Connect with us

Tech

Interview: Differentiating with AI in pet care | Computer Weekly

Published

on

Interview: Differentiating with AI in pet care | Computer Weekly


Over the past year, Kate Balingit has been leading the digital health initiative at Mars Nutrition, reporting to the company’s pet care chief information officer, where she is focused on commercialising and deploying artificial intelligence (AI) through the Mars pet nutrition brands. These include well-known pet foods brands such as Pedigreee, Iams, Royal Canine, Sheba and Whiskas.

“Even though we’re building tech products, Mars is a non-tech company,” says Balingit, whose official job title is Mars Petcare head of digital innovation. “We kind of abide by the same standards of scientific credibility and scientific rigour that apply to our primary business of food.”

A former Googler, who was also involved in Waze, Balingit joined Mars Petcare in 2022 to head up Whistle, the “FitBit for dogs” company Mars acquired in 2016 (see Career at Google) .

She says Mars Petcare has made a large commitment to digitising the pet care business. This includes everything from upskilling staff to digitising factories and its supply chain, as well as elevating the e-commerce experiences. Digitisation also covers emerging technologies such as using agentic AI for automating workflows and mining digital health data.

On the AI front, rather than rely on existing large language models (LLMs), she says the business is focused on building the computer vision algorithms itself: “We’re building image classifiers to detect signs of emerging health conditions and enterprise software components that enable us to create user experiences that can safely live on our brand digital properties. It comes down to differentiated assets – our proprietary data sets bootstrap an image database and then we work with vets to label the images and train the algorithm.”

She says these algorithms go through the same kind of scientific governance rigor as the food part of the business. “We do have to be able to say where we sourced our data. We’re also very explicit about publishing how we train the models.” This, she says, is a differentiator. “You don’t get a free pass just because you’re working with algorithms. At a non-tech company, you have to abide by the same quality standards that apply to the entire business.”

Among the challenges the company aims to address is how to build products and digital experiences that meet the unique needs of individual brands, individual business units and offers a unique differentiator. A lot of the work involves its data architecture for structuring all of the data that the company collects from pet parents who use the apps and applications the company develops.

“We’re working with emerging technologies like computer vision and trying to build products with a platform approach to enable us to repurpose these assets in different types of applications,” she says. “My team takes a very component-based approach. I don’t see us building products. Instead, we are building a series of capabilities.”

Digitising pet care

There are around 200 people working in the digital transformation organisation at Mars Petcare. Balingit’s role involves orchestrating initiatives across three core functions: science, data science and software engineering.

“The digital health initiative starts with science; we’re building scientific instruments,” she says. These algorithms are capable of detecting the emerging presence of health conditions in dogs. “I start by partnering with the global R&D [research and development] science function, which includes specialists in oral health, skin health, gut health and healthy ageing.”

The team put together a specification for the product, such as deciding on the symptoms of a health condition that the software and AI it produces will be able to detect. The data science team is used to build the algorithm to detect the health condition.

“In the case of a canine dental check, we’re detecting plaque, tartar and gum irritation. I work with our data science team to build the algorithm – we have to acquire the training data and we have to label it, then we build the computer vision models using Azure developer tools.”

The algorithm is made available via an application programming interface (API). Balingit then works with the software engineering team on the actual product experience. “It’s a truly cross-functional effort,” she says.

The software not only needs to meet the high standards associated with the brand, but a high bar is also set for the enterprise architecture, data security and data privacy. With these high standards, Balingit says: “Data science and software engineering can do something really special, which is to scale scientific understanding and put these capabilities into the hands of pet parents around the world through our biggest brands.”

Greenies is a recent example of one of the brands with an AI tool. “Our use of AI in the Greenies Canine Dental Check tool started with a pet parent insight. We know that 80% of dogs have signs of periodontal disease by the age of three, but 72% of pet parents think that their dog’s oral health is fine,” she says.

The team wanted to address this awareness gap among pet owners using AI to, as Balingit puts it, “make the invisible visible and help people to understand that their dog is experiencing an oral health issue.”

“We’re very explicit about publishing how we train the models. You don’t get a free pass just because you’re working with algorithms”

Kate Balingit, Mars Petcare

The Greenies Canine Dental Check required a computer vision algorithm trained on more than 50,000 images of dogs. “We built an algorithm that was capable of taking a smartphone image to understand if the photograph is of a dog and, if it is, if it’s showing the dog’s mouth and its teeth are visible.” The algorithm then needs to analyse the image to determine whether the tooth has visual signs of oral disease. 

When asked about the success in capturing teeth in a pet dog’s mouth, she says: “We always encourage caution. But when I’ve looked at the data, the average user captures about 10.2 teeth in the photo itself.” So, while it may seem a major undertaking for pet owners to attempt taking smartphone photos of their dog’s mouth with visible teeth, in Balingit’s experience, pet parents are “very capable”.

Another consideration is the level of accuracy. Balingit says: “No algorithm is going to be 100% accurate. A human is not 100% accurate. What’s really important is that we are not building a diagnostic device. Our goal was to build a health-screening instrument that could find visual indicators of an emerging disease.” As such, the level of accuracy it can achieve of 97% is good enough.

An approach to business AI

As Balingit notes: “AI is just top of mind for everybody right now.” Like many businesses deploying AI applications, she points out that the past two years have been “a whirlwind”, which means companies such as Mars Petcare need to figure out what they should be doing with AI.

“It’s important to be intentional about what we’re doing, and the key question for me is, ‘What do we at Mars Petcare have that an AI company in Silicon Valley doesn’t have? What are our unique assets and how do we build an AI innovation agenda on top of them?’”

Looking to the future and advances in digital technologies, Balingit believes the world of internet of things (IoT) sensors and AI offers a tantalising opportunity for the business and pet owners alike. While people talking to their pets like Dr Dolittle may seem a bit far-fetched, she says: “Our pets do talk to us with their movements, their facial expressions.” Inevitably, many pet owners may miss these subtle signs, but AI could offer a way to spot these.

Ballingit sees an opportunity to use sensor data to help quantify animal behaviour and then apply AI to translate the sensor data into something humans can understand. In a world where digital technologies have made people ever-more disconnected from the real world, tech innovation may one day offer a way for pet parents to have a closer relationship with their furry friends.



Source link

Continue Reading
Click to comment

Leave a Reply

Your email address will not be published. Required fields are marked *

Tech

Air conditioning isn’t the only answer

Published

on

Air conditioning isn’t the only answer


Credit: Pixabay/CC0 Public Domain

I recently returned from visiting family in America and was struck by how hot I felt back home in London, despite the temperatures being lower. Partly, this was down to humidity: London is sticky in summer, while Utah, where my uncle lives, is very dry.

But it’s also down to the buildings. My brick house absorbs and retains heat while every building I went to in America was either well ventilated or had air conditioning blasting away.

That contrast got me thinking: as the UK warms, can it keep its homes and workplaces comfortable without relying solely on air-con?

Jesus Lizana, Nicole Miranda and Radhika Khosla at the University of Oxford say that northern Europe is dangerously unprepared for the heat of the near future.

They looked at the coming demand for cooling using the concept of “cooling degree days,” which essentially assesses how often people will need to take extra measures, like switching the on, to keep themselves cool.

They found countries like Nigeria and Chad will see the biggest absolute rise in cooling degree days. “A clear indication that Africa is shouldering the burden of a problem it did not create,” they note.

But they also found that countries in northern latitudes will face the greatest relative increase in uncomfortably hot days.

“Of the top ten countries with the most significant relative change in cooling degree days as global warming exceeds 1.5°C and reaches 2°C, eight are located in northern Europe.”

It gets worse. “Buildings in the northern hemisphere,” they write, “are primarily designed to withstand cold seasons by maximizing solar gains and minimizing ventilation—like greenhouses.”

The solution seems obvious: let’s all get air-con.

Coal-powered air-con?

But Mehri Khosravi says it isn’t that simple. An energy researcher at the University of East London, she warns that:

“Cooling requires huge amounts of energy at the exact moments when demand is already high. In 2022 and 2023, the UK had to briefly restart a coal power plant to keep the lights—and the air conditioners—on.”

Khosravi says the UK and similar countries should instead focus on reducing demand for cooling.

In winter, she says, we rightly focus on better insulation to reduce heating demand, as “it’s a lot harder to warm a house than it is to stop heat escaping in the first place.”

So how do we stop a northern European brick house from heating up in the first place?

Khosravi suggests we look to southern Europe for inspiration, where 35°C summers were common long before climate change. Her suggestions include shading and shutters to block sunlight before it enters a building, natural ventilation to let heat escape in cooler hours, and reflective or light-colored buildings that reflect sunlight.

It’s hard to imagine Scarborough being turned into Santorini any time soon. But while we wait to adapt our buildings for the new normal, Khosravi says we should adapt our behavior too.

In Spain, the hottest hours are for siestas. Outdoor activities are paused, and people are more active in the mornings and evenings. Culturally, they understand that keeping curtains closed during the day and opening windows at night can prevent homes from overheating.

In the UK, heat is still culturally framed as “good weather”. Sunny weekends trigger beach trips, barbecues and more outdoor activity, even when it’s dangerously hot. This mismatch between perception and risk is a major public health challenge.
Smarter cooling

Perhaps there are smarter ways to cool down. Academics in Australia recently published research suggesting a “fan first” approach, even when air-conditioning is installed.

“The approach is simple,” they write: “use electric fans as your first cooling strategy, and only turn on air conditioning when the indoor temperature exceeds 27°C.”

These fans use only a tiny fraction of the electricity used to run air conditioning, but “can make you feel up to 4°C cooler.” In their research, the Australian team increased an office’s air conditioning set-point from 24 to 26.5°C, with supplementary air movement from desk and ceiling fans. This “reduced energy consumption by 32%, without compromising thermal comfort.”

Air conditioning doesn’t have to mean the typical rows of humming white boxes. Heat pumps—already central to Britain’s low-carbon heating plans—can also keep homes cool in summer.

Essentially, they’re able to act like reversible air conditioners: in winter, they draw warmth into a building, and in summer they can run in reverse to push heat out.

Crucially, they do so with far greater efficiency than traditional systems. Theresa Pistochini, an engineer at UC Davis in California, points out that heat pumps can be “anywhere from 200% to 400% efficient,” meaning they move more than twice as much energy (heat) than the energy required to operate them.

Her analysis found that “buying a heat pump today will reduce impact in almost all geographical locations.”

For households, this could mean one appliance that covers both heating and cooling, slashes energy bills, and avoids the climate-damaging lock-in of conventional air conditioning. For policymakers, heat pumps may offer a way to meet surging cooling demand without blowing the carbon budget.

But heat pumps aren’t a perfect fix. Installation is costly, many older homes will still need upgrades, and there aren’t enough trained engineers. They’ll need further support if they’re to become a mainstream alternative to air-con.

Nonetheless, together with simple measures like fans and shutters, heat pumps point to a smarter approach to cooling. And it could be made even more sustainable if paired with clean energy from rooftop solar.

Homes equipped with can generate electricity during the hottest parts of the day—exactly when air conditioners or heat pumps are working hardest.

Tom Rogers and colleagues at Nottingham Trent University say solar will play a “pivotal role” in “addressing summer cooling demand and enhancing climate resilience.” They analyzed satellite images to estimate that rooftop solar could provide “nearly one third” of the city’s electricity demand.

The UK is warming, and staying comfortable in hotter summers is a must. But there’s more than one way to cool down. Simple measures like fans, efficient and rooftop solar—combined with smarter building design and passive —could keep homes safe, energy use low and emissions in check.

Provided by
The Conversation


This article is republished from The Conversation under a Creative Commons license. Read the original article.The Conversation

Citation:
Air conditioning isn’t the only answer (2025, August 28)
retrieved 28 August 2025
from https://techxplore.com/news/2025-08-air-conditioning-isnt.html

This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no
part may be reproduced without the written permission. The content is provided for information purposes only.





Source link

Continue Reading

Tech

Minimal 3D model reveals fundamental mechanisms behind toughening of soft–hard composites

Published

on

Minimal 3D model reveals fundamental mechanisms behind toughening of soft–hard composites


Though relatively simple compared to previously used models, the proposed soft–hard composite (SH-com) framework developed in the study accurately reflects well-known physical phenomena observed in material systems. This image depicts the failure of a notched block for different combinations of soft and hard building blocks. Credit: Prof. Katsuhiko Sato from the University of Toyama, Japan Source Link: https://doi.org/10.1073/pnas.2506071122

Engineers have long grappled with a fundamental challenge: creating materials that are both strong and tough enough to resist deformation and prevent fractures. These two properties typically exist in opposition, as materials that excel in one area often fail in the other.

Nature, however, has elegantly solved this trade-off in like bone, teeth, and nacre, which strategically combine soft and hard components in multi-layered architectures. These blueprints have inspired scientists to develop artificial soft–hard composites—from advanced dual-phase steels to specialized gels and reinforced rubbers—that demonstrate performance exceeding that of their individual components.

While artificial soft–hard composites have shown impressive performance in and , the fundamental mechanisms behind their enhanced properties remain largely unclear. The inherent complexity of these materials, encompassing nonlinear behaviors, intricate internal structures, and multi-scale interactions, has made it difficult to isolate the essential design principles.

Specifically, scientists have struggled to understand how these materials transition from brittle-to-ductile (BTD) fracture behavior, and what the minimum requirements are for constituent components to achieve this toughening effect.

In this vein, a research team including Dr. Fucheng Tian and Professor Jian Ping Gong from the Faculty of Advanced Life Science, Hokkaido University, Japan, as well as Specially Appointed Professor Katsuhiko Sato from the Program of Mathematics and Informatics, University of Toyama, Japan, recently undertook a study to tackle this complex problem.

In their pioneering work published in the journal Proceedings of the National Academy of Sciences, the researchers introduce a minimal three-dimensional soft–hard composite (SH-com) framework. By eliminating complicated nonlinear effects and intricate network structures, their model enabled them to focus on the core underlying principles governing the toughening effect.







Evolution of crack patterns and damage morphologies in the pure hard system (ϕs = 0). Damaged hard elements are highlighted in orange. Credit: Proceedings of the National Academy of Sciences (2025). DOI: 10.1073/pnas.2506071122

The SH-com model uses randomly distributed linear-elastic soft and hard elements, each characterized by its elastic stiffness and the energy required for failure. Despite its simplicity, this model successfully reproduced several hallmark behaviors of tough composite materials, including mechanical hysteresis (the Mullins effect), sacrificial bond-driven toughening, and the critical BTD transition fracture behavior. Through systematic testing of different compositions, the team discovered that the BTD transition occurs when the soft and hard phases reach a specific mechanical equilibrium.

Moreover, they found that optimal toughening occurs at a specific ratio of soft to hard components, governed by a universal scaling relationship linked to the differences in fracture toughness between components. When an optimal composition is achieved, the composite can exceed the toughness of its individual constituents.

“Though the SH-com model is anchored in the fundamental linear-elastic regime, the outcomes exhibit compelling consistency with the experimental findings from nonlinear soft–hard composite materials. This consistency emphasizes the fundamental principles underlying the toughening mechanisms in general soft–hard composite materials,” remarks Dr. Fucheng.

Based on these insights, the team developed a “toughening phase diagram,” which serves as a practical guide illustrating the optimal combinations of stiffness and toughness between components to achieve superior material performance. Notably, the simplicity and universality of their model suggest that these principles can be applied broadly.

“Our study reveals the fundamental toughening mechanisms of SH-com systems, offering insights for designing tougher materials,” conclude the authors. “In fields such as , the development of tough gels is required, and we expect our study to contribute to those efforts.”

From the development of more resilient components for aerospace and automotive applications to advanced biomaterials for and , this research provides a powerful theoretical foundation for engineering materials that are both strong and tough.

More information:
Fucheng Tian et al, Fundamental toughening landscape in soft–hard composites: Insights from a minimal framework, Proceedings of the National Academy of Sciences (2025). DOI: 10.1073/pnas.2506071122

Citation:
Minimal 3D model reveals fundamental mechanisms behind toughening of soft–hard composites (2025, August 28)
retrieved 28 August 2025
from https://techxplore.com/news/2025-08-minimal-3d-reveals-fundamental-mechanisms.html

This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no
part may be reproduced without the written permission. The content is provided for information purposes only.





Source link

Continue Reading

Tech

Data visualization emerges a key driver of decision-making at organizational and community levels

Published

on

Data visualization emerges a key driver of decision-making at organizational and community levels


Classification of decision-making problem supported by data visualization. Data visualization typically supports organizational-level decision-making, primarily addressing structured problems in which evaluation is feasible. The findings indicate that data visualization is used at the operational level, with an emphasis on collective decision-making by business domain experts. Furthermore, data visualization has proven effective in supporting problems with high interdependency among various decisions. Credit: 2025 IEEE 18th Pacific Visualization Conference (PacificVis) (2025). DOI: 10.1109/PacificVis64226.2025.00033

Data visualization has emerged as a powerful tool for enabling data-driven decision-making across diverse domains, including business, medicine, and scientific research. However, no comprehensive analysis has previously addressed the types of decision-making problems supported by data visualization or how its role has evolved.

Researchers have conducted a systematic review of significant research over the past 16 years, classifying and analyzing the studies within a multidimensional decision-making framework. They determined that data visualization primarily facilitates decision-making at the organizational and community levels. Their study is published as part of the 2025 IEEE 18th Pacific Visualization Conference (PacificVis).

Although earlier efforts primarily addressed “evaluative” decision-making, recent trends indicate increasing support for a broader range of decision-making types, including “constructive” and “cognitive dominance” decision-making. Moreover, the structure of decision-making problems addressed by data visualization has expanded from “largely structured problems” to “semi-structured problems.”

The findings indicate that data visualization increasingly supports advanced decision-making by experts in fields such as business and , particularly concerning semi-structured problems.

The findings of this study clarify the current scope of decision-making support provided by data visualization and offer insights to guide the development of new visualization techniques. They also highlight the need for further research into visualization methods capable of supporting individual-level and unstructured problems.

More information:
Midori Sugihara et al, Contribution of Data Visualization to Decision-Making: A Classification of Data Visualization Research Based on the Characteristics of Decision Problems, 2025 IEEE 18th Pacific Visualization Conference (PacificVis) (2025). DOI: 10.1109/PacificVis64226.2025.00033

Citation:
Data visualization emerges a key driver of decision-making at organizational and community levels (2025, August 28)
retrieved 28 August 2025
from https://techxplore.com/news/2025-08-visualization-emerges-key-driver-decision.html

This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no
part may be reproduced without the written permission. The content is provided for information purposes only.





Source link

Continue Reading

Trending