Research Trends of Local Wisdom E-LKPD for Newton Law Problem Solving

Improving students' problem-solving skills can be done through teaching materials. Teaching materials used in schools throughout Indonesia have not been integrated with local potential or wisdom. This research aims to develop teaching materials based on local wisdom to improve students' problem-solving abilities. The local wisdom raised in the teaching materials is the local wisdom of agriculture in Binjai Medan and the Balinese environment based on the local wisdom of the Tumpek Wariga ceremony. The development of teaching materials uses the ADDIE design model (Analyze, Design, Develop, Implement, Evaluate). The implementation phase uses a quasi-experimental method with a non-equivalent control group design in a high school located where the local wisdom applies. The results showed that the feasibility test of teaching materials and the readability test showed that teaching materials based on local agricultural wisdom in Binjai were 83.643% (very feasible) and 77.13% (high). In contrast, environmental teaching materials in Bali were based on local wisdom Tumpek Wariga. Successively very feasible (88.10%) high (95.39%). Students' problem-solving ability has increased with an N-gain of 0.67 (medium) on teaching materials based on local agricultural wisdom in Binjai and 0.71 (high) in Balinese environmental teaching materials based on Tumpek Wariga. The study results showed that teaching materials based on local wisdom of Agriculture in Binjai and Tumpek Wariga in Bali were valid and could improve students' problem-solving skills on Ecosystem and Environmental Change materials.

Problem-solving skills are not only correlated to academic success but also to increased competitiveness in a professional environment. However, many junior high school students have both weak mathematical problem-solving and teamwork skills. This study aims to describe the improvement of mathematical problem-solving and teamwork skills of students using the Project Based Learning (PjBL) model and scientific learning. This study is a quantitative study with a quasi-experimental method, using Pretest-Posttest Control Group Design. The population in this study consisted of 186 junior high school students in Bengkalis Regency. Data collection techniques were carried out through mathematical problem-solving ability tests and teamwork questionnaires. Data analysis was carried out using normalized gain (N-Gain) and one-way ANOVA. Based on the results of the data analysis, the results obtained were that students in the PjBL group showed a higher increase in problem-solving and teamwork skills with N-gains of 0.48 and 0.42, respectively, compared to the control class which obtained N-gains of 0.21 and 0.09, respectively. Teamwork skills consistently improved across all grades, while improvement in problem-solving skills varied according to students' initial abilities. This study supports existing research by integrating cognitive and affective aspects of problem-solving and financial literacy skills into everyday life.

Assessment of lymphovascular invasion (LVI) in breast cancer (BC) primarily relies on preoperative needle biopsy. There is an urgent need to develop a non-invasive assessment method. To develop an effective model to assess the LVI status in patients with BC using magnetic resonance imaging morphological features (MRI-MF), Radiomics, and deep learning (DL) approaches based on dynamic contrast-enhanced MRI (DCE-MRI). Cross-sectional retrospective cohort study. The study included 206 BC patients, with 136 in the training set [97 LVI(-) and 39 LVI(+) cases; median age: 51.5 years] and 70 in the test set [52 LVI(-) and 18 LVI(+) cases; median age: 48 years]. 1.5 T/T1-weighted images, fat-suppressed T2-weighted images, diffusion-weighted imaging (DWI), and DCE-MRI. The MRI-MF model was developed with conventional MR features using logistic analyses. The Radiomic feature extraction process involved collecting data from categorized DCE-MRI datasets, specifically the first and second post-contrast images (A1 and A2). Next, a DL model was implemented to determine LVI. Finally, we established a joint diagnosis model by combining the MRI-MF, Radiomics, and DL approaches. Diagnostic performance was compared using receiver operating characteristic curve analysis, confusion matrix, and decision curve analysis. Rim sign and peritumoral edema features were used to develop the MRI-MF model, while six Radiomics signature from the A1 and A2 images were used for the Radiomics model. The joint model (MRI-MF + Radiomics + DL models) achieved the highest accuracy (area under the curve [AUC] = 0.857), being significantly superior to the MRI-MF (AUC = 0.724), Radiomics (AUC = 0.736), or DL (AUC = 0.740) model. Furthermore, it also outperformed the pairwise combination models: Radiomics + MRI-MF (AUC = 0.796), DL + MRI-MF (AUC = 0.796), or DL + Radiomics (AUC = 0.826). The joint model incorporating MRI-MF, Radiomics, and DL approaches can effectively determine the LVI status in patients with BC before surgery. 4 TECHNICAL EFFICACY: Stage 2.

This article describes mathematical problem solving and critical thinking skills and examines the relationship between junior high school students’ problem solving skills and critical thinking skills in learning mathematics. The research samples consisted of thirty-six students at the age of 13 to 14 having mathematical abilities on above average who were selected through purposive random sampling technique from one public junior high school of Yogyakarta. Data were obtained from tests of problem solving skills and critical thinking skills. Both instruments are essay questions. Quantitative analysis is used to determine level of problem solving skills, level of critical thinking skills, and relationship between them. The results revealed that the average of students’ problem solving skills and mathematical critical thinking skills was in the medium criteria where critical thinking skills were slightly higher than problem solving skills. Besides, the relationship between them belonged to medium category.

Automatic Speech Recognition: A survey of deep learning techniques and approaches

Purpose of the study: This research aims to analyze the needs for developing an Ethno-STEM-integrated Problem-Based Learning (PBL) e-module to enhance the creative thinking skills of 8th-grade junior high school students on the topics of vibrations, waves, and sound. Methodology: This study employed a mixed method. The instrument used was a questionnaire adapted from previous research. The sample consisted of junior high school science teachers and students in Karanganyar Regency. Data analysis used descriptive statistics. Main Findings: The findings revealed a significant gap between current science learning practices and the demands of 21st-century education. Teachers reported difficulties in explaining abstract concepts such as vibrations, waves, and sound using conventional methods, compounded by the limited availability of instructional media that integrates local cultural wisdom. Meanwhile, students expressed strong interest in digital and contextual learning resources, yet their creative thinking skills remained low, with an average score of only 49.4%. This indicates the urgent need for innovative, interactive, and culturally relevant learning solutions. Novelty/Originality of this Study: The development of an Ethno-STEM-based PBL e-module that not only integrates science, technology, engineering, and mathematics with local wisdom but also explicitly targets the four core aspects of creative thinking: fluency, flexibility, originality, and elaboration. Unlike conventional modules, this approach leverages ethnoscience contexts to make abstract concepts more tangible while simultaneously fostering problem-solving and higher-order thinking. Thus, the research provides a strategic foundation for designing learning media that is pedagogically sound, culturally meaningful, and aligned with the competencies required in the global era.

The purpose of this study is to describe the effect of Outdoor Learning Math using GPS-based mobile technology-assisted math traces on students' problem solving and mathematical communication skills, describe the effect of Outdoor Learning Math using GPS-based mobile technology-assisted math traces on problem solving skills, and describe the effect of Outdoor Learning Math using GPS-based mobile technology-assisted math traces on students' mathematical communication skills. This type of research is Quasi Experimental using Nonequivalent Control Group Design. This research was conducted at SMP Negeri 1 Malinau, North Kalimantan City with 60 students from two 9th grade classes. The instruments used in this study were descriptive test questions of problem solving ability, mathematical communication and observation sheets for the implementation of Outdoor Learning Math learning activities using GPS-based mobile technology-assisted math traces. The results showed that there was an effect of Outdoor Learning Math using GPS-based mobile technology-assisted math traces on students' problem solving and mathematical communication skills together, there was no effect of Outdoor Learning Math using mobile technology-assisted math traces on problem solving skills, and there was no effect of Outdoor Learning Math using GPS-based mobile technology-assisted math traces on mathematical communication skills. Therefore, for future researchers to expand the scope of materials such as geometry, statistics and probability, algebra, arithmetic and add student motivation variables.

Purpose: Although deep learning (DL) models have shown increasing ability to accurately classify diagnostic images in oncology, significantly large amounts of well-curated data are often needed to match human level performance. Given the relative paucity of imaging datasets for less prevalent cancer types, there is an increasing need for methods which can improve the performance of deep learning models trained using limited diagnostic images. Deep metric learning (DML) is a potential method which can improve accuracy in deep learning models trained on limited datasets. Leveraging a triplet-loss function, DML exponentially increases training data compared to a traditional DL model. In this study, we investigated the utility of DML to improve the accuracy of DL models trained to classify cancerous lesions found on screening mammograms. Methods: Using a dataset of 2620 lesions found on routine screening mammogram, we trained both a traditional DL and DML models to classify suspicious lesions as cancerous or benign. The VGG16 architecture was used as the basis for the DL and DML models. Model performance was compared by calculating model accuracy, sensitivity, and specificity on a blinded test set of 378 lesions. In addition to individual model performance, we also measured agreement accuracy when both the DL and DML models were combined. Sub-analyses were conducted to identify phenotypes which were best suited for each model type. Both models underwent hyperparameters optimization to identify ideal batch size, learning rate, and regularization to prevent overfitting. Results: We found that the combination of the traditional DL model with DML model resulted in the highest overall accuracy (78.7%) representing a 7.1% improvement compared to the traditional DL model (p<.001). Alone, the traditional DL model had an improved accuracy compared to the DML model (71.4% vs 66.4%). The traditional DL model had a higher sensitivity (94.8% vs 73.6 %) , but lower specificity (34.7% vs 55.1%) compared the DML model. Sub-analyses suggested the traditional DL model was more accurate on higher density breasts, whereas the DML model was more accurate on lower density breasts. Additionally, the traditional DL model had the highest accuracy on oval shaped lesions, compared to the DML model which was most accurate on irregularly shaped breast lesions. Conclusion: Our study suggests that addition of DML models with traditional DL models can improve diagnostic image classification performance in cancer. Our results suggest DML models may provide increased specificity and help with classification of unique populations often misclassified by traditional DL models. Further studied investigating the utility of DML on other cancer imaging tasks are necessary to successfully build more robust DL models in cancer imaging. Citation Format: Justin Du, Sachin Umrao, Enoch Chang, Marina Joel, Aidan Gilson, Guneet Janda, Rachel Choi, Yongfeng Hui, Sanjay Aneja. The utility of deep metric learning for breast cancer identification on mammographic images [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2021; 2021 Apr 10-15 and May 17-21. Philadelphia (PA): AACR; Cancer Res 2021;81(13_Suppl):Abstract nr 184.

Deep learning has become increasingly popular due to its remarkable ability to learn high-dimensional feature representations. Numerous algorithms and models have been developed to enhance the application of deep learning across various real-world tasks, including image classification, natural language processing, and autonomous driving. However, deep learning models are susceptible to backdoor threats, where an attacker manipulates the training process or data to cause incorrect predictions on malicious samples containing specific triggers, while maintaining normal performance on benign samples. With the advancement of deep learning, including evolving training schemes and the need for large-scale training data, new threats in the backdoor domain continue to emerge. Conversely, backdoors can also be leveraged to protect deep learning models, such as through watermarking techniques. In this thesis, we conduct an in-depth investigation into backdoor techniques from three novel perspectives. In the first part of this thesis, we demonstrate that emerging deep learning training schemes can introduce new backdoor risks. Specifically, pre-trained Natural Language Processing (NLP) models can be easily adapted to a variety of downstream language tasks, significantly accelerating the development of language models. However, the pre-trained model becomes a single point of failure for these downstream models. We propose a novel task-agnostic backdoor attack against pre-trained NLP models, wherein the adversary does not need prior information about the downstream tasks when implanting the backdoor into the pre-trained model. Any downstream models transferred from this malicious model will inherit the backdoor, even after extensive transfer learning, revealing the severe vulnerability of pre-trained foundation models to backdoor attacks. In the second part of this thesis, we develop novel backdoor attack methods suited to new threat scenarios. The rapid expansion of deep learning models necessitates large-scale training data, much of which is unlabeled and outsourced to third parties for annotation. To ensure data security, most datasets are read-only for training samples, preventing the addition of input triggers. Consequently, attackers can only achieve data poisoning by uploading malicious annotations. In this practical scenario, all existing data poisoning methods that add triggers to the input are infeasible. Therefore, we propose new backdoor attack methods that involve poisoning only the labels without modifying any input samples. In the third part of this thesis, we utilize the backdoor technique to proactively protect our deep learning models, specifically for intellectual property protection. Considering the complexity of deep learning tasks, generating a well-trained deep learning model requires substantial computational resources, training data, and expertise. Therefore, it is essential to protect these assets and prevent copyright infringement. Inspired by backdoor attacks that can induce specific behaviors in target models through carefully designed samples, several watermarking methods have been proposed to protect the intellectual property of deep learning models. Model owners can train their models to produce unique outputs for certain crafted samples and use these samples for ownership verification. While various extraction techniques have been designed for supervised deep learning models, challenges arise when applying them to deep reinforcement learning models due to differences in model features and scenarios. Therefore, we propose a novel watermarking scheme to protect deep reinforcement learning models from unauthorized distribution. Instead of using spatial watermarks as in conventional deep learning models, we design temporal watermarks that minimize potential impact and damage to the protected deep reinforcement learning model while achieving high-fidelity ownership verification. In summary, this thesis investigates the evolving landscape of backdoor threats during the development of deep learning techniques and the use of backdoors for beneficial purposes in intellectual property protection.

Introduction: Current guidelines for elective surgery of ascending thoracic aortic aneurysms (aTAAs) use aneurysm size as primary determinant for risk stratification of adverse events. Biomechanically, dissection may occur when wall stress exceeds wall strength. A widespread method for stress analysis is structural finite-element analysis (FEA). Patient-specific aortic geometries are easily obtainable and stress distributions can potentially predict risk of dissection. However, FEA is a time-consuming and difficult procedure. To bypass this issue, a recent study has developed the first deep learning (DL) approach for a fast and accurate estimation of aortic wall stress distributions. Hypothesis: In this study, we assessed the hypothesis that this deep learning approach can be applied to a large clinical dataset. Model performance was measured by comparing FEA and DL stress predictions in parallel. Methods: Patients with aTAA (n = 169) were studied. Patient-specific aneurysm geometries were obtained from ECG-gated computed tomography. Shapes were represented by hexahedral meshes with 9648 nodes and 6336 solid elements. FEA peak wall stresses and stress distributions were determined using LS-DYNA software with user-defined fiber-embedded material models under systolic pressure. The DL model was implemented in Julia and consisted of unsupervised and supervised learning algorithms. Training was performed on a training set of 152 shapes and testing set of 17 shapes with 10-fold cross-validation. Mean absolute error (MAE) and absolute error of peak stress values (APE) were used to compare DL model predictions with FEA values considered to be ground truth. Results: Average stress values predicted by our DL model were 175.64 ± 4.17 kPa and 95.69 ± 2.15 kPa in the circumferential and longitudinal direction, respectively. We computed a MAE of 5.06 ± 1.08 kPa and APE of 2.58 ± 1.39 kPa in the circumferential direction and MAE of 4.51 ± 0.98 kPa and APE of 2.32 ± 1.84 kPa in the longitudinal direction. Conclusions: DL model trained exclusively on clinical data was able to accurately predict stress distributions on complex aortic geometries. Fast and accurate stress predictions will facilitate real-time clinical applications for the risk assessment of aTAAs.

The increasing reality of climate change demands innovative and sustainable solutions to maintain ecosystem balance and community resilience. In Indonesia, agroforestry based on local wisdom emerges as a practical approach to tackle these challenges. This study aims to delve deeper into the role of locally-informed agroforestry in strengthening community resilience and enhancing carbon sequestration. The method employed is a Systematic Literature Review (SLR) covering publications from 2020 to 2025, allowing for the comprehensive collection and synthesis of scientific evidence. Data analysis techniques involve grouping information based on key themes such as types of agroforestry practices, integration of local wisdom, and their impact on carbon sequestration and community resilience. The analysis results indicate that locally-based agroforestry enhances land productivity and sustainability and strengthens local communities' socio-economic structure. Significant contributions to carbon sequestration are demonstrated through planting endemic trees and traditional medicinal plants, which also serve as local ecosystem balancers. This research also highlights the need to integrate environmental education and local cultural wisdom to build holistic ecological awareness. This is crucial in establishing a more comprehensive sustainability approach. By combining environmental education and local wisdom, communities can better understand the importance of preserving the environment and utilizing natural resources sustainably. In conclusion, agroforestry based on local wisdom offers a sustainable solution to addressing climate change by strengthening community resilience and increasing carbon sequestration. It emphasizes the importance of leveraging local wisdom in designing more effective mitigation and adaptation strategies. Therefore, further research is needed to explore integrating environmental education and local cultural wisdom as a holistic approach to sustainability.

This study aimed to examine the effectiveness of Problem-Based Learning (PBL) in improving eighth-grade students’ problem-solving skills in Social Studies at SMP Negeri 35 Bekasi. The study was motivated by students’ low problem-solving ability, which has been influenced by the dominance of conventional instruction. A quantitative approach was employed using a quasi-experimental Nonequivalent Control Group design involving 62 students, divided into an experimental group taught with PBL and a control group taught with conventional methods. Data were collected through a 20-item multiple-choice test validated by experts and confirmed reliable, supported by classroom observation. The data were analyzed using prerequisite tests, an independent samples t-test, and N-Gain. The results indicated that the experimental group achieved a higher posttest mean score (83.24) than the control group (75.32). The experimental group also demonstrated a moderate N-Gain and outperformed the control group in learning improvement. These findings confirm that PBL is effective as an alternative strategy in Social Studies to strengthen students’ problem-solving and critical-thinking skills.

The aim of this research was to develop digital learning media in the form of android games to improve students’ scientific literacy skills. Digital learning media are developed based on the joyful inquiry learning model for the subject matter of vibration. The validation of digital learning media was carried out by media experts, subject matter experts, science teachers, and second year students of Junior High School 1 Duduksampeyan in Gresik Regency, Indonesia. The results of expert validation showed that digital learning media is very valid with a validity rate of 84% and readability rate of 87%. The effectiveness of digital learning media in increasing students’ scientific literacy was measured by quasi experiments using two classes of second year students of Junior High School 1 Duduksampeyan in Gresik Regency, Indonesia. The class VIII-F used digital learning media with the joyful inquiry learning model and the class VIII-E used the inquiry learning model. The results of the independent sample t-test showed a significance value of 0.0012 (smaller than α = 0.05) which meant that there were significant differences between the scientific literacy abilities of the class VIII- F and the class VIII-E. The N-gain value of the class VIII-F is 0.72 and this value is greater than the N-gain value of the class VIII-E that is 0.47. These results indicate an increase in the scientific literacy ability of students in the class VIII-F is higher than that of class VIII-E students which means that the digital learning media developed are effective in increasing students’ literacy abilities.

Person re-identification (ReID) aims to find the person of interest across multiple non-overlapping cameras. It is considered an essential step for person tracking applications which is vital for surveillance. Person ReID could be investigated either using image-based or video-based. Video-based person ReID is considered more discriminating and realistic than image-based ReID due to the massive information extracted for each person. Different deep-learning techniques have been used for video-based ReID. In this survey, recently published articles are reviewed according to video-based ReID system pipeline: deep features learning, deep metric learning, and deep learning approaches. The deep feature learning approaches are categorized into spatial and temporal approaches, while deep metric learning is divided into metric and metric learning approaches. The deep learning approaches are differentiated into: supervised, unsupervised, weakly-supervised, and one-shot learning. A detailed analysis is held for the architectures of the state-of-the-art deep learning approaches. And their performance on four benchmark datasets is compared.

This study aims to analyze the integration of Merauke's local wisdom into deep learning through a literature study using a qualitative approach. Deep learning is understood as a pedagogical approach that emphasizes mindful, meaningful, and joyful learning, thereby encouraging students to construct conceptual understanding, think critically, and apply knowledge contextually. On the other hand, Merauke's local wisdom, reflected in the practices of totemism, adat sasi, yur traditions, as well as social rituals and traditional leadership systems, has ecological, social, and spiritual values that are relevant to contextual education. The results of the analysis show that integrating the two can strengthen cultural literacy, ecological awareness, and character building among students. The ecological values in sasi and yur can be used for meaningful learning, spiritual and social values such as “Izakod Bekai Izakod Kai” are relevant for mindful learning, while traditional celebrations contribute to joyful learning. However, challenges such as limited infrastructure, teacher competence, and scientific validation of local knowledge need to be overcome through training, innovative learning media, and an ethnoscience approach. This research concludes that integrating deep learning with Merauke's local wisdom has the potential to create a contextual pedagogical model that not only enriches the learning experience but also preserves cultural identity and supports sustainable education.