本網站使用瀏覽器紀錄 (Cookies) 來提供您最好的使用體驗，我們使用的 Cookie 也包括了第三方 Cookie。相關資訊請訪問我們的隱私權與 Cookie 政策。如果您選擇繼續瀏覽或關閉這個提示，便表示您已接受我們的網站使用條款。 關閉
TAIPEI, Dec. 17, 2025 /PRNewswire/ -- Advantech, a global leader in IoT intelligent systems and embedded platforms, today announced its partnership with DEEPX, a leading Korean AI semiconductor innovator specializing in NPU (Neural Processing Unit) technology. This collaboration expands Advantech's AI chipset ecosystem and introduces the company's first AI acceleration solution powered by DEEPX technology, the EAI-1961 series Edge AI Acceleration Module. Advantech Expands Global Edge AI Partner Ecosystem with DEEPX and Launches First Joint Solution "Advantech evaluates a broad range of AI chip technologies to address diverse industrial needs," said Joey Hsu, Director of Advantech's Embedded Sector. "DEEPX demonstrates commendable efficiency in power and thermal performance, which is essential for reliable edge AI deployment. By integrating DEEPX's energy-efficient NPU with Advantech's industrial hardware expertise, we aim to offer more optimized AI solutions for next-generation edge systems." The newly launched EAI-1961 series is Advantech's first product featuring DEEPX's DX-M1 NPU technology. Designed in the industry-standard M.2 form factor, the module delivers up to 25 TOPS of AI inference while supporting up to 4GB of LPDDR5 memory. Its highly energy-efficient architecture ensures stable thermal behavior even during heavy workloads, making it well suited for vision-centric applications such as robotic vision, intelligent surveillance, in-vehicle computing, and precision medical diagnostics. "Advantech is the undisputed leader shaping the global industrial automation and embedded computing ecosystem," said DEEPX CEO Lokwon Kim. "This collaboration marks a defining moment for DEEPX as our technology moves toward becoming a global industrial standard. By leveraging Advantech's unparalleled worldwide network, we are ready to showcase the strength and competitiveness of DEEPX's AI chips on the global stage. The integration of our DX-M1 NPU into Advantech's platforms will empower customers with unprecedented AI performance and efficiency, enabling smarter, faster, and more sustainable edge applications." By adding DEEPX to its expanding roster of AI technology partners, including Intel, Qualcomm, NVIDIA, Hailo, and Axelera AI, Advantech continues to deliver one of the industry's most comprehensive portfolios of edge AI solutions. As edge AI becomes increasingly critical for applications such as predictive maintenance, quality inspection, real-time situational awareness, and adaptive robotic control, Advantech remains dedicated to providing ready-to-deploy platforms that help customers implement scalable, production-ready edge AI with confidence. For more information, please visit http://www.advantech.com. # # # Advantech Contact: Assistant Manager, Public Relations Marco Hsieh Tel: +886-2-7732-3399, Ext. 7388 Marco.hsieh@advantech.com Marketing, Embedded Sector Pamela Huang Tel: +886-2-2792-7818, Ext. 9851 Pamela.Huang@advantech.com.tw
Showcasing transformative edge AI innovations across robotics, healthcare and smart city solutions SEOUL, South Korea, Dec. 8, 2025 /PRNewswire/ -- Qualcomm Technologies, Inc. hosted the Qualcomm AI Program for Innovators (QAIPI) 2025 – APAC Demo Day in Seoul, where 15 shortlisted startups from Japan, Singapore, and South Korea presented on-device AI solutions by leveraging Snapdragon® X Series processors, Snapdragon® 8 Series Mobile Platforms and Qualcomm Dragonwing™ products. These solutions demonstrate how real-time, power-efficient AI inference runs directly on Qualcomm® platforms enabling new capabilities across robotics, healthcare and smart cities. The “Qualcomm AI Innovators Program 2025 – APAC Demo Day” held in Seoul was attended by (from left) Yvie Tai, Qualcomm Director of Business Development; O.H. Kwon, President of Qualcomm APAC; Noh Young-seok, First Vice Minister of the Ministry of SMEs and Startups, South Korea; Sudeepto Roy, Qualcomm Vice President of Engineering and Lead for Global Ecosystem Development Program; Sang-pyo Kim, President of Qualcomm Korea; and representative from the U.S. Embassy in Korea. As part of the six-month Mentorship Phase, participating startups received technical support from Qualcomm engineers, access to Qualcomm Technologies' hardware development kits, as well as business workshops designed to support deployment readiness. The program also includes intellectual property (IP) training and eligibility for a patent filing incentive of up to US$5,000, reinforcing long-term competitiveness and ecosystem growth. The 15 shortlisted teams presenting at Demo Day are (in alphabetical order): AMATAMA, Cear, Guide Robotics, ModAstera, and Noahlogy from Japan; AI Seer, Biorithm, LINGOAI, MetaOptics, and Vilota from Singapore; and BanyaAI, MaumAI, MOTOV, SAKAK, and SqueezeBits from South Korea. The latest wave of startups highlights the transformative potential of edge AI across industries. Applications range from robotics and computer vision in industrial operations, to analytics platforms in healthcare, and smart city solutions. Innovations in on-device AI are delivering personalized, privacy-preserving experiences, demonstrating how edge AI, integrated with Qualcomm Technologies' powerful mobile, computing, and industrial and embedded IoT (IEoT) platforms, is creating real-world impact. Qualcomm also led four Singapore startups—Biorithm, LingoAI, MetaOptics, and Vilota to demo at the Singapore Week of Innovation and Technology (SWITCH) from October 29 to 31, 2025. The companies showcased edge AI innovations spanning healthcare monitoring, real-time translation, advanced metalens optics, and robotics perception, showcasing the cutting-edge technologies shaping the future of AI-enabled solutions. "AI continues to reshape industries globally, and we are excited to empower innovators in the Asia-Pacific region to lead this evolution," said O.H. Kwon, Senior Vice President & President, Qualcomm APAC. "We are committed to supporting innovators as they move from prototyping to real deployment, and to actively building the next generation of the region's AI ecosystem. Through our global technology leadership and ongoing investment in developer enablement, we are empowering teams to scale their solutions, create new market opportunities, and drive long-term innovation across industries." "We are anchoring high-performance, energy-efficient edge computing in the deep domain expertise of inventors in Japan, Singapore, and South Korea—the essential catalyst for deploying embodied AI across diverse regional workflows," said Sudeepto Roy, Vice President of Engineering for Qualcomm Incorporated and Lead of Qualcomm's Global Ecosystem Development Program. "By providing advanced platforms and guidance on patent protection, we empower these innovators to translate their specific industrial insights into scalable solutions, effectively reimagining their operations for the age of physical AI." Qualcomm Technologies continues to drive the global deployment of edge AI. In addition to empowering end devices through its technology platforms—combining AI, high-performance, low-power computing, and connectivity—Qualcomm Technologies has further expanded developer resources and its innovation ecosystem by acquiring the premier open-source hardware and software company, Arduino. The new Arduino UNO Q, Arduino's first dual-brain board, will enable millions of developers with the power of Qualcomm Dragonwing processors. Looking ahead to the Qualcomm AI Program for Innovators (QAIPI) 2026 – APAC, the program will continue to empower startups across the region and drive innovation through platforms such as Arduino for rapid prototyping, along with expanded support for device-level AI and machine learning integration. These efforts reinforce Qualcomm Technologies' commitment to open-source collaboration and ecosystem development, enabling startups to progress efficiently from early concepts to prototypes and market-ready solutions, while supporting their transition from innovation to patentable IP. Further details of QAIPI 2026 will be announced in the near future. For more information, please visit the program website: www.qualcomm.com/ai-program-for-innovators/apac. About Qualcomm Qualcomm relentlessly innovates to deliver intelligent computing everywhere, helping the world tackle some of its most important challenges. Building on our 40 years of technology leadership in creating era-defining breakthroughs, we deliver a broad portfolio of solutions built with our leading-edge AI, high-performance, low-power computing, and unrivaled connectivity. Our Snapdragon® platforms power extraordinary consumer experiences, and our Qualcomm Dragonwing™ products empower businesses and industries to scale to new heights. Together with our ecosystem partners, we enable next-generation digital transformation to enrich lives, improve businesses, and advance societies. At Qualcomm, we are engineering human progress. Qualcomm Incorporated includes our licensing business, QTL, and the vast majority of our patent portfolio. Qualcomm Technologies, Inc., a subsidiary of Qualcomm Incorporated, operates, along with its subsidiaries, substantially all of our engineering and research and development functions and substantially all of our products and services businesses, including our QCT semiconductor business. Snapdragon and Qualcomm branded products are products of Qualcomm Technologies, Inc. and/or its subsidiaries. Qualcomm patented technologies are licensed by Qualcomm Incorporated. Snapdragon, Qualcomm and Qualcomm Dragonwing are trademarks or registered trademarks of Qualcomm Incorporated. ARDUINO and other Arduino brands and logos are trademarks of Arduino SrL. CONTACT: qaipi_apac@qualcomm.com O.H. Kwon, Senior Vice President & President, Qualcomm APAC, delivered the opening remarks at the “Qualcomm AI Innovators Program 2025 – APAC Demo Day” held in Seoul. 15 shortlisted startups from Japan, Singapore, and South Korea presenting their on-device AI solutions, demonstrating real-time, power-efficient AI inference enabled by Qualcomm’s platforms. Startups showcase edge-AI innovations across robotics, healthcare, and smart cities by using Snapdragon X series processors and Qualcomm Dragonwing products.
Smart connectivity made simple with scalable edge AI and 5G-ready IoT solutions KEY POINTS Unified edge intelligence: ASUS IoT gateways and CTHINGS.CO Orchestra enable faster, more secure, and easily managed IoT deployment Smarter operations: Real-time analytics and automation deliver predictive insights and improved efficiency across connected assets Collaborative innovation: Joint development accelerates smart city transformation with scalable, AI-driven infrastructure solutions SINGAPORE, Dec. 8, 2025 /PRNewswire/ -- ASUS IoT, a global leader in intelligent edge AI and embedded IoT hardware, has entered a strategic partnership with CTHINGS.CO, a Europe-based innovator connecting IoT platforms to industrial applications. The collaboration aims to help businesses extract actionable insights from their processes and assets by combining advanced hardware with AI-driven software for simplified, secure edge IoT deployments. CTHINGS.CO specializes in industrial system integration, edge ML/AI computing, real-time remote actuation, advanced analytics, digital twins, and secure cloud-based platforms. With a strong focus on digitizing physical assets and unifying operations, the company helps organizations gain real-time visibility, break down system silos, and accelerate smarter decision-making. Leveraging next-generation connectivity and zero-trust security principles, CTHINGS.CO empowers businesses to optimize processes, reduce maintenance costs, streamline workflows, and future-proof their infrastructure, unlocking operational efficiency, scalability, and sustainable long-term growth. Under the partnership, ASUS IoT's industry-grade gateways will integrate with CTHINGS.CO's Orchestra platform, which streamlines device deployment, enables rapid configuration, ensures secure connectivity, and provides centralized remote management. This integration lowers the barriers to large-scale edge computing adoption, allowing enterprises to deploy edge devices faster, connect seamlessly to the cloud, and accelerate digital transformation. Transforming assets into insights for intelligent infrastructure Through a collaboration with CTHINGS.CO, ASUS IoT hardware supports an intelligent reverse-vending machine solution that features real-time monitoring, predictive analytics, and enhanced bottle-verification accuracy. Powered by CTHINGS.CO's Orchestra platform, the system utilizes ASUS IoT gateways to ensure reliable, low-latency computing and communication between devices and the cloud. Together, these technologies automate object recognition, streamline operations, and provide actionable insights into fraud detection, bin capacity, return volumes, and compliance, enhancing overall efficiency and the customer experience. In addition to developing intelligent reverse-vending solutions, this partnership also aims to deliver the IoT-enabled multifunctional smart pole. This solution transforms static urban infrastructure into dynamic, remotely managed poles by integrating surveillance cameras, energy-efficient lighting, weather sensors, public announcement systems, and EV chargers. By running the Orchestra platform on ASUS IoT gateways, this complex system ensures streamlined, secure, and accelerated deployment for municipalities and private entities. Currently, the collaboration leverages the ultra-compact ASUS IoT PE100A to ensure robust performance. To further expand the partnership and serve a broader market, CTHINGS.CO is validating additional ASUS IoT products, such as edge AI computers built on NVIDIA® Jetson™ platform and the Tinker Board series. Casper Lee, EMEA Regional Head at ASUS IoT, said: "Partnering with CTHINGS.CO combines our world-class hardware with intelligent orchestration software, delivering a powerful, easy-to-manage edge solution. This collaboration simplifies deployment and accelerates time-to-value, empowering enterprises to fully leverage their edge ecosystems securely and at scale." Arnold Wierzejski, the CEO of CTHINGS.CO, added: "Running Orchestra on ASUS IoT's gateways enables new levels of operational efficiency and innovation. Together with our partners, we are helping enterprises embrace digital transformation confidently and achieve measurable business impact through intelligent edge computing." Creating smarter, safer and more sustainable cities Building on their initial successes, the companies are actively collaborating on several smart city projects, including initiatives to optimize transportation and enhance security systems in public areas. One key project focuses on smart streetlights equipped with sensors to monitor air quality, weather conditions, traffic flow, and pedestrian activity, providing comprehensive situational awareness. Looking ahead, ASUS IoT and CTHINGS.CO are committed to leveraging their combined strengths to deliver groundbreaking edge AI and IoT solutions. This partnership is poised to create significant value for businesses worldwide, driving innovation and shaping the future of connected industries. Availability & Pricing ASUS IoT PE100A is available in Singapore. Please contact your local ASUS representative for further information. About CTHINGS.CO CTHINGS.CO is a leading innovator in edge computing and IoT. Headquartered in Warsaw, Poland, and active since 2020, the company develops advanced software, hardware, and hybrid cloud solutions that help enterprises and municipalities unlock hidden data and turn it into actionable intelligence. Its AI-powered Orchestra Platform makes edge orchestration simple, secure, and scalable, streamlining operations, ensuring reliable performance in distributed environments, while reducing complexity and cost. With deep expertise and a global reach, CTHINGS.CO supports digital transformation across industries including manufacturing, logistics, retail, energy, and smart cities. Visit CTHINGS.CO for more information. About ASUS IoT ASUS IoT is a sub-brand of ASUS dedicated to the creation of incredible solutions in the fields of AI and IoT. Our mission is to become a trusted provider of embedded systems and a partner in the AIoT solutions ecosystem. ASUS IoT strives to deliver best-in-class products and services across diverse vertical markets – providing convenient and efficient environments for people everywhere. Visit ASUS IoT for more information. About ASUS ASUS is a global technology leader that provides the world's most innovative and intuitive devices, components, and solutions to deliver incredible experiences that enhance the lives of people everywhere. With its team of 5,000 in-house R&D experts, the company is world-renowned for continuously reimagining today's technologies. Consistently ranked as one of Fortune's World's Most Admired Companies, ASUS is also committed to sustaining an incredible future. The goal is to create a net zero enterprise that helps drive the shift towards a circular economy, with a responsible supply chain creating shared value for every one of us.
SAN JOSE, Calif., Nov. 26, 2025 /PRNewswire/ -- As AI computing moves rapidly from the cloud to the edge, devices such as AI PCs, intelligent vehicles, and robotics face mounting storage challenges: real-time multimodal data throughput, extreme random I/O workloads, environmental reliability requirements, and barriers to moving systems and data across devices. Traditional storage methods can no longer keep pace with AI-driven endpoints, making storage bandwidth and responsiveness a critical bottleneck. Gartner forecasts that AI PC shipments will reach 143 million units in 2026, representing more than half of the global PC market. In this landscape, storage must deliver higher bandwidth, faster responsiveness, and greater flexibility. Today, Lexar, a leading high-performance memory brand is introducing the industry's first AI Storage Core, offering up to 4TB capacity, high-speed performance, and a hot-swappable design tailored for AI-enabled endpoints. Lexar Unveils Industry’s First AI Storage Core for Next Generation Edge AI Devices Three Core Innovations Built for the AI Era High Performance for AI Acceleration: The Lexar AI Storage Core delivers sequential read/write speeds that far exceed traditional memory cards, enabling rapid handling of AI-scale data. Lexar is advancing small-block (512B) I/O optimization and host-system collaboration in SLC Boost and Read Cache layers to improve LLM loading, generative image workflows, and other real-time AI tasks. High Reliability for Harsh Environments: Built with Longsys' integrated packaging technology, the device offers dustproof, waterproof, shock-resistant, and radiation-resistant protection. Select upcoming models will support –40°C to 85°C wide-temperature operation, addressing the needs of autonomous driving, outdoor robotics, and mission-critical applications. High Flexibility for Cross-Device AI Collaboration: The hot-swappable design enables users to insert or remove the device while the system is running. A co-engineered thermal solution ensures stable performance under sustained workloads. With PCIe boot support, users can launch Windows OS, applications, and data directly from the module—enabling effortless system portability and seamless cross-device collaboration. Purpose-Built for Five Key AI Application Scenarios AI PC: High capacity and high-speed performance accelerate model loading, LLM workflows, and generative tasks. Hot-swap support enables full mobile-workstation portability. AI Gaming: High IOPS and fast random-read performance reduce load times and stutter, supporting high-frame-rate rendering and real-time AI interactions. AI Camera: Sustained performance supports continuous 4K/8K video capture and real-time AI processing such as subject tracking and scene optimization. Shock-resistant construction is ideal for outdoor and professional imaging environments. AI Driving: Capable of ingesting multi-sensor data streams from cameras, radar, and LiDAR. Wide-temperature, shock-resistant models (to be released) ensure stable operation under extreme automotive conditions. AI Robotics: Compact packaging fits space-constrained robotic designs. Wide-temperature and anti-shock capabilities support factory, logistics, and outdoor scenarios. As robotics evolve toward rapid learning and adaptation, the AI Storage Core enables intelligence, identity, and security upgrades simply by swapping modules. Advancing Intelligent Storage for the AI Future AI is reshaping every industry, placing storage at the foundation of real-time data processing and on-device intelligence. The Lexar AI Storage Core reflects Lexar's deep understanding of AI-era storage needs and its commitment to next-generation innovation. By delivering efficient, reliable, and flexible storage performance tailored for AI endpoints, Lexar is helping accelerate the adoption of AI technologies across consumer, industrial, and automotive applications—setting a new benchmark for intelligent storage in the years ahead. About Lexar For more than 29 years, Lexar has been trusted as a leading global brand of memory solutions. Our lineup includes memory cards, USB flash drives, card readers, solid-state drives, and DRAM. With so many options, it's easy to find the right Lexar solution to fit your needs. For more information, please visit lexar.com and follow us on Instagram, Facebook, X and LinkedIn. Media contact: lexarbm@lexar.com
TAIPEI, Nov. 26, 2025 /PRNewswire/ -- With artificial intelligence rapidly advancing toward end devices, Edge AI has become a critical technology driving intelligent and IoT applications. Compared to cloud-based processing, Edge AI enables real-time inference directly on the sensor node or local MCU, effectively reducing latency, enhancing privacy, and lowering power consumption. This makes it particularly suitable for scenarios requiring fast response time, such as gesture control, motion recognition, and equipment monitoring. Leveraging the high performance, low-power design, and rich peripherals of AT32 MCUs—combined with the Edge Impulse platform—ARTERY Technology continues to accelerate the deployment of multi-sensor Edge AI technology. Developers can integrate various AI functions with shorter development cycles, reducing the time to market and mass production for new products. To further enhance developers' integrated experience in Edge AI, ARTERY Technology officially launches the AT32 Edge AI Sensor EV Board. Powered by the AT32F403A MCU, the board integrates a variety of sensors including TOF, IMU, magnetometer, ambient light, temperature & humidity, and barometric pressure, and fully supports Edge Impulse model deployment. Developers can run gesture classification, motion recognition, and anomaly detection AI models directly on the device, accelerating product design for AIoT and smart applications. AT32 Edge AI Sensor EV Board Three Key Edge AI Applications 1. TOF Gesture Recognition Based on the onboard VL53L7CX TOF sensor, the AT32 Edge AI Sensor EV Board detects a 4×4 depth array within a 5–20 cm range and uses centroid-weighted algorithms with Edge Impulse neural network models to perform four-direction gesture recognition (up/down/left/right). The OLED can simultaneously display gesture trajectories, making it suitable for smart appliances, HMI interfaces, and in-vehicle controls requiring low-latency, contactless operation. 2. IMU Vibration Anomaly Detection Using data from the onboard LSM6DS3TR accelerometer and gyroscope, a K-means self-learning model automatically builds "normal operation signatures" to detect abnormal vibrations in fans, motors, or equipment in real time. This is ideal for industrial equipment health monitoring, predictive maintenance, and environmental sensing. Features: 8-D feature extraction (mean, variance, RMS, kurtosis, etc.) Local MCU inference without cloud dependence Self-learning model that automatically generates anomaly thresholds 3. IMU Motion Classification (Edge Impulse Pipeline) The AT32 Edge AI Sensor EV Board supports training and deploying IMU-based motion classification models using Edge Impulse. It can recognize movements such as up, down, left, right, circle, and idle, making it suitable for wearables, motion-sensing interaction, and smart control. Models are directly deployable on the AT32F403A and LSM6DS3TR sensor and can be optimized through CMSIS-DSP/NN for improved MCU-based inference performance. Complete Edge AI Workflow Support The AT32 Edge AI Sensor EV Board includes a full Edge Impulse development pipeline, covering: Sensor data acquisition (TOF / IMU) Feature extraction (Spectral Analysis / Feature Engineering) Model training for classification and anomaly detection (Neural Networks, K-means) MCU-side deployment (EON Compiler / TensorFlow Lite for Microcontrollers) Real-time inference output via OLED and UART Faster AI Development and Mass Production With the AT32 Edge AI Sensor EV Board, developers can quickly validate multi-sensor AI models at minimal cost and deploy them directly on end devices, accelerating the overall development journey from prototype to mass production. ARTERY will continue to provide more AI models, algorithms, and tool resources to help the industry further popularize edge intelligence and explore new possibilities for AIoT innovation. Looking Ahead ARTERY Technology will continue strengthening R&D in Edge AI while enhancing integration between high-performance MCUs and AI algorithms, enabling global customers to build smarter, low-power, and competitive products. As more sensor, voice, and imaging applications emerge, ARTERY will collaborate with partners to advance Edge AI adoption, accelerate smart-industry upgrades, and shape a more efficient and sustainable technological future. Related Technical Documents (Application Notes): AN0286 : Introduction to Edge AI Sensor EV BoardAN0287 : IMU K-means Anomaly Detection
台北2025年11月26日 /美通社/ -- 隨著人工智慧快速邁向終端設備，邊緣 AI（Edge AI）已成為推動智慧化與物聯網（IoT）應用的重要技術。相較於仰賴雲端的運算模式，Edge AI 能在感測器端或本地 MCU 上直接完成即時推論，有效降低延遲、提升隱私並減少能耗，特別適用於手勢操控、動作識別與設備監測等對反應速度高度敏感的場景。 雅特力科技（ARTERY Technology）憑藉 AT32 MCU 的高效能、低功耗與豐富外設，並結合 Edge Impulse 平台，持續推動多感測器邊緣 AI 技術落地，協助客戶以最短開發週期導入各式 AI 功能，縮短產品導入與量產時程。 為進一步強化開發者在 Edge AI 領域的整合體驗，雅特力科技正式推出 AT32 Edge AI Sensor EV Board。該開發板以 AT32F403A MCU 為核心，整合 TOF、IMU、磁力計、環境光、溫濕度與氣壓等多類感測器，並全面支援 Edge Impulse 模型部署。開發者可在終端設備直接運行手勢分類、動作識別及異常偵測等 AI 模型，加速 AIoT 與智慧設備的產品化設計。 AT32 Edge AI Sensor EV Board 三大 Edge AI 應用亮點 一、TOF 手勢識別（Gesture Recognition） 基於板載 VL53L7CX TOF Sensor，AT32 Edge AI Sensor EV Board 可在 5-20 公分範圍內偵測 4×4 深度陣列資料，並利用質心權重演算法與 Edge Impulse 神經網路模型，完成「上／下／左／右」四方向手勢識別。OLED 亦可同步顯示手勢軌跡，適用於智慧家電、人機介面與車載控制等需低延遲、免接觸操作的應用場景 二、IMU 異常偵測（IMU Vibration Anomaly Detection） 使用板載 LSM6DS3TR 加速度與陀螺儀資料，透過 K-means 自學習模型自動建立「正常運轉特徵」，可即時偵測風扇、馬達與設備振動異常，適用於工業設備健康監測、智慧維護與環境感測。 特色： 8-D 特徵擷取（均值、方差、RMS、峰度等） MCU 本地推論，無需倚賴雲端 自學習模型，自動產生異常閾值 三、IMU 動作識別（Motion Classification，Edge Impulse Pipeline） AT32 Edge AI Sensor EV Board 支援使用 Edge Impulse 訓練並部署 IMU 動作分類模型，可識別上下、左右、圓圈（circle）、靜止（idle）等動作類型，適用於穿戴式裝置、體感互動與智能控制。模型可直接導入 AT32F403A 與 LSM6DS3TR 感測器，並透過 CMSIS-DSP/ NN 進行優化，加速 MCU 端推論效能。 完整 Edge AI 開發流程支援 AT32 Edge AI Sensor EV Board內建完整 Edge Impulse 開發鏈路，包括： 感測器資料收集（TOF / IMU） 特色擷取（Spectral Analysis / Feature Engineering） 分類與異常偵測模型訓練（Neural Networks、K-means） MCU 端部署（EON Compiler / TensorFlow Lite for Microcontrollers） OLED 與串口即時顯示推論結果 更高效的 AI 開發與量產流程 透過 AT32 Edge AI Sensor EV Board，開發者能以最少的成本快速驗證多感測器 AI 模型，並直接部署於終端設備，加速產品從原型到量產的整體開發流程。雅特力亦將持續提供更多 AI 模型、演算法與工具資源，協助產業加速邊緣智慧應用的普及，開創更多 AIoT 創新可能。 展望未來 雅特力科技將持續深化 Edge AI 技術研發，並以前瞻規劃強化高性能 MCU 與人工智慧演算法的整合能力，協助全球客戶打造智慧、低功耗且具競爭力的產品。隨著更多感測、語音與影像場景逐步開放，雅特力也將攜手合作夥伴推動 Edge AI 普及化，加速產業智慧化升級，實現更高效、更永續的科技未來。 相關技術文件 (Application Note): AN0286 : Edge AI Sensor EV Board 介紹AN0287 : IMU K-means 異常偵測
A12 藝術空間
Edge AI
請先登入後才能發佈新聞。
還不是會員嗎？立即 加入台灣產經新聞網會員 ，使用免費新聞發佈服務。 （服務項目） （投稿規範）
