Jurnal LPPM iSTTS
Not a member yet
189 research outputs found
Sort by
Implementation of Hand Gesture Recognition as Smart Home Devices Controller
Full text linkSome current virtual assistant products such as Alexa, Siri and Google Home facilitate features to control smart home devices through voice input, which has become increasingly popular in recent years. In addition to voice input, smart home devices can also be monitored and controlled through smartphones or computers using applications that provide users with flexibility. However, both control systems are less efficient, as they consume time and voice input utilization may sometimes not be recognized in crowded conditions. Therefore, this research introduces an application to recognize real-time hand gestures and utilize them for a new control system that provides time and energy efficiency. This application processes images using the Mediapipe framework, generating hand landmark outputs. These landmark outputs are utilized to determine the combination of raised or lowered fingers, which is then used to control smart home devices. The application is developed with ESP32 and ESP01s modules as data receivers from gesture recognition, and ESP32-CAM for image acquisition. Meanwhile, the gesture recognition computation process is executed on a Raspberry Pi 3 Model B. The gesture recognition application achieves good accuracy at 88%, but may experience occasional failures for certain gestures. However, the response time generated by the smart home control system is still relatively long, averaging 7.88 seconds
Peran Moderasi Keamanan Kerja Pada Hubungan Psychological Contract Breach dan Turnover Intention
Full text linkTurnover intention adalah fenomena yang menarik untuk diteliti karena memiliki dampak yang signifikan terhadap berbagai aspek dalam sebuah organisasi. Dengan memahami faktor-faktor yang mempengaruhi turnover, organisasi dapat mengambil langkah-langkah proaktif untuk mengelola turnover dan meningkatkan kinerja serta keberlanjutan organisasi dalam jangka panjang. Psychological contract breach (pelanggaran kontrak psikologis) dan keamanan kerja adalah dua faktor yang sering dikaitkan dengan tingginya turnover intention dalam konteks organisasi. Ketika karyawan merasa kontrak psikologisnya dilanggar, hal ini dapat meningkatkan niat untuk berpindah kerja. Di sisi lain, keamanan kerja yang tinggi dapat memberikan rasa nyaman dan keyakinan bahwa mereka dapat mengandalkan pekerjaan mereka untuk jangka waktu yang lama. Studi ini menguji pengaruh psychological contract breach terhadap turnover intention. Studi ini juga menguji keamanan kerja karyawan sebagai pemoderasi pada hubungan psychological contract breach dan turnover intention. Data dikumpulkan dengan desain survei melalui distribusi kuesioner. Responden studi ini adalah 165 karyawan yang bekerja sebagai tenaga penjual dan tenaga pemasaran di berbagai industri di Surabaya. Pendistribusikan kuesioner dilakukan secara daring dengan menggunakan google form kepada karyawan yang berada pada lingkup jejaring sosial. Pengujian hipotesis dilakukan dengan menggunakan analisis regresi hirarkikal. Hasil Penelitian ini menunjukkan bahwa psychological contract breach berpengaruh postitif pada turnover intention dan keamanan kerja memoderasi hubungan antara psychological contract breach dan turnover intention. Pada akhir artikel ini dibahas keterbatasan dan saran penelitian serta implikasi praktis untuk organisasi
Perancangan Sistem Informasi Pencatatan Pekerjaan Pada Telkom Akses Sidoarjo Menggunakan Metode Rapid Application Development (RAD)
Full text linkPT Telkom Akses merupakan salah satu anak perusahaan PT Telekomunikasi Indonesia (Telkom) yang bergerak di bidang konstruksi pembangunan dan manage service infrastruktur jaringan. Perusahaan ini bergerak dalam bisnis penyediaan layanan konstruksi dan pengelolaan infrastruktur jaringan. PT Telkom Akses dengan produk Indihome-nya, memiliki permasalahan dimana saat ini masih menerapkan sistem monitoring manual dengan cara Team Leader (TL) akan mengirimkan kumpulan Work Order dalam format Excel yang didistribusikan ke PIC (Person In Charge). Nantinya Work Order tersebut didistribusikan ke para teknisi melalui aplikasi Telegram sehingga rentan terjadi kesalahan dan keterlambatan pelaporan pada saat pelaksanaan pekerjaan di lapangan. Pada penelitian ini dikembangkan sistem informasi untuk pendistribusian work order agar lebih tersistematis dan terarsip dengan baik. Pengembangan aplikasi ini akan menggunakan metode Rapid Application Development (RAD) karena mempertimbangkan efisiensi waktu pada saat fase implementasi. Hasil dari implementasi aplikasi berbasis web ini adalah sistem yang mampu memonitor Work Order yang telah di pick up oleh teknisi terkait secara berkala dan tepat waktu. Dari hasil uji coba menggunakan metode blackbox testing terlihat semua fitur pada aplikasi dapat berjalan dengan baik. Selain itu lewat pengujian kuisioner Webqual 4.0 didapatkan hasil bahwa sistem mampu mempercepat dan mengefisienkan kerja dari tim
Deep Learning Models Comparison for Emotion Classification With Image Pre-Processing Methods
Full text linkThis research investigates advancements in Facial Expression Recognition (FER) within the domain of affective computing, focusing on improving the accuracy and robustness of FER systems under diverse, real-world conditions. Facial expressions serve as critical non-verbal cues in human communication, yet existing FER systems often face challenges due to environmental variability such as changes in lighting, pose, and occlusions. This study evaluates the performance of three Convolutional Neural Network (CNN) architectures—ResNet50, VGG16, and MobileNetV3Large—integrated with preprocessing techniques like Contrast Limited Adaptive Histogram Equalization (CLAHE) and the Synthetic Minority Oversampling Technique (SMOTE). These methods address key challenges such as class imbalance and low contrast in datasets. Results demonstrate the pivotal role of tailored preprocessing strategies. For instance, the application of CLAHE and SMOTE improved the VGG16 model's test accuracy from 0.70 to 0.79, representing a 0.09 or 9% increase. This significant improvement underscores the effectiveness of combining advanced preprocessing methods with CNN architectures. Furthermore, the findings highlight the advantages of optimizing preprocessing to enhance the recognition of subtle emotions in uncontrolled settings, offering practical insights for deploying FER systems in real-time applications. Overall, this research demonstrates the potential of preprocessing techniques to enhance FER system performance significantly, particularly when paired with well-established deep learning models. These insights pave the way for the development of more accurate, robust, and adaptable FER systems capable of functioning reliably in dynamic, real-world environments
Etika Teknologi: Kajian Sistematis, Trend dan Potensi Riset Etika Teknologi Digital
Full text linkIntegrasi etika ke dalam teknologi diperlukan untuk memberikan kompas etis yang lebih jelas bagi pengguna dan pengembang teknologi, pengambil kebijakan, dan semua stakeholder. Penelitian ini bertujuan untuk memperdalam konsep etika digital dan menggali rumusan techno-ethics sehingga membantu masyarakat menghadapi tantangan etis dalam era digitalisasi. Etika digital mengacu pada panduan dan nilai-nilai moral yang mengatur perilaku manusia dalam menggunakan, mengembangkan, dan berinteraksi dengan teknologi digital. Penelitian ini dilakukan dengan menggunakan metode systematic review, dengan mengambil sumber data artikel dari database terindeks Scopus. Hasil penelitian menunjukkan bahwa riset tentang tekno etika mengalami tren meningkat dalam dua dekade terakhir, namun masih membutuhkan lebih banyak kajian. Meningkatnya minat penelitian dalam tekno-etika ini menjadi iklim positif untuk menyuarakan praktik etis dalam gempuran teknologi. Diperlukan upaya yang lebih banyak untuk menjawab keterbatasan dan kekurangan publikasi penelitian yang masih belum mampu mencakup seluruh pengetahuan yang terfragmentasi dalam konsep kajian tekno-etika. Hasil penelitian ini juga berimplikasi praktis bagi para pimpinan, pelaku, dan pengembang teknologi maupun organisasi untuk mengurangi praktik-praktik tidak etis dalam penggunaan teknologi. Semua stakeholder perlu mendorong perilaku yang etis dalam rangka menciptakan ekosistem digital yang berkelanjutan. Temuan penelitian mengidentifikasi celah-celah riset yang memberi masukan bagi para pimpinan, pengembang teknologi, pembuat kebijakan, dan masyarakat
Chi-Square Histogram Analysis of Woven Fabric Images Made from Natural Dyes Due to Exposure to Sunlight
Full text linkThis research aims to conduct a Chi-square analysis on the histogram of woven fabric images dyed with natural dyes following exposure to sunlight. Woven fabrics dyed with natural dyes have attracted attention in the textile industry due to their sustainability and environmental safety. Continuous sunlight is a significant factor influencing color changes in woven fabric dyed with natural dyes. The methodology involves capturing images of woven fabric pre- and post-sunlight exposure, followed by histogram analysis using Chi-Square testing, mean, mode, and standard deviation. We utilize pre-cropped and resized grayscale images. Research findings demonstrate that sunlight significantly impacts the histogram of woven fabric images dyed with natural dyes, causing shifts in color distribution, standard deviation, and mode. These findings hold critical implications for the textile industry, particularly for manufacturers of woven fabrics dyed with natural dyes. The application of Chi-Square analysis and standard deviation provides guidelines for product design, maintenance procedures, and consumer education regarding the preservation of color quality in fabrics exposed to sunlight. Changes in the quality of woven fabric images under sunlight exposure can offer essential guidance in the care and maintenance of textile products dyed with natural dyes. This research contributes to a deeper understanding of the interplay between natural dyes, sunlight, and woven fabrics, supporting the development of sun-resistant natural dyes
Procedural Map Generation for 'Splatted': Enhancing Player Experience through Genetic Algorithms and AI Finite State Machines in a Snowball Throwing Game
Full text linkGames, a now extremely prevalent form of global entertainment, have emerged as a leading industry in the entertainment media, surpassing other entertainment media such as books, films, and music. However, game development is a complex endeavor, requiring a diverse set of talents to create a decent game for people to enjoy. Some of the talents needed to create a good game is a game designer, which dictates how a player can interact with the world, a writer, which pours a meaningful story inside said world, and a composer, which uses music to elevate the emotions evoked by the game and its events. With that being said, this research aims to streamline the creation process of the game designers, specifically the level designers by focusing on procedural map generation and artificial intelligence to create a map that is in a playable state for the players to play in. Procedural map generation, facilitated by a genetic algorithm inspired by Darwin's evolutionary theory, expedites the level design process. The research explores two types of map generation—tile-based and template-based, each with distinct advantages and disadvantages. Through user acceptance tests and expert-level analysis, it is evident that the genetic algorithm performs effectively, achieving a noteworthy level of player satisfaction
A Hybrid Approach Using K-Means Clustering and the SAW Method for Evaluating and Determining the Priority of SMEs in Palembang City
Full text linkThe current efforts to develop Small and Medium Enterprises (SMEs) are still facing challenges in setting appropriate targets. Although the Palembang City Cooperative and SME Agency has launched various programs and initiatives to support SME development, they have not yet successfully identified the SMEs that should be given priority for development. This study aims to apply a hybrid approach that combines the K-Means Clustering method and Simple Additive Weighting (SAW) to evaluate and prioritize SME development in Palembang City. The K-Means Clustering method is used to group SMEs based on their characteristics, while SAW provides preference values ( ). The SME data was obtained from the Palembang City Cooperative and SME Agency, covering 362 SME units. The K-Means Clustering results yielded two clusters: Cluster 0 as the High Growth Cluster and Cluster 1 as the Stability and Improvement Cluster. Validation using cross-validation showed that this model achieved an accuracy of 99.72%. The SAW analysis on Cluster 0 indicated that the Kopi Kaljo SME received the highest priority with a preference value of 45.71. This study confirms that this hybrid approach is effective in grouping SMEs based on their characteristics and prioritizing them based on data-driven evaluation. The research results are expected to help the Palembang City Cooperative and SME Agency design more effective and targeted assistance programs to optimize the contribution of SMEs to local economic growth to the maximum extent
Perancangan UI/UX Prototipe Website RFC Telkom University Surabaya Menggunakan Metode Lean UX
Full text linkSaat ini, website memiliki berbagai peran bagi suatu proses bisnis seperti dalam proses penjualan produk atau website e-commerce. Rooftop Farming Center (RFC) merupakan komunitas yang berinovasi untuk mengelola lahan rooftop Telkom University Surabaya dengan menggunakan smart urban farming yang memanfaatkan Internet of Things (IoT) untuk mendapatkan hasil yang maksimal sekaligus untuk mewadahi mahasiswa untuk melakukan riset terkait IoT. RFC telah menghasilkan berbagai jenis sayuran, buah-buahan, dan ikan air tawar yang dijual ke masyarakat sekitar dengan sistem penjualan konvensional yaitu secara mouth-to-mouth maupun dengan melalui whatsapp sehingga masih belum terintegrasi. Oleh karena itu, Hal ini mengakibatkan sulitnya mendapatkan informasi stok terbaru, sulitnya memperluas jangkauan penjualan produk RFC, serta sulitnya mendapatkan data-data untuk keperluan riset. untuk meningkatkan jangkauan pasar dan efektifitas pengelolaan produk yang dihasilkan oleh RFC, diperlukan perancangan User Interface (UI) dan User Experience (UX) sebuah website RFC. Penelitian ini menggunakan metode Lean UX untuk melakukan perancangan desain UI/UX yang dikembangkan dalam bentuk high-fidelity prototype. Perancangan tersebut akan dievaluasi dengan thinking aloud dan kuesionerSystem Usability Scale (SUS) untuk mendapatkan desain yang sesuai dengan kebutuhan pengguna. Setelah itu, desain tersebut akan disesuaikan kedalam front-end yang akan diuji menggunakan black box testing. Dari hasil pengujian desain yang telah dilakukan dengan metode thinking aloud dan SUS, diperloleh nilai 81,4 pada tampilan pelanggan dan 85 pada tampilan admin yang keduanya telah disesuaikan berdasarkan hasil pengujian thinking aloud. Sedangkan dalam pengujian black box testing yang telah dilakukan, keseluruhan fitur pada sistem yang dibuat dapat berjalan dengan baik
Thesis Defense Scheduling Optimization Using Harris Hawk Optimization
Full text linkThis research discusses how the Harris Hawk Optimization (HHO) algorithm handles scheduling problems. The scheduling of thesis defenses at the Institut Sains dan Teknologi Terpadu Surabaya (ISTTS) is a complex issue because it involves the availability of lecturers, teaching/exam schedules, lecturer preferences, and limited room and time availability. The scheduling constraints in this research are divided into two categories: Hard Constraints and Soft Constraints. Hard constraints must not be violated, including each lecturer's unique availability, conflicts, and existing exam or teaching schedules. Soft constraints, on the other hand, include preferences for specific days or rooms for the defense. The complexity of scheduling due to these two types of constraints leads to longer scheduling times and an increased likelihood of human error. To automate and optimize this process, the author employs the HHO algorithm. HHO is inspired by the behavior of the Harris Hawk, known for its intelligence and ability to coordinate while hunting. The results of the HHO algorithm are translated into a slot meter, which helps to map the solution to available time slots. The HHO algorithm can generate schedules that comply with 90% of the hard constraints at ISTTS. Evolutionary algorithms typically have high complexity and computational time; in this case, the researcher experimented with multiprocessing. Multiprocessing improved the computational time by up to 39%