cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Frieyadie
Contact Email
Frieyadie
Phone
-
Journal Mail Official
frieyadie@nusamandiri.ac.id
Editorial Address
-
Location
Kota adm. jakarta pusat,
Dki jakarta
INDONESIA
Techno Nusa Mandiri : Journal of Computing and Information Technology
Published by Universitas Nusa Mandiri
ISSN : 19782136     EISSN : 2527676X     DOI : -
Core Subject : Science,
Computer Science & IT
Jurnal TECHNO Nusa Mandiri, merupakan Jurnal yang diterbitkan oleh Pusat Penelitian Pengabdian Masyarakat (PPPM) STMIK Nusa Mandiri Jakarta. Jurnal TECHNO Nusa Mandiri, berawal diperuntukan menampung paper-paper ilmiah yang dibuat oleh dosen-dosen program studi Teknik Informatika.
Arjuna Subject : -
Articles 5 Documents
 1 
Search results for , issue "Vol 18 No 2 (2021): TECHNO Period of September 2021" : 5 Documents clear
K-MEANS SEGMENTATION AND CLASSIFICATION OF SWIETENIA MAHAGONI WOOD DEFECTS Sri Rahayu; Dwiza Riana; Anton Anton
Techno Nusa Mandiri: Journal of Computing and Information Technology Vol 18 No 2 (2021): TECHNO Period of September 2021
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/techno.v18i2.2222

Abstract

The potential and usefulness of wood to meet the needs of human life are not in doubt. Demands us to continue to maintain the quality. Wood quality is closely related to wood defects. Manual defect checks in the wood industry are unreliable because they are prone to human error, For example, due to acute symptoms of headaches and tired eyes, technology in the form of image processing can help identify wood defects Swietenia Mahagoni. In this case, the method used is Euclidean distance with a ratio of k-means segmentation and thresholding on 42 images of wood defects consisting of 3 types of defects, namely growing skin defects, rotting knots, and healthy knots, every 14 images with data sharing. training for 30 images and testing for 12 images. The results of the k-means segmentation are then extracted on 6 features including metric, eccentricity, contrast, correlation, energy, and homogeneity using the Gray Level Co-occurrence Matrix (GLCM) extractor and classified by calculating the closest distance using the euclidean distance between the results of data feature extraction. testing of the value of feature extraction in the training data which is used as a previous database. It is the smallest value that indicates the type of defect. The success calculation is presented in the confusion matrix calculation and gets a success or accuracy value of 91.67%.
ANALYSIS OF DEPRESSION IN COLLEGE STUDENT DURING COVID-19 PANDEMIC USING EXTREAM GRADIENT BOOST Agung Prabowo; Dharma Ajie Nur Rois; Amar Luthfi; Ultach Enri
Techno Nusa Mandiri: Journal of Computing and Information Technology Vol 18 No 2 (2021): TECHNO Period of September 2021
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/techno.v18i2.2399

Abstract

The Covid-19 pandemic that spreads in Indonesia causes health, economic, and social problems in the community, including mental health. Of course, this mental health problem also hit students. Seeing these conditions, we conducted research on students of the Faculty of Computer Science, University of Singaperbangsa Karawang using the Patient Health Questionnaire-9 which measures a person's level of depression. In this study, we used Extreme Gradient Boost or XGBoost to classify students' depression tendencies. We break down the dataset into training data and testing data with 4 data sharing combinations, they are 80 : 20, 50 : 50, 90 : 10, 70 : 30. The combination of 90 : 10 data sharing has the best performance with accuracy, precision, recall, and F1-scores respectively 92.86%, 94.29%, 92.86% , and 92.06%. This method also has better performance than K-Nearest Neighbor, Random Forest, Multi Layer Perception, Support Vector Machine and Decision Tree .
COMPARISON OF ACCURACY MEASUREMENTS IN MOTION SENSORS AND HEART RATE MEASUREMENTS USING ANALYTICAL HIERARCHY PROCESS METHODS Tomi Lifti Novier; Nurmalasari Nurmalasari; Widi Astuti; Siti Masturoh; M. Rangga Ramadhan Saelan
Techno Nusa Mandiri: Journal of Computing and Information Technology Vol 18 No 2 (2021): TECHNO Period of September 2021
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/techno.v18i2.2547

Abstract

The use of motion sensors in measuring heart rate using smartwatch applications is currently a trend. Everyone is very helpful for measuring their own heart rate. This research is about the comparison of accuracy in motion sensors and measuring heart rate using the Analytical Hierarchy Process (AHP) method. Every technology and application in motion sensor measurement in heart rate measurement has almost the same features and uses as Xiaomi, Samsung, and Apple Inc. From the calculations carried out by the researcher, it shows that the field/stadium that is the most chosen by the community (respondents) is by Random Sampling, with the acquisition of a value of 0.490 aka 49.00%. The second is Treadmill with a value of 0.294 aka 29.40%. the overall value is 0.216 aka 21.60% The alternative that is most chosen by the community (respondents) is the field/stadium. The Analytical Hierarchy Process method can make it easier for prospective technology users to be able to measure the accuracy of motion sensors and detect heart rates, the AHP method makes product decisions based on criteria and alternatives contained in the hierarchy, the results of the study are Apple Inc. as the respondent's choice for technology that is trusted to measure better accuracy on the motion sensor and measure heart rate.
APPLICATION OF CALCULATION METHODS MULTI ATRIBUTTE UTILITY THEORY (MAUT) IN SELECTION OF YARN SUPPLIER Susliansyah Susliansyah; Yahdi Kusnadi; Heny Sumarno; Hendro Priyono; Linda Maulida
Techno Nusa Mandiri: Journal of Computing and Information Technology Vol 18 No 2 (2021): TECHNO Period of September 2021
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/techno.v18i2.2706

Abstract

The main objective of the yarn supplier selection process is to determine suppliers who have efficiency in meeting the company's needs consistently and minimize risks related to the procurement of yarn and components needed. In solving problems in supplier selection using the Multi Attribute Utility Theory (MAUT) method which consists of calculating matrix normalization and attribute normalization. The results obtained in this study are to find out the best supplier from other suppliers, namely GSM suppliers with a value of 0.87.
COMPARATION OF CLASSIFICATION ALGORITHM ON SENTIMENT ANALYSIS OF ONLINE LEARNING REVIEWS AND DISTANCE EDUCATION Lila Dini Utami; Siti Masripah
Techno Nusa Mandiri: Journal of Computing and Information Technology Vol 18 No 2 (2021): TECHNO Period of September 2021
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/techno.v18i2.2715

Abstract

As of January 27, 2021, confirmed cases of COVID-19 nationally stood at 1,024,298 people, this data is data that has been officially announced by the Indonesian Ministry of Health. Meanwhile, in Jakarta, there are 256,416 confirmed cases of COVID-19. In July 2021, there was a very significant increase, seeing the data caused the Central government to make a decision to continue the Large-Scale Social Restrictions (PSBB), followed by the Enforcement of Restrictions on Community Activities (PPKM), which affected all aspects, especially the education aspect. In the education aspect, the government applies distance and online learning. Of course, many people agree or disagree with this decision, because there must be sacrifices, both in terms of time and cost. Seeing these conditions makes the authors interested in discussing and processing public opinions on distance and online learning systems which certainly have positive and negative responses from learning implementers, to process the data the author uses Data Mining, namely using the Text Mining Classification method with several The classification algorithms are the Naïve Bayes Algorithm (NB), the k-Nearest Neighbor (k-NN) Algorithm and the Support Vector Machine (SVM) Algorithm to see which classification algorithm has the highest accuracy and diagnostic value in processing this opinion. After the calculations are done, the algorithm that is more suitable for analyzing reviews or opinions in this study is to use the Support Vector Machine (SVM) classification algorithm with the highest accuracy value of 87.67% and an AUC value of 0.939 with an Excellent Classification diagnostic level.

Page 1 of 1 | Total Record : 5

 1 

Filter by Year

2021 2021


Reset
Filter By Issues
All Issue Vol 20 No 2 (2023): TECHNO Period of September 2023 Vol 20 No 1 (2023): TECHNO Period of March 2023 Vol 19 No 2 (2022): TECHNO Period of September 2022 Vol 19 No 1 (2022): TECHNO Period of March 2022 Vol 18 No 2 (2021): TECHNO Period of September 2021 Vol 18 No 1 (2021): TECHNO Period of March 2021 Vol 17 No 2 (2020): TECHNO Period of September 2020 Vol 17 No 1 (2020): TECHNO Period of March 2020 Vol 16 No 2 (2019): TECHNO Periode September 2019 Vol 16 No 1 (2019): TECHNO Periode Maret 2019 Vol 15 No 2 (2018): TECHNO Periode September 2018 Vol 15 No 1 (2018): TECHNO Periode Maret 2018 Vol 14 No 2 (2017): TECHNO Periode September 2017 Vol 14 No 1 (2017): TECHNO Periode Maret 2017 Vol 13 No 2 (2016): TECHNO Periode September 2016 Vol 13 No 1 (2016): TECHNO Periode Maret 2016 Vol 12 No 2 (2015): TECHNO Periode September 2015 Vol 12 No 1 (2015): TECHNO Periode Maret 2015 Vol 11 No 2 (2014): TECHNO Periode September 2014 Vol 11 No 1 (2014): TECHNO Periode Maret 2014 Vol 10 No 2 (2013): TECHNO Periode September 2013 Vol 10 No 1 (2013): TECHNO Periode Maret 2013 More Issue