Jurnal Informatika: Jurnal Pengembangan IT
Not a member yet
437 research outputs found
Sort by
Sistem Smart Home untuk Deteksi Potensi Kebakaran Berbasis Internet of Things dengan Notifikasi WhatsApp
No full textThe security and comfort of homes are fundamental needs that have become increasingly urgent with the advancement of technology. According to fire data released by the Pekalongan City Government in 2023, there were 101 reported cases of fires in Pekalongan, a threefold increase from 38 incidents in 2022. This study aims to design and implement a smart home system for detecting potential fires based on the Internet of Things (IoT) using NodeMCU ESP8266, ThingSpeak, and sensors including MQ2, flame sensors, and DHT11. The development method employs a prototyping model, supported by interviews with firefighters to identify relevant fire variables and ensure the system design meets user needs through hardware experimentation. Testing results indicate that the flame sensor can detect flames of 1.5 cm in length at a distance of up to 15 cm, with an average response time of 7.22 seconds to send notifications to WhatsApp. It can also detect flames of 3 cm in length at a distance of up to 50 cm, with an average response time of 8.79 seconds. The MQ2 sensor successfully detects gas concentrations above a value of 35, sending notifications to WhatsApp with an average response time of 8.89 seconds. Sensor data is visualized in real-time through ThingSpeak. Based on usability testing results, 68% of respondents expressed agreement, 24% were neutral, and 8% disagreed. The conclusion of this study is that the system can serve as an innovative alternative to create a safer and more efficient home environment. This research is expected to contribute to the development of smart home technology in Indonesi
Analisis Pengaruh SMOTE terhadap Kinerja Model KNN untuk Prediksi Risiko Stroke
No full textPenelitian ini membahas masalah ketidakseimbangan data dalam klasifikasi risiko stroke, di mana kasus non-stroke secara signifikan lebih rendah daripada kasus stroke. Ketidakseimbangan kelas cenderung menimbulkan bias terhadap kelas mayoritas, yang menyebabkan berkurangnya efektivitas klasifikasi. Untuk mengatasi hal ini, SMOTE (Synthetic Minority Over-sampling Technique) digunakan untuk mengatasi ketidakseimbangan kelas dalam dataset dan algoritma K-Nearest Neighbor (KNN) digunakan untuk klasifikasi. Dataset mengalami preprocessing, aplikasi SMOTE, dan algoritma KNN dilatih dan dievaluasi menggunakan metrik standar termasuk akurasi, presisi, recall, dan F1-score. Penerapan SMOTE bersama dengan KNN menghasilkan peningkatan yang signifikan dalam hasil klasifikasi, mencapai akurasi 91,87%, presisi 94,27%, recall 89,20%, dan F1-score 91,66%. Temuan ini menegaskan bahwa pendekatan yang diimplementasikan berkinerja baik dalam mendeteksi risiko stroke meskipun ada set data yang tidak seimbang. Tujuan dari penelitian ini adalah untuk menginformasikan kemajuan teknologi deteksi dini stroke yang lebih kuat dan mendukung peningkatan dalam penyediaan layanan kesehatan
Analisis Forensik Digital terhadap Kasus Penipuan pada E-Commerce Menggunakan Metode ACPO
No full textAbstrak – Perkembangan e-commerce berbasis media sosial telah meningkatkan risiko kejahatan siber, terutama kasus penipuan yang dilakukan di luar sistem resmi platform. TikTok Shop menjadi salah satu platform yang paling banyak digunakan, tetapi maraknya transaksi di luar sistem menimbulkan tantangan dalam investigasi kejahatan digital. Penelitian ini bertujuan untuk menganalisis efektivitas metode ACPO (Association of Chief Police Officers) dalam proses investigasi forensik digital guna mengidentifikasi dan mengamankan bukti elektronik terkait kasus penipuan pada e-commerce berbasis media sosial. Penelitian dilakukan dengan pendekatan eksperimental menggunakan Belkasoft dan MOBILedit Forensic Express untuk mengekstraksi bukti digital dari perangkat seluler. Dataset awal terdiri dari 2 akun, 2 gambar, 1 video, dan 8 percakapan pesan, sehingga total terdapat 13 bukti digital. Hasil pengujian menunjukkan bahwa Belkasoft berhasil mengekstraksi gambar dan video (100%) tetapi gagal memperoleh akun serta percakapan pesan, sedangkan MOBILedit Forensic Express berhasil mengekstraksi seluruh bukti (100%) kecuali video. Dengan menerapkan prinsip ACPO, memastikan penyelidikan bahwa seluruh bukti digital dikumpulkan secara sistematis dengan tetap menjaga integritasnya agar dapat digunakan dalam proses hukum. Hasil penelitian ini menunjukkan bahwa metode ACPO dapat diimplementasikan secara efektif dalam analisis forensik digital guna mendukung investigasi kejahatan siber di platform e-commerce berbasis media sosial. Penerapan metode ini berkontribusi dalam meningkatkan efektivitas investigasi dan validitas bukti digital dalam sistem peradilan.
Perancangan Aplikasi Web Asisten Dosen dengan Metode Design Thinking
No full textTeaching assistants (TAs) play a crucial role in supporting practical learning processes. However, TA management often encounters challenges in class and teaching time allocation, TA attendance recapitulation, and end-of-semester evaluations. To address these issues, a system that facilitates the management of practical sessions involving TAs is necessary. This web application system is designed to streamline task management, class scheduling, material collection, attendance tracking, and TA evaluations at the end of each semester. Furthermore, supporting features such as an integrated dashboard and automated notifications can enhance the delivery of practical services to students. This research employs the Design Thinking methodology, an innovative, user-centered design approach, to develop solutions that meet user needs. Through the stages of empathize, define, ideate, prototype, and test, the resulting web application not only simplifies practical management but also improves the user experience for both lecturers and TAs. Based on a questionnaire administered to 20 teaching assistants, usability testing of the web application using the System Usability Scale (SUS) method yielded an average score of 77.25, which falls under the 'good' category. Thus, this web application is expected to serve as an innovative solution that fosters a more flexible and integrated teaching and learning environment
Penerapan Linear Discriminant Analysis Untuk Meningkatkan Kinerja Algoritma Support Vector Machine
No full textObesity is a complex chronic disease influenced by various factors, such as genetic, environmental, and lifestyle, which is characterized by excess body weight due to the excessive accumulation of body fat. With the rapid advancement of technology and digitalization across all sectors, data has become increasingly vital, as large datasets generate valuable information. However, a key challenge in data analysis is addressing redundancy, noise, and high dimensionality, which can affect the performance of machine learning algorithms. This study aims to investigate the effectiveness of combining Linear Discriminant Analysis (LDA) and Support Vector Machine (SVM) in enhancing the accuracy and efficiency of high-dimensional data classification, particularly in predicting obesity levels. LDA is employed to reduce data dimensionality while retaining the most relevant features, whereas SVM is utilized as the classification algorithm to predict obesity levels based on patterns identified within the dataset. The research was conducted using a dataset consisting of 779 training samples and 195 testing samples. The results reveal that the combination of LDA and SVM achieved a classification accuracy of up to 99%, with a 50% reduction in data dimensionality and a computation speed of 0,0696 second. Moreover, computation time was significantly reduced, indicating that LDA not only facilitates data simplification but also improves the overall efficiency of the classification process
OPTIMASI PERFORMA ALGORITMA DOUBLE EXPONENTIAL SMOOTHING HOLT UNTUK PERAMALAN JUMLAH MAHASISWA BARU MENGGUNAKAN MODIFIED GOLDEN SECTION
No full textPenelitian ini membahas tentang perencanaan Universitas Buana Perjuangan Karawang dalam menghadapi peningkatan jumlah pendaftar mahasiswa baru. Berdasarkan penelitian sebelumnya, algoritma double exponential smoothing (holt) telah terbukti efektif dalam meramalkan jumlah mahasiswa baru. Namun, algoritma tersebut membutuhkan waktu lama untuk menentukan parameter terbaik. Data yang digunakan adalah jumlah mahasiswa dari tahun 2015 hingga 2023 yang dibagi berdasarkan pergelombang pemdaftaran. Pengujian dilakukan berdasarkan Mean Squared Error (MSE) dan Root Mean Squared Error (RMSE). Kontribusi penelitian ini adalah optimasi nilai alhpa dan betha pada algoritma double exponential smoothing untuk menghasilkan peramalan jumlah mahasiswa baru dengan tingkat eror terkecil. Berdasarkan hasil penelitian yang telah dilakukan, bahwa teknik modified golden section terbukti bisa mengoptimalkan nilai alpha dan beta pada metode double exponential smoothing untuk peramalan jumlah mahasiswa baru di Universitas Buana Perjuangan Karawang. Hal tersebut dibuktikan dengan nilai MSE dan RMSE pada hasil perbandingan metode double exponential smoothing dengan optimasi dan tanpa optimasi menunjukkan adanya kesamaan. Adapun nilai MSE yaitu 0,05876 dan RMSE yaitu 0,19137. Sehingga, metode tersebut terbukti optimal dapat mengurangi perhitungan berulang-ulang yaitu cukup dengan iterasi ke 19 telah didapatkan nilai alpha dan beta terbaik
Prediksi Kebutuhan Beras Di Jawa Timur Menggunakan Metode Gated Recurrent Unit (GRU)
No full textFood security is a strategic issue that affects economic stability and community welfare, especially in ensuring the availability of rice as a staple food in East Java. Uncertainty in food planning can cause an imbalance between rice production and consumption. Consequently, a precise forecast technique is necessary to aid decision-making. The objective of this research is to forecast or predict rice needs using the Gated Recurrent Unit (GRU) model to support more effective food management. The research methods include Min-Max Scaling normalization, and data division into 80% training and 20% testing. The GRU model has two main layers with 64 and 32 neuron units, The system was trained for 100 epochs with a batch size of 32 using the Adam optimizer and the MSE loss function. The evaluation results show high performance with MAE 0.0103, MSE 0.0001, RMSE 0.0116, and R² 0.9935, indicating low error and good generalization. The Training and Validation Loss graph shows a stable learning model without overfitting. This model can be a reliable prediction tool in food planning. Implementation of the model can help the government maintain the balance of rice supply and optimize agricultural policies
Implementasi Sistem IoT Pada Akuakultur Dan Hydroponik (Akuaponik) Modern Untuk Pertumbuhan Ikan Nila
No full textIn modern times, there are many types of agricultural and fish farming systems, one of which is the modern aquaculture system which has been recognized as an innovative method of sustainable food production that combines fish cultivation with agriculture simultaneously. Modern aquaponics is able to overcome problems in urban areas which require land for growing crops and cultivating fish. Good fish cultivation means always monitoring the growth and health of fish to reduce the risk of crop failure, therefore this research aims to implement an Internet of Things (IoT) system in modern aquaponics to increase the growth of tilapia. IoT parameters consisting of pH sensors, Total Dissolved Solids (TDS) sensors, and temperature sensors are used to monitor water quality conditions in modern aquaponics. Through IoT systems, data collected in real-time enables more effective environmental monitoring. The creation of an IoT system in modern aquaponics shows that the implementation of IoT can increase the efficiency of modern aquaponic environmental management, resulting in better fish growth and plant productivity. This was verified through the pH sensor test results with a value of 7.2 indicating optimal conditions of acid-base balance in the water, which is essential for the health of tilapia fish. The TDS sensor test with a value of 300 ppm confirmed that the concentration of solid particles in the water was at an optimal level, which is also an indicator of the health of the tilapia fish. Temperature measurement using a temperature sensor with a value of 28°C, shows that the water temperature is within the ideal range for comfort for tilapia, which is usually comfortable at temperatures between 28-30°
Perbandingan Hasil Nilai Baca Konsumsi Air Antara Sensor Water flow YF-B6 dan YF-S201 dalam Penggunaan Internet of Things
No full textThe use of clean water is very necessary for human life, the existence of clean water requires adequate infrastructure, especially in the distribution and quality of the water. Water usage measurements at PDAM and Pamsimas still use analog water meters, although the reading values are relatively accurate, the entire calculation process is less efficient because it has to be done manually by humans which requires energy and time and there is the possibility of recording errors. Water flow sensors are able to provide an alternative as a projection for the future which makes it possible to build smart water meters by applying IoT. However, the level of accuracy of water flow sensor readings needs to be studied more deeply for its use considering the many types of shapes, materials and sizes of water flow sensors. This research presents a comparison of sensor reading values by changing several constant parameters in each test, which is the most precise and accurate in each measurement test. These results are up to the accumulated amount of water in milli liters, then measured to obtain the accuracy value of each sensor reading value, thus the comparison of two water flow sensors can be used as a reference for the use of which sensor is most suitable for use as a water meter for each different uses
Pengumpulan Informasi pada Situs Web Dengan Menyusun Kerangka Kerja Keamanan Siber NIST
No full textIn the current era, the rapid development of websites has made them one of the most significant modern information media. Website creation is not only focused on the design and information presented, but also focuses on security aspects. The presence of security on a website is very important, considering the need to protect the data and information contained therein. Information Gathering is one method used to test a website's security. This information gathering is the earliest stage to obtain ownership and other sensitive information. This research aims to conduct security testing of the oase.poltektegal.ac.id website using tools in the form of penetration testing software; then, the testing results are entered into the cybersecurity framework issued by N.I.S.T. The test results obtained and adjusted to N.I.S.T. Cybersecurity are that the oase.poltektegal.ac.id website has vulnerabilities in the form of CVE-2003-1418 (apache webserver vulnerability), CVE-2005-3299 (PHP vulnerability), CVE-2010-4344 ( Buffer Overflow Vulnerability), CVE-2007-6750 (XSS). The solution to this vulnerability is updating the software and closing unused ports. These results will be used as a benchmark in creating or improving similar websites to increase awareness and vigilance in achieving cyber resilienc