Childhood stunting is a condition anticipated to affect the growth potential of children under the age of five. With numerous stunting researches that have been conducted, stunting datasets are now widely available to...
Childhood stunting is a condition anticipated to affect the growth potential of children under the age of five. With numerous stunting researches that have been conducted, stunting datasets are now widely available to facilitate stunting research. This provides an opportunity to implement machine learning (ML) principles to produce a broader insight or a novel technique in stunting prediction. A systematic literature review is necessary to discover the landscape of machine learning implementation in the application domain as a preliminary study for creating an effective research roadmap. This paper presents a systematic literature review (SLR) of 22 curated manuscripts that focuses on identifying the ML models applied in stunting research, as well as the datasets used in such studies that were published during 2017–2022. The SLR process found that ML principles have been applied in stunting research since 2017, and the diversity of ML implementation has become more varied in 2021–2022. In terms of ML models, XGBoost and Random Forest are recognized as the two most utilized models, and stunting prediction is the most common ML implementation. The majority of stunting research utilizing ML has been conducted in Indonesia. Although national survey data has been the most commonly utilized dataset in stunting research, researchers in Indonesia have shown a preference for utilizing data from regional or independent surveys. This study will be followed by developing a classifier model for stunted children using XGBoost and Random Forest algorithms. The model will be trained on a dataset generated from StuntingDB.
Traditional perception systems for TJA (Traffic Jam Assistance) are mostly implemented by fusing images with radar or lidar. As computer vision techniques become more powerful, cameras can almost replace the need for ...
Traditional perception systems for TJA (Traffic Jam Assistance) are mostly implemented by fusing images with radar or lidar. As computer vision techniques become more powerful, cameras can almost replace the need for radar and lidar in perception tasks, which reduces the hardware cost of the system. In this research, we propose a camera-only perception system for TJA, which is able to provide the information of the vehicles ahead and the drivable area. The proposed system has been evaluated through real-world scenario sequences, and proved that it achieves high robustness, which is highly possible to be adopted for TJA development.
This research discusses the improvement of Long Short-Term Memory (LSTM) model accuracy in translating Batak to Indonesian by utilizing FastText and GloVe embeddings. Traditional LSTM models often struggle with the co...
详细信息
ISBN:
(数字)9798350351613
ISBN:
(纸本)9798350351620
This research discusses the improvement of Long Short-Term Memory (LSTM) model accuracy in translating Batak to Indonesian by utilizing FastText and GloVe embeddings. Traditional LSTM models often struggle with the complexity and richness of underrepresented languages like Batak. By integrating FastText and GloVe, which provide word vectors with deeper semantic meanings, the translation quality can be significantly enhanced. Experimental results show that this approach offers a substantial performance improvement compared to conventional LSTM models, producing more accurate and contextual translations. These findings have the potential to be applied in broader multilingual translation systems and support the preservation and digital accessibility of minority languages.
Nowadays, every company knows that when making a decision that has a potential in affecting their assets, an accurately processed report is necessary in order to support the reasoning behind their decision. Generating...
详细信息
Text classification is a process of locating text documents automatically into categories based on the text content. In-text classification, there is a stage that has an important role in giving the value of importanc...
详细信息
This paper describes the implementation and evaluation of an RC polyphase filter (RCPF) and circuitry for measuring its frequency characteristics. The integrated circuit is fabricated on a 0.6 µm CMOS process and...
详细信息
The Healthcare Accreditation Institute has an assessment and certification process for hospitals applying for Healthcare Accreditation. The assessment process requires a large number of text-based reports. The purpose...
The Healthcare Accreditation Institute has an assessment and certification process for hospitals applying for Healthcare Accreditation. The assessment process requires a large number of text-based reports. The purpose of this research was to study the text analysis of the self-assessment reports of healthcare facilities and surveyor reports on issues related to the pharmaceutical system to evaluate and rate the accreditation of medical facilities. The natural language text vector analysis technique, together with the Universal Sentence Encoder (USE) was compared to Learning Lightweight Language-agnostic Sentence Embeddings (LEALLA) for encoding data into a high-dimensional format. Next the sentence encoding feature was fed through a machine learning procedure, including artificial neural networks, logistic regression, and support vector machines to classify nursing facility accreditation ratings. The experimental results showed that the USE embedding yielded better performance than the LEALLA embedding across all models with a precision of 0.70 but took slightly longer to encode feature sentences. This research could improve the performance of the analysis and scoring.
In order to reduce Polyethylene Terephthalate (PET) bottle plastic waste, Universitas Brawijaya (UB) provided reverse osmosis drinking water in some buildings. Water monitoring is needed to keep the water quality. The...
详细信息
This study aims to find articles and clauses from the 1945 Constitution (UUD 1945) using the Vector Space Model method that calculates the similarity of many documents. One document is represented by one clause from e...
详细信息
Medication errors threaten patient safety considerably, underscoring the necessity for enhanced detection and prevention techniques. A prevalent classification system in hospitals relies on the standard practice of me...
Medication errors threaten patient safety considerably, underscoring the necessity for enhanced detection and prevention techniques. A prevalent classification system in hospitals relies on the standard practice of medication administration known as the Five Rights (5R). This study seeks to develop an NLP-based tool designed to expand 5R error categorization coverage and alleviate the workload of medical professionals. The proposed method focuses on Thai medical text, incorporating Thai and English vocabulary. In this investigation, we developed a supervised learning classification framework using the Universal Sentence Encoder (USE) for sentence embedding, followed by an Artificial Neural Network (ANN) for model training. Additionally, we explored a zero-shot classification model employing pre-trained Large Language Models (PLMs). Our findings reveal that the supervised learning classification model provides the most favorable performance, albeit with the limitation of reliance on labeled datasets, which can be resource intensive. Conversely, the zero-shot classification framework's performance is less optimal. However, future advancements in Thai medical PLMs may improve efficacy and present a viable alternative for medical data analysis without dependence on labeled datasets. This initiative lays the groundwork for potential future applications and advantages within Thailand's medical domain.
暂无评论