eJournal Komunitas Dosen Indonesia
Not a member yet
1406 research outputs found
Sort by
An Analysis of the Effectiveness of KAN and CNN Algorithms for Human Facial Emotion Classification
Full text linkFacial expression-based emotion recognition has various applications, including security, healthcare, human-computer interaction, and behavioral analysis. This study analyzes the effectiveness of the Kolmogorov Arnold Networks and Convolutional Neural Networks algorithms in classifying human facial expressions of emotion using the OSEMN. Experimental data were obtained from the FER-2013 dataset, which consists of 35,887 facial expression images categorized into seven primary emotions: happy, sad, angry, fearful, disgusted, surprised, and neutral. The CNN model was designed with four convolutional layers, while the KAN model used three convolutional layers and a B-spline-based approach to handle non-linear transformations. Evaluation was based on accuracy, precision, recall, F1-score, and computational efficiency. The results showed that CNN achieved higher accuracy but tended to overfit, particularly on emotion classes with imbalanced data distribution. On the other hand, KAN demonstrated more stable performance with lower computational resource consumption, making it more efficient for systems with limited power and memory. CNN was selected for its superior pattern recognition capability, while KAN was chosen due to its efficiency in resource-constrained environments. From the comparison, CNN performed better in detecting complex expressions, while KAN was more optimal in processing efficiency and classification stability. The choice of the most suitable algorithm depends on the specific needs of the system—whether prioritizing high accuracy (CNN) or computational efficiency (KAN). This study is expected to provide insights into the development of more adaptive and efficient deep learning-based emotion recognition systems for practical applications such as mobile devices, healthcare monitoring, and smart surveillance
Prototype of Monitoring and Controlling Rice Field Irrigation Based on Internet of Things
Full text linkThe advancement of Internet of Things (IoT) technology has significantly impacted various sectors, including agriculture, by enabling automation and real-time monitoring. In rice farming, one persistent challenge is the reliance on manual irrigation, which often results in water waste, increased labor demands, and reduced crop yields due to delayed or inconsistent water management. This research aims to design and implement a prototype IoT-based irrigation system to address these inefficiencies. The proposed system allows farmers to remotely monitor and control water flow using a smartphone via the Telegram messaging application. Telegram is chosen for its ubiquity, cross-platform compatibility, and ease of use, making it accessible to farmers without specialized technical skills. The system uses an ESP32 microcontroller as the core processor, an HC-SR04 ultrasonic sensor to detect water levels, and an SG90 servo motor to automate the sluice gate mechanism. A 16x2 LCD is integrated for real-time field display. Telegram enables interactive control through command inputs (e.g., opening and closing gates) and automated notifications, providing continuous status updates. The system operates autonomously based on preset water level thresholds but also supports manual override. Testing results show that the system is responsive and accurate (within ±1 cm), and it significantly reduces the need for frequent field visits. This solution enhances irrigation precision, reduces labor, and contributes to better water resource management. By integrating commonly available digital tools with low-cost hardware, the prototype offers a practical and scalable solution for improving agricultural productivity, especially in remote rural areas.The advancement of Internet of Things (IoT) technology has significantly impacted various sectors, including agriculture, by enabling automation and real-time monitoring. In rice farming, one persistent challenge is the reliance on manual irrigation, which often results in water waste, increased labor demands, and reduced crop yields due to delayed or inconsistent water management. This research aims to design and implement a prototype IoT-based irrigation system to address these inefficiencies. The proposed system allows farmers to remotely monitor and control water flow using a smartphone via the Telegram messaging application. Telegram is chosen for its ubiquity, cross-platform compatibility, and ease of use, making it accessible to farmers without specialized technical skills. The system uses an ESP32 microcontroller as the core processor, an HC-SR04 ultrasonic sensor to detect water levels, and an SG90 servo motor to automate the sluice gate mechanism. A 16x2 LCD is integrated for real-time field display. Telegram enables interactive control through command inputs (e.g., opening and closing gates) and automated notifications, providing continuous status updates. The system operates autonomously based on preset water level thresholds but also supports manual override. Testing results show that the system is responsive and accurate (within ±1 cm), and it significantly reduces the need for frequent field visits. This solution enhances irrigation precision, reduces labor, and contributes to better water resource management. By integrating commonly available digital tools with low-cost hardware, the prototype offers a practical and scalable solution for improving agricultural productivity, especially in remote rural areas
Building a School Guest Book Information System Using the Waterfall Method
Full text linkThe increasing volume of data on human activities has resulted in a growing number of visitors to schools, particularly in the western part of Rangkasbitung, Lebak, Banten. Prospective parents visit the RA (Raudhatul Athfal) institution to enroll their children in school, pay monthly administration fees, and engage in educational activities with various general visitors. This influx poses several challenges for school administration and security, especially since visit records are still maintained manually, leading to data loss, difficulties in accessing visit histories, and limitations in monitoring guests, including parents and vendors. This issue impacts the transparency of school activity records. To address this, the research proposes a web-based school booking system to record visitor data based on the purpose of the visit, thus allowing for more effective data access and preliminary analysis in the event of an incident. This system is developed using the waterfall method, which is chosen for its structured concept, suitable for small to medium-sized school environments. Each phase consists of needs analysis, design, implementation, testing, and maintenance, carried out sequentially. Evaluation using a Likert scale from 104 respondents (determined by Slovin's formula) showed the Daily Report feature scored highest at 3.81, while the Weekly Report was lowest at 3.04. Maintenance tests found input validation and weekly report printing less smooth (2.84 and 2.69). Overall, the system effectively supports visitor monitoring with accessible features.The increasing volume of data on human activities has resulted in a growing number of visitors to schools, particularly in the western part of Rangkasbitung, Lebak, Banten. Prospective parents visit the RA (Raudhatul Athfal) institution to enroll their children in school, pay monthly administration fees, and engage in educational activities with various general visitors. This influx poses several challenges for school administration and security, especially since visit records are still maintained manually, leading to data loss, difficulties in accessing visit histories, and limitations in monitoring guests, including parents and vendors. This issue impacts the transparency of school activity records. To address this, the research proposes a web-based school booking system to record visitor data based on the purpose of the visit, thus allowing for more effective data access and preliminary analysis in the event of an incident. This system is developed using the waterfall method, which is chosen for its structured concept, suitable for small to medium-sized school environments. Each phase consists of needs analysis, design, implementation, testing, and maintenance, carried out sequentially. Evaluation using a Likert scale from 104 respondents (determined by Slovin's formula) showed the Daily Report feature scored highest at 3.81, while the Weekly Report was lowest at 3.04. Maintenance tests found input validation and weekly report printing less smooth (2.84 and 2.69). Overall, the system effectively supports visitor monitoring with accessible features
Thesis Title Similarity Detection System Using Levenshtein Distance and Cosine Similarity
Full text linkThe manual verification process of thesis titles in higher education institutions is often time-consuming and prone to oversight, making it difficult to ensure the uniqueness of each student’s work. This poses serious academic risks, as undetected similarities in thesis titles can lead to unintended plagiarism, compromise academic integrity, and undermine the credibility of educational institutions. In a broader sense, repeated or overlapping research topics also reflect a lack of innovation and weaken the scientific contribution of academic programs. To address this issue, an automated detection system is needed to efficiently identify similarities between thesis titles. This study aims to develop a web-based thesis title similarity detection system that integrates Levenshtein Distance and Cosine Similarity algorithms. The system was developed using the Waterfall model, involving stages of requirements analysis, design, implementation, and evaluation. Functional features such as login, title data management, old spelling normalization, and real-time similarity detection were implemented. The results show that the combination of both algorithms effectively detects similarities in character and semantic aspects. The inclusion of an old spelling normalization feature significantly improves detection accuracy by aligning historical and modern word forms prior to analysis. In conclusion, the developed system not only supports a faster and more objective title verification process but also contributes to the prevention of academic plagiarism and promotes integrity in higher education environments
Pengaruh Motivasi Kerja dan Kepuasan Kerja Pada Kinerja Pegawai di Puskesmas Langsa Baro
Full text linkTujuan utama riset ini adalah untuk menganalisis sejauh mana pengaruh motivasi kerja dan kepuasan kerja pada kinerja pegawai di Puskesmas Langsa Baro. Penelitian dilaksanakan dengan pendekatan kuantitatif menggunakan 94 responden yang dipilih secara acak melalui metode simple random sampling. Teknik pengumpulan data melalui penyebaran kuesioner, sementara analisis data dengan regresi linier berganda yang dilengkapi dengan uji t, uji F, dan koefisien determinasi. Hasil uji parsial menemukan bahwa motivasi kerja berkontribusi signifikan pada peningkatan kinerja pegawai, dibuktikan dengan nilai signifikansi 0,000 < 0,05. Demikian pula, kepuasan kerja juga mengindikasikan hubungan yang signifikan dengan kinerja pegawai, dengan nilai signifikansi sebesar 0,034. Uji simultan menemukan bahwa kedua variabel secara bersama-sama berdampak secara signifikan pada kinerja pegawai (nilai sig = 0,000). Adapun nilai koefisien determinasi (R²) sebesar 0,178 mengindikasikan bahwa kontribusi gabungan motivasi dan kepuasan kerja pada kinerja hanya sebesar 17,8%, sedangkan sisanya sebesar 82,2% dipengaruhi oleh variabel lain. Temuan ini menegaskan pentingnya peningkatan motivasi dan kepuasan kerja dalam strategi manajemen sumber daya manusia guna mendorong kinerja optimal di sektor pelayanan publik, khususnya di lingkungan puskesmas
Pengaruh Content Marketing terhadap Keputusan Pembelian melalui Minat Beli sebagai Intervening di Aplikasi Tiktok pada Mahasiswa di Kota Semarang
Full text linkContent Marketing berperan sebagai jantungnya suatu bisnis dikarenakan adanya strategi dalam sub bisnis yang sangat sulit dan menentukan perkembangan suatu perusahaan dengan hal ini marketing dioptimalkan melalui strategi yang efisien dengan format yang terbarukan serta telah teruji pada suatu konsumen. Dengan adanya perkembangan pesat, khususnya pada platform media social seperti Tiktok. Penelitian ini bertujuan untuk menganalisis pengaruh Content Marketing terhadap Keputusan Pembelian dengan Minat Beli sebagai variable intervening pada mahasiswa di Kota Semarang. Penelitian ini menggunakan pendekatan kuantitatif deskriptif dengan pengumpulan data olahan berupa primer melalui pembagian kuesioner pada 100 responden mahasiswa pemakai aplikasi Tiktok di Kota Semarang. Teknik mengambil sampel dengan metode non-probability sampling bersama metode purposive sampling. Analisis data menggunakan regresi linear berganda dan uji sobel untuk menguji efek intervening. Hasil penelitian menunjukan bahwa Content Marketing berpengaruh positif dan signifikan terhadap Keputusan Pembelian, dengan Selain itu, Minat Beli terbukti secara positif dan signifikan mengintervening pengaruh antara Content Marketing terhadap Keputusan Pembelian sebesar , 2 0,792. Penelitian ini memperkuat pentingnya strategi Content Marketing pada Aplikasi Tiktok dalam membentuk Minat Beli yang pada akhirnya mendorong Keputusan Pembelian khususnya di kalangan mahasiswa sebagai konsumen digital aktif. Penelitian ini diharapkan dapat berkontribusi pada pengembangan literatur dan rujukan bagi akademisi terkait Content Marketing pada Aplikasi Tiktok dalam mempengaruhi Keputusan Pembelian dan Minat Beli terhadap Konsumen terutama mahasiswa di Kota Semarnag dan pelaku bisnis dalam pengoptimalan Content Marketing digital diera Media Sosial khususnya pada Aplikasi Tiktok
The Role of Financial Literacy in Moderating the Influence of Fintech and Financial Inclusion on Financial Performance
Full text linkMicro, small, and medium-sized businesses (MSMBs) are crucial for boosting community economic empowerment and job creation. Unfortunately, many players in the MSME sector struggle with good financial management due to even a simple lack of knowledge about financial reporting. In this study, we aim to analyze how fintech and financial inclusion affect the financial performance of micro, small, and medium-sized enterprises (MSMEs), controlling for financial literacy as a moderating variable. A quantitative explanatory research approach is utilized in this work. Using a purposive sample technique, one hundred MSME players in the culinary sector of Semarang City were chosen. The data was collected via secondary sources, surveys, and interviews conducted by the Central Java Provincial Cooperatives and MSMEs Office. Moderated Regression Analysis (MRA) and multiple linear regression were employed for the data analysis. The findings were reliable according to the traditional premise. Financial inclusion (β = 0.171; p < 0.05) and financial performance (B = 0.289; p < 0.05) were both markedly enhanced by fintech, according to the study's findings. The effect of financial literacy on financial success was stronger than that of fintech (B = 0.017; p < 0.05) and financial inclusion (B = 0.022; p < 0.05). This research highlights the critical importance of financial literacy for MSMEs to maximize digital financial services
Analisis Kinerja Keuangan Terhadap Perubahan Harga Saham Pada Perusahaan Sektor Tembakau yang Terdaftar di Bursa Efek Indonesia Periode Tahun 2020-2023
Full text linkTujuan dari penelitian ini adalah untuk memastikan sejauh mana rasio profitabilitas, likuiditas, dan solvabilitas memiliki dampak pada nilai saham di industri tembakau. Populasi penelitian mencakup semua perusahaan yang terdaftar di Bursa Efek Indonesia (BEI), sedangkan sampel terdiri dari empat perusahaan tembakau yang terdaftar di BEI. Variabel yang diteliti mencakup ukuran profitabilitas, seperti Return On Equity (ROE), Return On Assets (ROA), Net Profit Margin (NPM), dan Gross Profit Margin (GPM); indikator likuiditas, seperti Current Ratio (CR) dan Quick Ratio (QR); dan indikator solvabilitas, seperti Debt To Equity Ratio (DER) dan Debt To Assets Ratio (DAR). Dengan nilai 0,029, yang berada di bawah ambang batas 0,05, temuan uji-t menunjukkan bahwa profitabilitas memiliki dampak yang substansial terhadap harga saham, yang mengarah pada penolakan hipotesis nol (Ho) dan penerimaan hipotesis alternatif (Ha). Di sisi lain, tingkat kepentingan profitabilitas terhadap nilai saham adalah 0. 0,05, yang lebih tinggi dari ambang batas 0,05, sementara likuiditas hanya memiliki sedikit pengaruh. 218 Akibatnya, Ha ditolak, sementara Ho diterima. Variabel solvabilitas ditemukan memiliki pengaruh yang cukup besar terhadap harga saham, dengan nilai signifikansi 0,050, yang menunjukkan bahwa Ha diterima dan Ho ditolak
Faktor-Faktor yang Mempengaruhi Harga Saham (Studi Kasus pada Perusahaan Sektor Kesehatan yang Terdaftar di Bursa Efek Indonesia Periode 2021-2024)
Full text linkKajian ini dimaksudkan untuk mengevaluasi hubungan antara beberapa indikator kinerja keuangan dengan harga saham pada perusahaan sektor kesehatan yang tercatat di Bursa Efek Indonesia (BEI) selama periode 2021 hingga 2024. Variabel independen yang dianalisis mencakup Economic Value Added (EVA), Market Value Added (MVA), Earnings Per Share (EPS), Dividend Per Share (DPS), serta ukuran perusahaan (Size). Dari total populasi sebanyak 118 perusahaan, dipilih 10 perusahaan sebagai sampel melalui teknik purposive sampling, sehingga diperoleh 40 data observasi. Analisis yang digunakan adalah regresi linier berganda. Temuan menunjukkan bahwa secara simultan, seluruh variabel independen memberikan kontribusi signifikan pada harga saham. Secara parsial, EVA dan Size menunjukkan hubungan negatif yang signifikan pada harga saham, sementara EPS memiliki hubungan positif signifikan. Di sisi lain, MVA dan DPS tidak memiliki keterkaitan signifikan dengan harga saham. Hasil ini memberikan pandangan bahwa investor sebaiknya memperhatikan indikator nilai tambah ekonomi serta kinerja laba per saham sebagai landasan dalam mengambil keputusan investasi pada perusahaan sektor kesehatan di pasar modal Indonesia
Pengaruh Motivasi Kerja dan Gaya Kepemimpinan Terhadap Kinerja karyawan Pada CV. Galih Langgeng Jaya
Full text linkDalam suatu organisasi, Sumber Daya Manusia (SDM) merupakan aset paling strategis yang memainkan peran krusial dalam menentukan efektivitas operasional serta daya saing jangka panjang perusahaan. Hal ini menjadi semakin penting khususnya di sektor jasa, di mana Perusahaan tidak dapat lepas dari pentingnya memberikan pelayanan terbaik kepada pelanggan. Untuk itu, performa karyawan menjadi faktor sentral dalam membangun keunggulan kompetitif. Penelitian ini bertujuan untuk menganalisis dampak motivasi dan gaya kepemimpinan terhadap kinerja karyawan pada CV. Galih Langgeng Jaya. Dalam dinamika industri jasa yang kompetitif, kinerja karyawan menjadi kunci keberhasilan perusahaan. Pendekatan kuantitatif diterapkan melalui survei dengan menggunakan kuesioner yang dibagikan kepada 50 responden, yang ditentukan berdasarkan rumus Slovin dari jumlah populasi sebanyak 100 karyawan. Teknik analisis regresi linier berganda digunakan dengan bantuan SPSS 25. Temuan ini menjelaskan jika baik motivasi maupun gaya kepemimpinan berpengaruh positif dan signifikan terhadap kinerja karyawan, baik secara parsial maupun simultan. Temuan ini memberikan implikasi bahwa perusahaan perlu meningkatkan strategi motivasi dan mengadopsi gaya kepemimpinan yang partisipatif serta transformasional guna mendukung pencapaian kinerja optimal.