Emotion-Aware Smart Home Automation Based on the eBICA Model

Hideyuki Shimonishi; Hiroko Hara; Masaaki Yamauchi; Masayuki Murata; Yiyuan Liang

arxiv: 2512.21589 · v1 · submitted 2025-12-25 · 💻 cs.HC

Emotion-Aware Smart Home Automation Based on the eBICA Model

Masaaki Yamauchi , Yiyuan Liang , Hiroko Hara , Hideyuki Shimonishi , Masayuki Murata This is my paper

Pith reviewed 2026-05-16 19:46 UTC · model grok-4.3

classification 💻 cs.HC

keywords emotion-aware automationsmart homeeBICApsychological safetystate anxietySTAI-Saffective computing

0 comments

The pith

Emotion-aware smart home automation based on eBICA reduces state anxiety after stress events.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper develops an automation system for smart homes that responds to a user's emotional state using the emotional Biologically Inspired Cognitive Architecture, known as eBICA. This framework combines appraisal of situations, bodily responses, and selection of behaviors to adapt the environment, such as by avoiding anxiety triggers. In a controlled experiment with participants in a simulated home, an anxiety-inducing event was followed by comfort automation, leading to a measurable drop in state anxiety scores. The work shows that such emotion-based control can promote feelings of psychological safety in daily living spaces, with potential for tailoring to individual personality traits.

Core claim

The central claim is that an eBICA-guided emotion-aware automation framework, which integrates appraisal, somatic responses, and behavior selection, can effectively reduce state anxiety as measured by STAI-S immediately after introducing avoidance automation in a pseudo-smart-home environment, thereby promoting psychological safety, and that individual characteristics modulate this effect.

What carries the argument

The eBICA model, which integrates appraisal, somatic responses, and behavior selection to guide emotion-aware automation.

If this is right

Emotion-based control can effectively promote psychological safety in smart homes.
Personalized emotion-adaptive automation is possible based on personality and anxiety traits.
eBICA-based emotional control functions effectively in smart home environments.
The approach offers a foundation for next-generation affective home automation systems.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

This approach could extend to other environments like offices or vehicles for emotional adaptation.
Future systems might integrate real-time emotion detection for proactive adjustments.
Individual differences suggest that one-size-fits-all automation may be less effective than personalized ones.

Load-bearing premise

The reduction in anxiety is specifically due to the emotion-aware nature of the automation and the eBICA model rather than any automation or the experimental setting.

What would settle it

A follow-up experiment comparing the eBICA-based automation to a non-emotion-aware automation system in the same pseudo-smart-home setup, measuring if the anxiety reduction is greater with emotion awareness.

Figures

Figures reproduced from arXiv: 2512.21589 by Hideyuki Shimonishi, Hiroko Hara, Masaaki Yamauchi, Masayuki Murata, Yiyuan Liang.

**Figure 1.** Figure 1: Overview of the proposed framework. facial or vocal emotion recognition [6]–[8], the psychological impact of such interventions has rarely been validated. In this study, we propose a home-automation framework that estimates a user’s emotional state from observations obtained in a smart-home environment and dynamically controls appliance behaviors according to that state ( [PITH_FULL_IMAGE:figures/full_fi… view at source ↗

**Figure 2.** Figure 2: Overview of the eBICA model, redrawn by authors based on [9]. [PITH_FULL_IMAGE:figures/full_fig_p002_2.png] view at source ↗

**Figure 3.** Figure 3: Layout of the experimental environment and behaviors during the experiment. Physiological data, including heart rate, are measured using an EEG device and a wristband-type vital sensor. For psychological measures, the Japanese version of the State-Trait Anxiety Inventory, State form (STAI-S) [13], [14], a standard scale for assessing state anxiety, is administered at each measurement point. In addition, d… view at source ↗

**Figure 4.** Figure 4: Transition of STAI-S scores in the main ( [PITH_FULL_IMAGE:figures/full_fig_p004_4.png] view at source ↗

**Figure 5.** Figure 5: Transition of STAI-S scores in the long-duration experiment ( [PITH_FULL_IMAGE:figures/full_fig_p004_5.png] view at source ↗

read the original abstract

Smart home automation that adapts to a user's emotional state can enhance psychological safety in daily living environments. This study proposes an emotion-aware automation framework guided by the emotional Biologically Inspired Cognitive Architecture (eBICA), which integrates appraisal, somatic responses, and behavior selection. We conducted a proof-of-concept experiment in a pseudo-smart-home environment, where participants were exposed to an anxiety-inducing event followed by a comfort-inducing automation. State anxiety (STAI-S) was measured throughout the task sequence. The results showed a significant reduction in STAI-S immediately after introducing the avoidance automation, demonstrating that emotion-based control can effectively promote psychological safety. Furthermore, an analysis of individual characteristics suggested that personality and anxiety-related traits modulate the degree of relief, indicating the potential for personalized emotion-adaptive automation. Overall, this study provides empirical evidence that eBICA-based emotional control can function effectively in smart home environments and offers a foundation for next-generation affective home automation systems.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

The paper shows a quick anxiety drop after eBICA-guided automation in a simulated home, but the within-subject design leaves open whether the model itself drove the effect.

read the letter

This paper's main result is a significant drop in state anxiety right after their eBICA-guided avoidance automation kicks in, but the experiment lacks the controls needed to show that the emotion model is what made the difference. They apply the emotional Biologically Inspired Cognitive Architecture to smart home automation. The setup integrates appraisal, somatic responses, and behavior selection to decide on actions that promote comfort after an anxiety-inducing event. In a pseudo-smart-home test, they track STAI-S scores through the sequence and find an immediate reduction once the automation starts. They also check how personality and anxiety traits influence the amount of relief. That application to a home environment and the inclusion of individual differences are the fresh elements. It gives a practical example of how such a model could work in everyday tech. The design is the weak part. Without a condition that uses non-emotion-aware automation or no automation at all, the anxiety drop could be explained by any environmental change or just time. The abstract does not include sample size or full statistical details, so it's hard to gauge how reliable the finding is. Readers in human-computer interaction or affective computing would get the most from this. It offers a starting point for building emotion-adaptive systems, even if the evidence for the specific benefits is preliminary. I would send it to peer review. The experiment is concrete enough to be worth referee feedback on methods and controls.

Referee Report

2 major / 2 minor

Summary. The paper proposes an emotion-aware smart home automation framework guided by the emotional Biologically Inspired Cognitive Architecture (eBICA), which integrates appraisal, somatic responses, and behavior selection. In a proof-of-concept experiment conducted in a pseudo-smart-home environment, participants were exposed to an anxiety-inducing event followed by comfort-inducing avoidance automation. State anxiety (STAI-S) was measured throughout, showing a significant immediate reduction after the automation. The authors also report that personality and anxiety-related traits modulate the degree of relief, concluding that eBICA-based emotional control can promote psychological safety and providing a foundation for personalized affective home automation.

Significance. If the central claim can be isolated from nonspecific effects, the work would supply preliminary empirical evidence for the deployment of biologically inspired cognitive architectures in real-world smart environments. It would advance affective computing by linking emotional modeling to measurable psychological outcomes and highlighting individual-difference moderators, offering a starting point for next-generation adaptive domestic systems.

major comments (2)

[Experimental Design / Results] The experimental design is a single-arm within-subject pre/post sequence with no yoked control condition (generic automation, random automation, or no automation). This prevents isolation of whether the reported STAI-S reduction is due to the specific appraisal/somatic/behavior-selection components of eBICA rather than expectation effects, relief from any salient change, or passage of time. The central claim that emotion-based control promotes psychological safety therefore rests on an untested attribution. (See abstract and task-sequence description.)
[Results] The abstract states a 'significant reduction' in STAI-S but supplies no sample size, exact statistical test, p-value, effect size, or power information. Without these details it is impossible to evaluate the robustness or replicability of the primary finding.

minor comments (2)

[Abstract / Methods] Specify which personality and anxiety-related traits were measured and the instruments or scales used for their assessment.
[System Description] Provide additional implementation details on how the eBICA components (appraisal, somatic responses, behavior selection) were realized in the automation controller.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback. We address each major comment below, providing honest responses based on the proof-of-concept nature of the study while committing to revisions that strengthen the manuscript without overstating the current evidence.

read point-by-point responses

Referee: [Experimental Design / Results] The experimental design is a single-arm within-subject pre/post sequence with no yoked control condition (generic automation, random automation, or no automation). This prevents isolation of whether the reported STAI-S reduction is due to the specific appraisal/somatic/behavior-selection components of eBICA rather than expectation effects, relief from any salient change, or passage of time. The central claim that emotion-based control promotes psychological safety therefore rests on an untested attribution. (See abstract and task-sequence description.)

Authors: We agree that the single-arm pre/post design limits causal attribution to the specific eBICA mechanisms versus nonspecific factors such as expectation or passage of time. This study was explicitly framed as a proof-of-concept to demonstrate initial feasibility of integrating eBICA appraisal, somatic, and behavior-selection components in a pseudo-smart-home setting. We did not include yoked controls at this stage to keep the protocol focused on establishing the basic automation pipeline. In the revised manuscript, we will expand the limitations and future-work sections to explicitly discuss this design choice, clarify that the observed STAI-S reduction provides preliminary rather than definitive evidence, and outline a planned follow-up with appropriate control conditions (e.g., generic automation and no-automation baselines). revision: partial
Referee: [Results] The abstract states a 'significant reduction' in STAI-S but supplies no sample size, exact statistical test, p-value, effect size, or power information. Without these details it is impossible to evaluate the robustness or replicability of the primary finding.

Authors: We acknowledge that the current abstract is insufficiently self-contained. The full results section reports the sample size, the exact statistical test (paired t-test on STAI-S scores), p-value, and Cohen’s d effect size. We will revise the abstract to include these quantitative details (sample size, test statistic, p-value, effect size) so that the primary finding can be evaluated directly from the abstract. Power information will also be added if not already present in the results. revision: yes

Circularity Check

0 steps flagged

No circularity: empirical experiment reports observed STAI-S changes without derivation loops

full rationale

The paper is a proof-of-concept user study that induces anxiety then applies eBICA-guided automation and measures pre/post STAI-S scores. No equations, fitted parameters, or predictions are presented that reduce by construction to the inputs. The central claim rests on direct experimental observations rather than self-definitional mappings, fitted-input renamings, or load-bearing self-citations. The eBICA model is referenced as an external framework; the reported anxiety reduction is a measured outcome, not a mathematical tautology. Absence of a non-eBICA control arm is a validity concern but does not create circularity in the reported chain.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The claim depends on the established eBICA model and the assumption that the pseudo-smart-home setup validly tests real-world emotional responses.

axioms (1)

domain assumption The eBICA model accurately captures appraisal, somatic responses, and behavior selection in emotional processing.
The framework is guided by eBICA as stated in the abstract.

pith-pipeline@v0.9.0 · 5475 in / 1087 out tokens · 40471 ms · 2026-05-16T19:46:52.121894+00:00 · methodology

discussion (0)

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

IndisputableMonolith/Foundation/Cost/FunctionalEquation.lean washburn_uniqueness_aczel unclear

?

unclear
Relation between the paper passage and the cited Recognition theorem.

E(t+1)=(1-r)E(t)+r(c1A(t)+c2S(t)+c3F(t)); B(a)=-||F-A(a)||; a*=argmax B(a)

What do these tags mean?

matches: The paper's claim is directly supported by a theorem in the formal canon.
supports: The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends: The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses: The paper appears to rely on the theorem as machinery.
contradicts: The paper's claim conflicts with a theorem or certificate in the canon.
unclear: Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

17 extracted references · 17 canonical work pages

[1]

An intelligent human behavior-based reasoning model for service prediction in smart home,

W. Yang, X. Jing, and H. Huang, “An intelligent human behavior-based reasoning model for service prediction in smart home,”IEEE Access, vol. 6, pp. 68 535–68 544, 2018

work page 2018
[2]

Autonomous living building: Adapting to occupant’s behavior,

D. Benhaddou, L. Afogbuom, F. Attia, and M. Anan, “Autonomous living building: Adapting to occupant’s behavior,” inProc. 15th Int. Wireless Commun. & Mobile Comput. Conf., 2019, pp. 1803–1808

work page 2019
[3]

Prototype smart home environment with biofeedback,

A. M. Kalam, M. Azad, and S. J. Chowdhury, “Prototype smart home environment with biofeedback,” inProc. IEEE Region 10 Symp. (TENSYMP), 2020, pp. 449–452

work page 2020
[4]

EmoSe- cure: Enhancing smart home security with fisherface emotion recogni- tion and biometric access control,

P. Ghadekar, M. Ranjan Pradhan, D. Swain, and B. Acharya, “EmoSe- cure: Enhancing smart home security with fisherface emotion recogni- tion and biometric access control,”IEEE Access, vol. 12, pp. 93 133– 93 144, 2024

work page 2024
[5]

iSecureHome: A deep fusion framework for surveillance of smart homes using real-time emotion recognition,

H. Kaushik, T. Kumar, and K. Bhalla, “iSecureHome: A deep fusion framework for surveillance of smart homes using real-time emotion recognition,”Appl. Soft Comput., vol. 122, p. 108788, 2022

work page 2022
[6]

Emotion linked AIoT based cognitive home automation system with sensovisual method,

V . K. Patil, O. Hadawale, V . R. Pawar, and M. Gijre, “Emotion linked AIoT based cognitive home automation system with sensovisual method,” inProc. IEEE Pune Sect. Int. Conf. (PuneCon), 2021, pp. 1–7

work page 2021
[7]

Implementa- tion of an automated smart home control for detecting human emotions via facial detection,

L. T. Boon, M. H. Husin, Z. F. Zaaba, and M. A. Osman, “Implementa- tion of an automated smart home control for detecting human emotions via facial detection,” inProc. 5th Int. Conf. Comput. & Inform. (ICOCI), 2015, pp. 39–45

work page 2015
[8]

Smart home automation using machine learning algorithms,

J. Jaihar, N. Lingayat, P. S. Vijaybhai, G. Venkatesh, and K. P. Upla, “Smart home automation using machine learning algorithms,” inProc. Int. Conf. Emerg. Technol. (INCET), 2020, pp. 1–4

work page 2020
[9]

Socially emotional brain-inspired cognitive archi- tecture framework for artificial intelligence,

A. V . Samsonovich, “Socially emotional brain-inspired cognitive archi- tecture framework for artificial intelligence,”Cogn. Syst. Res., vol. 60, pp. 57–76, 2020

work page 2020
[10]

Emotional BICA for non- player characters: New empirical data,

N. O. Veselov, A. A. Chubarov, M. N. Roshchin, L. M. Marder, S. M. Segal, and A. V . Samsonovich, “Emotional BICA for non- player characters: New empirical data,” inProc 10th Annu. Int. Conf. Biologically Inspired Cogn. Archit., vol. 169, 2020, pp. 412–422

work page 2020
[11]

Virtual pet powered by a socially-emotional BICA,

A. A. Bogatyreva, A. D. Sovkov, S. A. Tikhomirova, A. R. Vinogradova, and A. V . Samsonovich, “Virtual pet powered by a socially-emotional BICA,” inProc. 9th Annu. Int. Conf. Biologically Inspired Cogn. Archit., vol. 145, 2018, pp. 564–571

work page 2018
[12]

Intellectual productivity under task ambient lighting,

H. Ishii et al., “Intellectual productivity under task ambient lighting,” Lighting Res. & Technol., vol. 50, no. 2, pp. 237–252, 2018

work page 2018
[13]

Self–evaluation Questionnaire

C. D. Spielberger, R. L. Gorsuch, and R. E. Lushene,STAI Manual for the State–Trait Anxiety Inventory (“Self–evaluation Questionnaire”). Palo Alto, CA: Consulting Psychologists Press, 1970

work page 1970
[14]

A study of the State–Trait Anxiety Inventory (STAI) and its application to noise stress,

M. Iwamoto et al., “A study of the State–Trait Anxiety Inventory (STAI) and its application to noise stress,”Japanese J. Hygiene, vol. 43, no. 6, pp. 1116–1123, 1989, (in Japanese, with English abstract)

work page 1989
[15]

A very brief measure of the Big-Five personality domains,

S. D. Gosling, P. J. Rentfrow, and W. B. Swann, “A very brief measure of the Big-Five personality domains,”J. Res. Personality, vol. 37, no. 6, pp. 504–528, 2003

work page 2003
[16]

Development, reliability, and validity of the Japanese version of Ten Item Personality Inventory (TIPI-J),

A. Oshio, S. Abe, and P. Cutrone, “Development, reliability, and validity of the Japanese version of Ten Item Personality Inventory (TIPI-J),” Japanese J. Personality, vol. 21, no. 1, pp. 40–52, 2012

work page 2012
[17]

The impact of personality on technology acceptance: A study on smart phone users,

V . ¨Ozbek, U. Alnıac ¸ık, F. Koc, M. E. Akkılıc ¸, and E. Kas ¸e, “The impact of personality on technology acceptance: A study on smart phone users,” Procedia - Social & Behav. Sciences, vol. 150, pp. 541–551, 2014

work page 2014

[1] [1]

An intelligent human behavior-based reasoning model for service prediction in smart home,

W. Yang, X. Jing, and H. Huang, “An intelligent human behavior-based reasoning model for service prediction in smart home,”IEEE Access, vol. 6, pp. 68 535–68 544, 2018

work page 2018

[2] [2]

Autonomous living building: Adapting to occupant’s behavior,

D. Benhaddou, L. Afogbuom, F. Attia, and M. Anan, “Autonomous living building: Adapting to occupant’s behavior,” inProc. 15th Int. Wireless Commun. & Mobile Comput. Conf., 2019, pp. 1803–1808

work page 2019

[3] [3]

Prototype smart home environment with biofeedback,

A. M. Kalam, M. Azad, and S. J. Chowdhury, “Prototype smart home environment with biofeedback,” inProc. IEEE Region 10 Symp. (TENSYMP), 2020, pp. 449–452

work page 2020

[4] [4]

EmoSe- cure: Enhancing smart home security with fisherface emotion recogni- tion and biometric access control,

P. Ghadekar, M. Ranjan Pradhan, D. Swain, and B. Acharya, “EmoSe- cure: Enhancing smart home security with fisherface emotion recogni- tion and biometric access control,”IEEE Access, vol. 12, pp. 93 133– 93 144, 2024

work page 2024

[5] [5]

iSecureHome: A deep fusion framework for surveillance of smart homes using real-time emotion recognition,

H. Kaushik, T. Kumar, and K. Bhalla, “iSecureHome: A deep fusion framework for surveillance of smart homes using real-time emotion recognition,”Appl. Soft Comput., vol. 122, p. 108788, 2022

work page 2022

[6] [6]

Emotion linked AIoT based cognitive home automation system with sensovisual method,

V . K. Patil, O. Hadawale, V . R. Pawar, and M. Gijre, “Emotion linked AIoT based cognitive home automation system with sensovisual method,” inProc. IEEE Pune Sect. Int. Conf. (PuneCon), 2021, pp. 1–7

work page 2021

[7] [7]

Implementa- tion of an automated smart home control for detecting human emotions via facial detection,

L. T. Boon, M. H. Husin, Z. F. Zaaba, and M. A. Osman, “Implementa- tion of an automated smart home control for detecting human emotions via facial detection,” inProc. 5th Int. Conf. Comput. & Inform. (ICOCI), 2015, pp. 39–45

work page 2015

[8] [8]

Smart home automation using machine learning algorithms,

J. Jaihar, N. Lingayat, P. S. Vijaybhai, G. Venkatesh, and K. P. Upla, “Smart home automation using machine learning algorithms,” inProc. Int. Conf. Emerg. Technol. (INCET), 2020, pp. 1–4

work page 2020

[9] [9]

Socially emotional brain-inspired cognitive archi- tecture framework for artificial intelligence,

A. V . Samsonovich, “Socially emotional brain-inspired cognitive archi- tecture framework for artificial intelligence,”Cogn. Syst. Res., vol. 60, pp. 57–76, 2020

work page 2020

[10] [10]

Emotional BICA for non- player characters: New empirical data,

N. O. Veselov, A. A. Chubarov, M. N. Roshchin, L. M. Marder, S. M. Segal, and A. V . Samsonovich, “Emotional BICA for non- player characters: New empirical data,” inProc 10th Annu. Int. Conf. Biologically Inspired Cogn. Archit., vol. 169, 2020, pp. 412–422

work page 2020

[11] [11]

Virtual pet powered by a socially-emotional BICA,

A. A. Bogatyreva, A. D. Sovkov, S. A. Tikhomirova, A. R. Vinogradova, and A. V . Samsonovich, “Virtual pet powered by a socially-emotional BICA,” inProc. 9th Annu. Int. Conf. Biologically Inspired Cogn. Archit., vol. 145, 2018, pp. 564–571

work page 2018

[12] [12]

Intellectual productivity under task ambient lighting,

H. Ishii et al., “Intellectual productivity under task ambient lighting,” Lighting Res. & Technol., vol. 50, no. 2, pp. 237–252, 2018

work page 2018

[13] [13]

Self–evaluation Questionnaire

C. D. Spielberger, R. L. Gorsuch, and R. E. Lushene,STAI Manual for the State–Trait Anxiety Inventory (“Self–evaluation Questionnaire”). Palo Alto, CA: Consulting Psychologists Press, 1970

work page 1970

[14] [14]

A study of the State–Trait Anxiety Inventory (STAI) and its application to noise stress,

M. Iwamoto et al., “A study of the State–Trait Anxiety Inventory (STAI) and its application to noise stress,”Japanese J. Hygiene, vol. 43, no. 6, pp. 1116–1123, 1989, (in Japanese, with English abstract)

work page 1989

[15] [15]

A very brief measure of the Big-Five personality domains,

S. D. Gosling, P. J. Rentfrow, and W. B. Swann, “A very brief measure of the Big-Five personality domains,”J. Res. Personality, vol. 37, no. 6, pp. 504–528, 2003

work page 2003

[16] [16]

Development, reliability, and validity of the Japanese version of Ten Item Personality Inventory (TIPI-J),

A. Oshio, S. Abe, and P. Cutrone, “Development, reliability, and validity of the Japanese version of Ten Item Personality Inventory (TIPI-J),” Japanese J. Personality, vol. 21, no. 1, pp. 40–52, 2012

work page 2012

[17] [17]

The impact of personality on technology acceptance: A study on smart phone users,

V . ¨Ozbek, U. Alnıac ¸ık, F. Koc, M. E. Akkılıc ¸, and E. Kas ¸e, “The impact of personality on technology acceptance: A study on smart phone users,” Procedia - Social & Behav. Sciences, vol. 150, pp. 541–551, 2014

work page 2014