cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
DIRJA NUR ILHAM
Contact Email
dirja.poltas@gmail.com
Phone
085261233288
Journal Mail Official
dirja.poltas@gmail.com
Editorial Address
Kampus Politeknik Aceh Selatan Jl. Merdeka Komplek Reklamasi Pantai
Location
Kab. aceh selatan,
Aceh
INDONESIA
PERFECT: Journal of Smart Algorithms
Published by Politeknik Aceh Selatan
ISSN : 30640377     EISSN : 30640377     DOI : https://doi.org/10.62671/perfect.v1i1.1
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Library & Information Science
PERFECT: Journal of Smart Algorithms is an international, Computer Technology, peer-reviewed and open-access journal that provides a platform to produce high-quality original research, Reviews, Letters, and case reports in natural, social, applied, formal sciences, arts, and all other related fields. Our aim is to ameliorate the speedy distribution of new research ideas and results and allow the researchers to create new knowledge, studies, and innovations that will aid as a reference tool for the future. PERFECT is published twice in one year, namely in January and July.
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 20 Documents
 1   2 
Flood Detection Tool Using Ultrasonic Sensor Based on Telegram and Sound in Krueng Kluet River Flow Ilham, Dirja Nur; Candra, Rudi Arif; Fardiansyah, Fardiansyah; Sipahutar , Erwinsyah; Budiansyah, Arie
PERFECT: Journal of Smart Algorithms Vol. 1 No. 2 (2024): PERFECT: Journal of Smart Algorithms, Article Research July 2024
Publisher : LEMBAGA KAJIAN PEMBANGUNAN PERTANIAN DAN LINGKUNGAN (LKPPL)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62671/perfect.v1i2.29

Abstract

Flooding is a problem that until now still requires special handling from various parties, both from the government and the community. Flooding is not a light problem because flooding can disrupt community activities and cause losses, such as the washing away of household equipment, valuables, and electronic goods. Flooding occurs due to rising water levels in rivers due to abnormal rainfall, damaged dams, obstruction of water flow at the site of the dam's destruction in the River Basin Area (DAK), and the construction of facilities and infrastructure. The series of "Flood Detection Devices using Ultrasonic Based on Telegram and Sound consists of three parts, namely the input section, the control section, and the display section. This design was made to simplify the process in the Ultrasonic Flood Detection Device Design using telegrams and sound. The Ultrasonic Flood Detection Device Design Circuit using telegrams and sound consists of three parts, namely the input section, the control section, and the display section. The first Flood Detection Device Test using Ultrasonic Sensors Based on Telegram and Sound has been tried as many as 10 The first experiment The water depth is 1 meter, the distance of the sensor to the water surface is 3 meters, it is said that the status is safe, there is no notification to the telegram and the siren does not sound. Experiment 2: The water depth is 2 meters, the distance of the sensor from the water surface is 2 meters, it is said to be on standby, then the flood detector provides notification to the telegram via the telegram bot, and the siren sounds. Experiment 3: The water depth is 3 meters, the distance of the sensor from the water surface is 1 meter, it is said to be on standby, then the flood detector provides notification to the telegram via the telegram bot, and the siren sounds.
Smart Algorithm Applications in Mechanical Engineering and Physical Sciences for Optimizing Systems and Materials Hassien, Ali Soluman Ali; Abosetah , Nuri Salem Ali
PERFECT: Journal of Smart Algorithms Vol. 2 No. 1 (2025): PERFECT: Journal of Smart Algorithms, Article Research January 2025
Publisher : LEMBAGA KAJIAN PEMBANGUNAN PERTANIAN DAN LINGKUNGAN (LKPPL)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62671/perfect.v2i1.50

Abstract

  The increasing complexity of modern engineering systems and the demand for efficient, cost-effective, and high-performance designs have driven the adoption of intelligent computational strategies in mechanical engineering and physical sciences. Traditional simulation and optimization techniques often struggle with nonlinear, multi-objective problems that span both material and structural design spaces. This study aims to develop a unified smart algorithmic framework capable of optimizing both mechanical systems and material properties concurrently. The research focuses on integrating data-driven models with physics-informed techniques to improve predictive accuracy, computational efficiency, and practical applicability. The proposed framework combines artificial neural networks (ANNs), physics-informed neural networks (PINNs), genetic algorithms (GAs), and Bayesian optimization to form a hybrid multi-objective optimization system. A case study on an electric vehicle (EV) suspension system is used to validate the approach. Surrogate models were trained on finite element analysis (FEA) data and applied within a Pareto optimization loop to explore trade-offs among mass, fatigue life, and material cost. The framework achieved a 27% reduction in structural mass, a 35% increase in fatigue life, and a 13% decrease in material cost. Surrogate models attained R² values exceeding 0.90, with validation showing less than 5% deviation from FEA results. Sensitivity analysis confirmed design robustness under input variation. The findings demonstrate the effectiveness of smart algorithms in co-optimizing systems and materials. The proposed framework enhances the speed, accuracy, and physical validity of intelligent engineering design.
Prototype Design and Development of an IoT-Enabled Monitoring and Control System for Public Street Lighting Ilham, Dirja Nur; Candra, Rudi Arif; Budiansyah, Arie; Zulfan, Zulfan
PERFECT: Journal of Smart Algorithms Vol. 2 No. 1 (2025): PERFECT: Journal of Smart Algorithms, Article Research January 2025
Publisher : LEMBAGA KAJIAN PEMBANGUNAN PERTANIAN DAN LINGKUNGAN (LKPPL)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62671/perfect.v2i1.53

Abstract

This research discusses the Internet of Things (IoT)-based Public Street Lighting (PJU) system to improve energy efficiency and remote monitoring. The background problem is the need to improve operational efficiency and energy savings in the PJU system. This final project aims to design and test an IoT-based PJU system that transmits real-time data between nodes and gateways using LoRa technology and the MQTT protocol. The research process involves hardware and software design, as well as system testing under various conditions. The tests measured the data transmission time and analyzed the delay using LED indicators on the gateway and dashboard devices. The test results showed significant variations in data transmission time compared to the programmed time. The programmed transmission time was 10 seconds for node 1 and 20 seconds for node 2, but the test results showed an average time of about 15 seconds for node 1 and 21.89 to 36.02 seconds for node 2. This variation is due to factors such as network communication delay, processor load, and LoRa system efficiency.
Real-Time Classification of Local Orange Fruit Quality Using YOLO (You Only Look Once) and SVM (Support Vector Machine) Methods Harahap, Muhammad Khoiruddin; Candra, Rudi Arif; Budiansyah, Arie; Aritonang, Romulo P.; Zulfan, Zulfan; Saputra, Devi Satria
PERFECT: Journal of Smart Algorithms Vol. 2 No. 2 (2025): PERFECT: Journal of Smart Algorithms, Article Research July 2025
Publisher : LEMBAGA KAJIAN PEMBANGUNAN PERTANIAN DAN LINGKUNGAN (LKPPL)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62671/perfect.v2i2.55

Abstract

Oranges are a fruit that we often encounter and are even consumed by people because of their various benefits. Oranges have commercial value in Indonesia and have a fairly wide reach. In order to increase competitiveness, oranges must also meet market standards, both domestic and foreign, so that they can be accepted by consumers. Of course, in this case, orange selection is very important. increasing sales and market competition by sellers, important indicators in selecting citrus fruit are in terms of size and color. In general, the selection of citrus fruit is done manually and based on human thinking, which causes several weaknesses that must be corrected, including requiring a long time, human visual limitations, and being influenced by human psychology itself. This is what causes inconsistencies in selection. oranges and does not comply with existing market requirements. So a research was carried out regarding the quality classification of local citrus fruit using the YOLO (You Only Look Once) and SVM (Support Vector Machine) methods in real time. In the comparison made between the two methods used, Yolo was found to be the best method for classifying citrus fruit.
MIMO Microstrip Antenna with Multiple Inputs at 2.4 GHz Frequency for Long Term Evolution (LTE) Sipahutar, Erwinsyah; Oktrison, Oktrison
PERFECT: Journal of Smart Algorithms Vol. 2 No. 1 (2025): PERFECT: Journal of Smart Algorithms, Article Research January 2025
Publisher : LEMBAGA KAJIAN PEMBANGUNAN PERTANIAN DAN LINGKUNGAN (LKPPL)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62671/perfect.v2i1.69

Abstract

LTE (Long Term Evolution) is a fourth-generation wireless communication technology that is currently under development, necessitating the use of efficient antennas. This research focuses on the design and realization of a Multiple Input Multiple Output (MIMO) microstrip antenna operating at a frequency of 2.4 GHz, which is essential for LTE applications. The MIMO technique employs multiple antennas on both the transmitter and receiver sides, aiming for a correlation coefficient below 0.2 to enhance communication quality and channel capacity without requiring additional bandwidth. The antenna design was simulated using CST Studio Suite 2019 software, followed by fabrication. The simulation results indicated a return loss of -25.411 dB, a Voltage Standing Wave Ratio (VSWR) of 1.113, a gain of 6.464 dBi, an omnidirectional radiation pattern, and a bandwidth of 20 MHz. Upon fabrication, the measured return loss was -18.071 dB, with a VSWR of 1.285 and an increased bandwidth of 50 MHz. The results demonstrate that the designed antenna meets the necessary specifications for LTE applications, confirming its suitability for practical use in modern wireless communication systems.
Serial Rectifier Antenna (Rectenna) Circular Microstrip Patch 2.4 GHz for RF Energy Harvesting Asyifa, Salwa; Pharmayeni, Pharmayeni
PERFECT: Journal of Smart Algorithms Vol. 2 No. 1 (2025): PERFECT: Journal of Smart Algorithms, Article Research January 2025
Publisher : LEMBAGA KAJIAN PEMBANGUNAN PERTANIAN DAN LINGKUNGAN (LKPPL)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62671/perfect.v2i1.70

Abstract

The rapid development of Radio Frequency (RF) usage at this time causes the abundance and waste of radio frequency (RF) electromagnetic wave energy sources in the air. This RF energy source can be used as an environmentally friendly alternative by harvesting energy using the rectenna system . The rectifier antenna (rectenna) system is designed using the serial rectenna system , this system is used to improve the performance of the rectenna in converting electromagnetic waves into a direct voltage (DC) source. To design a serial rectenna system, use 3 antennas and 3 series of rectifiers . The antenna used in the serial rectenna system is a 2.4 GHz circular microstrip patch antenna for WiFi signal reception. Meanwhile, the rectifier circuit uses a 6-stage voltage doubler using a Schottky 2860 diode and a 1nF smd capacitor. From testing and measuring the serial rectenna system , the circular patch microstrip antenna is able to capture and rectify the voltage to DC. Antenna system has return loss values of -26.29 dB, -21.75 dB, and -28.57dB, VSWR 1.11, 1.16, and 1.07, impedances 51.1, 55.56, and 50.22, bandwidth 60 MHz, 60 MHz and 50 MHz with resonant frequency 2.42 GHz, 2.36 GHz and 2.48 GHz. So that the voltage generated by a single rectenna system is 51.3 mV at a distance of 25 cm. Meanwhile, the rectenna serial system can convert direct voltage of 151.3 mV at a distance of 25 cm from the source of the Access Point transmitter.
From Static to Contextual: A Survey of Embedding Advances in NLP Alkaabi, Hussein; Jasim, Ali Kadhim; Darroudi, Ali
PERFECT: Journal of Smart Algorithms Vol. 2 No. 2 (2025): PERFECT: Journal of Smart Algorithms, Article Research July 2025
Publisher : LEMBAGA KAJIAN PEMBANGUNAN PERTANIAN DAN LINGKUNGAN (LKPPL)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62671/perfect.v2i2.77

Abstract

Embedding techniques have been a cornerstone of Natural Language Processing (NLP), enabling machines to represent textual data in a form that captures semantic and syntactic relationships. Over the years, the field has witnessed a significant evolution—from static word embeddings, such as Word2Vec and GloVe, which represent words as fixed vectors, to dynamic, contextualized embeddings like BERT and GPT, which generate word representations based on their surrounding context. This survey provides a comprehensive overview of embedding techniques, tracing their development from early methods to state-of-the-art approaches. We discuss the strengths and limitations of each paradigm, their applications across various NLP tasks, and the challenges they address, such as polysemy and out-of-vocabulary words. Furthermore, we highlight emerging trends, including multimodal embeddings, domain-specific representations, and efforts to mitigate embedding bias. By synthesizing the advancements in this rapidly evolving field, this paper aims to serve as a valuable resource for researchers and practitioners while identifying open challenges and future directions for embedding research in NLP.
An Analysis of User Satisfaction on the Official Website of Politeknik Aceh Selatan Using the EUCS Method Fardiansyah, Fardiansyah; Ihsan, M Arinal; Kurniadi, Sepri
PERFECT: Journal of Smart Algorithms Vol. 2 No. 2 (2025): PERFECT: Journal of Smart Algorithms, Article Research July 2025
Publisher : LEMBAGA KAJIAN PEMBANGUNAN PERTANIAN DAN LINGKUNGAN (LKPPL)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62671/perfect.v2i2.97

Abstract

This study aims to assess user satisfaction with the evaluated information system by employing a quantitative research approach, specifically through the use of a five-point Likert scale questionnaire. Respondents were asked to rate their level of agreement with 16 structured statements designed to reflect five key dimensions of user satisfaction: content, accuracy, format, ease of use, and timeliness. The Likert scale ranged from 1 (strongly disagree) to 5 (strongly agree), allowing for the collection of measurable and standardized responses. The collected data were analyzed by calculating the Actual Satisfaction Score (SKN), which represents the total cumulative score based on all respondents’ answers. This score was then compared to the Ideal Satisfaction Score (SKI), which was determined by multiplying the total number of respondents by the total number of questions and the highest possible Likert score. In this case, with 112 valid respondents, the SKN was calculated at 7,841, while the SKI reached 8,960, resulting in a Satisfaction Percentage (PK) of 87.52%. This high level of satisfaction suggests that the system effectively meets user expectations, particularly in delivering high-quality information, ensuring timely services, and providing a user-friendly interface. These findings highlight the system’s strong performance in key usability areas and underscore its potential for further development. Furthermore, the results serve as an evidence-based foundation for future enhancements, especially in fostering user-centered, accessible, and sustainable digital services.
Explainable AI for Medical Imaging: A Taxonomy Based on Clinical Task Requirements Kamber, Ali Nadhim; Alkaabi, Hussein; Al-Rekabi, Mohammed; Jasim, Ali Kadhim
PERFECT: Journal of Smart Algorithms Vol. 2 No. 2 (2025): PERFECT: Journal of Smart Algorithms, Article Research July 2025
Publisher : LEMBAGA KAJIAN PEMBANGUNAN PERTANIAN DAN LINGKUNGAN (LKPPL)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62671/perfect.v2i2.115

Abstract

Explainable Artificial Intelligence (XAI) has emerged as a critical enabler for deploying AI-driven medical imaging systems where transparency, trust, and accountability are paramount. However, most current taxonomies of XAI methods categorize techniques based on algorithmic families (e.g., saliency maps, attribution methods), which often fail to reflect the practical requirements of clinical tasks. This paper proposes a novel task-centric taxonomy of XAI in medical imaging that aligns explanation techniques with four key clinical tasks: classification, detection, segmentation, and prognostic assessment. For each task, we analyze how different XAI methods enhance model interpretability, their suitability for clinical decision-making, and their limitations in real-world applications. Our taxonomy aims to provide a practical framework for researchers and practitioners to select appropriate XAI strategies tailored to the specific demands of medical imaging workflows. Furthermore, we highlight the current gaps in task-specific explainability and propose future research directions towards clinically meaningful, task-driven XAI solutions. This work serves as a step towards bridging the gap between technical XAI developments and the functional needs of clinical practice.
Harnessing Artificial Intelligence for Education Reform in Libya: Opportunities and Challenges Aboseta , Abdarahmah Kamees A Aboseta; Salem, Asma Al Mokhtar Miftah Alhaj; Alnagrat, Ahmed Jamah Ahmed
PERFECT: Journal of Smart Algorithms Vol. 2 No. 2 (2025): PERFECT: Journal of Smart Algorithms, Article Research July 2025
Publisher : LEMBAGA KAJIAN PEMBANGUNAN PERTANIAN DAN LINGKUNGAN (LKPPL)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62671/perfect.v2i2.117

Abstract

Many education systems are seeking ways to improve teaching quality, personalize learning, and increase administrative efficiency. Libya faces recovery challenges and regional disparities that make scalable solutions especially important. Objective: This study examines how artificial intelligence could contribute to education reform in Libya while safeguarding equity, privacy, and academic integrity. Methods: We conducted a scoping review of recent empirical studies and policy documents, compared implementation frameworks, and completed a Libya‑focused desk review on governance, infrastructure, human capacity, and curriculum‑aligned content. Results: The synthesis indicates that intelligent tutoring, adaptive practice, automated feedback for low‑stakes writing, and responsible data use can support gains in achievement and teacher efficiency when aligned with curriculum and accompanied by sustained professional development. Constraints include uneven connectivity, capacity gaps, and limited high‑quality Arabic content; these factors can widen disparities if not addressed. Conclusion: A staged roadmap is proposed that prioritizes national guidance and safeguards, teacher capacity building, targeted pilots in foundational literacy, mathematics, and writing support, and careful scale‑up based on evidence and inclusiveness across regions.

Page 2 of 2 | Total Record : 20

 1   2 

Filter by Year

2024 2025


Reset
Filter By Issues
All Issue Vol. 2 No. 2 (2025): PERFECT: Journal of Smart Algorithms, Article Research July 2025 Vol. 2 No. 1 (2025): PERFECT: Journal of Smart Algorithms, Article Research January 2025 Vol. 1 No. 2 (2024): PERFECT: Journal of Smart Algorithms, Article Research July 2024 Vol. 1 No. 1 (2024): PERFECT: Journal of Smart Algorithms, Article Research January 2024