This paper describes a laboratory application for the forecasting the dielectric properties, using an artificial neural network embedded in a microprocessor. The dielectric permittivity and loss factor of the insulation material were determined as a function o…
Search
Year: 2017 ×
Clear filters
28 results for “Neural network, complex-valued neural network, activation function, swish”
The aim of this study is to forecast installed wind power which is a one of the renewable energy resources in Turkey for the year of 2017 based on artificial neural network method using the normalized last ten-year data. An artificial neural network has been c…
In this paper, a structural-output is obtained to estimate 3D human pose using 3D human point cloud and monocular images. The Neural Network takes a human image and 3D pose as inputs and gives outputs a score value. Conditional Random Field (CRF) approach is u…
Taguchi’s robust parameter design focuses on reducing the system variability caused by the noise factors. The results obtained under unrealistic assumptions about the noises may mislead the practitioners when it comes to improving quality in robust design. For…
Social networks are formed from interactions of peoples. Measuring the degree of those relationships requires interpreting connectivity of vertices and extracting information from it. Generally individuals form smaller sub-communities in those networks. Identi…
In the study synchronization was studied using an all-to-all network structure in a multiple system of Kuramoto oscillators. Synchronization performance was first investigated in a weakly connected system, and the effects of link strength and number of oscilla…
Field Programmable Gate Arrays (FPGAs) are configurable logic semiconductor devices which connect by programmable interconnections. They can be reprogrammed to desired application or functionality requirements. VHDL is a one of the hardware descriptive languag…
Evrimsel algoritma ve parçacık sürü algoritması çok uzun zamandır ayrı ayrı çeşitli karmaşık problemlerin çözümünde yaygın olarak kullanılan sezgisel algoritmalardır. Evrimsel algoritma canlıların çoğalmasını ve hayatta kalmak için en iyilerin seçilmesi tekniğ…
The column materials in the form of monodisperse and porous particles were synthesized with regard to test their column performances in Ion Exchange Chromatography (IEC) mode. Particles in the form of poly(glycidil methacrylate-coethyleneglycol dimethacrylate)…
The column materials in the form of monodisperse and porous particles were synthesized with regard to test their column performances in Ion Exchange Chromatography (IEC) mode. Particles in the form of poly(glycidil methacrylate-coethyleneglycol dimethacrylate)…
The column materials in the form of monodisperse and porous particles were synthesized with regard to test their column performances in Ion Exchange Chromatography (IEC) mode. Particles in the form of poly(glycidil methacrylate-coethyleneglycol dimethacrylate)…
Several test suites have been developed to test the statistical properties of random numbers generated from pseudotrue random number generators. Some of these are Crypt-X, Diehard, FIPS 140, NIST 800-22 AIS31 test suites. In this study, web based application o…
Aim of the study: It is important to be able to plan the production transmission and distribution necessary for uninterrupted electricity and to use the electricity more efficiently and to make demand forecasts. For this reason, it is aimed to estimate the ele…
Wireless Sensor Networks have many application fields including both industrial and military usages. They are used for monitoring temperature, distance, light, and motion in laboratories and/or application specific environments. This paper focuses on developin…
In this study, the elimination of zero diffraction order and twin image from three dimensional reconstructed images in digital holography and the image enhancement are desired to achieve in a short time by using hybrid methods. In addition, the brightness of t…
The purpose of this study is to examine the software libraries and data sets used for Deep Learning architectures. Deep Learning brings a different perspective to the field of artificial intelligence. It has begun to be used an incredibly wide field in recent …
In this study, the accelerations caused by the diaphragm movements during respiration were monitored with a 3-axis accelerometer and the measured accelerations were recorded on an SD card. A measurement system for this purpose was developed. The moments in whi…
Nowadays, competition in industrial production has come to the top with technological improvements. In this competitive environment, producers need better quality, faster and less costly production methods. So, the use of industrial robotic systems is becoming…
The aim of this study is to determine instantaneous irradiance and annual percentile sunlit time on the available rooftop floor area of Technical and Social Science Vocational School at Usak University by simulation using open source software. The building of …
Wireless sensor network (WSN) is a distributed system usually comprising a set of autonomous sensors nodes. These sensors are physically small in size and are capable to communicate with each other and capable of conveying data to recipients. In a large number…