Clean Energy and Smart Technology

IMPLEMENTATION OF CONVOLUTIONAL NEURAL NETWORK (CNN) ALGORITHM IN MOBILE APPLICATION-BASED VOICE EMOTION CLASSIFICATION SYSTEM

2026-04-21T07:18:58+07:00

The ability of machines to recognize emotions from voice is known as Speech Emotion Recognition (SER). This study developed a voice emotion classification system using a Convolutional Neural Network (CNN) and implemented it in the form of an Android mobile application. The main problem raised is how to recognize human emotions through voice signals accurately, efficiently, and in real-time on mobile devices. The study was conducted with two training stages, namely pre-training using the RAVDESS dataset and fine-tuning with the IndoWaveSentiment dataset. Audio data was converted into a 128×128×1 Mel-spectrogram to be input to the CNN. The CNN model consists of three convolution and pooling blocks, as well as dense and softmax layers. After training, the model was converted to TensorFlow Lite format and integrated with the Android application through a client-server architecture using Flask. The test results showed that the system was able to recognize neutral, happy, disappointed, and surprised emotions with a high level of accuracy both on test data but not as good on live recorded voice. The system also features a SQLite-based history feature. Test results showed 96% accuracy on external test data and 55% on live recorded audio, with an average accuracy of 75.5%. This indicates the model performs very well in structured conditions, but still needs improvement for real-world input.

IMPLEMENTATION OF THE FORCED ALIGNMENT ALGORITHM FOR AUDIO AND TEXT ALIGNMENT ON THE WEBSITE FOR THE MEANING OF THE JURUMIYAH BOOK

2026-04-16T09:09:43+07:00

Learning basic nahwu in studying yellow books still faces various challenges, especially in terms of interpreting books objectively and interactively. This study aims to build an automatic book interpretation system using forced alignment based on Wav2Vec2 + CTC Segmentation for audio and text alignment. This system is designed to provide automatic interpretation with audio and text alignment to facilitate the preparation of students in interpreting books and learning nahwu, especially jurumiyah books. The implementation process involves the extraction and pre-processing of audio and text data, audio and text are then aligned using Wav2Vec2 to produce logits output containing the number of samples, frames, and character tokens, then logits are received by CTC to calculate the alignment, manage blank tokens, calculate sequence probabilities and decoding to text to produce a timestamp array. Then the timestamp is validated and normalized and the final result is TextGrid or JSON. Then the results are integrated in an interactive website interface. The results of this study indicate that the forced alignment algorithm using the Wav2Vec2 model is capable of aligning audio and text with a fairly high level of accuracy. This makes it easier for users to understand the contents of the book through segmented audio playback per sentence or chapter. It is hoped that this research can contribute to the development of learning media for Islamic boarding schools' yellow books based on alignment technology.

HOUSING PLANNING WITH A SCANDINAVIAN CONTEMPORARY ARCHITECTURE APPROACH IN WONOSOBO

2026-04-16T09:12:27+07:00

To realize the concept of housing planning and design with a Scandinavian contemporary architectural approach as a clean, healthy, and cool residential area equipped with supporting facilities such as sports facilities, prayer rooms, gardens, which can provide a sense of comfort through processing the site plane layout based on architectural concepts so that it can give an impression to the building by applying appropriate forms. The Design Method is a system or strategy used to collect data in the form of information and ideas that can support the design. By analyzing the results of observation data and literature studies, so that potential and problems can be obtained that will be the basis for design. Analyze site conditions in the form of site utilities, sun orientation, wind direction, noise, achievement/accessibility, location and social conditions of the local community. From the results of comparative studies that have been carried out on four different buildings, students draw conclusions about how the concept of a Scandinavian contemporary house and what components are usually found in Scandinavian contemporary house buildings. From the three buildings, students will take several room criteria that will be used as considerations in planning Housing Planning With a Scandinavian Contemporary Architectural Approach in Wonosobo. The plan will include the construction of several housing clusters of various sizes. Natural lighting will be maximized so that the homes will reflect Scandinavian contemporary values.

Design and Application for End of Arm Tooling in Plastic Injection Molding

2026-04-16T14:05:35+07:00

This study discusses the implementation of End of Arm Tooling (EOAT) in the injection molding production process at Toyoda Kakou Co., Ltd. EOAT is a device attached to the end of a robotic arm that functions to automatically remove products from the mold. The research method used is descriptive qualitative with a case study approach. The evaluation results show that the use of EOAT is able to reduce the cycle time from approximately 26,0 seconds to 22.5 seconds, product defect rate decrease from 4% to 1%, and reduce from 1 employee to zero. This study also presents the detailed cost of EOAT components using the Yushin brand, with a total estimated value of IDR 6,350,000. The conclusion of this research is that EOAT has been proven to improve the efficiency and safety of the production process. It is recommended that EOAT be implemented more widely in other production lines.

OPTIMIZATION OF THE STRUCTURAL DESIGN OF THE CHASSIS OF AN AUTOMATED GUIDE VEHICLE USING EXPERIMENTAL AND NUMERICAL METHODS

2026-04-16T09:11:45+07:00

Automated Guided Vehicles (AGVs) are a smart transportation solution that is increasingly being used in industry. The stability and strength of the chassis are critical factors in ensuring AGV performance when carrying loads. This study examines the effects of load variations and material types on the structural performance of AGV chassis through an experimental approach and numerical simulation based on Finite Element Analysis (FEA). The materials used were ASTM A36 and ASTM A500, with loads of 5 kg, 10 kg, and 15 kg. A chassis design with dimensions of 400 × 300 × 80 mm was modeled and analyzed using Computational Fluid Dynamics (CFD) software. Validation was performed through experimental testing using a dial indicator. The results show that at a 15 kg load, ASTM A500 experienced a maximum stress of 60.15 MPa and a deflection of 0.00078 m, lower than ASTM A36, which reached 68.06 MPa and a deflection of 0.00089 m. The difference between the simulation and experimental results was well below 10%. Similarly, regarding the safety factor, ASTM A500 has a value of 2.7145 at maximum load, indicating that this material has a higher safety margin compared to ASTM A36. Based on these results, ASTM A500 is considered more efficient and stable, and is more recommended for AGV chassis applications. This study highlights the importance of integrating numerical and experimental methods to produce optimal structural designs.