• Journal of Intelligence and Information Systems
• /
• v.18 no.2
• /
• pp.29-45
• /
• 2012

Bond rating is regarded as an important event for measuring financial risk of companies and for determining the investment returns of investors. As a result, it has been a popular research topic for researchers to predict companies' credit ratings by applying statistical and machine learning techniques. The statistical techniques, including multiple regression, multiple discriminant analysis (MDA), logistic models (LOGIT), and probit analysis, have been traditionally used in bond rating. However, one major drawback is that it should be based on strict assumptions. Such strict assumptions include linearity, normality, independence among predictor variables and pre-existing functional forms relating the criterion variablesand the predictor variables. Those strict assumptions of traditional statistics have limited their application to the real world. Machine learning techniques also used in bond rating prediction models include decision trees (DT), neural networks (NN), and Support Vector Machine (SVM). Especially, SVM is recognized as a new and promising classification and regression analysis method. SVM learns a separating hyperplane that can maximize the margin between two categories. SVM is simple enough to be analyzed mathematical, and leads to high performance in practical applications. SVM implements the structuralrisk minimization principle and searches to minimize an upper bound of the generalization error. In addition, the solution of SVM may be a global optimum and thus, overfitting is unlikely to occur with SVM. In addition, SVM does not require too many data sample for training since it builds prediction models by only using some representative sample near the boundaries called support vectors. A number of experimental researches have indicated that SVM has been successfully applied in a variety of pattern recognition fields. However, there are three major drawbacks that can be potential causes for degrading SVM's performance. First, SVM is originally proposed for solving binary-class classification problems. Methods for combining SVMs for multi-class classification such as One-Against-One, One-Against-All have been proposed, but they do not improve the performance in multi-class classification problem as much as SVM for binary-class classification. Second, approximation algorithms (e.g. decomposition methods, sequential minimal optimization algorithm) could be used for effective multi-class computation to reduce computation time, but it could deteriorate classification performance. Third, the difficulty in multi-class prediction problems is in data imbalance problem that can occur when the number of instances in one class greatly outnumbers the number of instances in the other class. Such data sets often cause a default classifier to be built due to skewed boundary and thus the reduction in the classification accuracy of such a classifier. SVM ensemble learning is one of machine learning methods to cope with the above drawbacks. Ensemble learning is a method for improving the performance of classification and prediction algorithms. AdaBoost is one of the widely used ensemble learning techniques. It constructs a composite classifier by sequentially training classifiers while increasing weight on the misclassified observations through iterations. The observations that are incorrectly predicted by previous classifiers are chosen more often than examples that are correctly predicted. Thus Boosting attempts to produce new classifiers that are better able to predict examples for which the current ensemble's performance is poor. In this way, it can reinforce the training of the misclassified observations of the minority class. This paper proposes a multiclass Geometric Mean-based Boosting (MGM-Boost) to resolve multiclass prediction problem. Since MGM-Boost introduces the notion of geometric mean into AdaBoost, it can perform learning process considering the geometric mean-based accuracy and errors of multiclass. This study applies MGM-Boost to the real-world bond rating case for Korean companies to examine the feasibility of MGM-Boost. 10-fold cross validations for threetimes with different random seeds are performed in order to ensure that the comparison among three different classifiers does not happen by chance. For each of 10-fold cross validation, the entire data set is first partitioned into tenequal-sized sets, and then each set is in turn used as the test set while the classifier trains on the other nine sets. That is, cross-validated folds have been tested independently of each algorithm. Through these steps, we have obtained the results for classifiers on each of the 30 experiments. In the comparison of arithmetic mean-based prediction accuracy between individual classifiers, MGM-Boost (52.95%) shows higher prediction accuracy than both AdaBoost (51.69%) and SVM (49.47%). MGM-Boost (28.12%) also shows the higher prediction accuracy than AdaBoost (24.65%) and SVM (15.42%)in terms of geometric mean-based prediction accuracy. T-test is used to examine whether the performance of each classifiers for 30 folds is significantly different. The results indicate that performance of MGM-Boost is significantly different from AdaBoost and SVM classifiers at 1% level. These results mean that MGM-Boost can provide robust and stable solutions to multi-classproblems such as bond rating.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.57-78
• /
• 2020

With the development of the Internet, consumers have had an opportunity to check product information easily through E-Commerce. Product reviews used in the process of purchasing goods are based on user experience, allowing consumers to engage as producers of information as well as refer to information. This can be a way to increase the efficiency of purchasing decisions from the perspective of consumers, and from the seller's point of view, it can help develop products and strengthen their competitiveness. However, it takes a lot of time and effort to understand the overall assessment and assessment dimensions of the products that I think are important in reading the vast amount of product reviews offered by E-Commerce for the products consumers want to compare. This is because product reviews are unstructured information and it is difficult to read sentiment of reviews and assessment dimension immediately. For example, consumers who want to purchase a laptop would like to check the assessment of comparative products at each dimension, such as performance, weight, delivery, speed, and design. Therefore, in this paper, we would like to propose a method to automatically generate multi-dimensional product assessment scores in product reviews that we would like to compare. The methods presented in this study consist largely of two phases. One is the pre-preparation phase and the second is the individual product scoring phase. In the pre-preparation phase, a dimensioned classification model and a sentiment analysis model are created based on a review of the large category product group review. By combining word embedding and association analysis, the dimensioned classification model complements the limitation that word embedding methods for finding relevance between dimensions and words in existing studies see only the distance of words in sentences. Sentiment analysis models generate CNN models by organizing learning data tagged with positives and negatives on a phrase unit for accurate polarity detection. Through this, the individual product scoring phase applies the models pre-prepared for the phrase unit review. Multi-dimensional assessment scores can be obtained by aggregating them by assessment dimension according to the proportion of reviews organized like this, which are grouped among those that are judged to describe a specific dimension for each phrase. In the experiment of this paper, approximately 260,000 reviews of the large category product group are collected to form a dimensioned classification model and a sentiment analysis model. In addition, reviews of the laptops of S and L companies selling at E-Commerce are collected and used as experimental data, respectively. The dimensioned classification model classified individual product reviews broken down into phrases into six assessment dimensions and combined the existing word embedding method with an association analysis indicating frequency between words and dimensions. As a result of combining word embedding and association analysis, the accuracy of the model increased by 13.7%. The sentiment analysis models could be seen to closely analyze the assessment when they were taught in a phrase unit rather than in sentences. As a result, it was confirmed that the accuracy was 29.4% higher than the sentence-based model. Through this study, both sellers and consumers can expect efficient decision making in purchasing and product development, given that they can make multi-dimensional comparisons of products. In addition, text reviews, which are unstructured data, were transformed into objective values such as frequency and morpheme, and they were analysed together using word embedding and association analysis to improve the objectivity aspects of more precise multi-dimensional analysis and research. This will be an attractive analysis model in terms of not only enabling more effective service deployment during the evolving E-Commerce market and fierce competition, but also satisfying both customers.

• Journal of the Korean Society of Groundwater Environment
• /
• v.7 no.3
• /
• pp.103-115
• /
• 2000

The formation of brown-colored precipitates is one of the serious problems frequently encountered in the development and supply of groundwater in Korea, because by it the water exceeds the drinking water standard in terms of color. taste. turbidity and dissolved iron concentration and of often results in scaling problem within the water supplying system. In groundwaters from the Pajoo area, brown precipitates are typically formed in a few hours after pumping-out. In this paper we examine the process of the brown precipitates' formation using the equilibrium thermodynamic and kinetic approaches, in order to understand the origin and geochemical pathway of the generation of turbidity in groundwater. The results of this study are used to suggest not only the proper pumping technique to minimize the formation of precipitates but also the optimal design of water treatment methods to improve the water quality. The bed-rock groundwater in the Pajoo area belongs to the Ca-$HCO_3$type that was evolved through water/rock (gneiss) interaction. Based on SEM-EDS and XRD analyses, the precipitates are identified as an amorphous, Fe-bearing oxides or hydroxides. By the use of multi-step filtration with pore sizes of 6, 4, 1, 0.45 and 0.2 $\mu\textrm{m}$, the precipitates mostly fall in the colloidal size (1 to 0.45 $\mu\textrm{m}$) but are concentrated (about 81%) in the range of 1 to 6 $\mu\textrm{m}$in teams of mass (weight) distribution. Large amounts of dissolved iron were possibly originated from dissolution of clinochlore in cataclasite which contains high amounts of Fe (up to 3 wt.%). The calculation of saturation index (using a computer code PHREEQC), as well as the examination of pH-Eh stability relations, also indicate that the final precipitates are Fe-oxy-hydroxide that is formed by the change of water chemistry (mainly, oxidation) due to the exposure to oxygen during the pumping-out of Fe(II)-bearing, reduced groundwater. After pumping-out, the groundwater shows the progressive decreases of pH, DO and alkalinity with elapsed time. However, turbidity increases and then decreases with time. The decrease of dissolved Fe concentration as a function of elapsed time after pumping-out is expressed as a regression equation Fe(II)=10.l exp(-0.0009t). The oxidation reaction due to the influx of free oxygen during the pumping and storage of groundwater results in the formation of brown precipitates, which is dependent on time, $Po_2$and pH. In order to obtain drinkable water quality, therefore, the precipitates should be removed by filtering after the stepwise storage and aeration in tanks with sufficient volume for sufficient time. Particle size distribution data also suggest that step-wise filtration would be cost-effective. To minimize the scaling within wells, the continued (if possible) pumping within the optimum pumping rate is recommended because this technique will be most effective for minimizing the mixing between deep Fe(II)-rich water and shallow $O_2$-rich water. The simultaneous pumping of shallow $O_2$-rich water in different wells is also recommended.

• Journal of Chest Surgery
• /
• v.31 no.5
• /
• pp.472-480
• /
• 1998

We reviewed the surgical results of intracardiac lateral tunnel Fontan procedure for the repair of functional single ventricles. Between 1990 and 1996, 104 patients underwent total cavopulmonary anastomosis. Patients' age and body weight averaged 35.9(range 10 to 173) months and 12.8(range 6.5 to 37.8) kg. Preoperative diagnoses included 18 tricuspid atresias and 53 double inlet ventricles with univentricular atrioventricular connection and 33 other complex lesions. Previous palliative operations were performed in 50 of these patients, including 37 systemic to pulmonary artery shunts, 13 pulmonary artery bandings, 15 surgical atrial septectomies, 2 arterial switch procedures, 2 resections of subaortic conus, 2 repairs of total anomalous pulmonary venous connection and 1 Damus-Stansel-Kaye procedure. In 19 patients bidirectional cavopulmonary shunt operation was performed before the Fontan procedure and in 1 patient a Kawashima procedure was required. Preoperative hemodynamics revealed a mean pulmonary artery pressure of 14.6(range 5 to 28) mmHg, a mean pulmonary vascular resistance of 2.2(range 0.4 to 6.9) wood-unit, a mean pulmonary to systemic flow ratio of 0.9(range 0.3 to 3.0), a mean ventricular end-diastolic pressure of 9.0 (range 3.0 to 21.0) mmHg, and a mean arterial oxygen saturation of 76.0(range 45.6 to 88.0)%. The operative procedure consisted of a longitudinal right atriotomy 2cm lateral to the terminal crest up to the right atrial auricle, followed by the creation of a lateral tunnel connecting the orifices of either the superior caval vein or the right atrial auricle to the inferior caval vein, using a Gore-Tex vascular graft with or without a fenestration. Concomitant procedures at the time of Fontan procedure included 22 pulmonary artery angioplasties, 21 atrial septectomies, 4 atrioventricular valve replacements or repairs, 4 corrections of anomalous pulmonary venous connection, and 3 permanent pacemaker implantations. In 31, a fenestration was created, and in 1 an adjustable communication was made in the lateral tunnel pathway. One lateral tunnel conversion was performed in a patient with recurrent intractable tachyarrhythmia 4 years after the initial atriopulmonary connection. Post-extubation hemodynamic data revealed a mean pulmonary artery pressure of 12.7(range 8 to 21) mmHg, a mean ventricular end-diastolic pressure of 7.6(range 4 to 12) mmHg, and a mean room-air arterial oxygen saturation of 89.9(range 68 to 100) %. The follow-up duration was, on average, 27(range 1 to 85) months. Post-Fontan complications included 11 prolonged pleural effusions, 8 arrhythmias, 9 chylothoraces, 5 of damage to the central nervous system, 5 infectious complications, and 4 of acute renal failure. Seven early(6.7%) and 5 late(4.8%) deaths occured. These results proved that the lateral tunnel Fontan procedure provided excellent hemodynamic improvements with acceptable mortality and morbidity for hearts with various types of functional single ventricle.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.139-156
• /
• 2021

The biggest reason for using a deep learning model in image classification is that it is possible to consider the relationship between each region by extracting each region's features from the overall information of the image. However, the CNN model may not be suitable for emotional image data without the image's regional features. To solve the difficulty of classifying emotion images, many researchers each year propose a CNN-based architecture suitable for emotion images. Studies on the relationship between color and human emotion were also conducted, and results were derived that different emotions are induced according to color. In studies using deep learning, there have been studies that apply color information to image subtraction classification. The case where the image's color information is additionally used than the case where the classification model is trained with only the image improves the accuracy of classifying image emotions. This study proposes two ways to increase the accuracy by incorporating the result value after the model classifies an image's emotion. Both methods improve accuracy by modifying the result value based on statistics using the color of the picture. When performing the test by finding the two-color combinations most distributed for all training data, the two-color combinations most distributed for each test data image were found. The result values were corrected according to the color combination distribution. This method weights the result value obtained after the model classifies an image's emotion by creating an expression based on the log function and the exponential function. Emotion6, classified into six emotions, and Artphoto classified into eight categories were used for the image data. Densenet169, Mnasnet, Resnet101, Resnet152, and Vgg19 architectures were used for the CNN model, and the performance evaluation was compared before and after applying the two-stage learning to the CNN model. Inspired by color psychology, which deals with the relationship between colors and emotions, when creating a model that classifies an image's sentiment, we studied how to improve accuracy by modifying the result values based on color. Sixteen colors were used: red, orange, yellow, green, blue, indigo, purple, turquoise, pink, magenta, brown, gray, silver, gold, white, and black. It has meaning. Using Scikit-learn's Clustering, the seven colors that are primarily distributed in the image are checked. Then, the RGB coordinate values of the colors from the image are compared with the RGB coordinate values of the 16 colors presented in the above data. That is, it was converted to the closest color. Suppose three or more color combinations are selected. In that case, too many color combinations occur, resulting in a problem in which the distribution is scattered, so a situation fewer influences the result value. Therefore, to solve this problem, two-color combinations were found and weighted to the model. Before training, the most distributed color combinations were found for all training data images. The distribution of color combinations for each class was stored in a Python dictionary format to be used during testing. During the test, the two-color combinations that are most distributed for each test data image are found. After that, we checked how the color combinations were distributed in the training data and corrected the result. We devised several equations to weight the result value from the model based on the extracted color as described above. The data set was randomly divided by 80:20, and the model was verified using 20% of the data as a test set. After splitting the remaining 80% of the data into five divisions to perform 5-fold cross-validation, the model was trained five times using different verification datasets. Finally, the performance was checked using the test dataset that was previously separated. Adam was used as the activation function, and the learning rate was set to 0.01. The training was performed as much as 20 epochs, and if the validation loss value did not decrease during five epochs of learning, the experiment was stopped. Early tapping was set to load the model with the best validation loss value. The classification accuracy was better when the extracted information using color properties was used together than the case using only the CNN architecture.

• Journal of Intelligence and Information Systems
• /
• v.27 no.4
• /
• pp.73-95
• /
• 2021

This study uses Node2vec graph embedding method and Light GBM link prediction to explore undeveloped export candidate countries in Korea's food and beverage industry. Node2vec is the method that improves the limit of the structural equivalence representation of the network, which is known to be relatively weak compared to the existing link prediction method based on the number of common neighbors of the network. Therefore, the method is known to show excellent performance in both community detection and structural equivalence of the network. The vector value obtained by embedding the network in this way operates under the condition of a constant length from an arbitrarily designated starting point node. Therefore, it has the advantage that it is easy to apply the sequence of nodes as an input value to the model for downstream tasks such as Logistic Regression, Support Vector Machine, and Random Forest. Based on these features of the Node2vec graph embedding method, this study applied the above method to the international trade information of the Korean food and beverage industry. Through this, we intend to contribute to creating the effect of extensive margin diversification in Korea in the global value chain relationship of the industry. The optimal predictive model derived from the results of this study recorded a precision of 0.95 and a recall of 0.79, and an F1 score of 0.86, showing excellent performance. This performance was shown to be superior to that of the binary classifier based on Logistic Regression set as the baseline model. In the baseline model, a precision of 0.95 and a recall of 0.73 were recorded, and an F1 score of 0.83 was recorded. In addition, the light GBM-based optimal prediction model derived from this study showed superior performance than the link prediction model of previous studies, which is set as a benchmarking model in this study. The predictive model of the previous study recorded only a recall rate of 0.75, but the proposed model of this study showed better performance which recall rate is 0.79. The difference in the performance of the prediction results between benchmarking model and this study model is due to the model learning strategy. In this study, groups were classified by the trade value scale, and prediction models were trained differently for these groups. Specific methods are (1) a method of randomly masking and learning a model for all trades without setting specific conditions for trade value, (2) arbitrarily masking a part of the trades with an average trade value or higher and using the model method, and (3) a method of arbitrarily masking some of the trades with the top 25% or higher trade value and learning the model. As a result of the experiment, it was confirmed that the performance of the model trained by randomly masking some of the trades with the above-average trade value in this method was the best and appeared stably. It was found that most of the results of potential export candidates for Korea derived through the above model appeared appropriate through additional investigation. Combining the above, this study could suggest the practical utility of the link prediction method applying Node2vec and Light GBM. In addition, useful implications could be derived for weight update strategies that can perform better link prediction while training the model. On the other hand, this study also has policy utility because it is applied to trade transactions that have not been performed much in the research related to link prediction based on graph embedding. The results of this study support a rapid response to changes in the global value chain such as the recent US-China trade conflict or Japan's export regulations, and I think that it has sufficient usefulness as a tool for policy decision-making.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.8 no.1
• /
• pp.129-177
• /
• 1970

For the purpose of establishing the systematized technical scheme of the cooperative rice cultivation which has most significant impact to improve rice productivity and the farm management, the author have studied the cultivation practices, and the variation of rice growth and yield between the cooperative rice cultivation and the individual rice cultivation at random selected 18 paddy fields. The author also have investigated through comparative method on the cultivation practices, management, organization and operation scheme of the two different rice cultivation methods at 460 paddy fields. The economic feasibility has been ana lysed and added in this report. The results obtained from this study are summarized as follows; 1. In the nursery, the average amount of fertilizer application, especially, phosphate and potassium, and the frequency of chemicals spray for the disease, insect and pest control at the cooperative rice cultivation are significantly higher than those of the individual rice cultivation. 2. The cultivation techniques of the cooperative rice farming after the transplanting can be characterized by a) the earlier transplanting of rice, b) the denser hills per unit area and the lesser number of seedlings per hill, c) the application of larger quantities of fertilizer including nitrogen, phosphate and potassium, d) more divided application of fertilizers, split doses of the nitrogen and potassium, e) the increased frequencies of the chemicals spray for the prevention of disease, insect and pest damages. 3. The rate of lodging in the cooperative rice cultivation was slightly higher than that of the individual rice cultivation, however, the losses of rice yield owing to the occurrence of rice stem borer and grass leaf roller in the cooperative rice cultivation were lower than that of the individual rice cultivation. 4. The culm length, panicle length, straw weight and grain-straw ratio are respectively higher at the cooperative rice cultivation, moreover, the higher variation of the above factors due to different localities of the paddy fields found at the individual rice cultivation. 5. The number of panicles, number of flowers per panicle and the weight of 1, 000 grains, those contributing components to the rice yield were significantly greater in the cooperative rice cultivation, however, not clear difference in the maturing rate was observed. The variation coefficient of the yield component in the cooperative cultivation showed lower than that or the individual rice cultivation. 6. The average yield of brown rice per 10 are in the cooperative rice cultivation obtained 459.0 kilograms while that of the individual rice cultivation brought 374.8 kilograms. The yield of brown rice in the cooperative rice cultivation increased 84.2 kilogram per 10 are over the individual rice cultivation. With lower variation coefficient of the brown rice yield in the cooperative rice cultivation, it can be said that uniformed higher yield could be obtained through the cooperative rice cultivation. 7. Highly significant positive correlations shown between the seeding date and the number of flowers per panicle, the chemical spray and the number of flowers per panicle, the transplanting date and the number of flowers per panicle, phosphate application and yield, potassium application and maturing rate, the split application of fertilizers and yield. Whilst the significant negative correlation was shown between the transplanting date and the maturing rate 8. The results of investigation from 480 paddy fields obtained through comparative method on the following items are identical in general with those obtained at 18 paddy fields: Application of fertilizers, chemical spray for the control of disease, insects and pests both in the nursery and the paddy field, transplanting date, transplanting density, split application of fertilizers and yield n the paddy fields. a) The number of rice varieties used in the cooperative rice cultivation were 13 varieties while the individual rice cultivation used 47 varieties. b) The cooperative rice cultivation has more successfully adopted improved cultivation techniques such as the practice of seed disinfection, adoption of recommended seeding amount, fall ploughing, application of red soil, introduction of power tillers, the rectangular-type transplanting, midsummer drainage and the periodical irrigation. 9. The following results were also obtained from the same investigation and they are: a) In the cooperative rice cultivation, the greater part of the important practices have been carried out through cooperative operation including seed disinfection, ploughing, application of red soil and compost, the control of disease, insects and pests, harvest, threshing and transportation of the products. b) The labor input to the nursery bed and water control in the cooperative rice cultivation was less than that of the individual rice cultivation while the higher rate of labor input was resulted in the red soil and compost application. 10. From the investigation on the organization and operation scheme of the cooperative rice cultivation, the following results were obtained: a) The size of cooperative rice cultivation farm was varied from. 3 ha to 7 ha and 5 ha farm. occupied 55.9 percent of the total farms. And a single cooperative farm was consisted of 10 to 20 plots of paddies. b) The educational back ground of the staff members involved in the cooperative rice cultivation was superior than that of the individual rice cultivation. c) All of the farmers who participated to the questionaires have responded that the cooperative rice cultivation could promise the increased rice yield mainly through the introduction of the improved method of fertilizer application and the effective control of diseases, insects and pests damages. And the majority of farmers were also in the opinion that preparation of the materials and labor input can be timely carried out and the labor requirement for the rice cultivation possibly be saved through the cooperative rice cultivation. d) The farmers who have expressed their wishes to continue and to make further development of the cooperative rice cultivation was 74.5 percent of total farmers participated to the questionaires. 11. From the analysis of economical feasibility on the two different methods of cultivation, the following results were obtained: a) The value of operation cost for the compost, chemical fertilizers, agricultural chemicals and labor input in the cooperative rice cultivation was respectively higher by 335 won, 199 won, 288 won and 303 won over the individual rice cultivation. However, the other production costs showed no distinct differences between the two cultivation methods. b) Although the total value of expenses for the fertilizers, agricultural chemicals, labor input and etc. in the cooperative rice cultivation were approximately doubled to the amount of the individual rice cultivation, the net income, substracted operation costs from the gross income, was obtained 24, 302 won in the cooperative rice cultivation and 20, 168 won was obtained from the individual rice cultivation. Thereby, it can be said that net income from the cooperative rice cultivation increased 4, 134 won over the individual rice cultivation. It was revealed in this study that the cooperative rice cultivation has not only contributed to increment of the farm income through higher yield but also showed as an effective means to introduce highly improved cultivation techniques to the farmers. It may also be concluded, therefore, the cooperative rice cultivation shall continuously renovate the rice production process of the farmers.

• Proceedings of the KOR-KST Conference
• /
• 1995.02a
• /
• pp.101-113
• /
• 1995

The objective of this research is to test the feasibility of developing a statewide truck traffic forecasting methodology for Wisconsin by using Origin-Destination surveys, traffic counts, classification counts, and other data that are routinely collected by the Wisconsin Department of Transportation (WisDOT). Development of a feasible model will permit estimation of future truck traffic for every major link in the network. This will provide the basis for improved estimation of future pavement deterioration. Pavement damage rises exponentially as axle weight increases, and trucks are responsible for most of the traffic-induced damage to pavement. Consequently, forecasts of truck traffic are critical to pavement management systems. The pavement Management Decision Supporting System (PMDSS) prepared by WisDOT in May 1990 combines pavement inventory and performance data with a knowledge base consisting of rules for evaluation, problem identification and rehabilitation recommendation. Without a r.easonable truck traffic forecasting methodology, PMDSS is not able to project pavement performance trends in order to make assessment and recommendations in the future years. However, none of WisDOT's existing forecasting methodologies has been designed specifically for predicting truck movements on a statewide highway network. For this research, the Origin-Destination survey data avaiiable from WisDOT, including two stateline areas, one county, and five cities, are analyzed and the zone-to'||'&'||'not;zone truck trip tables are developed. The resulting Origin-Destination Trip Length Frequency (00 TLF) distributions by trip type are applied to the Gravity Model (GM) for comparison with comparable TLFs from the GM. The gravity model is calibrated to obtain friction factor curves for the three trip types, Internal-Internal (I-I), Internal-External (I-E), and External-External (E-E). ~oth "macro-scale" calibration and "micro-scale" calibration are performed. The comparison of the statewide GM TLF with the 00 TLF for the macro-scale calibration does not provide suitable results because the available 00 survey data do not represent an unbiased sample of statewide truck trips. For the "micro-scale" calibration, "partial" GM trip tables that correspond to the 00 survey trip tables are extracted from the full statewide GM trip table. These "partial" GM trip tables are then merged and a partial GM TLF is created. The GM friction factor curves are adjusted until the partial GM TLF matches the 00 TLF. Three friction factor curves, one for each trip type, resulting from the micro-scale calibration produce a reasonable GM truck trip model. A key methodological issue for GM. calibration involves the use of multiple friction factor curves versus a single friction factor curve for each trip type in order to estimate truck trips with reasonable accuracy. A single friction factor curve for each of the three trip types was found to reproduce the 00 TLFs from the calibration data base. Given the very limited trip generation data available for this research, additional refinement of the gravity model using multiple mction factor curves for each trip type was not warranted. In the traditional urban transportation planning studies, the zonal trip productions and attractions and region-wide OD TLFs are available. However, for this research, the information available for the development .of the GM model is limited to Ground Counts (GC) and a limited set ofOD TLFs. The GM is calibrated using the limited OD data, but the OD data are not adequate to obtain good estimates of truck trip productions and attractions .. Consequently, zonal productions and attractions are estimated using zonal population as a first approximation. Then, Selected Link based (SELINK) analyses are used to adjust the productions and attractions and possibly recalibrate the GM. The SELINK adjustment process involves identifying the origins and destinations of all truck trips that are assigned to a specified "selected link" as the result of a standard traffic assignment. A link adjustment factor is computed as the ratio of the actual volume for the link (ground count) to the total assigned volume. This link adjustment factor is then applied to all of the origin and destination zones of the trips using that "selected link". Selected link based analyses are conducted by using both 16 selected links and 32 selected links. The result of SELINK analysis by u~ing 32 selected links provides the least %RMSE in the screenline volume analysis. In addition, the stability of the GM truck estimating model is preserved by using 32 selected links with three SELINK adjustments, that is, the GM remains calibrated despite substantial changes in the input productions and attractions. The coverage of zones provided by 32 selected links is satisfactory. Increasing the number of repetitions beyond four is not reasonable because the stability of GM model in reproducing the OD TLF reaches its limits. The total volume of truck traffic captured by 32 selected links is 107% of total trip productions. But more importantly, ~ELINK adjustment factors for all of the zones can be computed. Evaluation of the travel demand model resulting from the SELINK adjustments is conducted by using screenline volume analysis, functional class and route specific volume analysis, area specific volume analysis, production and attraction analysis, and Vehicle Miles of Travel (VMT) analysis. Screenline volume analysis by using four screenlines with 28 check points are used for evaluation of the adequacy of the overall model. The total trucks crossing the screenlines are compared to the ground count totals. L V/GC ratios of 0.958 by using 32 selected links and 1.001 by using 16 selected links are obtained. The %RM:SE for the four screenlines is inversely proportional to the average ground count totals by screenline .. The magnitude of %RM:SE for the four screenlines resulting from the fourth and last GM run by using 32 and 16 selected links is 22% and 31 % respectively. These results are similar to the overall %RMSE achieved for the 32 and 16 selected links themselves of 19% and 33% respectively. This implies that the SELINICanalysis results are reasonable for all sections of the state.Functional class and route specific volume analysis is possible by using the available 154 classification count check points. The truck traffic crossing the Interstate highways (ISH) with 37 check points, the US highways (USH) with 50 check points, and the State highways (STH) with 67 check points is compared to the actual ground count totals. The magnitude of the overall link volume to ground count ratio by route does not provide any specific pattern of over or underestimate. However, the %R11SE for the ISH shows the least value while that for the STH shows the largest value. This pattern is consistent with the screenline analysis and the overall relationship between %RMSE and ground count volume groups. Area specific volume analysis provides another broad statewide measure of the performance of the overall model. The truck traffic in the North area with 26 check points, the West area with 36 check points, the East area with 29 check points, and the South area with 64 check points are compared to the actual ground count totals. The four areas show similar results. No specific patterns in the L V/GC ratio by area are found. In addition, the %RMSE is computed for each of the four areas. The %RMSEs for the North, West, East, and South areas are 92%, 49%, 27%, and 35% respectively, whereas, the average ground counts are 481, 1383, 1532, and 3154 respectively. As for the screenline and volume range analyses, the %RMSE is inversely related to average link volume. 'The SELINK adjustments of productions and attractions resulted in a very substantial reduction in the total in-state zonal productions and attractions. The initial in-state zonal trip generation model can now be revised with a new trip production's trip rate (total adjusted productions/total population) and a new trip attraction's trip rate. Revised zonal production and attraction adjustment factors can then be developed that only reflect the impact of the SELINK adjustments that cause mcreases or , decreases from the revised zonal estimate of productions and attractions. Analysis of the revised production adjustment factors is conducted by plotting the factors on the state map. The east area of the state including the counties of Brown, Outagamie, Shawano, Wmnebago, Fond du Lac, Marathon shows comparatively large values of the revised adjustment factors. Overall, both small and large values of the revised adjustment factors are scattered around Wisconsin. This suggests that more independent variables beyond just 226; population are needed for the development of the heavy truck trip generation model. More independent variables including zonal employment data (office employees and manufacturing employees) by industry type, zonal private trucks 226; owned and zonal income data which are not available currently should be considered. A plot of frequency distribution of the in-state zones as a function of the revised production and attraction adjustment factors shows the overall " adjustment resulting from the SELINK analysis process. Overall, the revised SELINK adjustments show that the productions for many zones are reduced by, a factor of 0.5 to 0.8 while the productions for ~ relatively few zones are increased by factors from 1.1 to 4 with most of the factors in the 3.0 range. No obvious explanation for the frequency distribution could be found. The revised SELINK adjustments overall appear to be reasonable. The heavy truck VMT analysis is conducted by comparing the 1990 heavy truck VMT that is forecasted by the GM truck forecasting model, 2.975 billions, with the WisDOT computed data. This gives an estimate that is 18.3% less than the WisDOT computation of 3.642 billions of VMT. The WisDOT estimates are based on the sampling the link volumes for USH, 8TH, and CTH. This implies potential error in sampling the average link volume. The WisDOT estimate of heavy truck VMT cannot be tabulated by the three trip types, I-I, I-E ('||'&'||'pound;-I), and E-E. In contrast, the GM forecasting model shows that the proportion ofE-E VMT out of total VMT is 21.24%. In addition, tabulation of heavy truck VMT by route functional class shows that the proportion of truck traffic traversing the freeways and expressways is 76.5%. Only 14.1% of total freeway truck traffic is I-I trips, while 80% of total collector truck traffic is I-I trips. This implies that freeways are traversed mainly by I-E and E-E truck traffic while collectors are used mainly by I-I truck traffic. Other tabulations such as average heavy truck speed by trip type, average travel distance by trip type and the VMT distribution by trip type, route functional class and travel speed are useful information for highway planners to understand the characteristics of statewide heavy truck trip patternS. Heavy truck volumes for the target year 2010 are forecasted by using the GM truck forecasting model. Four scenarios are used. Fo~ better forecasting, ground count- based segment adjustment factors are developed and applied. ISH 90 '||'&'||' 94 and USH 41 are used as example routes. The forecasting results by using the ground count-based segment adjustment factors are satisfactory for long range planning purposes, but additional ground counts would be useful for USH 41. Sensitivity analysis provides estimates of the impacts of the alternative growth rates including information about changes in the trip types using key routes. The network'||'&'||'not;based GMcan easily model scenarios with different rates of growth in rural versus . . urban areas, small versus large cities, and in-state zones versus external stations. cities, and in-state zones versus external stations.