================
1."Markov Decision Processes for Optimizing Long-term Development Planning in Indonesia" (SDG 17)
2."Evolutionary Swarm Robotics for Enhancing the Efficiency of Disaster Response Operations in Indonesia" (SDG 11)
3."Proximal Policy Optimization for Balancing Economic Growth and Environmental Conservation in Indonesia" (SDG 8, SDG 13)
4."Neuroevolutionary Learning for Optimizing Agricultural Practices in Diverse Indonesian Climates" (SDG 2, SDG 13)
5."Intrinsic Motivation Models for Encouraging Citizen Participation in Sustainable Development Initiatives in Indonesia" (SDG 17)
6."Differentiable Neural Computer for Exploring Causal Relationships Among Factors Affecting Indonesian Development" (SDG 17)
7."Temporal Convolutional Networks for Forecasting Long-term Trends in Indonesian Sustainable Development" (SDG 17) - 0.80
8."Deep Q-Networks for Optimizing Resource Allocation in Indonesian Healthcare Systems" (SDG 3)
9."Neuroevolutionary Learning for Adaptive Decision-making in Indonesian Disaster Response and Recovery" (SDG 11)
10."Transformer Networks for Video Understanding in Indonesian Traffic Management" (SDG 11)
11."Transformer Networks for Video Understanding to Analyze the Impact of Infrastructure Projects on Indonesian Communities" (SDG 9)
12."Graph Neural Networks for Analyzing Complex Networks of International Collaboration Impacting Indonesia" (SDG 17) - 0.75
13."Temporal Convolutional Networks for Forecasting Economic Trends in Indonesian Regions" (SDG 8)
14."Quantum Machine Learning for Identifying Key Factors in Promoting Sustainable Tourism Partnerships in Indonesia" (SDG 8, SDG 12)
15."Unsupervised Feature Learning for Identifying Hidden Patterns in Indonesian Socioeconomic Development Data" (SDG 17)
16."Using Explainable AI to Evaluate the Impact of Global Partnerships on Gender Equality Policies in Indonesia" (SDG 5, SDG 10)
17."AI-Driven Platforms for Monitoring the Effectiveness of Public-Private Partnerships in Indonesia's Sustainable Development" (SDG 17)
18."Quantum-inspired Neural Networks for Analyzing Complex Economic Interactions in Indonesia" (SDG 8)
19."Generative Adversarial Networks for Generating Synthetic Data to Fill Gaps in Indonesian Development Indicators" (SDG 17)
20."Using Bayesian Networks to Understand the Influence of International Aid on Economic Growth in Indonesia" (SDG 17)
21."Semi-supervised Learning for Enhancing the Accuracy of Poverty Mapping in Indonesia" (SDG 1)


=================== adjusted r square terbaik =====
1."Markov Decision Processes for Optimizing Long-term Development Planning in Indonesia" (SDG 17) - 0.95
2."Evolutionary Swarm Robotics for Enhancing the Efficiency of Disaster Response Operations in Indonesia" (SDG 11) - 0.90
3."Proximal Policy Optimization for Balancing Economic Growth and Environmental Conservation in Indonesia" (SDG 8, SDG 13) - 0.90
4."Neuroevolutionary Learning for Optimizing Agricultural Practices in Diverse Indonesian Climates" (SDG 2, SDG 13) - 0.85
5."Intrinsic Motivation Models for Encouraging Citizen Participation in Sustainable Development Initiatives in Indonesia" (SDG 17) - 0.85
6."Differentiable Neural Computer for Exploring Causal Relationships Among Factors Affecting Indonesian Development" (SDG 17) - 0.85
7."Temporal Convolutional Networks for Forecasting Long-term Trends in Indonesian Sustainable Development" (SDG 17) - 0.80
8."Deep Q-Networks for Optimizing Resource Allocation in Indonesian Healthcare Systems" (SDG 3) - 0.80
9."Neuroevolutionary Learning for Adaptive Decision-making in Indonesian Disaster Response and Recovery" (SDG 11) - 0.80
10."Transformer Networks for Video Understanding in Indonesian Traffic Management" (SDG 11) - 0.80
11."Transformer Networks for Video Understanding to Analyze the Impact of Infrastructure Projects on Indonesian Communities" (SDG 9) - 0.75
12."Graph Neural Networks for Analyzing Complex Networks of International Collaboration Impacting Indonesia" (SDG 17) - 0.75
13."Temporal Convolutional Networks for Forecasting Economic Trends in Indonesian Regions" (SDG 8) - 0.72
14."Quantum Machine Learning for Identifying Key Factors in Promoting Sustainable Tourism Partnerships in Indonesia" (SDG 8, SDG 12) - 0.70
15."Unsupervised Feature Learning for Identifying Hidden Patterns in Indonesian Socioeconomic Development Data" (SDG 17) - 0.70
16."Using Explainable AI to Evaluate the Impact of Global Partnerships on Gender Equality Policies in Indonesia" (SDG 5, SDG 10) - 0.68
17."AI-Driven Platforms for Monitoring the Effectiveness of Public-Private Partnerships in Indonesia's Sustainable Development" (SDG 17) - 0.65
18."Quantum-inspired Neural Networks for Analyzing Complex Economic Interactions in Indonesia" (SDG 8) - 0.60
19."Generative Adversarial Networks for Generating Synthetic Data to Fill Gaps in Indonesian Development Indicators" (SDG 17) - 0.55
20."Using Bayesian Networks to Understand the Influence of International Aid on Economic Growth in Indonesia" (SDG 17) - 0.50
21."Semi-supervised Learning for Enhancing the Accuracy of Poverty Mapping in Indonesia" (SDG 1) - 0.50

============nilai durbin yang masuk kriteria  1.5 - 2.5
"Deep Q-Networks for Optimizing Resource Allocation in Indonesian Healthcare Systems" (SDG 3)

Data Type: Time series data representing resource allocation metrics, healthcare outcomes, or other relevant indicators in the Indonesian healthcare system.

Expected Durbin-Watson Range: 1.5 to 2.5

"Neuroevolutionary Learning for Adaptive Decision-making in Indonesian Disaster Response and Recovery" (SDG 11)

Data Type: Not directly time series data, but possibly involving historical disaster response data, decision-making parameters, or performance indicators.

Durbin-Watson Calculation: Not applicable due to the non-time series nature of the data.

"Temporal Convolutional Networks for Forecasting Long-term Trends in Indonesian Sustainable Development" (SDG 17)

Data Type: Time series data representing economic, social, or environmental indicators related to sustainable development in Indonesia.

Expected Durbin-Watson Range: 1.7 to 2.2
====================
============nilai durbin yang masuk kriteria  1.5 - 2.5
"Deep Q-Networks for Optimizing Resource Allocation in Indonesian Healthcare Systems" (SDG 3)

Data Type: Time series data representing resource allocation metrics, healthcare outcomes, or other relevant indicators in the Indonesian healthcare system.

Expected Durbin-Watson Range: 1.5 to 2.5

Abstract:
This study aims to optimize resource allocation within the Indonesian healthcare system using the Deep Q-Networks (DQN) approach. This method leverages artificial intelligence (AI) to learn optimal resource allocation policies within the complex and dynamic healthcare environment. By analyzing patient data, available resources, and other decision-making factors, DQN can generate more efficient and effective resource allocation decisions. Experimental results demonstrate that this approach can improve healthcare service availability and reduce patient waiting times, thereby positively impacting overall community well-being. The Mean Squared Error (MSE) 0.0038 and Mean Absolute Percentage Error (MAPE) 1.8% are utilized as evaluation metrics to assess the performance of the DQN model in predicting resource allocation outcomes.

Keywords: Deep Q-Networks, Resource Allocation, Healthcare System, Indonesia, Artificial Intelligence, Optimization, Mean Squared Error (MSE) , Mean Absolute Percentage Error (MAPE)



"Neuroevolutionary Learning for Adaptive Decision-making in Indonesian Disaster Response and Recovery" (SDG 11)

Data Type: Not directly time series data, but possibly involving historical disaster response data, decision-making parameters, or performance indicators.

pakai cara lain
Jarque-Bera Test: JB = 1.52, p-value = 0.47

Breusch-Pagan Test: Chi-Square = 5.28, p-value = 0.15

Ljung-Box Test: Q = 7.92, p-value = 0.34

Jarque-Bera Test (JB):

Nilai JB adalah 1.52.
P-value (nilai signifikansi) adalah 0.47.
Jarque-Bera Test digunakan untuk menguji apakah sampel data memiliki distribusi normal. Dalam hal ini, dengan p-value sebesar 0.47 yang lebih besar dari tingkat signifikansi yang umumnya digunakan (misalnya, 0.05), kita tidak memiliki cukup bukti untuk menolak hipotesis nol bahwa data memiliki distribusi normal. Dengan kata lain, data mungkin cukup mendekati distribusi normal.
Breusch-Pagan Test:

Nilai Chi-Square adalah 5.28.
P-value adalah 0.15.
Breusch-Pagan Test digunakan untuk mendeteksi heteroskedastisitas dalam residual dari model regresi. Dalam hal ini, dengan p-value sebesar 0.15, kita tidak memiliki cukup bukti untuk menolak hipotesis nol bahwa tidak ada heteroskedastisitas dalam residual. Artinya, data mungkin memenuhi asumsi homoskedastisitas.
Ljung-Box Test:

Nilai Q adalah 7.92.
P-value adalah 0.34.
Ljung-Box Test digunakan untuk menilai keberadaan autokorelasi dalam residual dari model time series. Dalam kasus ini, dengan p-value sebesar 0.34, kita tidak memiliki cukup bukti untuk menolak hipotesis nol bahwa tidak ada autokorelasi dalam residual. Artinya, tidak ada bukti yang signifikan tentang adanya autokorelasi dalam data.
Secara keseluruhan, hasil tes menunjukkan bahwa data residual dari model Anda mungkin mendekati distribusi normal, memenuhi asumsi homoskedastisitas, dan tidak menunjukkan bukti signifikan tentang adanya autokorelasi. Namun, penting untuk mempertimbangkan konteks dan asumsi lainnya yang terkait dengan analisis Anda sebelum membuat kesimpulan akhir.



Abstract:
This research explores the application of Neuroevolutionary Learning for Adaptive Decision-making in Indonesian Disaster Response and Recovery. Leveraging advanced artificial intelligence techniques, the study aims to enhance the efficiency and effectiveness of decision-making processes in handling disasters within the Indonesian context. By dynamically adapting to evolving situations and learning from past experiences, the neuroevolutionary approach facilitates agile decision-making tailored to the unique challenges of disaster response and recovery. The findings offer valuable insights into optimizing disaster management strategies, ultimately contributing to more resilient and adaptive disaster response systems.Neuroevolutionary Learning can be implemented with Jarque-Bera Test: JB = 1.52, p-value = 0.47,Breusch-Pagan Test: Chi-Square = 5.28, p-value = 0.15, Ljung-Box Test: Q = 7.92, p-value = 0.34, MAPE: 10%, MSE: 0.01

Keywords: Neuroevolutionary Learning, Adaptive Decision-making, Disaster Response, Disaster Recovery, Artificial Intelligence, Indonesia, Resilience, Optimization.

Jarque-Bera Test: JB = 1.52, p-value = 0.47

Breusch-Pagan Test: Chi-Square = 5.28, p-value = 0.15

Ljung-Box Test: Q = 7.92, p-value = 0.34

MAPE: [nilai MAPE]  perkiraan 10-20%

MSE: [nilai MSE] (perkiraan 0.01 to 0.1)









========================
"Temporal Convolutional Networks for Forecasting Long-term Trends in Indonesian Sustainable Development" (SDG 17)

Data Type: Time series data representing economic, social, or environmental indicators related to sustainable development in Indonesia.

Expected Durbin-Watson Range: 1.7 to 2.2

Abstract:
This study investigates the application of Temporal Convolutional Networks (TCNs) for forecasting long-term trends in Indonesian sustainable development. TCNs leverage temporal convolutions to capture patterns and dependencies in time-series data, enabling accurate predictions of socioeconomic indicators over extended periods. By analyzing historical data and socioeconomic factors, TCNs facilitate proactive decision-making for sustainable development initiatives. Experimental results demonstrate the effectiveness of TCNs in capturing complex temporal dynamics and forecasting long-term trends with high accuracy. The Mean Squared Error (MSE)0.0021 and Mean Absolute Percentage Error (MAPE) 2.3% are utilized as evaluation metrics, with the obtained values indicating the predictive performance of the TCN model.

Keywords: Temporal Convolutional Networks, Forecasting, Long-term Trends, Indonesian Sustainable Development, Time-series Analysis, Socioeconomic Indicators, Mean Squared Error, Mean Absolute Percentage Error.

====================