EMITTER - International Journal of Engineering Technology
Not a member yet
261 research outputs found
Sort by
From Waste to Power: Fly Ash-Based Silicone Anode Lithium-Ion Batteries Enhancing PV Systems
Full text linkIndonesia's high solar irradiance, averaging 4.8 kWh/m²/day, presents a significant opportunity to harness solar power to meet growing energy demands. Fly ash, abundant in Indonesia and rich in silicon dioxide (40-60% SiO2), can be repurposed into high-value silicon anodes. The successful extraction of silicon from fly ash, increasing SiO2 content from 49.21% to 93.52%, demonstrates the potential for converting industrial waste into valuable battery components. Combining these advanced batteries with PV systems improves overall efficiency and reliability. Energy charge and discharge experiments reveal high energy efficiency for silicon-anode batteries, peaking at 80.53% and declining to 67.67% after ten cycles. Impedance spectroscopy tests indicate that the S120 sample, with the lowest impedance values, is most suitable for high-efficiency applications. Photovoltaic (PV) system integration experiments show that while increased irradiance generally boosts power output, other factors like PV cell characteristics and load conditions also play crucial roles. In summary, leveraging Indonesia's solar potential with fly ash-based silicon anode batteries and advanced predictive analytics addresses energy and environmental challenges. This innovative approach enhances battery performance and promotes the circular economy by converting waste into high-value products, paving the way for a sustainable and efficient energy future
Development of DOAS System for Hazardous Methane Detection in the Near-Infrared Region
No full textMethane (CH4) is a powerful greenhouse gas that greatly contributes to global warming. It is also very combustible, which means it has a large danger of causing explosions. It is crucial to tackle methane emissions, especially those arising from oil and gas extraction processes like transit pipes. An area of great potential is the advancement of dependable sensors for the detection and reduction of methane leaks, with the aim of averting dangerous consequences. An open-path differential optical absorption spectroscopy (DOAS) system was described in this paper for the purpose of detecting CH4 gas emission at a moderate temperature. An in-depth examination of the absorption lines was conducted to determine the optimal wavelength for measurement. The Near Infrared (NIR) region was identified as the most suitable wavelength for detecting methane. Multiple measurements were conducted at different integration times (1 second, 2 seconds, and 3 seconds) to ensure reliability and determine the optimal integration time for the CH4 detection system. The DOAS system has the capability of precisely detecting methane concentrations at 1M ppm in the NIR region with a quick integration time of 2 seconds.  
The Network Slicing and Performance Analysis of 6G Networks using Machine Learning
Full text link6G technology is designed to provide users with faster and more reliable data transfer as compared to the current 5G technology. 6G is rapidly evolving and provides a large bandwidth, even in underserved areas. This technology is extremely anticipated and is currently booming for its ability to deliver massive network capacity, low latency, and a highly improved user experience. Its scope is immense, and it’s designed to connect everyone and everything in the world. It includes new deployment models and services with extended user capacity. This study proposes a network slicing simulator that uses hardcoded base station coordinates to randomly distribute client locations to help analyse the performance of a particular base station architecture. When a client wants to locate the closest base station, it queries the simulator, which stores base station coordinates in a K-Dimensional tree. Throughout the simulation, the user follows a pattern that continues until the time limit is achieved. It gauges multiple statistics such as client connection ratio, client count per second, Client count per slice, latency, and the new location of the client. The K-D tree handover algorithm proposed here allows the user to connect to the nearest base stations after fulfilling the required criteria. This algorithm ensures the quality requirements and decides among the base stations the user connects to
Human-machine Translation Model Evaluation Based on Artificial Intelligence Translation
Full text linkAs artificial intelligence (AI) translation technology advances, big data, cloud computing, and emerging technologies have enhanced the progress of the data industry over the past several decades. Human-machine translation becomes a new interactive mode between humans and machines and plays an essential role in transmitting information. Nevertheless, several translation models have their drawbacks and limitations, such as error rates and inaccuracy, and they are not able to adapt to the various demands of different groups. Taking the AI-based translation model as the research object, this study conducted an analysis of attention mechanisms and relevant technical means, examined the setbacks of conventional translation models, and proposed an AI-based translation model that produced a clear and high quality translation and presented a reference to further perfect AI-based translation models. The values of the manual and automated evaluation have demonstrated that the human-machine translation model improved the mismatchings between texts and contexts and enhanced the accurate and efficient intelligent recognition and expressions. It is set to a score of 1-10 for evaluation comparison with 30 language users as participants, and the achieved 6 points or above is considered effective. The research results suggested that the language fluency score rose from 4.9667 for conventional Statistical Machine Translation to 6.6333 for the AI-based translation model. As a result, the human-machine translation model improved the efficiency, speed, precision, and accuracy of language input to a certain degree, strengthened the correlation between semantic characteristics and intelligent recognition, and pushed the advancement of intelligent recognition. It can provide accurate and high-quality translation for language users and achieve an understanding of natural language input and output and automatic processing
Deep Learning Approaches for Automatic Drum Transcription
Full text linkDrum transcription is the task of transcribing audio or music into drum notation. Drum notation is helpful to help drummers as instruction in playing drums and could also be useful for students to learn about drum music theories. Unfortunately, transcribing music is not an easy task. A good transcription can usually be obtained only by an experienced musician. On the other side, musical notation is beneficial not only for professionals but also for amateurs. This study develops an Automatic Drum Transcription (ADT) application using the segment and classify method with Deep Learning as the classification method. The segment and classify method is divided into two steps. First, the segmentation step achieved a score of 76.14% in macro F1 after doing a grid search to tune the parameters. Second, the spectrogram feature is extracted on the detected onsets as the input for the classification models. The models are evaluated using the multi-objective optimization (MOO) of macro F1 score and time consumption for prediction. The result shows that the LSTM model outperformed the other models with MOO scores of 77.42%, 86.97%, and 82.87% on MDB Drums, IDMT-SMT Drums, and combined datasets, respectively. The model is then used in the ADT application. The application is built using the FastAPI framework, which delivers the transcription result as a drum tab
Numerical Analysis of Wave Load Characteristics on Jack-Up Production Platform Structure Using Modified k-ω SST Turbulence Model
Full text linkOne of the important stages in the offshore structure design process is the evaluation of the marine hydrodynamic load in which the structure operates, this is to ensure an appropriate design and improve the safety of the structure. Therefore, accurate modeling of the marine environment is needed to produce good evaluation data, one of the methods that can accurately model the marine environment is through the Computational Fluid Dynamic (CFD) method. This research aims to analyze the ocean wave load of pressure and force characteristics on the jack-up production platform hull structure using the (CFD) method. The foam-extend 4.0 (the fork of the OpenFOAM) software with waveFoam solver is utilized to predict the free surface flow phenomena as its capability to predict with accurate results. The Reynold Averaged Navier Stokes (RANS) turbulence model of k-ω SST is applied to predict the turbulence effect in the flow field. Five variations of incident wave direction type are carried out to examine its effect on the pressure and force characteristics on the jack-up production platform hull. The wave model shows inaccurate results with the decrease in wave height caused by excessive turbulence in the water surface area. Excessive turbulence levels can be overcome by incorporating density variable and buoyancy terms based on the Standard Gradient Diffusion Hypothesis (SGDH) into the turbulent kinetic energy equation. The k-ω SST Buoyancy turbulence model shows accurate results when verified to predict wave run-up and horizontal force loads on monopile structures. Furthermore, test results of the wave load on the jack-up production platform hull structure shows that the most significant wave load is obtained in variations with the wave arrival direction relatively opposite to the platform wall. Especially in the direction of 90° because it also has the most expansive impact surface area. Meanwhile, the lower wave load is obtained in variations 45° and 135°, which have the relatively oblique direction of wave arrival to the surface
Federated Learning Framework for IID and Non-IID datasets of Medical Images
Full text linkAdvances have been made in the field of Machine Learning showing that it is an effective tool that can be used for solving real world problems. This success is hugely attributed to the availability of accessible data which is not the case for many fields such as healthcare, a primary reason being the issue of privacy. Federated Learning (FL) is a technique that can be used to overcome the limitation of availability of data at a central location and allows for training machine learning models on private data or data that cannot be directly accessed. It allows the use of data to be decoupled from the governance (or control) over data. In this paper, we present an easy-to-use framework that provides a complete pipeline to let researchers and end users train any model on image data from various sources in a federated manner. We also show a comparison in results between models trained in a federated fashion and models trained in a centralized fashion for Independent and Identically Distributed (IID) and non IID datasets. The Intracranial Brain Hemorrhage dataset and the Pneumonia Detection dataset provided by the Radiological Society of North America (RSNA) are used for validating the FL framework and comparative analysis
Planar Microwave Sensor with High Sensitivity for Material Characterization Based on Square Split Ring Resonator (SSRR) for Solid and Liquid
Full text linkMicrowave resonator sensors are the most extensively used sensors in the food industries, quality assurance, medical, and manufacturing. Planar resonant technique is chosen as the medium for characterizing dielectric properties of material due to its compact in size, low cost and easy to fabricate. But these techniques have a low Q-factor and little sensitivity. This work uses the perturbation approach to overcome this technique's flaw, which is that Q-factor and resonant frequency are affected by the resonator's dielectric properties. This suggested sensor operated at 2.5GHz between 1GHz and 4GHz for material characterisation of solid and liquid samples. These sensors were constructed on a substrate made of RT/Duroid Roger 5880, which has a copper layer that is 0.0175 mm thick and has a dielectric constant of 2.2. This square split ring resonator (SSRR) sensor thus generates narrower resonant, low insertion loss, and a high Q-factor value of 430 at 2.5GHz. The SSRR sensor's sensitivity is 98.59%, which is higher than that of past studies. The application of the suggested sensor as a tool for material characterisation, particularly for identifying material attributes, is supported by this findings
Comparative Evaluation of VAEs, VAE-GANs and AAEs for Anomaly Detection in Network Intrusion Data
Full text linkWith cyberattacks growing in frequency and sophistication, effective anomaly detection is critical for securing networks and systems. This study provides a comparative evaluation of deep generative models for detecting anomalies in network intrusion data. The key objective is to determine the most accurate model architecture. Variational autoencoders (VAEs), VAE-GANs, and adversarial autoencoders (AAEs) are tested on the NSL-KDD dataset containing normal traffic and different attack types. Results show that AAEs significantly outperform VAEs and VAE-GANs, achieving AUC scores up to 0.96 and F1 scores of 0.76 on novel attacks. The adversarial regularization of AAEs enables superior generalization capabilities compared to standard VAEs. VAE-GANs exhibit better accuracy than VAEs, demonstrating the benefits of adversarial training. However, VAE-GANs have higher computational requirements. The findings provide strong evidence that AAEs are the most effective deep anomaly detection technique for intrusion detection systems. This study delivers novel insights into optimizing deep learning architectures for cyber defense. The comparative evaluation methodology and results will aid researchers and practitioners in selecting appropriate models for operational network security
KFREAIN: Design of A Kernel-Level Forensic Layer for Improving Real-Time Evidence Analysis Performance in IoT Networks
Full text linkAn exponential increase in number of attacks in IoT Networks makes it essential to formulate attack-level mitigation strategies. This paper proposes design of a scalable Kernel-level Forensic layer that assists in improving real-time evidence analysis performance to assist in efficient pattern analysis of the collected data samples. It has an inbuilt Temporal Blockchain Cache (TBC), which is refreshed after analysis of every set of evidences. The model uses a multidomain feature extraction engine that combines lightweight Fourier, Wavelet, Convolutional, Gabor, and Cosine feature sets that are selected by a stochastic Bacterial Foraging Optimizer (BFO) for identification of high variance features. The selected features are processed by an ensemble learning (EL) classifier that use low complexity classifiers reducing the energy consumption during analysis by 8.3% when compared with application-level forensic models. The model also showcased 3.5% higher accuracy, 4.9% higher precision, and 4.3% higher recall of attack-event identification when compared with standard forensic techniques. Due to kernel-level integration, the model is also able to reduce the delay needed for forensic analysis on different network types by 9.5%, thus making it useful for real-time & heterogenous network scenarios