the diverse versions of learning content, a page’s original HTML will be transformed into a well-formed XHTML and tree-like Document Object Model (DOM) structure (2010). The details of the LCS are described in Algorithm 4.
Example 7 Assume the CADT structure has already been built. Then, given LR= ((LO2, p1), (500 KB, 1, 1000, 448, 480, 800, 24, 16, 140, 2, GPJB, 1, 0)) and the minimum threshold of satisfaction, Tscor e= 0.7. After the ADPAlgo(LR) process, there are two corresponding MOs in MPset, i.e., MPset={MP1, MP2}= {(“M1v0”, image,800, 400, 16, J, 160), (“M2v1”, image,480, 700, 24, P, 50)}. Thus, assume TA D P= 1 s, and Tdeliver of MP1= (size in MP1)/ (bandwidth in LR) = 160 KB/
500 KB= 0.32 s and Tdeliver of MP2 = 50 KB/ 500 KB= 0.1 s (Step 1.3.b). The associated Media Object, MO2, of MP2does not need to be adapted again because MO2has the adapted media version (V1) based on MP2, i.e., M2v1, in the LOR. On the contrary, M1v0, which is the original version (V0) of MO1, must be adapted according to the definition of MP1before it can be delivered to the learner. Therefore, assume Ttr anscodi ng= 1 s to adapt M1v0into the nearest version, i.e., (“M1v2,” image,800, 400, 16, B, 500)(Step 1.3.c).
In addition, according to the result of Example 4, the Sat1of MP1is 0.463 by the equa-tion: SatisfactionQualityOfMedia(LR,MP1) (Step 1.3.a). Consequently, the satisfaction score of MP1is calculated by:
SatisfactionScoreM P(0.463, 2/ 2, 0.32 + 1) = 0.463
1+ (1.32 − 1)/1 = 0.35.
Besides, Sat2is calculated by:
Sati s f acti onQualityOfMedia(LR, MP2) = 0.5 × SimofNum(480 ∈ HP, 480) + 0.1 × SimofNum(800 ∈ HP, 700) + 0.3 × SimofNum(24 ∈ HP, 24) + 0.1
× SimofImageT ype(“GPJB” ∈ LP, P) = 0.9625 (Step1.3.a).
Consequently, the satisfaction scores of MP2is calculated by:
SatisfactionScoreM P(0.9625, 2 / 2, 0.1 + 0) = 0.9625
1+ (0.1 − 1)/1= 0.9625, because the Ttranscoding= 0 s. for adapting M2v1(Step1.3.d).
Because the satisfaction score of MP1= 0.35, which is less than 0.7 (Tscor e), and the satisfaction score of MP2= 0.9625, which is larger than 0.7, the MO of MP1, M1v0, will be added to the Mediaadapt for further adaptation process, i.e., Mediaadapt = {“M1v0”} (Step1.3.e).
Assume TC A P= 0.2 s and TA D P= 1 s for the “M1v0” (Step 1.4), “M2v1” of MP2
doesn’t need to be adapted again, so the Tused for MP2= Tdeliver + Ttr anscodi ng= 0.1 + 0= 0.1 (Step 1.5). Afterward, we can get an MP = (“M v0,” image,480,
240, 24, P, 20) for the “M1v0” by calling the CAPAlgo(LR, TM DT) = CAP-Algo(LR, DT−(TC A P + TA D P+ Tsave)) = CAPAlgo(LR, 2−(0.2 + 1 + 0.1)), where Mediar eq in CAPAlgo = Mediaadapt={MO1} (Step 1.6.a). Therefore, MPset={MP3, MP2}= {(“M1v0,” image,480, 240, 24, P, 20), (“M2v1,” image,480, 700, 24, P, 50)} (Step 1.6.b). According to the MPset, the media version, M1v0, of MP3will be transcoded by the definition of MP3first, and then output the XHTML with associated transcoded media resources (Step 2 through Step 6).
6 Implementation and experiment
The prototypical PLCAM system was developed on an Apache Server, PHP, Perl and C Language, and a SCORM-compliant LOR. Implementation details and experimental results are described in this section.
6.1 Mobile learning scenario for the personalized learning content adaptation mechanism system
The mobile learning scenario for the prototypical PLCAM system deploys a SCORM-compliant Learning Object Repository (LOR) that allows teachers to upload teaching materials. Students, in turn, can search and download the desired learning content onto their mobile devices. Students can log in to the system through their mobile devices and manually configure their own Leaner Preference (LP) with Weight Vector (WV). They may then select the learning content to download, and proper personalized learning content will be adapted and delivered by the PLCAM according to the stu-dents’ Hardware Profile (HP) and LP, and the status of the wireless networks. As the number of Learner Requests (LRs) increases, the Learning Content Adaptation Management Scheme (LCAMS) will automatically rebuild the Content Adaptation Decision Tree (CADT) and manage the adapted version of the Media Object (MO) in the LOR.
The operational flow of the PLCAM is illustrated in Fig.6. First, a student uses an ID to log in to the prototypical PLCAM system [Step (a)]. After logging in, a student can use the menu on the index page of the LOR to manually configure the following: (1) the HP setting, (2) the LP setting, (3) browse the content of the LOR, and (4) read the system manual [Step (b)]. The PLCAM can automatically detect the HP of a mobile device and the current bandwidth of a wireless network, as shown in the “Dynamic Attributes” [Step (c)]. Next, a student can use the “User Preference Configuration” to manually define the data of an LP, such as the preferred maximum Delivery Time (DT), presentation ratio of audio and picture, and the preferred priority of picture, etc. [Step (d)]. After configuring the HP and LP, a student can click “(3) browse the content of LOR” in Step (b) to browse the contents by the “Category Page” of the LOR [Step (e)]. The system will list the learning content stored in the selected categories [Step (f)]. A student can also select interesting learning content to browse its “SCORM metadata” and “Table of Contents” [Step (g)]. Consequently, the PLCAM will adapt the chosen content according to the mobile device profile (HP),
Fig. 6 Operational flow for a user to retrieve the learning content by the PLCAM system
LP, and the current Bandwidth (B) together, and offer personalized learning content to the student’s mobile device [Step (h)].
Figure 7 illustrates screenshots of the PLCAM delivering proper personal-ized adapted learning object content to the similar LR without waiting for the
a b c
Fig. 7 a Adapted content version of LPa; b delivered the adapted content version of LPafor LPbdue to the higher similarity; and c delivered the content version created by LPbin advance for LPc
adaptation time of the requested content. The performance and effectiveness of the PLCAM will be evaluated and described in Sect. 6.2. Assume there is an existing adapted content version created by LPa=5,JGBP,0,0 of learner A, as shown in Fig.7a. This existing version will be selected in advance and delivered directly to the new request with LPb=5,JGBP,1,0 of learner B, due to the higher similarity estimation, as shown in Fig.7b. Therefore, learner B does not need to wait for the adaptation to take place again. In the meantime, the PLCAM will prepare an accu-rate content version with a background picture to meet LPb=5,JGBP,1,0, which is stored in the LOR for the next similar request. For example, this prepared version of LPb can be delivered directly to meet the new LPc=5,JBGP,1,0, as shown in Fig.7c.
Figure8shows several experimental screenshots of the PLCAM system executed on a PDA according to diverse user needs. Figures8a and b illustrate adapted content based on the same HP and LP with different adaptation parameters under different bandwidth values, respectively. As stated in Example 1, the attributes of the LP and HP can be extended to meet the various requirements. Thus, a new attribute in the LP, called Preferred Picture Property Ordering (PPPO), includes three properties:
Dimension (D), Color Depth (C), and Quality (Q). This attribute is used to define the learner’s preferred order of image properties. For instance, like the attribute PPFO, a string, DQC, denotes that the order of image priorities is D > C > Q. Hence, we added the PPPO attribute into the LP and changed several parameters, e.g., Delivery Time (DT) and Audio Switch (AS), to test the results of the learning content adaptation process. As shown in Fig.8c, according to the new LP setting and original HP, the property of the picture was changed and the audio, background picture, and icon were replaced by hyperlinks with annotation text. We further evaluated the learning content adaptation capability by changing the screen’s horizontal size and color depth of the
Fig. 8 Screenshots of the learning content adaptation process performed by the PLCAM system
HP while using the same LP in Fig.8c. The desired adapted learning content was delivered by the PLCAM system, as shown in Fig.8d.
The PLCAM system also includes a monitoring interface of the LCAMS Web server, used to monitor the latest system status and maintain the CADT. As shown in Fig.9, the “Assign Cluster Label” function button can be used to perform the LP Clustering Algorithm (LPCALgo) for grouping the historical CARs into several clus-ters according to the learners’ LPs, where the resultant clustered information of the LPCALgo will be shown in the bottom-left part of Fig.9. Furthermore, the CADT can be reconstructed by the “Rebuild Decision Tree” function button. Its graphical presentation and rule-based representation will be automatically shown in the top-left part of Fig.9. The right-hand side of Fig.9will list all of the CARs.
Fig. 9 Monitoring interface screen of the LCAMS Web server in the PLCAM system
6.2 The experimental results
To evaluate the PLCAM system, actual experiments and simulated experiments were performed. The details and results are described in the following subsections.
6.2.1 Results of actual experiments
In the actual experiments, performance of the prototypical PLCAM system was eval-uated by the experimenters in terms of the personalized learning content delivering process, including the Content Adaptation Process (CAP), the Adaptation Decision Process (ADP), and the Learning Content Synthesizer (LCS), and the dynamic band-width detection scheme, based on the SCORM-compliant learning content in relation to “the plants in campus” shown in Sect. 6.1. These characteristics were tested to observe and evaluate the resultant Delivery Time (DT) and the transmission data size according to various bandwidth settings for different requests. The performance of the PLCAM in terms of DT compared with inadaptation and static adaptation approaches was evaluated as well.
As mentioned in Sects.1and 2, the DT plays an important role in affecting one’s learning performance in mobile learning environments. Therefore, a bandwidth detec-tion scheme was developed to automatically detect the latest network bandwidth for providing the learner with more precise personalized learning content with higher fidelity. As shown in Fig.10a, with the decrease of “actual” network bandwidth, the
Fig. 10 Experiment results of the automatic dynamic bandwidth detection scheme
bandwidth that a user can consume will decrease as well by means of monitoring each transmission time compared with the setting of the user’s desired maximum DT.
For example, in Fig. 10b, a user’s functional bandwidth has been updated at 3, 5, and 7 (times) due to the detection of the long delivery latency at 2, 4, and 6 (times) (maximum DT= 5 s).
Figure7shows the effectiveness of the PLCAM in delivering proper personalized adapted learning content that meets a similar LR without waiting for the CAP to be completed. Therefore, Fig.11illustrates the DT, which consists of the data transmis-sion time and the PLCAM adaptation time, in terms of the different requests and the size of transmission data based on the various bandwidth settings. In Fig.11a, assume the definition of the maximum DT is 5 s, during the first request for a learning object, the average DT is about 8.416 s, including the content adaptation process (about 3 s) and the actual content delivery. On the contrary, the average DT during the second request can be controlled around 5.238 s to meet the constraint of the maximum DT without repeating the content adaptation process. Figure11b shows that the size and quality of transmission data can be increased gradually with the increase of usable bandwidth by the aforementioned dynamic bandwidth detection scheme based on the definition of maximum DT.
Assume that there is a learning object, which contains a Waveform Audio Format (WAV) file with 660,768 bytes and six pictures with 1,016,392 bytes. The original size is about 1.8 Mbytes. The learner specified the maximum tolerable DT to be 5 s We observed the transmission results based on the various bandwidth settings in terms of the approaches, which included the inadaptation, static adaptation, and PLCAM. In
Fig. 11 DT of different requests and transmission data size based on various bandwidth settings
Fig.12, the inadaptation approach transmits content without employing the content adaptation process and spends much more DT than the static adaptation approach and the PLCAM. In this example, the static adaptation approach prepared three versions of learning content in advance, i.e., 200, 170, and 140 KB. Therefore, within the bandwidth range from 140 to 220 KB, the DT is almost the same between the static adaptation approach and the PLCAM. However, the static adaptation approach cannot consistently provide users with the appropriate content version according to the var-ious bandwidths; thus, this approach spent a great deal of time gradually decreasing the bandwidth from 140 to 50 KB. On the contrary, the PLCAM is still able to offer a stable delivery time and the proper personalized adapted content to meet the diverse user needs.
6.2.2 Results of simulated experiments
To evaluate the performance and effectiveness of the PLCAM in depth, several simu-lated experiments were carried out, emulating a large number of diverse user requests with Learner Preferences (LPs) and Hardware Profiles (HPs) to access the desired Learning Objects (LOs) from the Learning Object Repository (LOR). The perFOR-mance and satisfaction degree of the PLCAM in terms of: (1) Learning Content Adapta-tion Management Scheme (LCAMS) with Content AdaptaAdapta-tion Decision Tree (CADT) in Figs.13,14,15, and16; (2) the parameter setting of the LP clustering algorithm in Fig.17; and (3) the CADT maintenance process in Figs.18and19were evalu-ated based on the different experimental conditions, including bandwidth, LPs, and devices.
Fig. 12 Comparison among the inadaptation, static adaptation, and PLCAM approaches
Fig. 13 Comparison of a the difference of query time; and b the difference of satisfaction between the PLCAM without and with the CADT based on different bandwidths and requested MOs
The simulated experiments were executed on a computer with a 1- GHz Central Processing Unit (CPU), 1 G of Random Access Memory (RAM), and a Windows XP Operating System (OS). Table5lists the HP data used to perform the following experiments.
The LCAMS in the PLCAM uses the CADT structure to efficiently determine the appropriate personalized learning content to meet the diverse learner requests.
Fig. 14 Comparison of a the delivery time; b the query time;
and c the satisfaction score between the PLCAM without and with CADT based on 500 KB bandwidth and different requested MOs
Therefore, we analyzed the performance and differences between the PLCAM without and with the CADT to perform the content adaptation based on different bandwidths, 5000, 2000, 1000, 500, 250, 50 KB, and the number of requested Media Objects (MOs) from 1 to 15, i.e., [1–15]. During this simulated experiment, each of the 250 Learner Requests (LRs) was generated by LP= (Maximum Delivery Time = 1 s, JPBG, 1/0,
Fig. 15 Comparison of a the average delivery time; b the average query time; and c the average satisfaction score between the PLCAM without and with the CADT based on different bandwidths and requested MOs
Fig. 16 Comparison of a the delivery time; b the query time;
and c the satisfaction score between the PLCAM without and with the CADT on random bandwidths [50 KB, 500 KB], random maximum DT [1,8], random requested MOs [1,9], and eight HP data points in Table5
Fig. 17 Most suitable threshold of rebuilding CADT based on the different amount of CARs in the CAR pool
Fig. 18 Resultant transcoding time of the PLCAM with auto-adjustment scheme
1/0) and the random HP ID between 1 and 6, i.e., [1,6], in Table5. The results of the simulated experiment are shown in Figs.13,14, and15, respectively.
In Fig. 13, the Query-Diff and Sat-Diff denote the difference of query time of determining the suitable MPsetand the satisfaction score between the PLCAM with-out and with the CADT, respectively. Figure13a shows that the Query-Diff explicitly increases with the increase of bandwidth >=250 KB and the number of requested MOs>=4, which shows that the CADT can efficiently speed up the performance of the Adaptation Decision Process (ADP).
Figure13b indicates that the Sat-Diff also increases if the bandwidth>=500 KB and the number of requested MOs>=7, which shows that decrease of query time can enhance the satisfaction score because response time is an important factor in user satisfaction. As for the bandwidth= 50 KB, the Sat-Diff and Query-Diff are very low because the available DT is insufficient to determine the MPsetwith a better satisfac-tion score in the ADP. On the contrary, the PLCAM without the CADT needs much more time to determine the suitable MPsetfrom the MP database while the number of requested MOs increases.
Fig. 19 Comparison of a query time; and b the satisfaction score of the PLCAM between dynamic-threshold and static-threshold by the random LRs and eight HP data points in Table5
Figure14shows the delivery time, the query time, and the satisfaction score between the PLCAM without and with the CADT based on 500 KB bandwidth only. In Fig.14a, the Delivery Time (CADT), consisting of physical data transmission time and trans-coding time, is almost the same as the PLCAM without CADT approach. In Fig.14b, the difference of query time (Query-Diff) is from 0.08 to 0.4 s, which saves 8–40%
time consumption in terms of DT= 1 s Furthermore, although the PLCAM uses the CADT to improve the performance of the content adaptation process, a higher satis-faction score than the score obtained without the CADT, can be maintained, as seen in Fig. 14c.
Regarding the influence of bandwidth between query time and the satisfaction score, Fig.15a shows that the average DT is almost the same without and with the CADT.
This finding indicates that the CADT can determine similar personalized learning content like the PLCAM without CADT. Also, query time (CADT) will decrease with the increase of bandwidth, while query time without the CADT is almost the same, as seen in Fig. 15b. This is a 2–27% (average 20%) time consumption savings in terms of DT= 1 s. Therefore, the average satisfaction score (CADT) is also better than “without CADT,” as presented in Fig.15c.
To evaluate the performance of the PLCAM in actual mobile learning environments, we emulated diverse LRs actually used by the PLCAM with randomized LRs, which
Table 5 HP in LR data used for
the simulation experiments ID HP in CAR Machine type
1 2, 600, 384, 320, 480, 24, 16, 40 Cell phone 2 1, 1000, 576, 480, 800, 24, 32, 100 PDA 3 1, 1000, 448, 480, 800, 24, 16, 140 PDA 4 2, 528, 288, 320, 480, 32, 8, 20 Cell phone 5 2, 528, 384, 320, 480, 16, 32, 120 Cell phone 6 2, 528, 288, 320, 480, 16, 8, 30 Cell phone 7 0, 2000, 8000, 1366, 768, 32, 32, 500 Notebook 8 0, 1200, 4000, 1366, 768, 32, 16, 300 Notebook
had random maximum DT between 1 and 8 s, [1,8], the random bandwidths between 50 and 500 KB, [50 KB, 500 KB], and the random number of requested MOs between 1 and 9, [1,9]. We tested this simulated experiment for eight iterations, each of which used eight participant HP data in Table5and generated 250 LRs to test the PLCAM system. Figure16shows the results of the experiment. The Delivery Time (CADT) is a bit higher than what is seen without the CADT, as shown in Fig.16a. The Query Time (CADT) is still better than what is observed without CADT, from about 0.15 to 0.27 s (average is 0.2 s), as seen in Fig.16b, and the satisfaction score is almost the same and stable around 0.7 during eight iterations. These results show that the PLCAM with the CADT can achieve better and more stable performance regarding learning content adaptation and the satisfaction degree in simulated actual learning environments.
To analyze the parameter setting of the LP Clustering Algorithm (LPCALgo), we used different parameter settings to test the satisfaction score of the PLCAM system based on LP= (1, JPBG, 1/0, 1/0), HP from 1 to 6 in Table5, bandwidth= 500 KB, and the number of MOs between 1 and 9. The parameter setting of the LPCALgo has been found as {K= 3, Ts= 0.004, Tm= 2, Tn= 3, Tp= 2}, where the PLCAM attains a better satisfaction degree.
By means of the analysis of the parameter setting of LPCALgo, we found that the number of CARs in the CAR Pool, employed to be the threshold of rebuilding the CADT, play an important role in satisfaction. Therefore, we used the aforementioned parameter setting to evaluate the performance of the PLCAM system by adjusting the threshold of rebuilding the CADT. Thus, the experimental results are shown in Fig.17, where we find that the most suitable thresholds to rebuild the CADT are: 5 at 250 requests, 35 at 500 requests, and 45 at 1000 requests, respectively. According to these results, we can use the ordinary least squares approach to estimate the CADT rebuilding equation:
CADT Rebuilding Equation: Y = 0.04857X,
where Y is the predicted thresholds of rebuilding the CADT and the X is the number of LRs.
For example, if the number of LRs is 750, we can use the Y = 0.04857X = 0.04857
× 750 = 36 to be the threshold. Therefore, if there are 36 new Content Adaptation Rules (CARs) in the CAR Pool and the total LRs is larger than 750, the CADT main-tenance process will rebuild the CADT automatically.
× 750 = 36 to be the threshold. Therefore, if there are 36 new Content Adaptation Rules (CARs) in the CAR Pool and the total LRs is larger than 750, the CADT main-tenance process will rebuild the CADT automatically.