Wyniki wyszukiwania - BazTech

1

Analysis recognition of Ghost Pepper and Cili-Padi using Mask RCNN and YOLO

Yin L. L., Zainudin M.N.Shah, Saad W. H. Mohd, Sulaiman N. A., Idris M. I., Kamarudin M. R., Mohamed R., Razak M. S. J. A.

Przegląd Elektrotechniczny

|

2023

|

R. 99, nr 8

92--97

EN

Fruit harvesting robots have made headlines in the agricultural industry in recent years. A fruit recognition system would assist farmers or agricultural industry practitioners in lessening workloads while increasing crop yields. Due to the similar characteristics of chili fruits, approximating the chili according to their grades and identifying its maturity will be difficult. Furthermore, because of their different appearances and sizes, distinguishing between the fruits and the leaves becomes difficult. As a result, a real-time object detection algorithm called You Only Look Once (YOLO) and Mask-RCNN is investigates in order to distinguish the fruit from its plant based on its shape and colour. YOLO version 5 (YOLOv5) uses to define and distinguish the chili fruits and its leaves based on two characteristics; shape and colour. The CSPDarknet network serves as the backbone in YOLOv5, where feature extraction and mosaic augmentation has used to combine multiple images into a single image. Total 391 images has divided into two subsets: training and testing, with an 80:20 ratio. YoLov5 is notable for its ability to detect small objects with high precision in a short amount of time while Mask-RCNN has proven its ability to recognize a chili fruits with high precision above 90%. The classification is evaluated using precision, recall, loss function, and inference time.

PL

Roboty do zbioru owoców trafiły w ostatnich latach na pierwsze strony gazet w branży rolniczej. System rozpoznawania owoców pomógłby rolnikom lub praktykom z branży rolniczej w zmniejszeniu obciążenia pracą przy jednoczesnym zwiększeniu plonów. Ze względu na podobne cechy owoców chili przybliżenie chili według ich klas i określenie stopnia dojrzałości będzie trudne. Ponadto, ze względu na ich różny wygląd i rozmiary, odróżnienie owoców od liści staje się trudne. W rezultacie algorytm wykrywania obiektów w czasie rzeczywistym o nazwie You Only Look Once (YOLO) i Mask-RCNN jest badany w celu odróżnienia owocu od rośliny na podstawie jego kształtu i koloru. YOLO wersja 5 (YOLOv5) służy do definiowania i rozróżniania owoców chili i ich liści w oparciu o dwie cechy; kształt i kolor. Sieć CSPDarknet służy jako szkielet w YOLOv5, w którym wyodrębnianie cech i rozszerzanie mozaiki wykorzystano do łączenia wielu obrazów w jeden obraz. Łącznie 391 obrazów zostało podzielonych na dwa podzbiory: treningowe i testowe, ze stosunkiem 80:20. YoLov5 wyróżnia się zdolnością do wykrywania małych obiektów z dużą precyzją w krótkim czasie, podczas gdy Mask-RCNN udowodnił swoją zdolność rozpoznawania owoców chili z wysoką precyzją powyżej 90%. Klasyfikacja jest oceniana za pomocą precyzji, pamięci, funkcji utraty i czasu wnioskowania.

2

Characterisation of nano-thin film GO/TiO2 layers for Kretschmann-based surface plasmon resonance visible sensing using FDTD method

Khairulazdan N. B., Mohamed R., Berhanuddin D. D., Menon P. S.

Optica Applicata

|

2021

|

Vol. 51, nr 4

579--587

EN

Kretschmann-based surface plasmon resonance (K-SPR) is suitable for biomolecular sensing which provides label-free and quick detection results with real-time analysis. In this work, we have investigated the effect of graphene oxide (GO) with titanium dioxide (TiO2) thin films that are placed in hybrid above metal layers such as gold (Au), silver (Ag) and copper (Cu) with the presence of chromium (Cr) as an adhesive layer. The thickness of the Au, Ag and Cu metal thin films were optimized to 40, 30 and 30 nm, respectively, with a fixed thickness of GO of 2 nm and TiO2 of 1.9 nm. The sensing was evaluated for SPR excitation at three different visible wavelengths of 633, 670 and 785 nm. The performance of sensing was analyzed based on the reflectance intensity and full-width at half-maximum (FWHM) of the spectrum using the finite-difference time-domain (FDTD) method. The sensitivity was calculated for analyte sensing in dielectric mediums of air versus water. The sensitivity increment percentage (%∆S ) was determined when comparing analyte detection using Cr/metal and Cr/metal/GO/TiO2 sensor structures. The highest sensitivity of 94.51 deg/RIU was achieved for Cr/Cu/GO/TiO2 K-SPR sensor at 633 nm wavelength.

3

Experimental comparison of vibration and acoustic emission signal analysis using kurtosis-based methods for induction motor bearing condition monitoring

Othman M. S., Nuawi M. Z., Mohamed R.

Przegląd Elektrotechniczny

|

2016

|

R. 92, nr 11

208--212

EN

Vibration and acoustic emission (AE) signal measurement are established tools in condition monitoring of bearings. This paper presents a comparison between two statistical methods, i.e. kurtosis, and another kurtosis based method called I-kaz using simultaneous signal of vibration and AE. The existence of harmonics fault frequencies in envelope spectrums also have been discussed. The results reveal that both signals are suitable for induction motor bearing fault detection.

PL

W artykule przedstawiono porównanie dwóch metod statystycznych, kurtozy oraz I-kaz używająnych do diagnostyki łożyskowania maszyn elektrycznych. Jako sygnały diagnostyczne wykorzystuuje się pomiar wibracji i emisji akustycznej.

4

Performance evaluation modeling a Microelectromechanical system based Finite Element piezoelectric Shear Actuated Beam

Sarker M. R., Mohamed A., Mohamed R.

Przegląd Elektrotechniczny

|

2015

|

R. 91, nr 3

5-8

EN

This paper presents the modeling a Microelectromechanical systems (MEMS) based Piezoelectric shear actuated beam by using COMSOL Multiphysics software of version 4.3a. The overall dimensions model of the beam is of 0.1-m long, 0.03-m width and 0.018-m thickness. For this model the structural mechanics boundary conditions are of the cantilever beam is fixed at its surfaces at x = 0 and that all other surfaces are free. In this model applied, the different materials (i.e., Silicon, Titanium, Barium titanate, Lead zirconate titanate, Material) with voltages between the top and bottom surfaces of the piezoceramic domain (i.e., 15V, 35V) have been analyzed. Firstly, select the Structural Mechanics of the Piezoelectric Devices and analyzed changing the selecting physics. Secondly, defining the Geometry on deflection of sandwiched beam is setting the boundary condition and analyzed changing of the beam. Thirdly, the beam is composed of a 0.001-m thick flexible foam core sandwiched by two 0.002-m thick silicon and titanium layers. In the Fourth step, bend of beam is analyzed by changing both materials of sandwiched beam and mashing of the defection beam is display by changing both thickness and electric potential. Finally, the results of analysis allowed to conclude us to design a piezoelectric shear actuated beam with different ranges and resolutions, under the condition of changing both thickness and material of electrodes gives the optimum deflection of 0.0308-um and 0.0815-um under 15V input voltage with different materials.

PL

W artykule zaprezentowano metodę projektowania układów typu MEMS na przykładzie piezoelektrycznego siłownika. Dla siłownika zaproponowano model numeryczny oraz warunki brzegowe. Przedstawiono obliczenia dla różnych materiałów i różnych konstrukcji.

5

A Batteryless low Input Voltage micro-scale Thermoelectric Based Energy Harvesting Interface Circuit with 100mV Start-up Voltage

Sarker M. R., Mohamed R.

Przegląd Elektrotechniczny

|

2014

|

R. 90, nr 4

49--52

EN

A Batteryless low input voltage micro-scale thermo electric based energy harvesting interface circuit with 0.1V start-up voltage presents in this paper. The active technique and its components have been chosen such as MOSFET and thyristor to design the proposed DC-DC boost converter with low input voltage (i.e., 0.1V) for energy harvesting interface circuit. The minimum working voltage as low as 0.1V an input the equivalent voltage of thermoelectric transducer has been proposed to design the boost converter. This paper presents techniques for the systematic modeling, analysis, and design of interface circuitry used in the equivalent voltage of the micro-scale thermoelectric energy harvesting systems. In the development of active-based circuits, the DC-DC step-up (boost) converter with thyristor have been designed instead of mainly diode and other components because the forward voltage of diode is (0.7V) higher than the incoming input voltage (0.1V). Finally, the complete proposed energy harvester circuit have been designed and simulated using the PSPICE software. The proposed circuit is capable to step-up regulated DC voltage up to 3.75V. The efficiency of the proposed circuit is greater than 65% following the simulation results. This work has focused on the application of micro-devices Wireless Sensor Network (WSN) device can be operated without battery.

PL

W artykule opisano oszczędnościowe źródło napięcia wykorzystujące jedynie siłę temoelektryczną. Układ elektroniczny startuje już przy napięciu zasilania 0.1V i potrafi wytworzyć wyjściowe napięcie o poziomie blisko 4 V. Jako zastosowanie układu przewiduje się możliwość zasilania czujników bezprzewodowych jedynie z baterii słonecznej.