Sinkron : jurnal dan penelitian teknik informatika
Not a member yet
1261 research outputs found
Sort by
Music Genre Classification Using K-Nearest Neighbor and Mel-Frequency Cepstral Coefficients
No full textMusic genre classification plays a pivotal role in organizing and accessing vast music collections, enhancing user experiences, and enabling efficient music recommendation systems. This study focuses on employing the K-Nearest Neighbors (KNN) algorithm in conjunction with Mel-Frequency Cepstral Coefficients (MFCCs) for accurate music genre classification. MFCCs extract essential spectral features from audio signals, which serve as robust representations of music characteristics. The proposed approach achieves a commendable classification accuracy of 80%, showcasing the effectiveness of KNN-MFCC fusion. Nevertheless, the challenge of overlapping genres, particularly rock and country, demands special attention due to their shared acoustic attributes. The inherent similarities between these genres often lead to misclassification, hampering accuracy. To address this issue, an enhanced feature engineering strategy is devised, leveraging deeper insights into the subtle nuances that differentiate rock and country music. Additionally, a refined KNN distance metric and neighbor selection mechanism are introduced to further refine classification decisions. Experimental results underscore the effectiveness of the refined approach in mitigating genre overlap issues, significantly enhancing classification accuracy for rock and country genres. This study contributes to the advancement of music genre classification techniques, offering an innovative solution for handling overlapping genres and demonstrating the potential of KNN-MFCC synergy in achieving accurate and refined genre classification
Internet Service Provider User Customer Lifetime Segmentation Analysis using RFM and K-Means Algorithm
No full textThe characteristics of each customer can be segmented using RFM (Recency, Frequency, Monetary) which means customer's last transaction time, number of customer transactions, and amount of money spent. The Lifetime and K-Means methods are used to perform the process of clustering or grouping customers based on segmentation through RFM. The results will be divided into 4 clusters namely Gold, Silver, Platinum and Diamond. The results of clustering are visualized with graphs and cluster tables containing the results of segmentation and clusters or groups of From the results obtained from the previous stage, of the 104 customers in the Retail & Distribution Services (RDS) sector, 4 segments resulted in 43 customers with Platinum class, 39 customers with gold class, 14 customers with silver class, and 8 customers with platinum level. The most popular services services or product is high speed dedicated internet services, VPN IP package, and service network package as top 3 results. The largest amount of revenue services or product is transponder full time use services, support network and contact center application as top 3 results
Evaluation of Accounting Information System Using Usability Testing Method and System Usability Scale
No full textThe computer-based accounting information system IBS Core has been used by Renon Pekraman Village Credit Institution since 2016 to facilitate all transaction processes. This study aims to evaluate the usefulness of the IBS Core accounting information system, determine the effectiveness, efficiency, and user satisfaction with the IBS Core accounting information system, and identify areas that need improvement in the IBS Core accounting information system.The method used in this study is Usability Testing using performance measurement and retrospective think aloud (RTA) as well as the System Usability Scale (SUS). The results of the study show that the IBS Core system has a high effectiveness score of 92.50%. The average time required for participants to complete the task scenario is 68.9 seconds, and users feel that the available content is clear and consistent. In addition, the average System Usability Scale (SUS) score is 86.125, where the results were above the standard average SUS score. The IBS Core System Score was ranked B with the adjective ratings "Excellent” Next, the acceptability ranges are included in the "Acceptable" category, and finally the net promote score (NPS) is included in the "Promoter" category, showing that the use of the IBS Core system gets a very good assessment from its users. This shows that the IBS Core system is highly appreciated and considered very useful by its users
Implementation Of The Arnold Catmap On A Combination Of Symmetric And Asymmetric Cryptography
No full textThe escalating need for robust data security has propelled cyber security practitioners into a perpetual quest for innovative solutions. This endeavor involves the strategic amalgamation of cryptographic algorithms with meticulously customized alterations to specific algorithmic processes. In this pursuit of heightened data protection, the Arnold Cat Map emerges as a pivotal tool, a mathematical transformation that gracefully elucidates the intricate movement of points within a two-dimensional plane. This movement occurs in a systematic and repetitive manner, rendering it an indispensable asset in the domains of cryptography and image scrambling. The Arnold Cat Map operates by meticulously relocating each point within the two-dimensional plane to a fresh coordinate, all the while adhering to an intricately structured pattern. The result is a formidable "mixing" effect that enhances data security. When applied theoretically to widely employed encryption methods like Advanced Encryption Standard (AES) for symmetric encryption and the Rivest-Shamir-Adleman (RSA) algorithm for asymmetric encryption, the Arnold Cat Map exhibits the potential to significantly augment the randomness of the encrypted output. This augmentation of randomness, in turn, fortifies the security of digital assets and communications, making them more resilient against adversarial attacks. By introducing this innovative concept into the realm of cryptography, cyber security practitioners endeavor to fortify data security, offering a higher degree of confidence in the protection of sensitive information and digital assets against a backdrop of ever-evolving cyber threats
Decision Making Model for Temple Revitalization in Bali Using Fuzzy-SMARTER Combination Method
No full textBali is dominated by Hindus and temples as places of worship. Revitalization is carried out periodically in order to preserve the temple. Many factors are taken into consideration in revitalization decisions so that they can be approved by a group or government. Through the decision-making model of temple revitalization in Bali, the entire complexity of decision-making factors can be integrated so as to produce an objective priority ranking of improvements as supporting data for a revitalization decision. The combination of fuzzy sets and the SMARTER (Simple Multi Attribute Rating Technique Exploiting Rank) method can help solve unstructured problems in determining temple revitalization decisions. The calculation between the Alternative sacred building and the complexity factor criteria with a final value of more than 0.5 is included as a revitalization priority suggestion
Improving Data Embedding Capacity in LSB Steganography Utilizing LSB2 and Zlib Compression
No full textIn an increasingly advanced era, the exchange of information through digital tools has become a common practice. With easy access and advancing facilities, securely and covertly exchanging data has become a challenging task. Therefore, the technique of steganography can be used as a solution for data hiding and protection, enabling safer data exchanges. Steganography is a method to conceal data within a transmission object, which can be an image, video, audio, and more. In this research, steganography will be performed using images as the transmission object. This study is done to offer a modification of the Least Significant Bit (LSB) steganography technique by utilizing the LSB-2 method, along with the utilization of the Zlib compression algorithm. The modification and use of the Zlib compression algorithm aim to increase the message capacity that can be embedded in the transmission object while preserving the image quality. The results of the experiments will be presented in tabular form by comparing the original image with the steganography-processed image using metrics such as Mean Square Error (MSE), Peak Signal-to-Noise Ratio (PSNR), and Structural Similarity Index (SSIM) as measures of image quality. The experiments conducted results in an increase of capacity of approximately 36.54%, an increase in PSNR value of approximately 4.72%, accompanied by a decrease in MSE value in average of 49.19%, and SSIM values constantly at 0,99999 thus proving the proposed method successfully increased the embedded massage capacity while preserving even enhance the quality of the stego image produced by the embedding proces
Knowledge of Songket Cloth Small Medium Enterprise Digital Transformation
No full textThis article examines the knowledge of digital transformation of Small and Medium Enterprises (SMEs) that specialize in traditional handicrafts, with a specific emphasis on the Songket textile sector. The study investigates the use of digital technologies, notably blog platforms and the e-commerce site Shopee, to improve and streamline several business processes in Songket textile SMEs. The report takes a case study approach, diving into the experiences of Songket clothing enterprises that have undergone digital transformation. Key areas studied include the use of Blog platforms for brand development, marketing, and consumer involvement, as well as the Shopee E-Commerce platform for online sales and order processing. The essay seeks to give insights into the problems and possibilities faced by Songket cloth SMEs along their digital transformation journey by conducting in-depth observation, interviews, and surveys. The findings add to the scholarly discussion on the digitization of traditional industries, with practical implications for SMEs in the Songket textile sector and other handicraft areas. This study emphasizes the necessity of using digital technologies to preserve and expand traditional crafts, while also throwing light on the potential role of prominent E-Commerce platforms like Shopee in facilitating worldwide market access for such firms
Analysis of The Use of Nguyen Widrow Algorithm in Backpropagation in Kidney Disease
No full textFast and accurate diagnosis is very important for kidney disease. This research conducts and analyzes by using Nguyen Widrow Algorithm in Back Propagation method in artificial neural network for kidney disease diagnosis with the aim to improve the accuracy in predicting and time efficiency in diagnosing. The Nguyen Widrow algorithm is very capable of accelerating convergence and stabilizing the learning process in artificial neural networks, which is also expected to present a meaningful contribution to the handling of health data. This study uses MATLAB as a platform for algorithm implementation and a dataset of medical records of kidney disease patients collected from a hospital that specializes in treating kidney disease patients. The data pre-processing and artificial neural network modeling stages use the Nguyen Widrow algorithm, while the model training process uses the Back Propagation method. The results showed that the Nguyen Widrow algorithm was able to improve the accuracy of predicting someone suffering from kidney disease compared to using only the Back Propagation method. Analysis of the performance of the model shows a significant improvement in stability and convergence speed during the learning process. This indicates that data processing and medical decision making becomes more efficient. On the other hand, this research also studied the challenges and limitations that will be faced in terms of implementation of the Nguyen Widrow algorithm. Also the sensitivity of the initialization parameters, the need for the quality of the dataset to be used in training the model.This research reveals the ability of the Nguyen Widrow algorithm to improve the performance of artificial neural networks in diagnosing kidney disease. By implementing this algorithm in MATLAB, the results show that the use of the latest data processing technology and analysis tools can provide significant improvements in accuracy and efficiency in the medical field. In addition, this research is expected to provide a new direction in the development of machine learning algorithms for applications in the healthcare field, especially for diagnosing kidney disease. By further utilizing this technology, it contributes significantly to improving the quality of healthcare and treatment outcomes for patients suffering from kidney disease
Indonesians Perception on the South China Sea Dispute: Support Vector Machine and Naïve Bayes Approach
No full textIn recent years, relations between Indonesia and China have become increasingly cordial. However, a potential source of tension is emerging in the form of a heightened dispute in the South China Sea. The government of Indonesia is considered an ally, however there has been a long-standing negative opinion among Indonesians regarding China, which has influenced the way both the general public and the political elite have perceived the relations between Indonesia and China. This research has two objectives. The first is to examine Indonesian perceptions regarding the South China Sea conflict. The second is to compare the performance of Support Vector Machine (SVM) and Multinomial Naïve Bayes as a method of sentiment analysis. Using 7.051 Indonesian-language posts from social media X as a dataset, the result shows that a significant portion of Indonesians view the dispute negatively, fearing potential escalation and threats to national security. Despite these concerns, there is reason to believe that Indonesia can play a proactive role in resolving the conflict through ASEAN and UNCLOS frameworks. Meanwhile, SVM has been demonstrated to be an effective method for handling sentiment analysis data, achieving an accuracy of 87.95%. This work contributes to the field of sentiment analysis by highlighting social media as a valuable platform and by demonstrating the effectiveness of SVM. Furthermore, the study offers new insights for the field of international relations by analyzing the South China Sea dispute through a machine learning lens, which may lead to the development of novel perspectives
K-Means and Naive Bayes Algorithms for Evaluation of Education Personnel Performance Based on SPMI Standards
No full textThis research compares the K-Means and Naive Bayes algorithms in evaluating the performance of educational staff based on SPMI standards at STMIK Triguna Dharma. The main objective is to identify the effectiveness of the two algorithms in grouping performance evaluation data and determine the advantages and disadvantages of each method. Primary data was obtained through surveys and interviews, while secondary data came from institutional archives. The K-Means algorithm shows 100% accuracy with the ability to group educational staff into very good, good, quite good, poor and poor performance categories. Meanwhile, the Naive Bayes algorithm shows 91% accuracy, with 100% precision results for the "good" and "fairly good" categories. These results indicate that K-Means is more effective in grouping educational staff based on performance evaluation compared to Naive Bayes. This research makes a significant contribution in the field of evaluating the performance of educational staff and offers insights for a more effective implementation of SPMI in higher education