cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
-
Contact Email
-
Phone
-
Journal Mail Official
-
Editorial Address
-
Location
Kab. minahasa utara,
Sulawesi utara
INDONESIA
CogITo Smart Journal
Published by Universitas Klabat
ISSN : 25412221     EISSN : 24778079     DOI : -
Core Subject : Science, Education, Engineering,
Computer Science & IT Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering
CogITo Smart Journal adalah jurnal ilmiah di bidang Ilmu Komputer yang diterbitkan oleh Fakultas Ilmu Komputer Universitas Klabat anggota CORIS (Cooperation Research Inter University) dan IndoCEISS (Indonesian Computer Electronics and Instrumentation Support Society). CogITo Smart Journal dua kali setahun, yaitu setiap bulan Juni dan Desember. CogITo Smart Journal menerima berbagai naskah yang sifatnya baru dan asli dari hasil penelitian, telaah pustaka, dan resensi buku dari bidang Ilmu Komputer dan Informatika yang boleh ditulis dalam Bahasa Indonesia atau Bahasa Inggris. Kata CogITo berasal dari Bahasa Latin yang berarti I Think. Sehihngga CogITo Smart berarti I Think Smart dalam Bahasa Inggris.
Arjuna Subject : -
Articles 22 Documents
 1   2   3 
Search results for , issue "Vol. 10 No. 2 (2024): Cogito Smart Journal" : 22 Documents clear
Analysis Comparison of K-Nearest Neighbor, Multi-Layer Perceptron, and Decision Tree Algorithms in Diamond Price Prediction Kamila, Ahya Radiatul; Andry, Johanes Fernandes; Kusuma, Adi Wahyu Candra; Prasetyo, Eko Wahyu; Derhass, Gerry Hudera
CogITo Smart Journal Vol. 10 No. 2 (2024): Cogito Smart Journal
Publisher : Fakultas Ilmu Komputer, Universitas Klabat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31154/cogito.v10i2.532.298-311

Abstract

Diamond price predictions are essential due to the high demand for these gemstones, valued as investments and jewelry. Diamonds are expensive due to their rarity and extraction process. Their prices vary depending on key factors like the diamond's inherent value and secondary factors such as marketing costs, brand names, and market trends. These variations often confuse customers, potentially leading to investment losses. This research aims to help investors determine the true price of diamonds based solely on their intrinsic value, excluding secondary factors. A machine learning approach was utilized to predict diamond prices, focusing on primary determinants. Three models such as Multi-Layer Perceptron (MLP), Decision Tree, and K-Nearest Neighbor (KNN) were compared with manual hyperparameter tuning to identify the best performing algorithm. Model performance was evaluated using Mean Absolute Percentage Error (MAPE), Mean Absolute Error (MAE), and Mean Squared Error (MSE). Among the models, KNN demonstrated the best results, achieving MAPE, MAE, and MSE values of 1.1%, 0.00038, and 〖2.687 x 10〗^(-6) respectively. This study offers valuable insights for investors by accurately predicting diamond prices based on fundamental attributes, minimizing the impact of secondary factors.
Predicting Stock Market Trends Based on Moving Average Using LSTM Algorithm Permana, Rizki Surya; Mahyastuty, Veronica Windha; Budiyanta, Nova Eka; Bachri, Karel Octavianus; Kartawidjaja, Maria Angela
CogITo Smart Journal Vol. 10 No. 2 (2024): Cogito Smart Journal
Publisher : Fakultas Ilmu Komputer, Universitas Klabat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31154/cogito.v10i2.648.486-495

Abstract

Prediction of the stock market is highly needed to assist traders in making decisions. Many methods are used by traders to predict this such as technical analysis and moving averages. Moving averages predict stock trends based on the past data of the stock. The disadvantage of using a moving average analysis is the delay in crossover signals. As a solution, a deep learning technique known as LSTM is applied to the moving average strategy in this paper. In this research, the BBCA stock dataset spanning from 2010 to 2018 was utilized. The data was segmented into two parts: 2010-2017 for training data and 2018 for testing data. The training process employed Long Short-Term Memory (LSTM) networks, with the subsequent results being combined with moving average crossover techniques. Validation results indicate that BBCA shows a relatively minimal error. BBCA's average MAPE is 1.1%, and its RMSE is 65.402, classifying it within the "Highly Accurate Forecasting" category. Various combinations of moving average crossovers were tested during model training, with the combination of SMA05 and SMA50 for BBCA yielding the highest profit potential. Stocks that exhibit a downward trend are more likely to incur substantial losses. The model can predict the reversal of trends by predicting the trading signal given by the moving averages.
A Usability Study of Augmented Reality Indoor Navigation using Handheld Augmented Reality Usability Scale (HARUS) Nendya, Matahari Bhakti; Mahastama, Aditya Wikan; Setiadi, Bantolo
CogITo Smart Journal Vol. 10 No. 2 (2024): Cogito Smart Journal
Publisher : Fakultas Ilmu Komputer, Universitas Klabat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31154/cogito.v10i2.658.326-338

Abstract

Indoor Navigasi barbasis Augmented Reality (AR) telah muncul sebagai metode yang belum pernah ada sebelumnya dan inventif dalam membantu dan mengarahkan pengguna saat mereka melintasi lanskap dalam ruangan yang rumit, termasuk kampus dan bangunan. Efektifitas penerapan sistem navigasi indoor berbasis AR sebagian besar bergantung pada kemudahan penggunaan dan kemahiran pengguna dalam menggunakan teknologi ini. Studi ini bertujuan untuk mengevaluasi secara komprehensif kegunaan navigasi dalam ruangan berbasis AR dengan fokus utama pada aspek manipulability dan comprehenesibility teknologi AR, menilai seberapa efektif teknologi tersebut memfasilitasi navigasi dalam ruang dalam ruangan. Untuk mencapai hal ini, Handheld Augmented Reality Usability Scale (HARUS) digunakan sebagai kerangka evaluasi. Penelitian ini melibatkan pembuatan aplikasi navigasi dalam ruangan berbasis AR menggunakan penanda "DutaNavAR," yang dirancang khusus untuk digunakan di Gedung Agape di Universitas Kristen Duta Wacana. Evaluasi tersebut memberikan hasil yang patut dicatat, dengan rata-rata skor manipulability sebesar 75,19 dan rata-rata skor comprehensibility sebesar 81,63. Secara ringkas, rata-rata keseluruhan skor HARUS yang diperoleh adalah 78,41. Skor ini menunjukkan tingkat kepuasan pengguna yang tinggi terhadap interaksi dan pengalaman keseluruhan aplikasi navigasi dalam ruangan. Temuan ini menggarisbawahi dampak positif teknologi AR dalam meningkatkan navigasi dalam ruangan, yang mana lebih menekankan kegunaan dan kemudahan penggunaan aplikasi berbasis AR dalam dalam ruangan yang kompleks.
Comparative Analysis of Clustering Approaches in Assessing ChatGPT User Behavior Setiawan, Dedy; Arsa, Daniel; Enggrani Fitri, Lucky; Fadhila Putri Zahardy, Farah
CogITo Smart Journal Vol. 10 No. 2 (2024): Cogito Smart Journal
Publisher : Fakultas Ilmu Komputer, Universitas Klabat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31154/cogito.v10i2.661.366-379

Abstract

ChatGPT is an artificial intelligence technology that is widely used and discussed. The technology invites mixed responses from various parties, mainly because of the benefits and risks of its use in multiple fields. Jambi University students also feel the influence of ChatGPT's presence in education. To determine the behavior of Jambi University students in using ChatGPT, four UTAUT variables were used, namely Performance Expectancy (PE), Effort Expectancy (EE), Social Influence (SI), and Facilitating Condition (FC) as independent variables in measuring the behavior of using ChatGPT. Where UTAUT states these four variables have a positive influence on the actual behavior of technology use. This study used K-Means and K-Medoids Clustering to group Jambi University students based on ChatGPT usage behavior. Based on the Silhouette Score calculation, each method's optimal number of clusters is 2. K-Means is considered more optimal in forming 2 clusters because it obtained a Silhouette Score of 0.2123864, higher than K-Medoids, which is 0.1766865.
Implementation of SAW and AHP in Decision-Making Models for Credit Provision in Cooperatives Rojakul, Rojakul; Sumardianto, Sumardianto; Triyono, Gandung
CogITo Smart Journal Vol. 10 No. 2 (2024): Cogito Smart Journal
Publisher : Fakultas Ilmu Komputer, Universitas Klabat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31154/cogito.v10i2.662.418-432

Abstract

The research aims to overcome the difficulties in selecting the best members of the Al-Amin Independent Corporation, focusing on the challenges faced in determining the best members in the process of giving credit and payments on time. However, many members fail to meet their obligations or fail to pay their contributions smoothly, leading to credit freezes and decreased cooperative income. The cause of a member's failure to pay quotas has not been identified by the current candidate admission selection system. The methods used are Simple Additive Weighting (SAW) and Analytical Hierarchy Process (AHP) applied in the Decision Support System (DSS) model. The results of the research showed the effectiveness of the SAW method in identifying the best and optimal alternative with the highest value on V2 of 4. The AHP method has successfully determined the priority weight and the level of importance for member selection criteria including Activity (0.50), Savings (0.13), Guarantee (0.09), Loan (0.10), Disbursement (0.10), Time Period (0.07). The research provides insight to decision-makers in cooperatives makes important contributions, especially in the granting of credit, and affirms the importance of objective methods in the selection of members.
Web-Based Village CCTV Information System to Support Smart City in Yogyakarta Prabowo, Hanang; Wahyuningrum, Dwi; Dewi Alfiani, Oktavia; Apriyanti, Dessy; Srinarbito, Adhiyatma
CogITo Smart Journal Vol. 10 No. 2 (2024): Cogito Smart Journal
Publisher : Fakultas Ilmu Komputer, Universitas Klabat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31154/cogito.v10i2.664.339-351

Abstract

Smart city dan safe city merupakan konsep kota modern berbasis teknologi informasi yang telah diterapkan di banyak kota besar di dunia. Smart city mencakup pengembangan kota berbasis teknologi informasi dan komunikasi dengan integrasi infrastruktur yang baik. Salah satu contoh penerapannya adalah pemasangan CCTV Kampung di Kota Yogyakarta. Untuk pengoperasian CCTV yang optimal, diperlukan sistem yang terintegrasi antar berbagai stakeholder. Dalam konteks tersebut, sistem informasi berbasis website dapat digunakan sebagai media untuk menggabungkan berbagai aspek. Website ini dikembangkan dengan menggunakan PHP MySQL sebagai basis data, bahasa pemrograman JavaScript dan PHP untuk logika dan fungsionalitas, HTML sebagai struktur website, dan desain tampilan menggunakan Bootstrap. Penelitian ini menggunakan metode kualitatif dan menghasilkan Website CCTV Kampung yang mempunyai tujuan utama memberikan informasi tentang CCTV secara efisien dan efektif terutama dalam hal pengelolaan CCTV. Pengguna dapat mengakses informasi terkait CCTV kampung dengan cepat dan akurat. Dengan demikian, sistem ini menjadi sarana penting dalam meningkatkan keamanan, kenyamanan, dan pengawasan di desa.
Evolution and Research Opportunities of Digital Forensic Tools: A Bibliometric Analysis Dwi Syahputri, Rischi; Anggono, Alexander; Prasetyono, Prasetyono; Djasuli, Mohamad
CogITo Smart Journal Vol. 10 No. 2 (2024): Cogito Smart Journal
Publisher : Fakultas Ilmu Komputer, Universitas Klabat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31154/cogito.v10i2.675.474-485

Abstract

The use of digital technology has increased rapidly, presenting new challenges such as cybercrime, online fraud and money laundering. To address these threats, digital forensic tools have become crucial in investigating and analyzing electronic evidence to combat increasingly complex digital crimes. Therefore, research and development in the field of digital forensics is crucial to address the growing digital security challenges. This study aims to conduct a bibliometric analysis of digital forensic tools research in the business, management and accounting domains over the past ten years, evaluate the evolution of the research, identify promising research opportunities and provide insights into future directions in the field. Bibliometric analysis was conducted with the help of VOSviewer software on 698 Scopus-indexed articles sourced from ScienceDirect during 2014-2023. Based on the network map analysis, it was found that despite much progress, the field continues to evolve and offers many opportunities for further research and innovation in digital forensic tools related to mobile forensics, memory forensics, anti-forensics, malware analysis, cloud forensics, cybersecurity, machine learning and deep learning, and ethics and privacy in forensic investigations.
Sentiment Classification of IT Service Feedback via TF-IDF Samidi, Samidi; Fatmawati, Devy
CogITo Smart Journal Vol. 10 No. 2 (2024): Cogito Smart Journal
Publisher : Fakultas Ilmu Komputer, Universitas Klabat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31154/cogito.v10i2.701.403-417

Abstract

Handling user complaints and feedback is a key strategy of Pusintek, the Ministry of Finance of the Republic of Indonesia, to enhance user satisfaction. The challenge faced is the difficulty in accurately analyzing feedback due to differences in comments and categories chosen by users, which requires manual category correction. This study aims to automate feedback comment categorization using classification algorithms. Specifically, Naïve Bayes, Support Vector Machine (SVM), and K-Nearest Neighbors (K-NN) algorithms were applied to 11,108 user feedback records. The CRISP-DM framework was used, with dataset preparation involving sentiment analysis techniques (cleansing, case folding, normalization, filtering, and tokenization) and Term Frequency-Inverse Document Frequency (TF-IDF) weighting. Accuracy values for each algorithm were evaluated. Results show that the SVM algorithm performed the best, achieving an accuracy of 94.10% and consistently delivering the highest precision, recall, and f1-score across all sentiment categories. This research contributes to the development of an automatic feedback classification system that improves categorization accuracy, minimizes manual intervention, and optimizes user feedback analysis. It is expected to enrich the understanding of text classification and natural language processing techniques and open up opportunities for further research.
U-MATE : Student And Lecturer Location-Based Social Network Aplication Tombeng, Marchel Thimoty; Mandias, Green F.; Putra, Edson Yahuda
CogITo Smart Journal Vol. 10 No. 2 (2024): Cogito Smart Journal
Publisher : Fakultas Ilmu Komputer, Universitas Klabat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31154/cogito.v10i2.714.352-365

Abstract

Students are individuals who pursue higher educcation, have an important role as agents of change and future leaders in various sectors. They are required to actively learn, participate in academic and social activities, and develop critical and innovative thinking. Interactions between students, both with peers and lecturers, play a crucial role in shaping the learning experience on campus. Student interactions with lecturers also have an impact on learning motivation and the lecture experience. The importance of these interactions prompted the researcher to design an application specifically for the campus environment. The app features chat, add friend, and find mate to expand students' social interactions. The find mate feature allows students to find friends randomly, while the maps feature makes it easier for them to find the location of their lecturers and friends in real-time. By integrating the concept of Location-Based Social Network (LBSN), this application is expected to reduce the level of academic stress and improve the quality of interaction among students and with lecturers. Through this application, students can more easily find friends and lecturers, and share locations in real-time. The questionnaire results from Klabat University students showed the need for this kind of application
Generalized Linear Mixed-Model Tree for Modeling Dengue Fever Cases Setiawan, Erwan; Notodiputro, Khairil Anwar; Sartono, Bagus
CogITo Smart Journal Vol. 10 No. 2 (2024): Cogito Smart Journal
Publisher : Fakultas Ilmu Komputer, Universitas Klabat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31154/cogito.v10i2.715.380-392

Abstract

The GLMM tree demonstrates flexibility when applied to complex dataset structures such as multilevel and longitudinal data. However, there has been no assessment of the performance of GLMM trees on panel data structures. This study aims to assess the performance of the GLMM tree on a panel data structure using a case study of dengue fever cases in West Java. The performance evaluation focuses on the accuracy of the model. The dataset includes cross-sectional data from 27 regencies/cities in West Jawa, covering different regions at a single point in time, and time-series data from 2014 to 2022, tracking dengue fever cases over the years. The results of this study show that the GLMM tree model is suitable for panel data that exhibit nuanced or intricate variability unrelated to temporal effects. When developing the incidence rate of the dengue fever model, the GLMM tree separates into two submodels depending on a GRDP growth rate threshold of 5.5%. The GLMM tree model shows significant differences in the incidence rate of dengue fever between regencies/cities. However, the differences in the incidence rate of dengue fever from year to year between the regencies/cities are not significant. It indicates that local factors, such as research predictor variables, are more dominant in influencing the incidence rate than global factors.

Page 1 of 3 | Total Record : 22

 1   2   3 

Filter by Year

2024 2024


Reset
Filter By Issues
All Issue Vol. 11 No. 2 (2025): Cogito Smart Journal Vol. 11 No. 1 (2025): Cogito Smart Journal Vol. 10 No. 2 (2024): Cogito Smart Journal Vol. 10 No. 1 (2024): Cogito Smart Journal Vol. 9 No. 2 (2023): Cogito Smart Journal Vol. 9 No. 1 (2023): Cogito Smart Journal Vol. 8 No. 2 (2022): Cogito Smart Journal Vol. 8 No. 1 (2022): Cogito Smart Journal Vol 7, No 2 (2021): Cogito Smart Journal Vol 7, No 1 (2021): Cogito Smart Journal Vol 6, No 2 (2020): Cogito Smart Journal Vol 6, No 1 (2020): Cogito Smart Journal Vol 5, No 2 (2019): Cogito Smart Journal Vol 5, No 1 (2019): Cogito Smart Journal Vol 4, No 2 (2018): CogITo Smart Journal Vol 4, No 1 (2018): CogITo Smart Journal Vol 3, No 2 (2017): CogITo Smart Journal Vol 3, No 1 (2017): CogITo Smart Journal Vol 2, No 2 (2016): CogITo Smart Journal Vol 2, No 1 (2016): CogITo Smart Journal Vol 1, No 1 (2015): CogITo Smart Journal More Issue