An effective analysis of clinical trials data involves analyzing different types of data such as heterogeneous and high dimensional time series data. The current time series analysis methods generally assume that the series at hand have sufficient length to apply statistical techniques to them. Other ideal case assumptions are that data are collected in equal length intervals, and while comparing time series, the lengths are usually expected to be equal to each other. However, these assumptions are not valid for many real data sets, especially for the clinical trials data sets. An addition, the data sources are different from each other, the data are heterogeneous, and the sensitivity of the experiments varies by the source. Approaches for mining time series data need to be revisited, keeping the wide range of requirements in mind. In this paper, we propose a novel approach for information mining that involves two major steps: applying a data mining algorithm over homogeneous subsets of data, and identifying common or distinct patterns over the information gathered in the first step. Our approach is implemented specifically for heterogeneous and high dimensional time series clinical trials data. Using this framework, we propose a new way of utilizing frequent itemset mining, as well as clustering and declustering techniques with novel distance metrics for measuring similarity between time series data. By clustering the data, we find groups of analytes (substances in blood) that are most strongly correlated. Most of these relationships already known are verified by the clinical panels, and, in addition, we identify novel groups that need further biomedical analysis. A slight modification to our algorithm results an effective declustering of high dimensional time series data, which is then used for "feature selection." Using industry-sponsored clinical trials data sets, we are able to identify a small set of analytes that effectively models the state of normal health.

No abstract

No abstract

~ radar ~t1eri iizerinde bulunan istemsiz modiilasyonlar kullamlarak radar parmak izinin olUt" turulmasJ. i~ yem bir ytintem tinerilInqtir. Dnerilen ytintem radar ~ti iizerindeki istemsiz modiilasyonIan Varyasyonel Kip AyrqbnCl (VKA) Ue bUqeolerine a)'ll"lll"llk bu bUqeoleri karakterize eden tiznitelilder besaplamaktacbr. Ge~ radarlara ait olan veriler kullamlarak yapIlan analizler sonucunda onerilen ytintemin veri setindeki radarlan yiiksek bqarun ile ayrqbrabildigi gtisterilInqtir.

Özetçe -Elektronik Harp (EH) sistemleri için ortamda yayın yapan bir radarın tespiti ve ilgili radarın fonksiyonunun belirlenmesi, sistemin en önemli görevlerinden biridir. Bu çalışmada, EH sistemleri tarafından ölçülen radar parametreleri kullanılarak radarların Elektronik Karşı Tedbir (EKT) kullanım konseptine uygun olarak fonksiyonlarının belirlenmesi hedeflenmiştir. Çok Görevli Ögrenme ve Tek Görevli Ögrenme sinir agları probleme uyarlanmıştır. Sınıflandırıcı öncesinde aşırı örnekleme, aralık degerleri için nicemleme ve sınıf degerleri için gruplama ön işlemleri yapılmıştır. Çok Görevli Ögrenme tekniginin performansının Tek Görevli Ögrenme teknigininkinden daha iyi oldugu gözlenmiştir. Sınıflandırıcı öncesinde uygulanan aşırı örnekleme algoritmasının, ön işlemler neticesinde elde edilen verisetinin ve gruplandırılmış sınıfların bir veya daha fazlasının kullanımıyla her iki metodun performanslarının arttıgı gözlenmiştir.Anahtar Kelimeler-Radar Fonksiyon Sınıflandırma, Çok Görevli Ögrenme, Makine Ögrenmesi, Elektronik Harp Abstract-The detection of a radar emittting signal and determining the associated radar function are among the most important duties of electronic warfare (EW) systems. In this study, the classification of radar function in accordance with Electronic Countermeasure (ECM) usage concept is aimed by using the radar parameters measured by EW systems. Multitask learning and single task learning neural networks are applied to this problem. Oversampling prior to classifier, quantization for interval values and grouping of class values are done in the pre-processing step. It is shown by the experimental results that, multitask learning technique outperforms single task learning technique. It is clearly observed that utilizing one or more of (1) oversampling algorithm, (2) preprocessed data set and (3) the grouped classes increases the performance of both methods.