This paper shows by a mathematical model that, for image classification/recognition purposes, high resolution pictures have lower recognition rate than relatively low resolution pictures. The analysis is based on the matching approach by a simple neural network, but we believe that the conclusion remains valid even when the classification process involves complicated matching schemes such as principal component analysis and Gabor transforms.

Abstract A new document representation model is presented in this paper. This model is based on the idea of representing a document by two or more pictures of the document taken from different perspectives. It is shown that by applying the stereo representation model, enhanced textual retrieval performance is achieved because the new model improves the capability of capturing individual features of the document. Experiments have been conducted on two standard corpora, TIME and ADI, using the standard term vector method and the latent semantic indexing (LSI) method based upon both the stereo representation model and the traditional representation model. Statistical t‐tests on the experimental results have convincingly illustrated that these methods achieve significant improvements in retrieval performances with the stereo representation model over those with the traditional representation model.

The previous discrete-model-based stability analysis of regional and national voting has been extended to a continuous-model-based analysis in the simultaneous presence of white and concentrated components of noise, reconfirming the previous conclusion that regional voting with smaller sized regions always demonstrates an improved stability over those with larger sized regions, including the national voting in its limiting case in particular. The conclusion remains valid as long as the weak distribution assumption is valid.

By exploiting the Fourier series expansion, we have developed a new constructive method of automatically generating a multivariable fuzzy inference system from any given sample set with the resulting multivariable function being constructed within any specified precision to the original sample set. The given sample sets are first decomposed into a cluster of simpler sample sets such that a single input fuzzy system is constructed readily for a sample set extracted directly from the cluster independent of the other variables. Once the relevant fuzzy rules and membership functions are constructed for each of the variables completely independent of the other variables, the resulting decomposed fuzzy rules and membership functions are integrated back into the fuzzy system appropriate for the original sample set requiring only a moderate cost of computation in the required decomposition and composition processes. After proving two basic theorems which we need to ensure the validity of the decomposition and composition processes of the system construction, we have demonstrated a constructive algorithm of a multivariable fuzzy system. Exploiting an implicit error bound analysis available at each of the construction steps, the present Fourier method is capable of implementing a more stable fuzzy system than the power series expansion method of ParNeuFuz and PolyNeuFuz, covering and implementing a wider range of more robust applications.

We have extended and reinforced the previous discrete-model-based stability analysis of the national and regional voting by a continuous model where we have allowed the presence of the so-called white noise, and the concentrated noise. The result reconfirms the previous conclusion developed for image processing application that as long as the divided regions are not too small, the regional voting with smaller sized regions demonstrates always an improved robustness than those with larger sized regions.

A new diagnostic system has been developed for an interactive template-structured intelligent language tutoring system (ILTS) for Japanese-English translation where an efficient heaviest common sequence (HCS) matching algorithm and a ‘part-of-speech tagged (POST) parser’ play a key role. This is implemented by exploiting the system template which consists of a complex transition networks comprising both model (correct) translations and many typical erroneous translations characteristic of nonnative beginners all collected and extracted from translations of about 200 monitors. By selecting, from among many candidates’ paths in the system template, a path having a HCS with the student’s input translation as a best matched sentence, the template structure of the diagnostic system allows the potentially complicated bug finding processes in natural language to be implemented by a much simpler and efficient HCS string matching algorithm [20]. To improve the precision of a parser, we have developed a ‘probabilistic POST parser’ where we have eliminated ambiguity in part-of-speeches by manually pre-assigning POS tags to all words in potentially correct paths of the template. Combining the templatebased diagnostic system and the parser, we found that the ILTS is capable of providing most adequate diagnostic messages and a tutoring strategy with appropriate comments after analyzing the keyed-in translated sentences from students.

This paper develops a buggy model-based intelligent tutoring system (ITS) capable of diagnosing multiple bugs, pinpointing not only their types but also their exact locations involved. The procedural grammar of context free type is used not only to decompose a complicated procedure involving possible steps of both correct and incorrect arithmetic into simplest, 'primitive' procedures but also to express control knowledge essential to implementing an efficient parser. An efficient parser is implemented by narrowing down the search space, exploiting the control knowledge, the selection and consistency conditions in selecting rules in parsing. Parsing of superficial symptoms such as a student's errors in arithmetic essentially reveals the deep structure of the buggy knowledge of the student so that teachers may now devise and offer a more effective means of instructions for acquiring the correct skill of arithmetic.