Keiichi Yasumoto

Florian Hettstedt, Cedric Giese, Tianheng Ling et al.

Sensing surface vibrations promise unobtrusive interaction for smart home systems by enabling gesture recognition on existing everyday surfaces without disturbing living-space design. Existing approaches typically address only parts of the processing chain, such as sensing hardware or offline gesture recognition, rather than providing an end-to-end system from surface-mounted sensors to the evaluation of the prediction model. This paper presents a custom sensor system and a configurable data-to-model pipeline for gesture recognition on a standard office desk. Our hardware enables a low-noise sensing of the vibrations using piezoelectric sensors. Building on a modular signal-processing framework, we model the full chain from continuous recordings through variable pre-processing to a model-ready dataset, and process the resulting data with compact depthwise separable 1D-CNNs. We conduct a joint search over pre-processing and model hyperparameters and identify a configuration with 8,722 parameters that uses band-pass filtering, fixed-length windows, and min-max normalization. On a self-recorded dataset with 15 participants performing six gestures this configuration achieves high accuracies across different data splitting methods, including strong user-independent performance in a leave-one-subject-out cross-validation.

Lucas Maris, Yuki Matsuda, Keiichi Yasumoto

Camera-based person re-identification is a heavily privacy-invading task by design, benefiting from rich visual data to match together person representations across different cameras. This high-dimensional data can then easily be used for other, perhaps less desirable, applications. We here investigate the possibility of protecting such image data against uses outside of the intended re-identification task, and introduce a differential privacy mechanism leveraging both pixelisation and colour quantisation for this purpose. We show its ability to distort images in such a way that adverse task performances are significantly reduced, while retaining high re-identification performances.

Hussein Chouman, Wataru Sasaki, Tomokazu Matsui et al.

Mechanistic interpretability has produced a rich inventory of component-level analyses that characterise what neural-network components encode and how they interact. Their outputs, however, are not easily reusable: selectivity tables, circuit diagrams, and feature lists remain locked in per-study notebooks - non-composable, not queryable in natural language, and not directly actionable for downstream audit or intervention. We study the representation layer that sits between these analyses and downstream use as a bottleneck that can be evaluated independently, and introduce Manifestation Units, a typed tuple protocol (E, S, R, D, G) extended with attention-head primitives (T) for transformer architectures, organising per-component statistics into structured fields populated automatically and queried through hybrid retrieval. Instantiated across generative vision (beta-VAE), discriminative vision (CNN), and language (GPT-2), the protocol supports two findings: typed structure substantially outperforms unstructured baselines on retrieval, and CNN filters retrieved by the schema satisfy causal sufficiency and necessity criteria under matched-budget controls. The schema absorbs attention-head primitives without modification, set-recovers known IOI circuit members under retrieval-budget-matched controls, and reveals an irreducible two-field core (S+R) with remaining fields either redundant or actively interfering. We present this as schema infrastructure for mechanistic interpretability rather than frontier-scale validation.

Hitoshi Shimizu, Hirohiko Suwa, Tomoharu Iwata et al.

Evacuation shelters, which are urgently required during natural disasters, are designed to minimize the burden of evacuation on human survivors. However, the larger the scale of the disaster, the more costly it becomes to operate shelters. When the number of evacuees decreases, the operation costs can be reduced by moving the remaining evacuees to other shelters and closing shelters as quickly as possible. On the other hand, relocation between shelters imposes a huge emotional burden on evacuees. In this study, we formulate the "Evacuation Shelter Scheduling Problem," which allocates evacuees to shelters in such a way to minimize the movement costs of the evacuees and the operation costs of the shelters. Since it is difficult to solve this quadratic programming problem directly, we show its transformation into a 0-1 integer programming problem. In addition, such a formulation struggles to calculate the burden of relocating them from historical data because no payments are actually made. To solve this issue, we propose a method that estimates movement costs based on the numbers of evacuees and shelters during an actual disaster. Simulation experiments with records from the Kobe earthquake (Great Hanshin-Awaji Earthquake) showed that our proposed method reduced operation costs by 33.7 million dollars: 32%.

Shogo Kawanaka, Juliana Miehle, Yuki Matsuda et al.

The collection of spatiotemporal tourism information is important in smart tourism and user-generated contents are perceived as reliable information. Participatory sensing is a useful method for collecting such data, and the active contribution of users is an important aspect for continuous and efficient data collection. This study has focused on the impact of task allocation interface design and individual personality on data collection efficiency and their contribution in gamified participatory sensing for tourism. We have designed two types of interfaces: a map-based with active selection and a chat-based with passive selection. Moreover, different levels of elaborateness and indirectness have been introduced into the chat-based interface. We have employed the Gamification User Types Hexad framework to identify the differences in the contributions and interface preferences of different user types. The results of our tourism experiment with 108 participants show that the map-based interface collects more data, while the chat-based interface collects data for spots with higher information demand. We also found that the contribution to sensing behavior and interface preference differed depending on the individual user type.

Yuki Matsuda, Shogo Kawanaka, Hirohiko Suwa et al.

Rapid proliferation of mobile devices with various sensors have enabled Participatory Mobile Sensing (PMS). Several PMS platforms provide multiple functions for various sensing purposes, but they are suffering from the open issues: limited use of their functions for a specific scenario/case and requiring technical knowledge for organizers. In this paper, we propose a novel PMS platform named ParmoSense for easily and flexibly collecting urban environmental information. To reduce the burden on both organizers and participants, in ParmoSense, we employ two novel features: modularization of functions and scenario-based PMS system description. For modularization, we provide the essential PMS functions as modules which can be easily chosen and combined for sensing in different scenarios. The scenario-based description feature allows organizers to easily and quickly set up a new participatory sensing instance and participants to easily install the corresponding scenario and participate in the sensing. Moreover, ParmoSense provides GUI tools as well for creating and distributing PMS system easily, editing and visualizing collected data quickly. It also provides multiple functions for encouraging participants' motivation for sustainable operation of the system. Through performance comparison with existing PMS platforms, we confirmed ParmoSense shows the best cost-performance in the perspective of the workload for preparing PMS system and varieties of functions. In addition, to evaluate the availability and usability of ParmoSense, we conducted 19 case studies, which have different locations, scales, and purposes, over 4 years with cooperation from ordinary citizens. Through the case studies and the questionnaire survey for participants and organizers, we confirmed that ParmoSense can be easily operated and participated by ordinary citizens including non-technical persons.