributing factors, management, and outcomes of a 14-month-old female toddler diagnosed with severe malnutrition and stunting without complications in Blang Dalam Geuteung Village, Nisam Subdistrict, North Aceh Regency. The assessment was conducted using a family medicine approach, incorporating detailed history taking, physical examination, anthropometric measurements, and nutritional status evaluation based on World Health Organization Z-score indicators. Interventions included nutritional rehabilitation through appropriate dietary intake, family education on balanced nutrition and proper feeding practices, routine growth monitoring, and optimization of primary healthcare services. The results showed gradual improvement in the child’s nutritional status, evidenced by weight gain, better appetite, and improved feeding patterns following the intervention. This case highlights the importance of early detection, comprehensive family-centered management, and continuous monitoring in addressing malnutrition and stunting at the primary care level. Strengthening community-based interventions, improving caregiver knowledge, and enhancing collaboration between healthcare providers and families are essential to reduce the burden of malnutrition and support optimal child growth and development.

Data from the 2020 LFSP (Long Form Population Census) recorded a maternal mortality ratio of 189 per 100,000 live births, while the infant mortality rate was recorded at 16.85 per 1,000 live births. The causes of maternal mortality were hemorrhage, preeclampsia/eclampsia, infection, prolonged labor, and miscarriage. Meanwhile, the majority of infant deaths were due to low birth weight, asphyxia, and infection at birth. Stunting remains a particular concern in Tegal City. Various measures have been taken, and the stunting rate has decreased to around 13.8% according to data from early 2025. This PKM is expected to increase public knowledge on caring for pregnant women, women in labor, postpartum women, and newborns, as well as preventing stunting in children, thereby reducing maternal and infant mortality rates. The methods used in this activity include health education and outreach with a promotive and preventive approach, targeting pregnant women and mothers with infants and toddlers. Community service was held on Wednesday, December 17, 2025, from 8:30 a.m. to 12:00 p.m. at the Boegenvil Health Center in Cabawan Village, Tegal City, with 53 participants. The results of this activity showed an increase in the level of knowledge of the participants, from 11 people with a good level of knowledge to 41 people after receiving counseling, with 3 participants still having a low level of knowledge.

Tuberculosis (TB) is a chronic, infectious disease caused by the bacterium Mycobacterium tuberculosis. Primary infection occurs upon first exposure to bacillary tuberculosis, which often occurs in childhood, hence the term "childhood TB." The diagnosis of TB is usually made through a history that includes complaints of persistent cough, weight loss, fever, and weakness, along with a chest X-ray that shows typical abnormalities of pulmonary TB. In this case, a 21-month-old girl presented with a worsening, persistent cough accompanied by weight loss. The patient's mother reported that her child frequently had fevers and appeared weak. After a physical examination and supporting tests, the patient was diagnosed with TB. The patient was given pharmacological therapy in the form of anti-tuberculosis drugs (OAT), and parents were educated about the importance of adherence to TB treatment as prescribed by the doctor. Furthermore, providing a balanced, nutritious diet is recommended to support successful treatment.

Floods and landslides in Hutanabolon Village, Tukka District, Central Tapanuli Regency have disrupted access to food and health services, particularly for vulnerable groups such as children. Public kitchens, as the frontline of emergency nutrition response, face challenges in providing food that meets the specific nutritional needs of children. This study aims to evaluate the effectiveness of public kitchens at Disaster Emergency Response Posts (TDB) in meeting the nutritional needs of post-disaster children, identify supporting and inhibiting factors, and formulate recommendations for improving the public kitchen management system. The research employed a descriptive evaluative approach using survey methods, structured interviews, direct observation, 24-hour dietary recall, and anthropometric measurements (weight and height). The study subjects included 15 children aged 1–12 years and 8 public kitchen managers selected purposively. Data were analyzed descriptively by comparing nutritional intake against the Recommended Dietary Allowance (RDA) standards and analyzing kitchen management practices based on emergency nutrition guidelines. The findings revealed that children's average energy intake was only 1,140 kcal/day (below the minimum standard of 1,200–2,000 kcal/day) and protein intake was 18.7 g/day (below the standard of 20–35 g/day). A total of 33.3% of children were classified as having malnutrition to severe malnutrition based on weight-for-age indicators. Public kitchen management showed weaknesses in menu planning (100% had no child-specific menu), managers' nutritional knowledge (62.5% categorized as low), food availability (75% relied on instant aid without variation), and limited cross-sectoral coordination (50%). The effectiveness of public kitchens in meeting children's nutritional needs after disasters remains low.

Low parental literacy regarding nutrition, parenting, and lack of utilization of Posyandu services as well as low father participation are among the factors contributing to the continued existence of malnutrition and stunting risks at the Flamboyan 3-4 Ulu Posyandu. This study aims to identify the root causes of low parental literacy, map its impact on the condition of toddlers, and evaluate two alternative policies to improve the quality of parenting education. This study uses a mixed method with a predominance of descriptive qualitative data. Data were collected through interviews, observations, questionnaires, and anthropometric data. Policy analysis was conducted using the six evaluation criteria of William Dunn (1999), namely effectiveness, efficiency, adequacy, fairness, responsiveness, and accuracy. The results of the study show that of the 13 children examined in August-September, there were 3 children whose weight and height were not appropriate for their age. The three main factors causing this problem were limited knowledge about nutrition and feeding, low understanding of child growth and development, and minimal use of posyandu services, including the involvement of fathers. The impact of this condition is evident in several toddlers with Z-scores for weight-for-age and height-for-age below the standard. Two policy alternatives were evaluated: the Healthy Family Room Program (RKS) and the 1000 HPK Home-to-Home Counseling Program. The evaluation results show that the RKS Program received the highest score with an average of 3.3, making it more feasible to implement because it is more effective, sufficiently efficient, and more responsive to family needs.

The construction and infrastructure sectors are shifting toward lighter, low-emission, and sustainable materials in response to the high carbon footprint and excessive weight of common materials such as concrete and steel. One promising alternative widely developed is natural fiber–based composites. However, studies comparing mechanical properties of variations of natural fibers within a single framework remain limited. This study aims to evaluate and compare composite mechanical properties reinforced by sisal fiber, bamboo fiber, and pineapple leaf fiber to determine the optimal fiber type for sustainable infrastructure applications. The research methodology involved fabrication of composite specimens using a unidirectional fiber configuration with a resin matrix, molded following ASTM D638 Type I dimensional and geometrical requirements. Tensile testing was conducted to evaluate mechanical responses, including ultimate tensile behavior, deformation characteristics, and elastic properties, which were presented in tabular and graphical forms. The results show that incorporation of all natural fiber types significantly enhanced composite mechanical properties, exhibiting an average tensile strength of approximately 26 MPa. Pineapple leaf fiber demonstrated balanced mechanical behavior combining strength and ductility, while sisal fiber showed superior tensile resistance and rigidity. Bamboo fiber provided moderate mechanical improvement. Overall, natural fiber–reinforced composites demonstrate strong potential as environmentally friendly alternative materials for infrastructure applications, with mechanical characteristics adjustable based on reinforcing fiber type.

Strategies to increase the income of self -help palm oil farmers can help farmers to increase production yields. This study aims to formulate and obtain strategies in an effort to increase the income of oil palm farmers. This research was conducted in Kalis District, Kapuas Hulu Regency. This study was carried out from April 5 to May 524. This study used a descriptive quantitative method with case study methods and identified internal factors (strengths and weaknesses) and external (opportunities and threats) used for the strategy to increase the income of oil palm farmers in the sub -district dull. The variables used in this study were obtained from indicators of strengths, weaknesses, opportunities and threats. Based on the results of the research results of the collection, processing and analysis of the main internal factors, it is found that the main strength factor of farmers is the status of land ownership and land area owned by farmers with a weight score of 0.41. As for the main weakness of self -help farmers is inadequate access to infrastructure with a weight score of 0.18 and the total score of the IFE matrix is ​​2.51. For data analysis of the main external factors, it is found that the main opportunity factor of farmers is oil palm can be a term investment for farmers with a weight score of 0.41. As for the main threat of self -help farmers is a long queue at the Palm Oil Mill (PKS) with a weight score of 0.18 and the total score of the IFE matrix is ​​2.62. The results of processing internal and external data of farmers using the IE matrix show that the position of farmers is in quadrant I, the suitable strategy is an aggressive strategy that can support the growth of oil palm farming.

This study aimed to determine the effect of different bait types on the catch of larval shrimp (Macrobrachium lar) using a lift net and to determine the best bait type in the waters of Cijeruk Indah, Garut Regency, West Java. The method used in this study was an experimental method with nine replications. The independent variables in this study consisted of three types of bait: earthworms, fine rice husks, and pellets, while the dependent variable was the weight of the larval shrimp caught. The results showed that different bait types significantly affected the larval shrimp catch. Based on the total catch during the study, pellet bait yielded the highest yield, with a total weight of 2,316 grams. This was followed by fine rice husk bait with a total weight of 1,256 grams, and earthworm bait with the lowest yield, at 364 grams. Data analysis using ANOVA showed a significance value of 0.031 (p < 0.05), confirming a significant difference in catch responses between the three bait types. In conclusion, pellets are the most effective type of bait to use in the anco net fishing gear in catching larval shrimp at the research location.

The determination of scholarship recipients is a very important process in supporting students’ educational success, particularly in providing fair opportunities for high-achieving students who require financial assistance. However, in practice, this process often faces various challenges, such as assessor subjectivity and uncertainty in evaluating the applied criteria. Therefore, a decision support system is needed to assist decision-making in an objective and measurable manner. This study aims to implement the Fuzzy Tsukamoto method as a decision support system for determining scholarship eligibility. The criteria used in this study include Grade Point Average (GPA) as an indicator of academic achievement and parents’ income as an indicator of students’ economic conditions. The Fuzzy Tsukamoto method was selected because it is capable of producing crisp output values based on predefined fuzzy rules. Student data were processed through several stages, namely fuzzification to transform input data into fuzzy values, inference using the minimum operator, and defuzzification using the weighted average method. The results of the study indicate that the application of the Fuzzy Tsukamoto method is able to generate more objective, consistent, and measurable decisions. Based on the calculation results, a scholarship eligibility score of 63.9 was obtained, which falls into the eligible category. Thus, the Fuzzy Tsukamoto method can be considered an effective alternative to support fair, systematic, and transparent decision-making in determining scholarship recipients.