Select Field
Select Ministry
124 results
Advancements in Silicon Photonic High-speed Modulators — Pushing the Boundaries with Novel Materials: Our core technology is based on a proprietary class of electro-optic materials called ferroelectric nematic liquid crystals (FNCs). These materials leverage the Pockels effect, allowing high-speed and efficient optical modulation suitable for next-generation optical data transfer applications.
Future Tech | Electronics ＆ OptoelectronicsThis study developed a 3D match reconstruction and immersive data analysis system for boxing broadcast videos. By combining 3D human pose and global position estimation technologies, along with interactive editing tools, the system accurately converts match footage into 3D reconstruction models. Users can view the match in an immersive environment, observing detailed movements from different angles. Additionally, the system integrates various visualization analysis tools within the 3D space, helping users deeply analyze the match process and understand the athletes' tactical intentions and strategies.
Future Tech | Life ApplicationThe self-developed 6" Cluster ALD/ALE Platform Integrated with in-situ XPS Analysis system is linked with multiple related process equipment to achieve the purpose of in-situ monitoring of the process. We can provide the novel material process R&D and analysis services to the industry, academia, and research institutions.
Future Tech | Machinery ＆ SystemOur technology focuses on assessment of wound healing status in chronic wound care. It employs multispectral imaging principles to provide healthcare professionals with blood oxygen saturation information. By training AI algorithms on clinical patient data collected at NCKU Hospital, we conduct wound tissue recognition and healing assessment. Through miniaturized systems and IoT technology, the technology enables continuous wound tracking and achieving the goal of remote healthcare.
Future Tech | Information ＆ CommunicationsThis invention introduces a method for producing activated carbon using microwave technology and carbonated water. Compared to traditional high-temperature and strong acid or base activation processes, this method is more environmentally friendly and safer. The pore structure of the carbonized material expands rapidly under microwaves, and the mild acidic environment from the carbonated water enhances adsorption capacity. This approach reduces activation time and energy consumption, with broad applications in water and air purification.
Future Tech | Biotechnology ＆ Medical careA million-pixel image might only have one annotation from a professional pathologist, posing a significant challenge for all AI models. Our team has designed the world＇s first weakly supervised multiple instance AI learning framework. This framework can analyze million-pixel pathology slides to predict gene expression and prognosis in colorectal cancer patients. Additionally, it has been successfully validated across patient datasets from multiple generational cohorts. A more significant challenge arises as each complete million-pixel digital pathology slide image often has only one set of annotated answers from a physician, which cannot be applied to all the smaller segmented images. This issue is exactly what top AI experts worldwide, NVIDIA, and our team aim to solve. Our research team has developed innovative AI algorithms to address this problem. We designed a novel attention-based multiple instance learning model embedded in a convolutional neural network, overcoming the limitations of traditional machine learning methods while effectively highlighting lesion features. This pioneering weakly supervised AI model can automatically analyze and accurately integrate the best prediction after processing a large volume of image data. Furthermore, our unique AI model enables computers to recognize gene features that pathologists cannot detect with the naked eyes. If successfully implemented in clinical practice, this achievement could reduce the workload of physicians＇ manual annotations by at least 75%. Remarkably, we developed the new deep learning model with an accuracy of up to 99.38%. This novel AI algorithm framework not only identifies specific gene expressions from million-pixel digital pathology images of colorectal cancer but also performs prognostic prediction tasks for patients. Additionally, the model＇s performance has been validated across different cohort study.
Future Tech | Information ＆ CommunicationsThe pulsed power system primarily consists of energy storage components, switching elements, and their peripheral components. By utilizing innovative circuit design and adjusting circuit loop impedance, the output current parameters were optimized, leading to the successful development of a short-pulse-width solid-state square wave pulsed power system.
Future Tech | Electronics ＆ OptoelectronicsThe acoustic vortex light guide tech uses ultrasonic waves to form bubble structure for non-contact, dynamic control, reversibility, and reduced light scattering. By employing acoustic vortices, it minimizes tissue scattering, increasing light fluence by about 34.3%. Simple to operate, non-invasive, and lowering tissue damage risks, it offers a novel solution for biomedical optical diagnostics and therapy.
Future Tech | Electronics ＆ OptoelectronicsAs communication systems evolve and grow more complex, AI powered joint sensing and communication networks will become a standard feature in future 6G and WLAN systems. By incorporating generative AI, such as Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs), we significantly enhance the performance of advanced wireless sensing and ISAC by generating synthetic training data, bolstering signal processing capabilities, and compensating for noise and missing data, all of which are critical for future intelligent heterogeneous 6G networks (3GPP). The potential applications of our AI-powered sensing silicon chip technology are vast. Our innovations are poised to elevate cellular networks in open spaces and support a wide range of use cases, including autonomous vehicles, vehicle to everything (V2X) communications, drone Synthetic Aperature Radar (SAR) imaging, robotics, health monitoring, people ID identification, 3D localization mapping and much more.
Future Tech | Information ＆ CommunicationsThis developed technology integrated big data analytics, meta model, and XAI algorithm to develop more accurate demand and cycle time prediction for supply chain and production planner to reduce production costs in semiconductor industry and enhance network resilience via analyzing big data of supply chain, capacity portfolio and production data enabling automated feature engineering. The developed solution (Advanced Artificial-intelligence based forecasting technology) integrates big data analytics, metamodels by incorporating interpretable AI algorithms, advanced cycle time prediction models for future new process platform introductions and new capacity portfolios. The fundamental goals are as follows: (1) Achieve flexible decision-making, enabling models to self-adjust and learn in different planning scenarios. (2) Achieve system resilience in production environments facing discrete events through action selection, monitoring of fluctuations, and adjustment. (3) Achieve real-time planning and control of dynamic systems. The technology includes (1) automated feature engineering techniques, (2) capacity configuration classifier, (3) integration of metamodels with XAI to interpret advanced prediction models, and (4) hybrid strategies to adapt linear models applicable to planning scenarios. By collecting supply chain information, capacity portfolio and production data, the technology automatically identifies key factors in semiconductor supply chain and manufacturing processes and provide more accurate forecasted demand and manufacturing cycle time (Enhance 30%, 23% accuracy), and thus enhances semiconductor supply chain resilience, while reducing manufacturing costs (30% inventory costs and 20% production costs).
Future Tech | Information ＆ CommunicationsThe "Blood Circulation Imaging System" combines optical and laser systems with advanced imaging to effectively monitor blood circulation in elderly individuals. Its non-invasive measurement quickly identifies microcirculation issues, offering important guidance for wound care and early detection of peripheral vascular disease risks. Through telemedicine, it expands assessment tools to improve health management in elderly communities, ultimately enhancing their quality of life.
Future Tech | Biotechnology ＆ Medical careThis system revolutionizes sports teaching with AI-enabled equipment, including smart racquets, AI cameras, AI shuttlecock machines, and a cloud platform. By combining deep learning and 3D posture estimation, it creates learner-centric programs and automated evaluations. It records and assesses training progress, enhancing skills and knowledge while quantifying performance metrics to boost athletic performance.
Future Tech | Life ApplicationOur team has developed a rapid microfluidic paper-based chip detection system that utilizes smart networking technology to upload results to the cloud for management and analysis. The system establishes predictive models to generate personalized reports, providing doctors and patients with immediate and accurate assessments and recommendations, achieving the goal of home testing. Through this innovative system, we aim to provide better health management tools for chronic kidney disease patients.
Future Tech | Biotechnology ＆ Medical careWe have developed innovative AI models, particularly for Extreme Gradient Boosting models, to integrate genetic information derived from whole-genome SNPs, medical imaging information from four types of medical images, and demographic variables (including age, sex, and family history of disease) obtained from the Taiwan Biobank. This integration allows for the identification of high-risk subgroups and early detection of T2D. Additionally, a T2D risk assessment system has been established.
Future Tech | Information ＆ Communications•Adaptive: unique for each user •Gamified: playful, fun, sticky •Generative: 100s of live conversation scenarios •Relevant: speak in English, learn in native language
Future Tech | Life ApplicationNational Science and Technology Center for Disaster Reduction (NCDR) has developed an alert gateway that allows the public to integrate cellular broadcast alert services with smart home systems without needing to use a mobile phone. When a disaster is imminent, the alert gateway can automatically trigger smart IoT devices. For example, in the event of an earthquake, it can automate disaster mitigation procedures such as controlling home lighting, shutting off gas appliances that are in use, or even opening doors in advance to facilitate evacuation. This automation helps people respond to disasters in a more orderly manner.
Future Tech | Information ＆ CommunicationsThis study develops highly active MoS2 nanoflowers with sulfur vacancies as piezocatalysts. Utilizing mechanical energy, it reduces N2 to NH3 (8294.1 μmol L-1 g-1 h-1) in an atmospheric environmentwithout needing an external light source or electricity. The method enhances piezoelectric properties and nitrogen reduction, offering high selectivity similar to electro- and photocatalysis, without the complexity of electrode/electrolyte systems, providing a new green NH3 production alternative.
Future Tech | Green Energy ＆ EnvironmentThis technology involves an oral available developmental drug candidate, DBPR728, that demonstrated in vivo efficacy in promoting the degradation of the MYC oncoprotein and inhibiting glycolysis of cancer cells, thereby inducing cancer cell apoptosis. Clinically, this technology primarily targets diseases such as small cell lung cancer and triple-negative breast cancer, which acquired MYC gene amplification.
Future Tech | Biotechnology ＆ Medical careComing soon!
