손실 값을 갖는 유비쿼터스 헬스케어 환경에서 신경망을 이용한 에이전트 기반 증상 패턴 분류

마이클안젤로살보 ( Michael Angelo G. Salvo ),이재완 ( Jaewan Lee ),이말례 ( Malrey Lee ) 한국인터넷정보학회 2010 인터넷정보학회논문지 Vol.11 No.2

무선선서네트워크의 주요 응용분야 중 하나가 유비쿼터스 헬스케어 시스템이다. 하지만 무선센서네트워크가 가지고 있는 과제중의 하나는 데이터 중에 나타나는 높은 손실 율이다. 바이오 센서로부터 들어오는 데이터는 기지국에 도착되지 않을 수 있으며, 이 값은 손실 값(missing value)이 된다. 본 논문은 기지국에서 데이터를 수집하고, 손실 값을 처리한 후, 증상 패턴에 따라 건강상태를 분류하여, 비상시에 적절한 행동을 취할 수 있도록 하는 헬스케어 모니터 에이전트(HMA)를 제안한다. 이 에이전트는 유비쿼터스 헬스케어 환경에 적용되며, 건강상태를 인지하기 위한 증상패턴으로 바이오 센서 및 환자의 가족력으로부터 생성된 데이터를 사용한다. 손실 값이 나타나면 HMA는 분류하기 전에 증상패턴의 손실 값을 채우기 위한 예측 알고리즘을 수행한다. 시뮬레이션 결과 HMA를 사용한 예측알고리즘이 다른 방법들에 비해 더 정확하게 증상패턴을 분류함을 보여 주었다. The ubiquitous healthcare environment is one of the systems that benefit from wireless sensor network. But one of the challenges with wireless sensor network is its high loss rates when transmitting data. Data from the biosensors may not reach the base stations which can result in missing values. This paper proposes the Health Monitor Agent (HMA) to gather data from the base stations, predict missing values, classify symptom patterns into medical conditions, and take appropriate action in case of emergency. This agent is applied in the Ubiquitous Healthcare Environment and uses data from the biosensors and from the patient`s medical history as symptom patterns to recognize medical conditions. In the event of missing data, the HMA uses a predictive algorithm to fill missing values in the symptom patterns before classification. Simulation results show that the predictive algorithm using the HMA makes classification of the symptom patterns more accurate than other methods.

비구조화 P2P 시스템에서 이동에이전트를 이용한 Peer의 속성기반 계층적 클러스터링

마이클안젤로살보 ( Michael Angelo G. Salvo ),마테오로미오 ( Romeo Mark A. Mateo ),이재완 ( Jaewan Lee ) 한국인터넷정보학회 2009 인터넷정보학회논문지 Vol.10 No.4

비구조화 P2P 시스템은 오늘날 인터넷에서 가장 널리 사용되지만, 파일의 배치는 임의로 이루어지며, Peer와 컨텐츠 간에는 어떤 상관관계도 존재하지 않는다. 또한 보낸 모든 질의가 원하는 데이터를 찾았는지에 대한 보장도 없다. 본 논문에서는 비구조화된 P2P시스템에서 군집형 계층 클러스터링을 사용하여 노드들을 클러스터화함으로써 검색을 향상시키는 방법을 제시한다. 제안한 기법과 k-means를 사용한 기법 간에 노드 클러스터링을 위한 지연시간을 비교하였다. 또한 제안한 알고리즘, k-means 클러스터링, 클러스터링을 사용하지 않은 방법간에 한 네트워크 토폴로지에서 데이터를 찾기 위한 지연시간에 대해 시뮬레이션을 수행하였다. 시뮬레이션 결과 제안한 기법의 지연시간이 다른 방법들보다 짧았음을 알 수 있었다. Unstructured peer-to-peer systems are most commonly used in today`s internet. But file placement is random in these systems and no correlation exists between peers and their contents. There is no guarantee that flooding queries will find the desired data. In this paper, we propose to cluster nodes in unstructured P2P systems using the agglomerative hierarchical clustering algorithm to improve the search method. We compared the delay time of clustering the nodes between our proposed algorithm and the k-means clustering algorithm. We also simulated the delay time of locating data in a network topology and recorded the overhead of the system using our proposed algorithm, k-means clustering, and without clustering. Simulation results show that the delay time of our proposed algorithm is shorter compared to other methods and resource overhead is also reduced.

Synthesis and Crystal Structure of a New Quaternary Nitride, Li₄Ca₁₃Ge₆N₁₈

Park, Dong-Gon,Salvo, Francis J. Di Korean Chemical Society 2012 Bulletin of the Korean Chemical Society Vol.33 No.5

Image quality assessment of pre-processed and post-processed digital panoramic radiographs in paediatric patients with mixed dentition

Isti Rahayu Suryani,Natalia Salvo Villegas,Sohaib Shujaat,Annelore De Grauwe,Azhari Azhari,Suhardjo Sitam,Reinhilde Jacobs 대한영상치의학회 2018 Imaging Science in Dentistry Vol.48 No.4

Purpose: To determine the impact of an image processing technique on diagnostic accuracy of digital panoramic radiographs for the assessment of anatomical structures in paediatric patients with mixed dentition. Materials and Methods: The study consisted of 50 digital panoramic radiographs of children aged from 6 to 12 years, which were later on processed using a dedicated image processing method. A modified clinical image quality evaluation chart was used to evaluate the diagnostic accuracy of anatomical structures in maxillary and mandibular anterior and maxillary premolar region of processed images. Results: A statistically significant difference was observed between pre and post-processed evaluation of anatomical structures (P<0.05) in the maxillary and mandibular anterior region. The anterior region was found to be more accurate in post-processed images. No significant difference was observed in the maxillary premolar region (P>0.05). The Inter-observer and intra-observer reliability of both pre and post processed images were excellent (>0.82) for anterior region and good (>0.63) for premolar region. Conclusion: The application of image processing technique in digital panoramic radiography can be considered a reliable method for improving the quality of anatomical structures in paediatric patients with mixed dentition.

RB1 alteration and poor prognosis in women with high-grade neuroendocrine carcinoma of the uterine cervix: a NeCTuR study

Alejandra Flores Legarreta,Gloria Salvo,Naomi R. Gonzales,Gary Chisholm,R. Tyler Hillman,Michael Frumovitz 대한부인종양학회 2023 Journal of Gynecologic Oncology Vol.34 No.4

Objective: To describe the gene alteration status in high-grade neuroendocrine cervical carcinoma (NECC) specimens and to explore the potential association of unique gene alterations with survival. Methods: Results from tumor-based molecular testing on specimens from women with high-grade NECC in the Neuroendocrine Cervical Tumor Registry were reviewed and analyzed. Tumor specimens could be from primary or metastatic sites and obtained at initial diagnosis, during treatment, or at recurrence. Results: Molecular testing results were available for 109 women with high-grade NECC. The genes most frequently mutated were PIK3CA (mutated in 18.5% of patients), TP53 (17.4%), and MYC (14.5%). Other targetable alterations identified were alterations in KIT (7.3%), KRAS (7.3%), and PTEN (7.3%). Women with tumors having an RB1 alteration (6.4%) had a median overall survival (OS) of 13 months, compared to 26 months for women with tumors that did not have an RB1 alteration (p=0.003). None of the other genes evaluated were shown to be associated with OS. Conclusion: Although no individual alteration was found in a majority of tumor specimens from patients with high-grade NECC, a large proportion of women with this disease will have at least one targetable alteration. Treatments based on these gene alterations may offer additional targeted therapies for women with recurrent disease, who currently have very limited therapeutic options. Patients with tumors that harbor RB1 alterations have decreased OS.

Validation of Actinides Nuclear Cross-Section Using Pile-Oscillation Experiments Performed at MINERVE Facility

D. Bernard,P. Leconte,A. Gruel,M. Antony,A. Pepino,J. Di Salvo,A. Lecluze,J-F. Ledoux,C. Morel,B. Sabatin 한국물리학회 2011 THE JOURNAL OF THE KOREAN PHYSICAL SOCIETY Vol.59 No.23

The CEA is deeply involved in a research program (Material Test Reactor and Zero Power Reactor) concerning the nuclear fuel advanced studies (actinides, plutonium), the waste management, the scientific and technical support of French PWR reactors and EPR reactor, and innovative systems. In this framework, specific neutron integral experiments have been carried out in the critical ZPR facilities of the CEA Cadarache such as MINERVE, EOLE and MASURCA. This paper deals with MINERVE Pool Reactor experiments. MINERVE is mainly devoted to neutronics studies of different reactor core types. The aim is to improve the knowledge of the integral absorption cross sections of actinides (OSMOSE program). The results show a very good accuracy of JEFF-3.1.1 files except for ²⁴¹Am(n,γ) which seems to be underestimated by about (-6± 2)% in the thermal and epithermal neutron energy range.

A novel pathogen detection system based on high-resolution CE-SSCP using a triblock copolymer matrix

Shin, Gi Won,Hwang, Hee Sung,Seo, Sang Woo,Oh, Mi-Hwa,Ryu, Chang Y.,Salvo, Charles J.,Feldman, Shaina,Doh, Junsang,Jung, Gyoo Yeol WILEY-VCH Verlag 2010 Journal of Separation Science Vol.33 No.11

<P>Although CE-SSCP analysis combined with 16S ribosomal RNA gene-specific PCR has enormous potential as a simple and versatile pathogen detection technique, low resolution of CE-SSCP causes the limited application. Among the experimental conditions affecting the resolution, the polymer matrix is considered to be most critical to improve the resolution of CE-SSCP analysis. However, due to the peak broadening caused by the interaction between hydrophobic moiety of polymer matrices and DNA, conventional polymer matrices are not ideal for CE-SSCP analysis. A poly(ethyleneoxide)-poly(propyleneoxide)-poly(ethyleneoxide) (PEO-PPO-PEO) triblock copolymer, with dynamic coating ability and a propensity to form micelles to minimize exposure of hydrophobic PPO block to DNA, can be an alternative matrix. In this study, we examined the resolution of CE-SSCP analysis using the PEO-PPO-PEO triblock copolymer as the polymer matrix and four same-sized DNA fragments of similar sequence content. Among 48 commercially available PEO-PPO-PEO triblock copolymers, three were selected due to their transparency in the operable range of viscosity and PEO<SUB>137</SUB>PPO<SUB>43</SUB>PEO<SUB>137</SUB> exhibited the most effective separation. Significant improvement in resolution allowed discrimination of the similar sequences, thus greatly facilitated CE-SSCP analysis compared to the conventional polymer matrix. The results indicate that PEO-PPO-PEO triblock copolymer may serve as an ideal matrix for high-resolution CE-SSCP analysis.</P>