| 1 |
What is the primary objective of landslide susceptibility mapping as described in the article?
|
To mitigate the economic and environmental damage by predicting areas at risk. |
|
The question asks for the main goal of mapping landslide susceptibility based on the research papers. Looking at the options, landslide mapping cannot predict exact dates of natural disasters it is done just for university research or without practical use. The main purpose of identifying which areas are highly prone to sliding is to help communities prepare, avoid unsafe zones, and minimize losses to both property and nature. |
In environmental hazard management and Geospatial Information Systems planning, susceptibility mapping is use as a spatial prediction tool. The main principle is that by analyzing past landslide factors like slope, soil, and rainfall, researchers can pinpoint high-risk zones. This data is critical for disaster risk reduction and helps governments make safer land-use policies. |
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 2 |
Which machine learning algorithm was noted for having the highest success rate according to the article?
|
Decision and Regression Tree |
|
the research estimated three separate machine learning models Logistic Regression, Random Forest, and Decision and Regression Tree. When reviewing the performance metrics from the paper: Logistic Regression achieved the highest overall prediction rate on the testing data. Decision and Regression Tree achieved the highest success rate on the training data with a training ROC value of 0.947. |
GIS-based landslide susceptibility mapping using logistic regression, random forest and decision and regression tree models in Chattogram District, Bangladesh. In machine learning hazard mapping, model accuracy is evaluated using two separate phases of the Receiver Operating Characteristic curve: Success Rate evaluated using the training dataset 80% of data to measure how well the algorithm fits the known historical landslide locations. Prediction Rate evaluated using the testing dataset 20% of the data to measure how well the model forecasts future or unseen landslide events. |
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 3 |
If the area of Chattogram district is 75% susceptible to landslides, and the highly susceptible zone covers approximately 12% of the district, what is the area (in percentage) that is not highly susceptible?
|
63% |
|
From the problem, the total area susceptible to landslides is 75% of the district. Inside this group, the highly susceptible zone accounts for 12% of the district.
To find the area within the landslide zones that is not highly susceptible, subtract the highly susceptible percentage from the total susceptible area .75% - 12% = 63% |
In GIS hazard mapping, the study area is categorized into different risk zones such as Low, Moderate, and High susceptibility. To find the proportion of a specific sub-zone, we subtract its value from the total hazard area.
The basic math formula is: Remaining Susceptible Area = Total Susceptible Area - Highly Susceptible Area
75% - 12% = 63% |
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 4 |
Considering that the total number of analyzed landslides is 255, and 80% were used for training the models, how many landslide instances were used for testing?
|
51 |
|
The total number of analyzed landslides is 255.
Since 80% of the data was used for training, the remaining percentage used for testing is: 100% - 80% = 20%
To find the exact number of testing instances, calculate 20% of 255: 255 x 0.20 = 51 |
In machine learning and spatial hazard mapping, historical data points are divided into an 80:20 ratio. The 80% portion is used to teach the algorithms the relationship between environmental factors and past events, while the 20% portion is held back to evaluate the model's accuracy on unseen data.
The basic math formula used is: Testing Instances = Total Instances x Testing Ratio
Testing Instances = 255 x 0.20 = 51 |
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 5 |
If the total area of Chattogram district is 7,000 km² and the very high susceptible zone covers 9% of the district, what is the area of the very high susceptible zone in km²?
|
630 km² |
|
The total area of the district = 7,000 km^2
The portion covered by the very high susceptible zone = 9%
To find the area in km^2, we multiply the total area by the percentage: 7,000 x 0.09 = 630 km^2 |
This calculation applies basic spatial proportion metrics to zoning data, which is an integral part of the GIS analysis outlined in Article 4 (GIS-based landslide susceptibility mapping). When evaluating hazard maps, converting regional risk percentages back into real-world geographic units (like square kilometers) helps disaster management teams understand exactly how much land needs protection or engineering reinforcement. The math formula used is:
Zone Area = Total District Area x Zone Percentage
Zone Area = 7,000 x 0.09 = 630 km^2 |
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 6 |
Assuming the false positive rate (FPR) for the logistic regression model is 0.05 and the true positive rate (TPR) is 0.95, calculate the specificity of the model.
|
0.95 |
|
The question prepares a False Positive Rate (FPR) of 0.05. By standard mathematical definition, Specificity and the False Positive Rate are perfect complements of each other.
Calculating the value: Specificity = 1 - FPR = 1 - 0.05 = 0.95. |
This is based on the confusion matrix identity where Specificity and the False Positive Rate (FPR) are complements that sum to 1. The formula is Specificity = 1 - FPR. Substituting the given values yields 1 - 0.05 = 0.95. |
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 7 |
Given that the area under the ROC curve (AUC) for the logistic regression model is 0.963, and the prediction rate is measured as the area under this curve, rate the model's prediction accuracy.
|
Excellent |
|
The model's prediction rate is measured by the Area Under the ROC Curve . AUC values range from 0.50 to 1.00 where higher scores mean better accuracy. Because the model scored 0.963, it falls into the highest tier (0.90 to 1.00) which means excellent prediction performance. |
This follows the standard academic classification for grading the Area Under the ROC Curve (AUC) in predictive mapping. An AUC score from 0.50 to 0.60 is poor, 0.60 to 0.70 is average, 0.70 to 0.80 is good, 0.80 to 0.90 is very good, and 0.90 to 1.00 is excellent. |
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 8 |
If the training dataset consists of 204 locations, calculate the percentage of this training dataset from the total landslide occurrences (255 locations).
|
80% |
|
Finding the percentage of the training dataset out of the total landslide occurrences, divide the number of training locations by the total number of locations and multiply by 100. Calculating 204 divided by 255 gives 0.80, which equals 80%. |
In machine learning and spatial hazard mapping, historical data points are divided into an 80:20 ratio.So the 80% portion (training set) is used to teach the algorithms the relationship between environmental factors and past events, while the 20% portion (testing set) is held back to evaluate the model's accuracy on unseen data. |
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 9 |
If the model predicts a 25% error rate for new observations, what is the accuracy percentage for predictions made by this model?
|
75% |
|
In predictive modeling and classification systems, total observations are divided into accuracy and error rate. Since the total percentage of all outcomes must equal 100%, find the accuracy percentage by subtracting the 25% error rate from 100%, which leaves 75% |
This follows the fundamental complement rule in statistical model evaluation. Accuracy and error rate are mutually exclusive and collectively exhaustive metrics that define the total outcomes of a binary evaluation matrix. The relationship is governed by the fixed identity equation: Accuracy=100%−Error Rate. |
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 10 |
Calculate the success rate if a model correctly predicted 181 out of 204 training data points.
|
88.73% |
|
Determine the success rate of the model during its training phase, divide the number of correctly predicted data points by the total number of data points in the training dataset, then multiply by 100. Calculating 181 divided by 204 results in approximately 0.88725, which converts to 88.73% when rounded to two decimal places. |
This calculation measures the model's descriptive accuracy or training fit, known as the success rate in landslide susceptibility workflows like Article 4. It rates how well a classification algorithm learns and replicates known historical training instances before it is tested against unseen data points. The formula used is: Success Rate=(Correct Predictions/Total Training Points)×100. |
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 11 |
What is the primary focus of multimodal transportation systems according to the article?
|
Enhancing environmental sustainability and safety. |
|
Traditional single-mode shipping methods (such as reliance strictly on heavy trucks) create major concerns regarding traffic congestion, accidents, and carbon emissions. Multimodal transport systems are designed precisely to address these problems by integrating multiple transit modes to seek energy-efficient options, minimize pollution, and mitigate systemic operations risks, thereby directly prioritizing environmental sustainability and transport safety. |
Modern logistics network design relies on Multi-Criteria Decision Making to resolve multi-objective conflicts. The shift toward multimodal corridors is fundamentally driven by international transport policies aimed at lowering environmental footprints and improving cargo safety, rather than purely focusing on speed or baseline capacity without care for operational risks. |
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 12 |
According to the study, what is the main advantage of using the FAHP-DEA method in risk analysis for multimodal transportation systems?
|
It allows for precise risk prioritization and optimization of routes. |
|
The question asks for the primary advantage of combining the Fuzzy Analytic Hierarchy Process and Data Envelopment Analysis methods when assessing risks in multimodal transport networks, based on the material in Article 2. Look at how the two models work together:FAHP handles the uncertainty of expert opinions to rank and calculate weights for individual risk criteria. DEA is an optimization tool used to measure efficiency and find the best performing solutions.
When combined into a single framework, their main strength is that they allow planners to precisely categorize (prioritize) risks across various route options and quantitatively evaluate which transit routes are optimized for safety and efficiency. It cannot completely eliminate risks, nor is it a purely subjective or non-quantitative approach, making the prioritization and optimization choice correct. |
In logistics and transportation systems engineering, standard risk models often struggle with qualitative factors or fail to offer clear optimization strategies for selecting paths. The two-stage hybrid model bridges this gap: FAHP sets up a rigorous multi-criteria structure to evaluate risk parameters under fuzzy or uncertain conditions, DEA acts as a mathematical programming tool to filter out inefficient alternatives, qualify precise route optimization. |
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 13 |
If the risk analysis model has five criteria and assigns importance weights such that the total sums up to 1, and the weights for operational risk and security risk are 0.157 and 0.073 respectively, what is the combined weight of the remaining three criteria?
|
0.770 |
|
The question states that the risk analysis model contains five criteria in total, and all of their importance weights add up to 1.
Given that the weights for two criteria: Operational risk = 0.157
Security risk = 0.073
First, we find the sum of these two known weights:
0.157 + 0.073 = 0.230 To find the combined weight of the remaining three criteria, we subtract this value from the total sum of 1: 1 - 0.230 = 0.770 |
This problem is based on the weight normalization property of multi-criteria decision-making frameworks, such as the AHP used in Article 2 . In any standardized AHP model, the total sum of priority weights at any given level of the hierarchy must equal exactly 1 (or 100%).The mathematical formula used is:
Combined Remaining Weights = Total Weight - Sum of Known Weights
Combined Remaining Weights = 1 - (0.157 + 0.073) = 0.770 |
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 14 |
If the probability of an accident occurring on a route is 0.2 and the consequence severity is rated at 0.5, what is the risk level for that route segment using the model
𝑅
=
𝑃
×
𝐶
R=P×C?
|
0.1 |
|
The question asks to calculate the risk level (R) for a route segment using the formula:R = P x C
From the given information: P (Probability of an accident) = 0.2
C (Consequence severity) = 0.5
Plugging the numbers into the formula:
R = 0.2 x 0.5 = 0.10 |
This calculation follows the foundational risk matrix principle used across transport safety analyses, such as the framework outlined in Article 2. Risk is defined mathematically as the product of how likely an undesirable event is to occur and the severity of its outcome. The formula to use is:
Risk Level (R) = Probability (P) x Consequence Severity (C)
R = 0.2 x 0.5 = 0.1 |
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 15 |
Calculate the aggregate risk score if the weights of the criteria are 0.321, 0.388, 0.157, 0.073, and 0.061, and the local risk scores for a route are 0.5, 0.6, 0.4, 0.3, and 0.2 respectively.
|
0.519 |
|
To find the aggregate risk score, we multiply each criterion's weight by its respective local risk score, and then add them all together:
Criterion 1: 0.321 x 0.5 = 0.1605
Criterion 2: 0.388 x 0.6 = 0.2328
Criterion 3: 0.157 x 0.4 = 0.0628
Criterion 4: 0.073 x 0.3 = 0.0219
Criterion 5: 0.061 x 0.2 = 0.0122
Adding these values together:
0.1605 + 0.2328 + 0.0628 + 0.0219 + 0.0122 = 0.4902 |
This calculation follows the Simple Additive Weighting method use to aggregate scores in Article 2 (A Risk Analysis Based on a Two-Stage Model of Fuzzy AHP-DEA for Multimodal Freight Transportation Systems). In multi-factor analysis, the total risk score is a linear weighted sum of the independent risk criteria inputs. The standard formula used is: Aggregate Risk Score = Sum of (Weight x Local Risk Score)Aggregate Risk Score = (0.321 x 0.5) + (0.388 x 0.6) + (0.157 x 0.4) + (0.073 x 0.3) + (0.061 x 0.2) = 0.4902 |
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 16 |
If the probability assessment for a risk is ranked 3 on a scale of 5 and the severity assessment is also ranked 3, with the transport segment accounting for 20% of the total route distance, calculate the risk assessment using the formula
𝑅
=
𝑃
×
𝐶
×
𝐷
R=P×C×D.
|
1.80 |
|
From the calculation in the previous step, our result for the formula R = P x C x D is exactly 1.8. Looking at the choices provided on the exam sheet, 1.80 is the matching option.
Steps quickly: P = 3
C = 3
D = 20% (which is 0.20)
Calculation: 3 x 3 x 0.20 = 1.80 |
This matches the risk calculation index from Article 2, where risk factors are multiplied by segment exposure (distance ratio) to establish a standardized route risk value.
The formula used is:
R = P x C x D
R = 3 x 3 x 0.20 = 1.80 |
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 17 |
Given that the weight for environmental risk is 0.061 and the local risk score for a route is 0.4, calculate the contribution of environmental risk to the overall risk score.
|
0.0244 |
|
The question asks for the contribution of environmental risk to the overall risk score. Given that the risk weight is 0.061 and the local risk score for the route is 0.4. Finding the contribution, multiply the weight by the local risk score:0.061 x 0.4 = 0.0244 |
A Risk Analysis Based on a Two-Stage Model of Fuzzy AHP-DEA for Multimodal Freight Transportation Systems). In multi-factor decision-making models, the final contribution of a specific hazard factor is determined by multiplying its priority weight by its performance or risk score.
The formula used is:Risk Contribution = Risk Weight x Local Risk Score
Risk Contribution = 0.061 x 0.4 = 0.0244 |
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 18 |
Calculate the new overall risk score if the weight of infrastructure risk is increased from 0.388 to 0.400 while keeping other parameters constant, given that its local risk score is 0.2.
|
0.140 |
|
The question asks to calculate the new total risk score when the weight of infrastructure risk increases from 0.388 to 0.400, while its local score stays at 0.2. First, find the change in the weight: 0.400 - 0.388 = 0.012
Next, we find how much this change adds to the total score by multiplying the weight change by the local score: 0.012 x 0.2 = 0.0024
Finally, we add this increase to our original total risk score from the previous question (0.13325): 0.13325 + 0.0024 = 0.13565
Rounding 0.13565 to two decimal places, we get 0.140. |
When one variable weight changes while others stay constant, the total system score updates based on the product of the weight difference and its local parameter. The formula used is: New Risk Score = Old Risk Score + (Weight Change x Local Risk Score)
New Risk Score = 0.13325 + (0.012 x 0.2) = 0.13565 (approximated to 0.140) |
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 19 |
If a mode of transportation has a risk weight of 0.073 and its risk score is reassessed from 0.4 to 0.35, what is the change in its contribution to the overall risk score?
|
0.00365 |
|
The question asks for the change in the risk contribution of a mode of transportation. We know the risk weight is 0.073. The risk score changes from 0.4 to 0.35, which means it decreases by: 0.4 - 0.35 = 0.05 To find the change in its total contribution, we multiply the risk weight by this change in score: 0.073 x 0.05 = 0.00365 |
The math formula to find this change is:Change in Contribution = Risk Weight x (Old Risk Score - New Risk Score)
Change in Contribution = 0.073 x (0.4 - 0.35)
Change in Contribution = 0.073 x 0.05 = 0.00365 |
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 20 |
If the local weights of freight-damage risk, infrastructure risk, and operational risk are 0.1, 0.2, and 0.15 respectively, what is their total contribution to the risk score if their respective weights are 0.321, 0.388, and 0.157?
|
0.12069 |
|
The question asks for the total contribution to the risk score from three risk types. To find the total risk contribution, we multiply each local risk weight by its respective global weight and then add them all together: Freight-damage risk: 0.1 x 0.321 = 0.0321. Infrastructure risk: 0.2 x 0.388 = 0.0776. Operational risk: 0.15 x 0.157 = 0.02355. Adding these values together: 0.0321 + 0.0776 + 0.02355 = 0.13325 |
n Fuzzy AHP models, the total risk score is calculated by combining local weights with their corresponding framework weights.The standard mathematical formula used is:
Total Risk Score = Sum of (Local Weight x Respective Weight)
Total Risk Score = (0.1 x 0.321) + (0.2 x 0.388) + (0.15 x 0.157) = 0.13325 |
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|