Garuda - Garba Rujukan Digital

Classification of Breast Cancer Using the Digital Mammogram Method Anggi Rizky Windra Putri
JATISI (Jurnal Teknik Informatika dan Sistem Informasi) Vol 9 No 4 (2022): JATISI (Jurnal Teknik Informatika dan Sistem Informasi)
Publisher : Lembaga Penelitian dan Pengabdian pada Masyarakat (LPPM) STMIK Global Informatika MDP

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/jatisi.v9i4.2578

Abstract Breast cancer threatens the female population worldwide. Prevention with early detection of this disease is essential in reducing mortality. The primary purpose of this study is to analyze the classification of breast cancer and determine the categories of normal and malignant cancers with computer-assisted detection and diagnosis (CAD) to detect the disease immediately. In this study, we offer a prototype of a breast cancer classification system using a digital mammogram method based on comparing the collaboration features of the Histogram and Gray Level Co-occurrence Matrix (GLCM). The results of this study indicate that the level of accuracy reached the value of 97.67%, sensitivity 98.40%, specificity 97.63%, and ROC 97.70%. This study serves to assist radiologists as a consideration in making decisions.

AST GRAPH FEATURES FOR CODE SIMILARITY SCREENING IN A CONTROLLED SYNTHETIC STUDY Reynaldy Nurcahyo; Anggi Rizky Windra Putri; Tasiu Abdullahi Yusuf
International Journal of Cyber Engineering Jil. 2 No. 1 (2026): International Journal of Cyber Engineering - June Edtition
Publisher : PT Baramedia Literasi Digital

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.68404/ijce.v2i1.25

Source-code similarity screening must distinguish lexical resemblance, structural similarity, behavioural agreement, and evidence of plagiarism. This study evaluates how identifier normalisation and abstract syntax tree (AST) graph features respond to controlled code transformations. A reproducible synthetic corpus contains 140 Python programs derived from 20 algorithm roots and 160 labelled pairs. Ten roots supply 80 validation pairs for threshold selection, while ten disjoint roots supply 80 test pairs. Positive pairs agree on 200 bounded input cases, whereas each negative pair has a recorded behavioural counterexample. Five deterministic representations are compared using cosine similarity: raw token trigrams, normalised token trigrams, an AST node histogram, and two graph-refinement variants with or without literal values. Normalised tokens achieved the highest test F1-score of 0.857, compared with 0.655 for raw tokens, 0.659 for the node histogram, and 0.667 for each graph-refinement variant. The identical graph F1-scores concealed opposite failure modes: the literal-preserving representation missed 20 positive pairs, whereas the literal-blind representation accepted all 40 negative pairs. Removing literal values therefore made behaviour-changing mutations indistinguishable from their source graphs. These findings identify representation and threshold trade-offs rather than demonstrating general superiority of graph methods. The contribution is an auditable pilot protocol and a transformation-level analysis of structural similarity failures.

DESIGN AND SIMULATION OF A TASK REMINDER WITH SPACED REVIEW AND DEADLINE PRESSURE DETECTION Hizba Muhammad Falah; Anggi Rizky Windra Putri; Tasiu Abdullahi Yusuf
International Journal of Cyber Engineering Jil. 2 No. 1 (2026): International Journal of Cyber Engineering - June Edtition
Publisher : PT Baramedia Literasi Digital

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.68404/ijce.v2i1.26

Describe Task reminders commonly indicate when an assignment is due, but deadline counts alone do not describe the effort required before each due date. Moreover, repeated notifications are not equivalent to retrieval-based spaced review. This study develops an explicit scheduling specification for an existing task-reminder prototype and evaluates a separate executable reference engine. The design combines a recall-dependent review rule, a cumulative deadline-pressure calculation, and an event resolver that distinguishes review prompts from deadline checks. Evaluation comprises 23 functional checks, three scripted review sequences, and 300 synthetic workload scenarios containing 1,150 task records. All functional checks passed. At an assumed capacity of two hours per day and a 72-hour horizon, count-based, aggregate-load, and cumulative deadline-pressure rules flagged 100, 100, and 150 scenarios, respectively. In 50 deliberately constructed early-bottleneck scenarios, only the cumulative rule flagged insufficient capacity before the earliest deadline. Conversely, all 50 light clustered workloads triggered the count rule without exceeding the assumed capacity. An independent exhaustive scheduling oracle agreed with the cumulative rule in all 300 scenarios; agreement was 50.0% for the count rule and 83.3% for the aggregate rule. These results verify logic under the stated capacity model. They do not establish improved retention, productivity, or student well-being. The contribution is a reproducible prototype extension with transparent assumptions and an evidence-based separation of reminder functionality from educational effectiveness.

A SIMULATION STUDY OF INDONESIAN SENTIMENT CLASSIFICATION FOR A WHATSAPP STUDENT SUPPORT CHATBOT Dian Dwi Lestari; Anggi Rizky Windra Putri; Tasiu Abdullahi Yusuf
International Journal of Cyber Engineering Jil. 2 No. 1 (2026): International Journal of Cyber Engineering - June Edtition
Publisher : PT Baramedia Literasi Digital

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.68404/ijce.v2i1.27

Short Indonesian messages may help institutions organise student support requests, but sentiment polarity does not directly measure psychological well-being. This study evaluates a text-classification component intended for a WhatsApp student support chatbot through a fully synthetic, reproducible simulation. A constructed corpus contains 360 messages from 60 scenario families across six support domains. Families, including their positive and negative variants, are separated into training, validation, and test partitions of 216, 72, and 72 messages. A further 48 synthetic messages test negation, abbreviations, language mixing, and explicitly mixed sentiment. Term frequency–inverse document frequency features and multinomial Naïve Bayes are compared with a constant baseline and logistic regression. On the held-out synthetic test set, Naïve Bayes achieves accuracy of 0.875 and macro-F1 of 0.875, matching logistic regression on both aggregate metrics. On the challenge set, its accuracy decreases to 0.813 and macro-F1 to 0.806. Negation is the weakest scenario, with six correct predictions out of twelve; all six positive negation examples are misclassified. Feature inspection links selected errors to polarity-bearing words and unseen abbreviations. The results establish a reproducible computational baseline and expose limitations obscured by aggregate scores. They do not validate real student conversations, live WhatsApp integration, stress detection, or improvements in well-being.

DESIGN AND IMPLEMENTATION OF A WEB-BASED EMPLOYEE ATTENDANCE SYSTEM WITH FUNCTIONAL EVALUATION Tri Yanto; Anggi Rizky Windra Putri; Tasiu Abdullahi Yusuf
International Journal of Cyber Engineering Jil. 2 No. 1 (2026): International Journal of Cyber Engineering - June Edtition
Publisher : PT Baramedia Literasi Digital

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.68404/ijce.v2i1.28

Manual attendance administration can fragment records and complicate the consolidation of employee arrival and departure information. This study presents the design and implementation of a web-based employee attendance system for centralised recording and administrative reporting. An applied system-development approach followed the Waterfall stages of requirements analysis, design, implementation, and functional testing. The application provides employee login, check-in, check-out, attendance history, and administrative interfaces for master data, reports, and leave requests. Evaluation used a black-box test table containing eight documented scenarios covering authentication, attendance recording, employee-data maintenance, report display, and logout. Seven scenarios have internally consistent input–output descriptions and are reported as successful. The remaining login scenario duplicates the valid-credential input while expecting an error message, leaving its interpretation unresolved. The results support a limited conclusion about the reported operation of the documented functions; they do not establish comprehensive system reliability or improvements in employee discipline, productivity, or administrative efficiency. The contribution is an application-level account linking the attendance workflow, role-specific interfaces, and functional-test evidence. Further evaluation should resolve the ambiguous test case, document the execution environment, and measure operational and organisational outcomes using traceable study data.

DESIGN OF A WEB-BASED LEARNING PROTOTYPE INTEGRATING MULTIMEDIA CONTENT, INTERACTIVE ASSESSMENT, AND PROGRESS TRACKING Risqi Setiawan; Anggi Rizky Windra Putri; Tasiu Abdullahi Yusuf
International Journal of Cyber Engineering Jil. 2 No. 1 (2026): International Journal of Cyber Engineering - June Edtition
Publisher : PT Baramedia Literasi Digital

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.68404/ijce.v2i1.29

Web-based learning environments increasingly combine multimedia resources, assessment tools, and progress information, but the coexistence of these features does not ensure a coherent learning workflow. This study develops a design specification for a web-based learning prototype integrating multimedia content, interactive assessment, and activity-based progress tracking. The reported work covers requirements analysis, traceability mapping, a three-layer architecture, a logical data model, an access-and-learning workflow, and four interface views within a staged Waterfall-oriented design process. Progress is defined through explicit activity-completion states rather than inferred from resource access or assessment scores. A prospective evaluation protocol separates functional verification, media-expert appraisal, subject-matter review, and intended-user feedback. The design is positioned against recent evidence on multimedia learning, online assessment, learning analytics, and LMS development. The available evidence supports the internal coherence and traceability of the proposed design but does not establish operational reliability, usability, learning gains, or engagement effects. The study therefore contributes a bounded integration design and an auditable evaluation framework for subsequent implementation and empirical testing.

Title

Found 6 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 6 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 6 Documents
Search