CBIR for image-based language learning within mobile environment

A formative assessment-based mobile learning approach to improving the learning attitudes and achievements of students

The purpose of the present study was to design a mobile learning environment that enables the use of a teleconference application used in simultaneous e-learning with mobile devices and to evaluate this mobile learning environment based on students‘ views. With the mobile learning environment developed in the study, the students are able to follow a teleconference application realized by using appropriate mobile devices. The study was carried out with 8 post-graduate students enrolled in Karadeniz Technical University (KTU), Department of Computer Education and Instructional Technologies (CEIT), Graduate School of Natural and Applied Science. The students utilized this teleconference application using mobile devices supporting internet access and Adobe Flash technology. Of the 8 students, 4 accessed the system using EDGE technology and 4 used wireless internet technology. At the end of the application, the audio and display were delayed by 4-5 seconds with EDGE technology, and were delayed by 7-8 seconds with wireless internet technology. Based on the students‘ views, it was concluded that the environment had some deficiencies in terms of quality, especially in terms of the screen resolution. Despite this, the students reported that this environment could provide more flexibility in terms of space and time when compared to other simultaneous distance education applications. Although the environment enables interaction, in particular, the problem of resolution caused by screen size is a disadvantage for the system. When this mobile learning application is compared to conventional education environments, it was found that mobile learning does have a role in helping the students overcome the problems of participating in learning activities caused by time and space constraints.

Mobile learning environments have the benefit of facilitating real time student learning and assessment. However, most of such learning environments only support static or traditional learning activities. In STEM disciplines, we need more active and engaging activities and mobile learning environments should be able to support such dynamic activities. By designing such learning environments to run completely on the cloud will limit its extensibility and will not accommodate interactive activities developed by anyone other than the developer of such learning environment. Instead, we argue that by incorporating cloud services in a traditional software architecture will allow the flexibility to develop and deploy interactive problem solving activities along with versatility that cloud computing brings. This paper presents Mobile Response System (MRS) that facilitates in-class interactive problem solving using mobile devices. MRS uses cloud services in the infrastructure to minimize instructor's workload, gives students transparent access, and makes the system failsafe alongside providing extensibility to any discipline.

Supporting efficient data access in the mobile learning environment is becoming a hot research problem in recent years, and the problem becomes tougher when the clients are light-weight mobile devices such as cell phones whose limited storage space prevents the clients from holding a large cache. A practical solution is to store the cache data at some proxies nearby, so that mobile devices can access the data from these proxies instead of data servers in order to reduce the latency time. However, when mobile devices move freely, the cache data may not enhance the overall performance because it may become too far away for the clients to access. In this paper, we propose a statistical caching mechanism which makes use of prior knowledge (statistical data) to predict the pattern of user movement and then replicates/migrates the cache objects among different proxies. We propose a statistical inference based heuristic search algorithm to accommodate dynamic mobile data access in the mobile learning environment. Experimental studies show that, with an acceptable complexity, our algorithm can obtain good performance on caching mobile data.

As the use of digital media increases, effective retrieval and management techniques become more important. In order to extract useful information from this huge amount of data, many content based image retrieval (CBIR) systems have been developed. A typical CBIR system captures image features such as color, texture, or shape of objects in the query image and tries to retrieve images from the database with similar features. The main advantage of CBIR systems with relevance feedback is that these systems take into account the gap between the high-level concepts and low-level features and subjectivity of human perception of visual content. In this paper, a CBIR system based on color histogram has been presented and a new approach for image storage and retrieval called association-based image retrieval (ABIR) has been studied. The results of both systems have been shown.

Mobile learning is gaining popularity as it modifies the conventional definition of teaching and learning by using portable devices. In order to cope with identified limitations of mobile learning, while maintaining its transformational potential of using mobile technology in higher education, we proposed a blended mobile learning environment. In this study, we described the mobile blended learning environment and examined its applicability in theatre arts classrooms by presenting and discussing how mobile devices were used in three blended theatre arts classes at a comprehensive university in Macau. Survey and interview data showed that though challenges exist, the fusion of the multichannel teaching approach (m-learning, blended learning, in class/online lectures) has greatly enhanced teaching and learning experiences.

With the rapid development of the Internet, mobile learning environment is rapidly and profoundly affecting the learning behavior of college students in the new era. This paper investigates the current situation and problems of college students' learning behaviors under the mobile learning environment by using a combination of questionnaire survey and interview with undergraduates in a certain university in a certain region as the research object. The survey results show that from the learning behavior of mobile learning environment, it can be seen that college students have a great demand for online learning, but most of them have not found a reasonable way of learning, resulting in low learning efficiency. In view of the existing problems, the author proposes corresponding online learning strategies, so that college students can exert greater learning potential in the mobile learning environment.

Many research indicates that the integration of mobile learning environment can effectively enhance students' motivation for learning. However, instructors adopt appropriate learning strategies is the main factor to help students improve their learning performance. The study expected the Predict-Observe-Explain (POE) teaching strategies in mathematics teaching has significant effects on learning effectiveness and retention. Few studies have explicitly incorporated the POE strategy and collaborative learning approach with mobile learning environment in elementary students' mathematics learning. The 41 fifth graders who participate in this research are assigned to an experimental group and a control group. The students in the experimental group will learn through the POE teaching strategy combined with the collaborative learning approach; while those who participant in control group will learn mathematics through the POE teaching strategy only. The aim of this research focuses on the effects of the POE strategy and collaborative learning approach with mobile learning environment on students' learning achievements, learning attitude, and self-efficacy of mathematics.

This research study aimed to synthesize theoretical framework and designing of constructivist mobile application learning environment to foster creative thinking on basic photography skill for high school students. The target group consisted of 3 expert reviewers for content, mobile application and learning environment designing. Research methodology is developmental research; developmental research consisted of 3 processes: (1) designing process, (2) developing process, (3) evaluate process. The procedures were as follows: (1) to examine and analyze the principles and theories, (2) to synthesize theoretical framework, and (3) to synthesize designing framework. The result revealed that: 1) to synthesize theoretical framework comprise of 6 components as following that. Contextual base, Psychological base, Pedagogies base, Creative Thinking base and Technologies and media base. 2) To synthesize design framework of mobile application learning environment to foster creative thinking of 6 components i.e., (1) Problem base, (2) Resource, (3) Creative Thinking Photo Lab, (4) Collaboration, (5) Coaching, (6) Scaffolding. The efficiency of this learning environment was evaluated by expert review. It was found that the learning environment is appropriate on 3 aspects: content, mobile application learning design, and learning environment design..

In the field of computer vision and image processing CBIR (Content based image retrieval) system become an active research area. The CBIR technique involves feature extraction based on image features (like color, shape and texture) and defining rules for comparing image. A classifier is also used by authors for image classification. For this purpose an image database taken from James Z. Wang research group website is used by many authors. Due to enormous increase in the size of database traditional methods of image retrieval by using keywords does not provide accurate result. Thus the concept of CBIR system is emerged. In last couple of years many method of feature extraction is developed but since now researcher are not able to develop a system which has gained high accuracy of human visual perception in distinguishing pictures. Therefore earlier researchers have concentrated to increase the retrieval accuracy of CBIR system by using different combination of features. The objective of this paper is to present review on a CBIR technique which combined four kinds of features set including every kind of feature for developing feature vector. Color based features (histogram), statistical features (mean, median and standard deviation), spatial features (Gabor feature and wavelet features) and texture features (GLCM) is used for forming feature vector. A SVM classifier is used with CBIR system to increase retrieval accuracy. SVM (support vector machine) is a machine learning classifier which provides good classification accuracy. Keywords: CBIR, SVM, NN, GLCM, HSV Color space, Euclidean distance matrix.

The finding that under split‐attention conditions students learn more from a picture and spoken text than from a picture and written text (ie, the modality effect) has consistently been found in many types of computer‐assisted multimedia learning environments. Using 58 fifth‐grade and sixth‐grade elementary school children as participants, we investigated whether the modality effect can also be found in a mobile learning environment (MLE) on plants' leaf morphology, in which students had to learn by integrating information from text and real plants in the physical environment. A single factor experimental design was used to examine the hypothesis that students in a mixed‐mode condition with real plants and spoken text (STP condition) would pay more attention to the real plants, and achieve higher performance on retention, comprehension, and transfer tests than the single‐mode condition with real plants and written text (WTP condition). Whereas we found that participants in the STP condition paid more attention to observing the plants, and achieved a higher score on the transfer test than participants in the WTP condition, no differences were found between the conditions for retention and comprehension test performance.

In this paper, the authors present their proposal for adaptation of educational contents of learning objects to a particular mobile device and a specific learner. Content adaptation in mobile learning objects implies user adaptation and device adaptation, and requires additional metadata categories in comparison with SCORM 2004. This learning object content model, ALMA (A Learning content Model Adaptation), inherits from the SCORM standard a subset of metadata categories, and extends it with three top level metadata categories for content adaptation, i.e., Knowledge, Use, and Mobile Device Requirements (Castillo & Ayala, 2008). For user adaptation, the authors developed NORIKO (NOn-monotonic Reasoning for Intelligent Knowledge awareness and recommendations On the move), a belief system based on DLV, a programming system based on Answer Set Programming paradigm. For device adaptation the authors designed CARIME (Content Adapter of Resources In Mobile learning Environments), which uses transcoding and transrating to adapt media content to suit the device characteristics.

Whether online or in a classroom, learners have long suffered from a lack of interactivity, several mobile learning system provide recorded lectures, which only enhance passive learning. Thus and in order to improve interactivity and motivation into the learning process, we propose in this paper a conceptual framework to be efficiently integrated into the learning process. This framework describes the design requirements of a mobile learning environment that can deliver live broadcast of real-time classroom teaching to online student with mobile devices. It suggests five perspectives: generic mobile environment, mobile learning context, learning experience, social learning strategy and learning objectives. It also clarifies how to apply these last perspectives and build a mobile learning application efficiently.

As we all know, the content-based image retrieval (CBIR) is very time-consuming due to the extraction and matching of high dimensional and complex features. The traditional CBIR systems could not respond to a very large number of retrieval requests at mean time, which are submitted from the Internet. In this paper, we propose a content-based parallel image retrieval system to achieve high responding ability. Our system is developed on cluster architectures. It has several retrieval servers to supply the service of content-based image retrieval. Our system adopts the Browser/Server (B/S) mode. The users could visit our system though web pages. Our system uses the Symmetrical Color-Spatial Features (SCSF)[25] to represent the content of an image. The SCSF is effective and efficient for image matching because it is independent of image distortion such as rotation and flip as well as it increases the matching accuracy. The SCSF was organized by M-tree[16], which could speedup the searching procedure. Our experiments show that the image matching is quickly and efficiently with the use of SCSF. And with the support of several retrieval servers, the system could respond to many users at mean time. (Abstract)

In order to narrow the learning divide, mobile learning should be provided to handicapped learners, especially to learners with visual impairment. However, in spite of development of the resolution and screen size of mobile devices, there are still many inconvenient factors. Among recent studies, there is a Proposal of Ahmed Rana and Four Startup Screen operates in mobile devices with touch screen. Although Proposal of Ahmed Rana gives magnified virtual key-board and startup screen, and Four Startup Screen reduce complexity of menu structure, it is not good enough for learners with visual impairment in mobile learning environment. In this paper, we have proposed universal design of a cursor for mobile learners with visual impairment. First of all, our cursor has been designed to separate objects under a magnifying glass on the rim of the cursor. Secondly, the cursor has four kinds of startup screens in order to reduce repetitive moving. Thirdly, by dragging the cursor to the border of the screen, entire screen perform the magnifier. Universal design of a cursor can help mobile learners with visual impairment to more easily read documents consisting of text and to look video. For performance evaluation, our cursor is easy to select a character and easy to reduce of repetitive moving and depth of the hierarchical menu structure than the Four Startup Screen and the proposed method of Ahmed Rana. Consequently, universal design of cursor improves the performance of the input tool for learners with visual impairment in e-learning environment using small size mobile devices screen.