Articles — Recent

El análisis estadístico de alta dimensión y tamaño de muestra pequeño (HDLSS) se está aplicando cada vez más en una amplia gama de contextos. En tales situaciones, se ve que el popular método de la Máquina de Vectores Soporte (SVM) sufre de ''Acumulación de datos'' en el margen, lo que puede disminuir la capacidad de generalización del modelo. Esto conduce al desarrollo de la Distance Weighted Discrimination para encontrar un hiperplano separador . En el presente trabajo se revisa y reproduce, con detalle en la derivación y solución de la función de pérdida que se resuelve usando SOCP, del método desarrollado en e implementado en el entorno R\cite{R}. Basado en el trabajo e implementación de se aplica y comparan resultados a conjuntos de datos reales y simulados (en medida de lo posible los mismos conjuntos de datos utilizados que en) Palabras clave: SVM, kernel, R (el ambiente de cómputo estadístico) y datos de alta dimensión con tamaño de muestra pequeño (data High Dimension Low Sample Size).

Juan Ignacio Basilio Flores's CV

With the detectors currently off, LIGO has detected and gathered an abundance of data from the second observing run (O2). Some of which, captures the most recent triggers that are potential candidates for future gravitational waves, are analyzed more thoroughly. My responsibility as a student researcher is to perform independent checks on four of the most recent Compact Binary Coalescence (CBC) triggers. In order to do so, I compare the \(h(t)\) Omega scans of these events to the Gravity Spy classes. Omega scans are a detector characterization tool to help measure the Signal-to-Noise-Ratio (SNR) of transient noises during detections. This helps scientists distinguish the difference between a gravitational wave signal, which looks like a `chirp' versus a glitch in the data. Gravity Spy is a citizen science program that helps LIGO in classifying glitches to improve machine learning for gravitational wave signals. For each event I determine if it looks like one of the known categories of solved or unsolved glitches seen in the Advanced LIGO detectors? My results are then recorded in the O2 event detection checklist. Omega scans are a `burst-type' search pipeline that detect glitches efficiently. The Omega scan is labeled using time measured in seconds on the x-axis, frequency measured in Hz on the y-axis and the signal measured is normalized to demonstrate how `loud' the noise is.

The kernel is a computer program that has complete control over the operating system. It handles the input/output requests and translates them into data-processing instructions for the CPU. It handles not only the memory, but also peripherals. The kernel controls the tasks that are managed in the running system, some of these are running processes, hardware management and handling interrupts, in the kernel space. On the other hand, the user performs in the user space. This separation helps to prevent data interfering that can cause instability and slowness, or worse, malfunctioning application programs that can crash the entire operating system. The process scheduler decides which is the next task to run. In the following project we analyzed the behavior of the scheduler changing the default value of the runtime scheduling, this value is 950000µs for the scheduler real time running variable. According to this, 5% of the CPU time is reserved for processes that are not running under a realtime or deadline scheduling policy. On this project, this value specifies how much of the period time could be used by real-time and deadline scheduled processes on the system.

My cv. Created with the Twenty Seconds CV template.

Created based on the Deedy résumé template

K.M. Imrul Kayes Sikdar's CV

Arslan Tariq's Curriculum Vitae Created with the Deedy résumé template

Daniel Fugisawa de Souza's CV