Akitsugu Ohtsuka

Self-Organizing Map Based Data Detection of Hematopoietic Tumors

Data detection based on self organizing maps is presented for hematopoietic tumor patients. Learning data for the maps are generated from the screening data of examinees. The incomplete screening data without some item values is then supplemented by substituting averaged non-missing item values. In addition, redundant items, which are common to all the data and tend to have an unfavorable influence on data detection, are eliminated by a genetic algorithm and/or an immune algorithm. It is basically judged, by observing the label of a winner neuron in the map, whether the data presented to the map belongs to the class of hematopoietic tumors. Some experimental results are provided to show that the proposed methods achieve the high probability of correctly identifying examinees as hematopoietic tumor patients.

On detection of hematopoietic tumors using self organizing maps and genetic algorithms

This paper proposes the scheme of detecting the screening data of hematopoietic tumor patients, using self-organizing maps. The data of an examinee frequently lacks several of the item values. In addition, there exist redundant common items that should be eliminated from all of the data because they have an unfavorable influence on classifying the data. The data imputation, which substitutes the averages of non-missing item values, and a genetic algorithm are adopted to overcome the above issues. It is basically judged, by observing a label of a winner neuron in a map, whether the data presented to the map belongs to the class of hematopoietic tumors. Quantitative evaluations show that the proposed scheme achieves the high probability of correctly identifying examinees as hematopoietic tumor patients.

Self-Organizing Map Based on Block Learning

A block-matching-based self-organizing map (BMSOM) is presented. Finding a winner is carried out for each block, which is a set of neurons arranged in square. The proposed learning process updates the reference vectors of all of the neurons in a winner block. Then, the degrees of vector modifications are mainly controlled by the size (i.e., the number of neurons) of the winner block. To prevent a single cluster with neurons from splitting into some disjointed clusters, the restriction of the block size is imposed in the beginning of learning. At the main stage, this restriction is canceled. In BMSOM learning, the size of a winner block does not always decrease monotonically. The formula used to update the reference vectors is basically uncontrolled by time. Therefore, even if a map is in a nonstationary environment, training the map is probably pursued without interruption to adjust time-controlled parameters such as learning rate. Numerical results demonstrate that the BMSOM makes it possible to improve the plasticity of maps in a nonstationary environment and incremental learning.

On Self-Organizing Maps Learning with High Adaptability under Non-Stationary Environments

In this paper, fast block-matching-based self-organizing maps (BMSOMs) are presented. Proposed learning defines a set of neurons arranged in square as a block, and find a winner block according to the decision-tree-like search. In other words, proposed learning determines a candidate out of four blocks included in the same block that has been most recently determined as another candidate. Proposed learning then chooses the candidate with the shortest Euclidean distance relative to the presented training data as the winner for it, out of such candidates. It accumulates two values associated with degrees of reference vector modifications for each member of the training data set, and updates reference vectors of all neurons at once per epoch. It copes well with the issue of reducing computational time complexity while retaining a high adaptability to a nonstationary environment. This advantage is demonstrated by experimental results obtained using artificially generated data set and object segmentation in a short video sequence

On Self-Organizing Map Based Classification of Insect Neurons

In this paper, a systematic method based on self-organizing maps is presented to classify interneurons of silkworm moths. Denseness of branching structures and existence of thick main dendrites are quantified by six fractal dimension values and three values calculated from images to which fundamental processing techniques are applied, respectively. Such values are employed as nine elements in training data for a map. The classification result is obtained as clusters with units in the trained map. Experimental results establish that the classification executed by the proposed method is comparable in accuracy to the manually executed classification

On detection of confused blood samples using self-organizing maps and genetic algorithm

A SOM (self-organizing map)-based detection of confusion of blood test data referred to as CBC (complete blood count) data is proposed. Firstly, the method based on only SOM is shown. The learning data applied to SOMs are generated by subtracting the immediately anterior CBC data of subjects from the present CBC data. All the neurons in the second layer of SOM trained by applying the above learning data are roughly divided into the following two clusters: a cluster with neurons reacting to regular input data, and a cluster reacting to irregular input data which are generated by subtraction between confused CBC data. So, if the firing neuron belongs to the latter cluster, it is presumed that the confusion arises among CBC data of some subjects. Next, a method based on both SOM and GA (genetic algorithm) is shown. With the exception of selecting some elements, which instruct the weights to be updated in the second layer of CBC data by means of GA, the learning and the detection strategy adopted by this method are similar to those by the firstly proposed method. Experimental results on detecting the confusion, which arises among CBC data of 750 subjects, show that the second proposed method produces the second layer which achieves the high accuracy of detection especially when the input data, not to be employed during the learning, are applied.

Self-Organizing-Map-Based Detection on Hematopoietic Tumors in a Nonstationary Environment

This paper proposes a scheme of detecting the screening data of hematopoietic tumor patients, using block-matching-based self-organizing maps. The data of an examinee frequently lacks several of the item values, and hence the data is presented to a map after averages of non-missing item values are substituted for items with no values. It is basically judged, by observing the label of a winner block in a map, whether the data presented to the map belongs to the class of hematopoietic tumors. Proposed scheme allows us to construct maps not only in stationary environments where members in a training data set never change but also in nonstationary environments where the data set is suddenly updated during learning. Simulation experiments established that the proposed scheme achieves high accuracy of correctly classifying the data, even if the map is in nonstationary environments.

On Self-Organizing Map Approaches for Data Detection of Hematopoietic Tumors

Data detection using self organizing maps is presented for hematopoietic tumor patients. The learning data for the maps is generated from the screening data. Redundant items, which have an unfavorable influence on data detection and are common to all the data, are eliminated by a genetic algorithm and an immune algorithm. It is basically judged, by observing a label of a winner neuron in a map, whether the data presented to the map belongs to the class of hematopoietic tumors. Quantitative evaluations show that the proposed methods achieve the high probability of correctly identifying examinees as hematopoietic tumor patients