• Proceedings of the KOSOMBE Conference
• /
• v.1993 no.11
• /
• pp.194-197
• /
• 1993

A technique for fast image reduction or expansion, in which the reduction(expansion) factor is either any integer or any rational number M/L Is represented. The multiresolution is modeled as an interpolation and filtering followed by a decimation. The model enables frequency domain analysts of the muitiresolution representations as well as convenient design of the Kernels(filters). Using any rin linear phase(Type I) filters a fine to coarse multiresolution structure can be generated.

• Electronics and Telecommunications Trends
• /
• v.34 no.5
• /
• pp.113-126
• /
• 2019

Based on the accumulation of medical big data, advances in medical artificial intelligence technology facilitate the timely treatment of disease through the reading the medical images and the increase of prediction speed and accuracy of diagnoses. In addition, these advances are expected to spark significant innovations in reducing medical costs and improving care quality. There are already approximately 40 FDA approved products in the US, and more than 10 products with K-FDA approval in Korea. Medical applications and services based on artificial intelligence are expected to spread rapidly in the future. Furthermore, the evolution of medical artificial intelligence technology is expanding the boundaries or limits of various related issues such as reference standards and specifications, ethical and clinical validation issues, and the harmonization of international regulatory systems.

• Journal of Electrical Engineering and Technology
• /
• v.11 no.5
• /
• pp.1509-1518
• /
• 2016

• Proceedings of the KOSOMBE Conference
• /
• v.1990 no.05
• /
• pp.29-32
• /
• 1990

In this paper, we designed and fabricated linear array transducer for ultrasonic medical imaging system. Fabricated transducer is 85mm in length and has 64 elements. It shows good sensitivity and band width characteristics compared with commercial transducers.

• Electronics and Telecommunications Trends
• /
• v.34 no.2
• /
• pp.19-28
• /
• 2019

In recent years, medical and health care fields have attracted attention for virtual reality (VR) applications. VR technology is emerging as a healthcare specialist and psychotherapy alternative to cope with the increase in the demand for the treatment of conditions such as psychological diseases caused by old age and stress. Using VR, virtual patients or organs can be trained, and the medical staff can plan and pre-test before surgeries. The use of VR technology for psychotherapy and rehabilitation of one-to-one, face-to-face treatment allows a single physician to respond to multiple health care needs.

• Proceedings of the KIEE Conference
• /
• 2000.11d
• /
• pp.845-847
• /
• 2000

깊은 생체 조직에서 전자기 에너지의 일부가 피부로 전달되는데, 이때 생체 내부에서 피부로 전달되는 전자기 에너지의 세기는, 주파수 대역과 전자기파를 흡수, 반사, 투과시키는 인체의 매질에 따라 다르다. Microwave Radiometry는 인체 내부 조직에서 방출되는 1-6 GHz 대역의 전자기 에너지 일부를 피부 표면에서 측정하여 일정한 체적내의 인체 내부 온도 평균온도를 추정하는 방법이다. 이러한 Radiometry로 암이나 종양 등의 이상 조직을 진단하는 의학적 가설은, 암이 진행시 악성 종양의 세포의 신진대사가 정상 세포보다 활발하게 되고 또한 종양 세포 주위로 혈액의 유입이 증가하게되어, 주위의 정상 세포 보다 열을 보다 더 방출하는 데 있다. 이때 발생된 열은 일정한 주파수 대역의 마이크로파 에너지를 방출하게 되고, 이에 Radiometry로 인체에 무해하고(passive), 비침습적(non-invasive), 방사능의 영향이 없는 (non-ionizing) 방법으로 인체 내부에서 전달되는 전자기 에너지 강도를 측정하여 종양 부위와 주위 정상부위의 온도 차이를 추정 의학진단에 응용할 수 있다. 본 논문에서는 이러한 Microwave Radiometry의 의학적 응용과 생리학적 특성을 고려한 인체모델용 팬텀에 대하여 살펴본다.

• Electronics and Telecommunications Trends
• /
• v.35 no.2
• /
• pp.1-16
• /
• 2020

"Artificial Intelligence+" is a key strategic direction that has garnered the attention of several global medical device manufacturers and internet companies. Large hospitals are actively involved in different types of medical AI research and cooperation projects. Medical AI is expected to create numerous opportunities and advancements in areas such as medical imaging, computer aided diagnostics and clinical decision support, new drug development, personal healthcare, pathology analysis, and genetic disease prediction. On the contrary, some studies on the limitations and problems in current conditions such as lack of clinical validation, difficulty in performance comparison, lack of interoperability, adversarial attacks, and computational manipulations are being published. Overall, the medical AI field is in a paradigm shift. Regarding international standardization, the work on the top 10 standardization issues is witnessing rapid progress and the competition for standard development has become fierce.

• Electronics and Telecommunications Trends
• /
• v.36 no.5
• /
• pp.21-31
• /
• 2021

Ransomware attacks, such as Conti, Ryuk, Petya, and Sodinokibi, that target medical institutions are increasing rapidly. In 2020, in the United States., ransomware attacks affected over 600 separate clinics, hospitals, and organizations, and more than 18 million patient records. The cost of these attacks is estimated to be almost $21 billion USD. The first death associated with a ransomware attack was reported in 2020 by the University Hospital of Düesseldorf in Germany. In the case of medical institutions, as introduced in the Medjack report issued by TrapX Labs, in many cases, attackers target medical devices that are relatively insecure and then penetrate deep into more critical network infrastructure, such as EMR servers. This paper introduces security vulnerabilities of hospital medical devices, considerations for ransomware response by medical institutions, and related technology trends.

• Proceedings of the KOSOMBE Conference
• /
• v.1996 no.05
• /
• pp.14-17
• /
• 1996

Evoked Potentials signals occur as a result of neuroelectric responses of the brain to sensory stimulation. In this paper, to analysis such signals we utilize a time-frequency analysis technique called wavelet transform. The wavelet analysis is performed based on a single prototype function,which can be thought of as a bandpass filter. Because the wavelet transform in a fine temporal analysis decomposes time-varying signals in EP into a dilated lowpass and a contracted highpass components, EP signal fetures can be obtained and analysed quantitatively at the levels of resolution. In the results, we analyze the VEP signal with the wavelet transform.

• ETRI Journal
• /
• v.45 no.1
• /
• pp.105-118
• /
• 2023

We tested the feasibility of automated discrimination of patients with panic disorder (PD) from healthy controls (HCs) based on multimodal physiological responses using machine learning. Electrocardiogram (ECG), electrodermal activity (EDA), respiration (RESP), and peripheral temperature (PT) of the participants were measured during three experimental phases: rest, stress, and recovery. Eleven physiological features were extracted from each phase and used as input data. Logistic regression (LoR), k-nearest neighbor (KNN), support vector machine (SVM), random forest (RF), and multilayer perceptron (MLP) algorithms were implemented with nested cross-validation. Linear regression analysis showed that ECG and PT features obtained in the stress and recovery phases were significant predictors of PD. We achieved the highest accuracy (75.61%) with MLP using all 33 features. With the exception of MLP, applying the significant predictors led to a higher accuracy than using 24 ECG features. These results suggest that combining multimodal physiological signals measured during various states of autonomic arousal has the potential to differentiate patients with PD from HCs.