• TDK introduces SensorStageTM software – a complete evaluation platform that simplifies and accelerates SmartMotion® IMU development through advanced visualization and automated workflows
• SensorStage permits seamless evaluation of complex on-chip features, including ML algorithms, sensor fusion, and power optimization, cutting development time and improving system performance
• Designed with a future-proof architecture, SensorStage supports both current and next-generation sensors for applications such as smart glasses, wearables, OIS, and IoT

TDK Corporation (TSE:6762) announces a new comprehensive sensor evaluation tool, InvenSense SensorStage^TM, designed to simplify and accelerate the development workflow for the company’s latest SmartMotion^® IMUs. This all-in-one platform bridges the gap between simple GUIs and custom test benches, offering advanced visual analytics and automated scripting to help engineers move from setup to insight without the traditional bottlenecks of manual configuration. By providing a future-proof architecture that supports existing and upcoming high-performance sensors, SensorStage enables seamless evaluation of complex on-chip algorithms for next-generation applications in OIS, wearables, AR/Smart Glasses, and IoT.

“Inertial sensor development has traditionally required extensive hands-on experience and deep expertise. But SensorStage speeds and simplifies this process with its data analysis platform and prebuilt sensing features,” said Rosa Chow, Software Vice President, InvenSense, a TDK group company. “With SensorStage, customers can more easily tailor workflows to their exact needs, for rapid iteration and optimization, which dramatically accelerates their time-to-market.” 

The SensorStage platform provides a unified environment for evaluating the latest features of TDK’s MEMS IMUs and TMR magnetometers. Paired with SmartMotion development board, sophisticated on-chip features—including Machine Learning (ML) algorithms, the APEX engine for Gyro Assisted Fusion, motion and event detection, and chip-level power consumption—are visualized, allowing for precise calibration and faster time-to-market for complex designs.

SensorStage is currently available for InvenSense SmartMotion IMUs ICM-456xx and ICM-426xx, and will soon be available for additional InvenSense MEMS sensor solutions. Learn more at https://invensense.tdk.com or e-mail inv.sales.us@tdk.com.

• Addresses key scalability barriers and deployment challenges inherent to intelligent edge IoT solutions.   
• Improves scalability by generating large and diverse datasets that accelerate the development of AI solutions for edge applications.  
• Reduces dependency on real data from 80% (market standard) to 10%, enabling accelerated innovation and faster time-to-deployment.

TDK Corporation (TSE:6762) announces advancements in sensor technology that optimize and accelerate the deployment of smart IoT solutions, SensorGPTTM. This technology uses generative AI, signal processing, statistical methods, and simulations to create and manage sensor data at scale. TDK’s SensorGPT will empower both the smart IoT market and the emerging Ambient IoT market segment to overcome key scalability challenges. It streamlines model development and deployment, cutting both time and cost, and significantly enhancing the performance and efficiency of edge AI models and applications.

Data is the bedrock of intelligence in smart edge systems – yet today, data collection consumes more time than building the intelligence it is meant to power. Nearly 80% of AI solution development time is spent on data collection and curation (Forbes). As the demand for edge AI continues to accelerate, projected to become the standard in 2026 (Gartner), data availability has become the primary barrier to scalability. SensorGPT directly addresses this challenge by reducing reliance on real-world data through intelligent sensor data synthesis, cutting data collection efforts from 80% to nearly 10%, and enabling faster, more scalable edge AI development.

Synthesizing sensor data with AI

By using advanced techniques to expand and enhance existing datasets, edge AI model building time that takes months can be reduced to weeks, said Jim Tran, Corporate Officer and General Manager, Americas HQ and Deputy General Manager, Technology & Intellectual Property HQ.
TDK USA Corporation. “By tapping into generative AI modeling, simulation, and more, engineers can use AI to generate additional, high-quality data that reflects real-world conditions — turning data into a scalable resource.”

SensorGPT data synthesis technology advancements:

• Generative AI models: train generative models over limited real-world data to learn underlying patterns and generate high-quality synthetic data that faithfully mimics real-world data.
• Physics-based simulation models: leveraging physics-based and mathematical models to simulate and generate synthetic sensor data.  
• Signal processing methods: employing mathematical and computational techniques to simulate data reflecting the dynamics and characteristics of real sensor outputs.
• Data augmentation techniques: automatically transform existing sensor data into rich, diverse datasets spanning a wide range of conditions and scenarios.
• Assisted annotation: streamline the labeling of training data, increasing its usefulness and quality for model training.

SensorGPT generates 90% similarity between synthetic and real-world sensor data, enabling the use of the synthetically generated data for faster edge AI solution deployment. Once deployed, it drives a virtuous cycle of feedback-driven improvement in which real-world data progressively refines and strengthens synthetic models over time, which in turn leads to more efficiently deployed models.

Differentiation of SensorGPT to existing technologies: 

• Improve scalability by generating large and diverse datasets that quickly help to create AI solutions for edge applications.
• Faster innovation and accelerated development by providing quick access to data for prototyping, testing, and deploying initial models.
• Customizability by providing tools to tailor data to specific sensors, smart IoT applications, and real-world scenarios and conditions they operate in.
• Enabler for edge intelligence intercepting the growing demand for quality data for smart edge AI applications.  

TDK’s new SensorGPT ultimately accelerates prototyping and proof of concepts, enabling orders-of-magnitude dataset size expansion, depending on the application and use case, significantly reducing edge AI model building time from 5+ months down to a few weeks. 

TDK Corporation (TSE: 6762) presents the B82722V6*B040 series of new compact high-voltage, current-compensated ring-core double chokes. Designed primarily for rated DC voltages of up to 1250 V (630 V AC), these compact common-mode chokes (23 x 15.5 x 24 mm) effectively suppress EMI in next-generation applications. These include power converters, industrial motor drives, and switch-mode power supplies that often deploy SiC and GaN power semiconductors and feature elevated DC bus voltages, where insulation coordination and PCB space are critical.

The series covers nominal inductance values ranging from 3.3 mH to 22 mH, with rated currents between 0.85 A and 3.0 A at a rated ambient temperature of +70 °C. Multilayer solid insulation construction and testing with voltages of 3,750 V (line-to-line) ensure robust electrical isolation. Thanks to the special automated winding technique, these chokes feature high resonance frequency characteristics and a typical stray inductance of around 0.6%, helping to suppress symmetrical interference.

The epoxy coating of the ferrite core and the plastic header comply with UL 94 V-0. The design fulfills the latest IEC 60938-2 and IEC/UL 60939-3 safety requirements for EMI chokes and filters. Suitable for wave soldering and offered in a compact vertical design, the B82722V6*B040 series enables engineers to realize 1250 V DC high-voltage architectures without increasing the PCB footprint.

• The filters achieve industry-leading* noise attenuation in the high-frequency range exceeding 5 GHz
• A newly developed low-distortion ferrite material significantly reduces audio distortion by minimizing performance variations in the audio line of small consumer devices
• Reduces attenuation of audio signals with lower resistance than conventional products, achieving a wide dynamic range

TDK Corporation (TSE:6762) has announced its latest noise suppression filters of the MAF0603GWY series. These measure only 0.6 mm x 0.3 mm x 0.3 mm (L x W x H) for use in small consumer devices like smartphones and wearables. Mass production of the new product series is set to begin in April 2026.

Electromagnetic noise radiated from audio lines in smartphones, wearable devices, and the like interferes with the built-in antenna and can reduce the receiver sensitivity. The common countermeasure is chip beads. While effective at suppressing noise, they have the drawback of degrading the audio quality on the audio line, which users may find annoying.

The new MAF0603GWY series of noise suppression filters resolves this drawback by employing a newly developed, proprietary low-distortion ferrite material. It introduces just minimal change to audio-line characteristics and significantly reduces audio distortion, eliminating the sound-quality degradation that occurs when chip beads are used. It provides industry-leading high attenuation in the 5-GHz band (impedance up to 3220 Ω at 5 GHz), effectively suppressing noise. Compared with conventional products, it also features lower resistance to reduce attenuation of audio signals and realizes a wide dynamic range.

TDK will continue to contribute to the industry by offering a broad lineup of noise suppression filters and technical support that reconcile audio-quality preservation with electromagnetic-noise countermeasures for mobile and wearable devices with communication functions.

*    As of April 2026, according to TDK.

TDK Corporation (TSE:6762) announces that TDK will start manufacturing advanced sensors for various Apple products in the US. Built on a partnership spanning more than 30 years with Apple, this initiative will allow both companies to reinforce their advanced sensors manufacturing capabilities via Japan–U.S. collaboration and, by producing at U.S. facilities, contribute to a more reliable sensor supply chain. In the context of Apple’s current American Manufacturing Program initiative, this is the first time a Japanese company will produce components for Apple in the US. 

TDK has been collaborating with Apple not only on the development of next-generation sensors to enhance mobile functionality, but also on many other devices such as electronic components and rechargeable batteries.  

“TDK is a long-time partner and we’re excited they’ve joined our American Manufacturing Program,” said Sabih Khan, Apple’s COO. “Apple is committed to working with suppliers — like TDK — to manufacture even more in the US, and this initiative is another powerful example of how much we can achieve together when we invest in advanced American manufacturing.” 

Regarding the mutual collaboration, TDK President and CEO Noboru Saito commented: “Based on the decade-long relationship with Apple, when Apple asked what more we could do in the United States beyond our existing relationship, we TDK saw that as an opportunity to grow our relationship even more, and in new ways. We are very proud to be working with Apple to accelerate US manufacturing. We share their commitment to do more in the US, and our teams are working side-by-side with theirs in the US.”