Body weight is the single most important biometric in livestock management. It determines how much feed an animal needs, whether it is growing healthily, and, critically, how much medicine it should be given. Yet on smallholder farms across much of the developing world, weighing cattle remains a logistical nightmare. Platform scales are expensive and immobile, and herding a 300-kilogram animal onto one is stressful for both beast and farmer. The traditional alternative, estimating weight from a tape measure wrapped around the animal’s heart girth, relies on century-old formulas that carry substantial error.

Computer vision has promised to change this for years, but most existing deep learning models present a paradox. The most accurate networks, such as ResNet50 or VGG16, contain tens of millions of parameters and require more memory and processing power than a low-cost phone can spare. They either run painfully slowly on the device or must ship images to a cloud server, which is useless in rural areas with no reliable connectivity. The team behind HEART-Net set out to break this trade-off, hypothesizing that a carefully designed lightweight network fused with physical measurements could match heavyweight accuracy while fitting under one megabyte and running in under 100 milliseconds.

To build their dataset, the researchers photographed 30 Pabna cattle over multiple days and sessions, capturing 2,000 images per animal under deliberately varied lighting, backgrounds, and postures, for a total of 60,000 frames. Alongside each image they recorded the animal’s true weight on a certified electronic scale, measured before morning feeding to minimize rumen-fill variance, plus three tape-measured biometrics: withers height, body length, and heart girth. Crucially, the data splits were organized by individual animal rather than by image, so the five test cattle had never been seen by the model during training. This prevents the network from cheating by memorizing the coat patterns of animals it has already met.

HEART-Net’s architecture is a study in compression. Its visual backbone uses inverted residual blocks, a narrow-wide-narrow bottleneck design in which cheap depthwise convolutions handle spatial filtering while pointwise convolutions expand and project features. A spatial attention module then generates a mask that highlights anatomically relevant regions, such as the contours of the heart girth, while suppressing background clutter. A stochastic depth regularizer randomly drops entire residual branches during training, discouraging the model from memorizing individual animals. The visual features are ultimately condensed into a compact latent vector through global average pooling.

The most distinctive element is the hybrid fusion layer. Rather than trusting the neural network alone, HEART-Net simultaneously computes a classical weight estimate using Schaeffer’s Livestock Formula, a deterministic equation based on heart girth squared times body length. Two learnable scalar weights, constrained by a softmax function, dynamically balance the neural prediction against this physical anchor. During inference, a dynamic trust factor monitors the variance of the visual features; when the camera image is noisy or ambiguous, the system automatically leans more heavily on the tape-measure physics. A confidence score then grades each estimate as precise, nominal, or requiring human review.

Benchmarked against seven standard backbones on identical data and deployment targets, HEART-Net achieved a mean absolute error of 7.52 kilograms, an R-squared of 0.979, and a concordance correlation coefficient of 0.988 against the electronic scale, with a mean bias of just 0.15 kilograms, the lowest systematic error of any model tested. Cluster bootstrap hypothesis testing with 1,000 resamples showed HEART-Net was statistically indistinguishable in accuracy from EfficientNetB0, EfficientNetV2B0, MobileNetV3-Large, and VGG16, and significantly better than MobileNetV2. Only ResNet50 and MobileNetV3-Small beat it on individual metrics, but ResNet50 required 45 megabytes and 159 milliseconds per inference, failing the edge deployment criteria entirely.

The deployment pipeline is as innovative as the model itself. The team converted the trained network into a Float16-quantized TensorFlow.js artifact and embedded it in a Progressive Web Application called Smart-Herbo, built with React and TypeScript. All inference runs locally in the browser via the WebGL backend, meaning no images ever leave the device, a privacy feature enforced by identifying animals only through local cryptographic hashing. Service workers store the model in device storage for full offline operation. An onboard object detector gates the camera, capturing frames only when a bovine subject is detected with confidence above 0.60, preventing wasted computation on empty paddocks.

The final step turns weight into action. The estimated mass feeds into a dosing module grounded in Kleiber’s Law of metabolic scaling, which holds that metabolic requirements scale with body weight raised to the three-quarters power rather than linearly. The app computes weight-proportional doses of plantain herb, a phytogenic supplement whose iridoid glycosides and acteosides have been shown to improve antioxidant profiles and daily weight gain in ruminants. Linear dosing, the researchers note, systematically under-supplements calves and over-supplements mature animals; allometric scaling corrects this drift automatically.

In a field pilot with 40 stakeholders, including 20 smallholder farmers and 20 agricultural extension workers in the Mymensingh region, the system earned a combined System Usability Scale score of 82.25, well above the industry average of 68 and within the excellent category. Extension workers scored slightly higher than farmers, a gap the authors attribute to greater prior exposure to digital tools rather than any design flaw. The team is careful to frame the work as a lab-to-field proof of concept: with only 30 animals from a single breed at one facility, multi-center validation across breeds and uncontrolled environments remains the essential next step. Future iterations will incorporate depth sensors for automated biometric capture and RFID identification for longitudinal herd management, potentially turning a 0.35-megabyte file into a portable veterinary clinic for the world’s smallholders.

Subject of Research: Ultra-lightweight multimodal deep learning for on-device cattle live-weight estimation and precision phytogenic dosing

Article Title: HEART-Net: An ultra-lightweight multimodal neural network for on-device cattle live-weight estimation and precision phytogenic dosing

Article References: Shuvo, A. A., Hasan, S., Anjum, A., Shahed, A., & Al-Mamun, M. (2026). HEART-Net: An ultra-lightweight multimodal neural network for on-device cattle live-weight estimation and precision phytogenic dosing. Smart Agricultural Technology, 15, Article 102587. https://doi.org/10.1016/j.atech.2026.102587

Image Credits: AI Generated

DOI: 10.1016/j.atech.2026.102587

Keywords: HEART-Net, precision livestock farming, cattle weight estimation, edge AI, multimodal neural network, Kleiber's Law, phytogenic dosing, TensorFlow.js, Pabna cattle, System Usability Scale, offline inference, spatial attention

The platform, known as MoDeRa-Ts, short for Decision Support Model for Enhancing Community Resilience in Tsunami-Prone Cities, was developed by Paula Villagra-Islas of the Universidad Austral de Chile and her collaborators, including Cristian Olivares-Rodriguez and Rafael Aránguiz. Its purpose is ambitious: to simulate community resilience across multiple dimensions—physical, social, institutional, and economic—under different tsunami inundation scenarios, and to help urban planners and municipal policymakers move from abstract risk maps to actionable strategies. The research team deliberately set out to answer a question that plagues the rapidly growing field of resilience-assessment tools: do these digital platforms actually work for the people expected to use them?

The literature suggests many do not. Over the past decade, dozens of indices, dashboards, and geographic information system tools have been proposed for measuring community disaster resilience, from composite indicator frameworks to co-created GIS dashboards. Reviews of these tools repeatedly flag the same weakness: a lack of validation with end users. Tools are often built by researchers, demonstrated at conferences, and then quietly abandoned because planners find them confusing, irrelevant, or disconnected from the practical constraints of municipal budgeting and land-use regulation. Villagra-Islas and her colleagues argue that without usability and utility testing, even the most technically elegant simulation platform risks becoming a digital orphan.

To test MoDeRa-Ts under realistic conditions, the researchers organized focus groups with 72 municipal officials drawn from nine representative coastal cities across Chile. These were not students or volunteer panels; they were the professionals responsible for planning, emergency management, and community development in towns where a major tsunami could strike within minutes of a megathrust earthquake. Participants worked with the platform in a controlled environment, completing structured activities that asked them to simulate resilience scenarios, evaluate the tool itself, and explore whether its outputs could be transformed into concrete planning strategies for their own municipalities.

The evaluation followed established, quantitative benchmarks. Usability was measured with the System Usability Scale, a widely used ten-item instrument scored from 0 to 100, in which scores of 68 or higher indicate acceptable usability. MoDeRa-Ts achieved a mean score of 69 out of 100—just above the acceptance threshold. Officials found the platform usable, but they consistently identified the need for a simpler interface, suggesting that the tool’s analytical depth came at some cost in navigability. The researchers treat this result not as a failure but as exactly the kind of actionable feedback that validation exercises are meant to produce: the science inside the platform works, but the packaging needs refinement before broad deployment.

Utility, by contrast, scored strikingly higher. Using the Evaluation Framework for Learning Analytics, a four-level instrument in which items are rated on a 1-to-10 scale and normalized scores above 70 indicate acceptability, MoDeRa-Ts received ratings ranging from 81 to 86 out of 100. Participants reported that the platform effectively helped them understand the information presented, reflect on the multidimensional nature of their communities’ resilience, and identify potential interventions. In other words, the platform did more than display data—it changed how officials thought about vulnerability in their cities, prompting them to consider social and institutional dimensions alongside the physical footprint of tsunami inundation.

The most consequential result emerged from that reflection. Through their interaction with the simulations, the 72 participants collectively identified 45 distinct planning strategies for strengthening tsunami resilience in Chilean coastal cities. The research team organized these strategies into ten Resilient Strategic Planning Themes, covering areas such as evacuation infrastructure, land-use controls in inundation zones, critical facility protection, and community preparedness. This is the step where most simulation tools stall: they can model scenarios elegantly, but converting model output into a portfolio of place-specific interventions requires domain knowledge, local context, and deliberation. The focus-group design appears to have supplied all three, turning the platform into a catalyst for genuine planning dialogue rather than a passive display.

The methodological rigor of the study deserves attention in its own right. Quantitative survey data were analyzed in SPSS, while qualitative responses were coded in Atlas.ti, allowing the team to combine statistical benchmarks with rich thematic analysis. The mixed-methods approach, the authors argue, is essential for evaluating emerging decision-support tools: a high usability score alone would say nothing about whether a tool is useful, and strong perceived utility would mean little if the interface frustrated every user who touched it. By measuring both dimensions with validated instruments, the study offers a template that other developers of resilience platforms—whether for floods, earthquakes, or wildfires—could readily adopt.

The stakes in Chile could hardly be higher. The country’s history is punctuated by catastrophic tsunamis, including the 1960 Valdivia event, the largest earthquake ever recorded, and the 2010 Maule earthquake and tsunami that killed hundreds. Recent research by the same team and collaborators has produced a new generation of probabilistic tsunami inundation maps for Chilean cities, and national agencies have invested in platforms for seismic and evacuation analysis. MoDeRa-Ts is designed to sit downstream of such hazard science, integrating inundation scenarios with resilience indicators so that a planner in a mid-sized port town can see not only how deep the water might run, but how the social fabric, economy, and institutions of the community would absorb and recover from the shock.

What happens next will determine whether the platform moves from validated research to national practice. The findings suggest a clear roadmap: simplify the interface while preserving the analytical engine, embed the tool within the planning workflows of Chile’s national disaster-prevention service and municipal governments, and extend the validation approach to more cities and user groups. If that transition succeeds, the study’s broader lesson will resonate far beyond Chile. In an era when coastal urbanization is accelerating worldwide and climate-driven hazards are intensifying, the bottleneck in disaster resilience is often not the science of simulation but the human science of adoption. By submitting their platform to skeptical scrutiny from the officials who matter most, the researchers have shown how decision-support technology can earn its way out of the laboratory and into the rooms where city futures are decided.

Subject of Research: Validation of a decision-support platform for tsunami-resilient coastal city planning

Article Title: From simulation to urban action: evaluating a decision-support platform for tsunami-resilient coastal cities

Article References: Villagra-Islas, P., Olivares-Rodriguez, C., & Aránguiz, R. (2026). From simulation to urban action: evaluating a decision-support platform for tsunami-resilient coastal cities. Natural Hazards, 122(19), Article 642. https://doi.org/10.1007/s11069-026-08410-4

Image Credits: AI Generated

DOI: 10.1007/s11069-026-08410-4

Keywords: tsunami, community resilience, decision support, Chile, coastal cities, urban planning, usability, System Usability Scale, disaster risk reduction, simulation, urban, action

The research, published open access in the Journal of Ambient Intelligence and Humanized Computing, addresses a gap that has grown as extended reality applications increasingly call on conversational agents for real-time guidance. Large language models have transformed what spoken assistants can do, replacing rigid dialogue trees with flexible, open-ended exchange. But in immersive, task-oriented environments, an agent must satisfy demands that go well beyond answering correctly: it must stay grounded in the task and the surrounding scene, respond within the tight timing of natural turn-taking, and offer help without breaking the user’s sense of presence. Menus, panels and controller commands pull attention away from the hands-on work; speech promises a more direct channel, particularly when assistance is needed mid-action rather than before or after it.

Whether an assistant should also read emotion from speech has remained an open question. Human voices carry information far beyond their linguistic content, and acoustic-prosodic features such as pitch, intensity, rhythm and pausing patterns offer partial evidence about a speaker’s affective state. In principle, an agent that detects frustration, hesitation or elevated effort could modulate its tone, phrasing and level of detail to better match the user’s needs. Previous work has examined conversational agents in extended reality, LLM-based dialogue and affect-aware systems largely in isolation or in pairs, but fully integrated evaluations combining spoken dialogue, language-model generation and real-time prosody-based adaptation in task-oriented immersive settings have been rare, and the empirical consequences of such adaptation for both experience and task execution were unclear.

To test the idea, the Salerno team designed a modular client-server system built around three layers. The client, developed in Unity 6 and running on standalone Meta Quest-class headsets, handles rendering, speech acquisition through the Meta Voice SDK, transcription via Wit.ai, gesture-based interaction through Meta’s hand-tracking SDKs, and voice playback through Meta Text-to-Speech. The backend, implemented as Python micro-services, hosts the computationally heavy work: a Dialog Orchestrator that queries GPT-4o-mini using the transcription and the retained dialogue history, and a speech emotion recognition model based on Whisper Large V3 that has been fine-tuned for emotion classification. Communication between the layers relies on JSON messages and streamed audio, with asynchronous exchanges deliberately chosen to avoid blocking operations and preserve conversational continuity.

The architectural elegance lies in running semantic and affective processing in parallel, so that emotional inference never delays a response. Raw audio is accumulated until roughly twenty-five seconds of speech are available, and the resulting affective estimate, complete with a confidence score, is stored in a short-lived memory valid for up to ninety seconds. When the orchestrator processes a dialogue request, it retrieves the most recent valid estimate if one exists; if not, the reply is generated without affective conditioning at all. Crucially, the emotional descriptor serves only as an additional conditioning signal. It shapes the wording, interpersonal tone, reassurance, response length and explanatory detail of the language model’s output, while leaving the procedural facts, the task objective, the agent’s voice and even its visual behavior untouched, so that affective conditioning is the only difference between the two experimental configurations.

The agent itself appears as a deliberately non-anthropomorphic symbolic sphere anchored in the workspace, whose brightness and surrounding animation signal whether it is idle, listening or speaking. Prior research on embodied agents suggests that less humanlike representations can strike a better balance between recognizability, expressiveness and comfort, especially when the system is not meant to emulate a person. Participants, all university students with little prior exposure to immersive technology and almost no laboratory experience, wore a Meta Quest 3 headset and carried out a nine-step chemistry procedure: placing a flask on a stand, measuring and transferring resorcinol, adding ethanol, heating the mixture, preparing a nitrating mixture from sulfuric and nitric acid, and observing the final color change. The chemistry framing was chosen not to study chemistry education but because such a procedure demands the coordination of physical manipulation, sequential decision making, spatial attention and continuous spoken dialogue that characterizes procedural assistance scenarios generally.

The results revealed a striking trade-off. On the System Usability Scale, the adaptive condition scored an average of 88.6 against 81.4 for the non-adaptive one, a statistically significant difference with a large effect size, and both ratings fall within what standardized guidelines describe as the excellent range. Yet participants guided by the empathetic agent took substantially longer to finish, averaging 693 seconds against 503 seconds, and engaged in more conversational turns, averaging 20.3 against 16.3, both differences statistically significant with large effects. Overall workload, measured with the NASA Task Load Index, showed no significant difference between conditions, though the subscales told a subtler story: the adaptive group reported lower physical and temporal demand but higher frustration, suggesting that the emotional adaptation softened the felt pressure of the task even as it lengthened it, and occasionally irritated users when responses seemed more elaborate than the moment required.

The qualitative interviews added texture to the numbers. Participants in the adaptive group frequently described the agent as more human, friendlier and more attentive, with remarks that the interaction felt natural, like dealing with someone trying to help rather than a device issuing commands, and that the agent’s manner made the procedure less stressful during its most complex phases. Others found the empathy excessive for a short task, noting that the agent sometimes explained too much or offered comfort when none was needed. The non-adaptive group, by contrast, described the interaction as simple, clear and direct, and offered notably fewer spontaneous comments, which the authors suggest may itself reflect lower engagement with an assistant perceived mainly as a functional tool.

The researchers are careful about interpretation. The longer completion times and extra turns cannot, on their own, distinguish productive support from unnecessary verbosity, and the authors argue the pattern is best read as a genuine trade-off between concise execution and a richer conversational experience, one whose desirability depends on context: extra dialogue may be an asset in education and training but a liability in time-critical procedures. They recommend treating affect-aware adaptation as a context-dependent design strategy rather than a default upgrade, triggering it selectively during hesitation, repeated clarification requests or errors, and regulating not just emotional tone but response length and detail. Limitations include the student-only sample, the single procedural domain, and reliance on vocal prosody alone; future work should explore multimodal affect recognition combining gestures, gaze, task progress and physiological signals, while addressing the privacy and transparency questions that such sensing inevitably raises. What the study establishes is that emotional attunement measurably reshapes how people experience machine guidance in immersive environments, making the interaction feel more supportive at the price of speed, and giving designers an evidence-based lever for deciding when that price is worth paying.

Subject of Research: Affect-aware conversational adaptation using LLM-driven dialogue and prosody-based emotion recognition in mixed-reality procedural tasks.

Article Title: Affect-aware conversational adaptation in mixed reality procedural tasks

Article References: Cantone, A. A., Ercolino, M., Sebillo, M., & Vitiello, G. (2026). Affect-aware conversational adaptation in mixed reality procedural tasks. Journal of Ambient Intelligence and Humanized Computing. https://doi.org/10.1007/s12652-026-05125-z

Image Credits: AI Generated

DOI: 10.1007/s12652-026-05125-z

Keywords: mixed reality, conversational agent, large language model, affect-aware adaptation, speech emotion recognition, extended reality, GPT-4o-mini, human-computer interaction, procedural guidance, System Usability Scale, vocal prosody, immersive training