Norihiko Moriwaki

Predicting flow state in daily work through continuous sensing of motion rhythm

We have constructed a new application of continuous sensing of human physiological data during daily a business setting. By capturing the subtle changes and differences in motion rhythm detected through an accelerator rather than trying to identify the context of human activities, we are envisioning the prediction of a persons psychological flow state, i.e., the engagement in ones task. A badge-shaped wearable sensor device called “Business Microscope” was developed and deployed in a real organization, an office supply firm, for one month to study how effectively flow states could be measured during daily work. We found that even though each subject behaved at different motion rhythms when they were in flow, the consistency of motion rhythm around 2 to 3 Hz was correlated with the richness of flow during work (r=0.47, p<0.01).

Beam-scan sensor node: Reliable sensing of human interactions in organization

We have developed a wearable sensor node with a low power and high detection rate by using sequential control of multiple infrared (IR) modules. Conventional sensor nodes are not practical in terms of size, sensing performance, and working hours. Therefore, we devised a name-tag-size (73 × 98 × 9 mm) sensor node, which captures face-to-face interactions within 2 meters and within an angle of 60°. The sensor node weighs 62 grams and works for more than twenty hours with a small 5-gram Li-ion battery. The sensor uses the beam-scan technique, in which four infrared modules, placed horizontally on the node, are controlled to be on and off sequentially, and this operation is done synchronously with other nodes. The beam-scan technique enables low-power operation with a consumption current of 7.2 mA and 21 hours of operation. We had tested the sensor node in a field trial that collected sensor data for six months from 20 people and had demonstrated that this technique is practical. Feedback from sensing data reminded us of the importance of meeting frequency and this improved our work habits.

Profiting from IoT: the key is very-large-scale happiness integration

Big data without link to value is merely a cost. We have studied how to profit from data with Internet-of-Things technologies for over 10 years to reach the answer: the Wearable Happiness Meter. It allows us to integrate the measure of both wellbeing and productivity of 7-billion people worldwide, which was the dream of the 18th-century philosopher Jeremy Bentham, numeration of the greatest happiness of the greatest number to measure the right and wrong. Knowing right and wrong with the 10x speed over conventional financial feedback accelerates the growth of the enterprise, the economy, and the individual to maximize the worldwide happiness. Here the integration is not only on a chip, but in the distributed massive chips embedded in the society.

Knowledge-creating behavior index for improving knowledge workers' productivity

Improving the productivity of knowledge workers is becoming a major issue in corporate management in the 21st century. “Business Microscope” is a sensornet application designed to improve organizations. Organizational improvement is facilitated by the visualization of each workers behavior. In addition, the improvement can be accelerated further by presenting a beneficial index. In this paper, we propose a novel index for organizational improvement using Business Microscope. Thus, “active face-to-face interaction” and “concentration time” are proposed as an effective knowledge-creating behavior index, and a knowledge-creating behavior balance graph is developed as a visualization application. We focus here on the quality of communication measured from gestures in face-to-face interactions. Additionally, the behavior index is obtained from infrared sensor data and acceleration sensor data. As a result of applying this proposed application to a real organization, we were able to identify which worker and organization problems need to be improved. The effectiveness of the productivity analysis on knowledge workers was also confirmed.

Visualization of knowledge-creation process using face-to-face communication data

No firm can survive without building a mechanism to create knowledge in the 21st century. The knowledge-creation theory by Nonaka has successfully generalized a knowledge-creation process in an organization. However, nobody has found a quantitative method for evaluating the process. This paper proposes a technique of visualizing the knowledge-creation process by plotting graphs of face-to-face contact time and number of people contacted. We applied the data of face-to-face communication of an organization to our proposed technique and confirmed that it represented dynamics of the knowledge-creation process. This technique will provide a new method of corporate management.

Large scale ATM switch architecture for Tbit/s systems

This paper discusses a large-scale ATM switch architecture toward a T(tera) bit/s system. A single-stage 40-Gbit/s ATM switch was developed using a parallel processing architecture incorporating current 0.35 /spl mu/m-CMOS device technology and conventional printed circuit boards (300mm/spl times/300mm approx.). This architecture is applicable to a 160-Gbit/s switch using the latest 0.25 /spl mu/m-CMOS device technology. Moreover, a scalable solution for different smaller capacity switches using the same switch elements is introduced. This paper also introduces an innovative method for switch capacity extension. By employing the multipath parallel distribution approach at the cell level with cell sequence integrity guaranteed, this method enables an existing switch to be efficiently expanded.

Automatic Label Data Abstraction Based on Information Entropy (Application Paper)

There is currently a big demand for automating big data analysis. In the data analysis field, data abstraction or summarization playes an important role in the extraction of generalized information from large scale data. We developped an artificial intelligence computer system with the aim of automating big data analysis and came up with a method that can abstract numerical type data (age, height, time, etc.). However, it could not abstract or summarize label type data (customer ID, product code, name, etc.). In the present work, we have developed a label abstraction method based on information entropy. Experiments using open real data showed that the proposed method achieved an extraction accuracy of 80% evaluated by f measure. We intended to apply the proposed method to our artificial intelligence and perform further evaluations.

Sensor-Data-Driven Knowledge Creation Model: A Model and Empirical Test

A new knowledge-creation model, called sensor-data-driven knowledge creation (SDD-KC), which utilizes sensor data for discovering tacit knowledge, is proposed and tested. The proposed model utilizes wearable sensors to digitize tacit activities such as location, motion, and social interaction of people. To derive practical knowledge, the obtained data is statistically analyzed and associated with performance outcome. An empirical test at a retail store demonstrated that the SDD-KC model was able to derive a rule that leads to customers’ behavioral change, which contributed to a sales increase. In contrast, the traditional knowledge-creation model, applied in the same setting, failed to identify effective ideas. The proposed SDD-KC model was thus shown to be effective for knowledge creation by overcoming cognitive limitations of people.

Managers’ Interactions and Their Effect on Productivity: A Case Study on a Product-Design Organization

A new methodology for assessing managers’ face-to-face (F-to-F) interactions in a hierarchical organization is proposed, and its effect on productivity was tested. On the basis of the proposed methodology, the centrality of F-to-F interactions across hierarchical layers in an organization is calculated. Unlike the traditional survey method, the F-to-F interaction is automatically captured from socio-metric sensors. An empirical test at two product-design organizations demonstrated that the high-productivity organization has the proposed F-to-F centrality in the middle layer, whereas the low-productivity organization has the centrality in the top layer. By clarifying the whole KM process of the target organizations through document update histories, field observations, and interviews, it was found that the autonomous task execution in the lower layers and the future strategy planning in the top layers are the underlying behavioral cause producing F-to-F centrality in the middle layer. The proposed methodology is thus a suitable index for assessing managers’ behaviors that increase productivity and sustainability.