이용자 현황조사

경북대학교 KNU전자전기융합인재양성교육연구단이용자 현황조사

  • 학부생
  • 대학부생
  • 일반인

* 사이트 이용을 위해 소속을 선택해 주세요.

BrainKorea21 FOUR Open Courseware KNU전자전기융합인재양성교육연구단

  • 전체메뉴
  • 외부링크
통합검색

카테고리

홈 > 학문/산업 분야별

전체강좌 107, 현재 1 / 전체 11 페이지
  • Deep Fault Diagnosis, Explainability and Information Fusion for Rotary Machinery 영상 +강의담기

    학문/산업 분야별 ▶ 인공지능 ▶

     

    The objective of this talk is to address some challenges and recent results on fault diagnosis of mechanical systems, with a focus on advanced artificial intelligence algorithms developments. Specifically, different deep learning models such as deep supervised, unsupervised and reinforcement learning algorithms are examined to establish a trustworthy intelligence fault diagnosis model. The talk will be concluded with some results on the development of explainable intelligence fault diagnosis framework based on post-hoc visualization methods as well as multi-source information fusion with complementary transferability metric for mechanical fault diagnosis.

     

    더보기+

    강의기간 : 2023-11-01 ~ 2023-11-01 강의수 : 1 최근 업데이트 : 2024-02-19 조회 : 18

  • A design of 12-bit 125-MS/s 2.5-bit/Cycle SAR-based pipeline ADC employing a loop-based gain-boosting amplifier 영상 +강의담기

    학문/산업 분야별 ▶ 전력전자 ▶ 세미나 및 튜토리얼

     

    This seminar covers a different approach of loop-based gain-boosting technique to provide a better matching of pole-zero doublet and a smaller power consumption, while achieving DC gain as high as multi-stage amplifiers. As an example of how to use this amplifier, pipeline ADCs are chosen because it requires a residue amplifier between the stages. A proposed ADC architecture combines a multi-bit per cycle SAR ADC and a pipeline approach to achieve a high-speed performance. Also, a 2.5 bit/cycle SAR ADC is applied as a sub-ADC in pipeline stages, and a resistor-DAC is utilized for SAR and residue operation. As a result, the prototype ADC achieves 12-bit and 125-MS/s with a loop-based gain-boosting amplifier.

     

    더보기+

    강의기간 : 2023-11-23 ~ 2023-11-23 강의수 : 1 최근 업데이트 : 2023-12-01 조회 : 80

  • Stepwise AI Models in Clinical Workflows 영상 +강의담기

    학문/산업 분야별 ▶ 인공지능 ▶

     

     

     

    Artificial intelligence, particularly deep learning, has gained widespread popularity across various medical applications. The current role of AI is to provide support to clinicians, physicians, and patients, ultimately enhancing the performance of a range of tasks such as noise reduction, segmentation, classification, regression, lesion detection, and risk prediction. Sometimes, a complex hierarchical pipeline, or pathway, can be established. This requires breaking down sub-tasks, which can be addressed by a single extensive model or subdivided into smaller, more specialized models. While a single, large model may be convenient (Foundation Model, LLM), it becomes challenging to assess or interpret results for individual sub-tasks, particularly when their performance is suboptimal. As a solution, we can divide these sub-tasks and employ a dedicated small model for each one. To maximize efficiency, closely related sub-tasks can share specific layers within a deep learning model. During this presentation, we will provide a comprehensive overview of the entire pipeline development process, including data cleansing strategies.  

     

    더보기+

    강의기간 : 2023-11-15 ~ 2023-11-15 강의수 : 1 최근 업데이트 : 2023-11-20 조회 : 41

  • Active Cell Balancing Algorithm considering Cycle Life of Battery Systems 영상 +강의담기

    학문/산업 분야별 ▶ 전력전자 ▶ 세미나 및 튜토리얼

     

    Lithium-ion batteries are widely used in energy storage systems thanks to their high energy density and relatively long lifespan compared to other types of batteries. In this seminar, I will cover the design of the battery management system (BMS) for managing Li-ion battery systems, especially the circuit design and algorithms for active cell balancing. In particular, I introduce techniques aimed at alleviating issues like cell aging caused by cell heating in high-power applications such as electric vehicles.

     

    더보기+

    강의기간 : 2023-08-09 ~ 2023-08-09 강의수 : 1 최근 업데이트 : 2023-08-14 조회 : 157

  • Machine Learning-Powered VLSI Physical Design Automation 영상 +강의담기

    학문/산업 분야별 ▶ 반도체_센서기술 ▶ 세미나 및 튜토리얼

     

    VLSI physical design, the process that converts circuit schematics to manufacturable layouts in an automatic fashion, consists of many long-lasting and challenging problems that have been solved by sub-optimal algorithms over the decades. As the technology scaling advances, the sub-optimality becomes more severe and problematic. Machine learning (ML) is one of the promising solutions that help designers achieve the desired Power, Performance, and Area (PPA) goals. In this talk, we present our recent works on utilizing ML algorithms to improve various stages of the modern physical design flow. They span from partitioning, placement, routing, and timing optimization, where Reinforcement, Transformer, Adversarial, and Graph Learning are adopted. We also showcase our recent work recognized with the best paper award from the ACM Design Automation Conference in 2023.

     

    더보기+

    강의기간 : 2023-07-28 ~ 2023-07-28 강의수 : 1 최근 업데이트 : 2023-08-08 조회 : 143

  • Quantitative Imaging Using MR and PET/MR 영상 +강의담기

    학문/산업 분야별 ▶ 의용전자 ▶

     

    Magnetic Resonance Imaging (MRI) is a powerful, generally non-invasive imaging modality that can provide anatomical and functional information in great detail. When combined with Positron Emission Tomography (PET), it can provide excellent soft-tissue contrast while yielding perfectly registered functional, morphologic, and molecular information. More importantly, combining MR and PET in a single imaging session can enable the estimation of physiological processes that otherwise would be impossible with PET or MR alone. In this presentation, Dr. Han will provide an overview of MR and PET imaging, together with examples of cutting-edge quantitative imaging methods developed for MR and PET/MR. Examples include the development of a novel non-invasive perfusion imaging method for the brain, the development of a new physical compartmental model-based PET attenuation correction method for PET/MR, and the development of a new free-breathing, 3-dimensional (3D) T1 mapping method of the heart.

     

    더보기+

    강의기간 : 2023-07-21 ~ 2023-07-21 강의수 : 1 최근 업데이트 : 2023-07-26 조회 : 77

  • Unique CVD Polymer Processing and Recent Device Applications 영상 +강의담기

    학문/산업 분야별 ▶ 반도체_센서기술 ▶

     

    Chemical Vapor Deposition (CVD) techniques represent a significant advancement over traditional surface coating methods, offering enhanced capabilities for producing conductive and functional polymeric films. In CVD polymerization, the vapor phase is utilized to deliver the monomer(s) to the surface, where they undergo simultaneous polymerization and thin film formation. This innovative approach eliminates the necessity of dissolving macromolecules, enabling the coating of insoluble polymers and safeguarding the substrate against solvent-induced damage. Furthermore, CVD coatings exhibit superior conformality to the underlying substrate geometry due to the absence of de-wetting and surface tension effects. As a result, CVD polymers can be easily applied to a wide range of substrates, including organic and inorganic materials, as well as rigid, flexible, planar, three-dimensional, dense, or porous structures. CVD methods readily integrate with other vacuum-based processes employed for the fabrication of patterned surfaces and devices, offering seamless compatibility and versatility.

     

    더보기+

    강의기간 : 2023-07-24 ~ 2023-07-24 강의수 : 1 최근 업데이트 : 2023-07-26 조회 : 89

  • Miniaturizing Artificial-Intelligence-of-Things into a Millimeter Scale 영상 +강의담기

    학문/산업 분야별 ▶ 전력전자 ▶ 세미나 및 튜토리얼

     

    Miniature Internet-of-Things (IoT) systems have unique feature sets that include wireless communication, energy harvesting, and a small form factor, thus enabling non-invasive, secure placement for biomedical, ecological, surveillance, and infrastructure applications, among others. There has been substantial research on the miniaturization of IoT systems. The size of the bare die is often only 1-2 mm; however, the associated systems are typically much larger than just the die, resulting in centimeter-size systems due to included peripherals such as batteries and casings. This leads to a design challenge for the electronics of miniaturized systems because the maximum physical battery size and battery storage capacity are severely limited.

    In this talk, I will discuss the challenges in developing miniature IoT systems and introduce a millimeter-scale system platform. The system has been developed as the world’s smallest computer. To optimize circuit performance, the system is constructed from die fabricated in different technologies which are then stacked and wire-bonded together. The stacked structure increases silicon area per unit volume and makes it easy to swap layers in and out for flexibility in system configuration. Also, I will describe several examples of a low-power circuit technique that enables the system for energy harvesting, sensor interface, and reference circuits. Then, I will introduce two interesting use scenarios of miniature systems for ecological studies. Lastly, I will share his future research directions with different applications and discuss how to transform a miniature IoT device into a miniature “Artificial-Intelligence-of-Things (AIoT)” device.

     

    더보기+

    강의기간 : 2023-06-07 ~ 2023-06-07 강의수 : 1 최근 업데이트 : 2023-06-12 조회 : 137

  • Artificial intelligence powers all-in-one miniaturized spectrometers 영상 +강의담기

    학문/산업 분야별 ▶ 반도체_센서기술 ▶

     

    분광계는 산업 및 연구 전반에 걸쳐 빛을 감지하고 분석하는 데 널리 사용됩니다. 분광계는 무지개의 색상과 같이 다양한 파장에서 강도를 나타내는 빛의 스펙트럼을 측정하며 표본과 재료를 식별하고 분석하는 데 필수적인 도구입니다. 2차원 물질의 반데르발스 이종 접합 구조 기반 마이크로 칩 크기의 단일 센서와 인공지능 알고리즘을 결합한 높은 피크 파장 정확도, 높은 스펙트럼 분해능 및 넓은 작동 대역폭을 갖춘 고감도 분광기를 소개합니다. 이 초소형 고감도 일체형 지능형 전산 분광기는 광학 및 기계 부품과 같은 기존 하드웨어를 대체하기 위해 인공 지능을 사용하여 칩 위의 광전자공학 실험실을 가능하게 합니다. 특히, 빛을 분산하고 여과하기 위해 별도의 부피가 큰 구성 요소나 센서 어레이 설계를 필요로 하지 않고 우리 손끝에서 온전히 전기적으로 빛의 스펙트럼을 제어 및 분석할 수 있으므로 스마트폰 및 드론과 같은 휴대용 장치에 대한 확장성과 통합 가능성을 갖습니다. 나아가, 품질 검사 플랫폼, 보안 센서, 생체 시료 분석기, 의료 시스템, 환경 모니터링 도구 및 우주 망원경을 비롯한 다양한 기술에 큰 도움이 됩니다.

     

    더보기+

    강의기간 : 2022-10-21 ~ 2022-10-21 강의수 : 1 최근 업데이트 : 2022-10-25 조회 : 327

  • High Performance, High Integration Density, and Secured Semiconductor System Design based on a Packaging Technology 영상 +강의담기

    학문/산업 분야별 ▶ 반도체_센서기술 ▶ 세미나 및 튜토리얼

     In this Seminar, Various Packaging researches such as high performance system design, a novel simulation tool development, and hardware security analysis/design will be delivered. Also, an important role of packaging technologies in the era of mobility requiring low noise, low power, and ultra-low latency will be emphasized. 

    더보기+

    강의기간 : 2022-07-21 ~ 2022-07-21 강의수 : 1 최근 업데이트 : 2022-07-27 조회 : 302

1 2 3 4 5 6 7 8 9 10

Back to Top