http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Performance Evaluation of YOLOv3 and YOLOv4 Detectors on Elevator Button Dataset for Mobile Robot
Sumaira Manzoor,Eun-Jin Kim,Gun-Gyo In,Tae-Yong Kuc 제어로봇시스템학회 2021 제어로봇시스템학회 국제학술대회 논문집 Vol.2021 No.10
The performance evaluation of an AI network model is the important part for building an effective solution before its deployment in real-world on the robot. In our study, we have implemented YOLOv3-tiny and YOLOv4-tiny darknet based frameworks for performance evaluation of the elevator button recognition task and tested both variants on image and video datasets. The objective of our study is two-fold: First, to overcome the limitation of elevator buttons dataset by creating new dataset and increasing its quantity without compromising the quality; Second, to provide a comparative analysis through experimental results and the performance evaluation of both detectors using four machine learning metrics. The purpose of our work is to assist the researchers and developers in decision making of suitable detector selection for deployment in the elevator robot towards button recognition application. The results show that YOLOv4-tiny outperforms YOLOv3-tiny with an overall accuracy of 98.60% compared to 97.91% at 0.5 IoU.
Qualitative Analysis of Single Object and Multi Object Tracking Models
Sumaira Manzoor,Kyu-Hyun Sung,Yueyuan Zhang,Ye-Chan An,Tae-Yong Kuc 제어로봇시스템학회 2022 제어로봇시스템학회 국제학술대회 논문집 Vol.2022 No.11
Tracking the object(s) of interest in the real world is one of the most salient research areas that has gained widespread attention due to its applications. Although different approaches based on traditional machine learning and modern deep learning have been proposed to tackle the single and multi-object tracking problems, these tasks are still challenging to perform. In our work, we conduct a comparative analysis of eleven object trackers to determine the most robust single object tracker (SOT) and multi-object tracker (MOT). The main contributions of our work are (1) employing nine pre-trained tracking algorithms to carry out the analysis for SOT that include: SiamMask, GOTURN, BOOSTING, MIL, KCF, TLD, MedianFlow, MOSSE, CSRT; (2) investigating MOT by integrating object detection models with object trackers using YOLOv4 combined with DeepSort, and CenterNet coupled with SORT; (3) creating our own testing videos dataset to perform experiments; (4) performing the qualitative analysis based on the visual representation of results by considering nine significant factors that are appearance and illumination variations, speed, accuracy, scale, partial and full-occlusion, report failure, and fast motion. Experimental results demonstrate that SiamMask tracker overcomes most of the environmental challenges for SOT while YOLOv+DeepSort tracker obtains good performance for MOT. However, these trackers are not robust enough to handle full occlusion in real-world scenarios and there is always a trade-off between tracking accuracy and speed.
Sumaira Manzoor,Sung-Hyeon Joo,Tae-Yong Kuc 제어로봇시스템학회 2019 제어로봇시스템학회 국제학술대회 논문집 Vol.2019 No.10
In this paper, we consider the problem of object recognition for a mobile robot in an indoor environment using two different vision approaches. Our first approach uses HOG descriptor with SVM classifier as traditional machine vision model while the second approach uses Tiny-YOLOv3 as modern deep learning model. The purpose of this study is to gain intuitive insight of both approaches for understanding the principles behind these techniques through their practical implementation in real world. We train both approaches with our own dataset for doors. The proposed work is assessed through the real-world implementation of both approaches using mobile robot with Zed camera in real world indoor environment and the robustness has been evaluated by comparing and analyzing the experimental results of both models on same dataset.
A Semantic Navigation Framework for Multi-Floor Building Environment
Sung-Hyeon Joo,Sumaira Manzoor,Tae-Yong Kuc 제어로봇시스템학회 2021 제어로봇시스템학회 국제학술대회 논문집 Vol.2021 No.10
Autonomous mobile robot navigation in a multi-floor building is a complex task requiring various components: planning, recognition, and localization. Despite the significant progress, an essential issue in a multi-floor environment is to endow the mobile robot with autonomous navigation inside the building via the elevator. Our proposed neuro-inspired cognitive framework provides an efficient solution to this problem based on semantic navigation. In this paper, we utilize three components of our proposed framework, which are the semantic modeling framework (SMF), semantic information processing (SIP) module, and semantic autonomous navigation (SAN) module. The SMF uses Triplet Ontological Semantic Model (TOSM) to build the semantic models of the environment. The SIP module includes active environment perception components, and the SAN module contains a behavior planner and behavior database. The development, integration, and interaction among these components based on semantic understanding is the major contribution of our proposed framework. The experimental results demonstrate that our framework effectively enables the mobile robot to move to different floors using the elevator autonomously.
Facile fabrication of ternary CuO/CuS/ZnS for photodegradation of methylene blue
Abudllah Muhammad,Al Huwayz Maryam,Alwadai Norah,Manzoor Sumaira,Nisa Mehar Un,John Peter,Ghori Muhammad Ishfaq,Aman Salma,Al-Buriahi M. S.,Ashiq Muhammad Naeem 한국세라믹학회 2023 한국세라믹학회지 Vol.60 No.3
Synthetic dyes play a vital role in our daily life because they are utilized in products ranging from clothing to leather acces- sories. Unfortunately, these carcinogenic dyes are discharged into water streams any prior process considering the health problems in aquatic life and human beings. It is mandatory to separate noxious materials from wastewater. Semiconductors are viewed as a viable possibility for photocatalytic mineralization of noxious dyes. Herein, facile in situ hydrothermal approach (HT) was utilized for the fabrication of CuO, CuS ZnS, and their ternary CuO/CuS/ZnS nanocomposite. The fab- ricated CuO/CuS/ZnS nanocomposites were analysed through powder X-ray diff raction (PXRD), Fourier-transform infrared spectroscopy (FTIR), scanning electron microscope equipped with energy-dispersive X-ray (SEM–EDX), and ultraviolet– visible spectroscopy (UV–Vis). Moreover, the optical investigation manifested the bandgap energy value of copper oxide, copper sulphides, zinc sulphides, and ternary CuO/CuS/ZnS nanocomposite, corresponding to 2.63, 3.1, 4.51, and 2.2 eV, respectively, which was estimated from absorption spectrum. Subsequently, the photocatalytic results of CuO, CuS, ZnS, and ternary CuO/CuS/ZnS nanocomposite against methylene blue (MB) dye were 71%, 42%, 45%, and 96%, respectively. The photocatalytic scheme showed the role of hydroxyl radicals and electrons in the photodegradation reaction. Our fi nding suggests that the fabricated nanocomposite shows superior photocatalytic efficiency towards mineralization of methylene blue which can be used for commercial applications.
Facile synthesis of rGO/PANI/ZnO ternary nanocomposites for energy storage devices
Abbas Sajid,Elqahtani Zainab Mufarreh,Yasmeen Ghazala,Manzoor Suryyia,Manzoor Sumaira,Al-Buriahi M. S.,Alrowaili Z. A.,Ashiq Muhammad Naeem 한국세라믹학회 2023 한국세라믹학회지 Vol.60 No.1
Due to the dire energy needs and the unavailability of energy storage devices, supercapacitors have become an inescapable substitute for energy storage systems. As a high energy density electrode material, we offer rGO/PANI/ZnO ternary nanocomposite designed via the polymerization method and are characterized by various analytical techniques. The results show that rGO/PANI/ZnO has the best capacitive behavior, with a specific capacity of 1546 F/g at 2 mV/s on the eggshell membrane electrode (ESME). The nanocomposite rGO/PANI/ZnO, on the other hand, presented the best cycling stability, retaining 97% of capacity after 3000 cycles. This is due to the fast transfer of electrons between rGO/ZnO and PANI in an electrochemical charge storage device. This research encompasses an enhanced flexible PANI-based electrode to become viable innovative wearable sensor alternative.
Abdullah Muhammad,Alharbi Fatemah Farraj,Khosa Rabia Yasmin,Alburaih Huda A.,Manzoor Sumaira,Abid Abdul Ghafoor,Ali Haitham Elhosiny,Waheed Muhammad Suleman,Ansari Muhammad Numair,Farid Hafiz Muhammad 한국화학공학회 2023 Korean Journal of Chemical Engineering Vol.40 No.6
Manganese ferrite offers several advantages when employed as an electrocatalytic material for supercapacitors, including outstanding cycle stability and energy capacity. When compared to identical-metal sulfides, specific capacitance (Csp) of MnFe2O4 remains inadequate. So, using the hydrothermal synthesis technique, partial sulfur doping of MnFe2O4 was achieved to investigate the synergetic effect of oxides and sulfides. Various spectroscopic and microscopic studies demonstrate that adding sulfur atoms into MnFe2O4 increases the lattice parameters, which improves electrochemical performance. At a current density around 2 A g−1, then calculating MnFe2O4 with partial sulfur doping has a Csp of 1,201.60 F g−1, that is greater than 784.0 F g−1 of pure MnFe2O4. Maximum energy density (Ed) of 93.62 Wh kg−1 was produced with a power density (Pd) of 749 W kg−1. The current study depicts that partial sulfur doping can enhance the electrochemical behavior of MnFe2O4. As a result, the present work shows more effective in field of energy storage by enhancing their poor electrochemical performance.
Munawar Tauseef,Bashir Ambreen,Mukhtar Faisal,Nadeem Muhammad Shahid,Manzoor Sumaira,Ashiq Muhammad Naeem,Khan Shoukat Alim,Koc Muammer,Iqbal Faisal 한국세라믹학회 2023 한국세라믹학회지 Vol.60 No.6
One of the main goals of energy conversion research is to develop effi cient, nonprecious, and stable electrocatalysts to replace defi cient and unstable noble metal catalysts. Hence, this work described metal–organic frameworks (MOFs) derived ZnO/C hybrid via a hydrothermal route grown on the surface of conducting stainless steel substrate (SS). By using multiple physical techniques (XRD, FTIR, TEM, XPS, and EDX), we compared structural and morphological properties of ZnO/C hybrid and MOF-5 electrodes. The electrocatalytic behaviour of amiable and economical ZnO/C/SS catalyst was noticed in catalyzing oxygen evolution reaction (OER) in one mole KOH electrolyzer with low overpotential and excellent stability. Cyclic sweep voltammetry indicated that the ZnO/C/SS hybrid only needs an ultralow overpotential of 282 mV to achieve a current density of 10 mA cm −1 for OER. In addition, ZnO/C/SS with a low Tafel slope of 39.3 mV/dec and higher 0.29 s −1 turnover frequency can serve as a profi cient electrocatalyst compared to commercial ZnO and MOF-5 electrodes. The stability of ZnO/C/SS hybrid electrocatalyst approaching minor chronoamperometric degradation after 55 h. The electrochemical response depicts that the successful synthesis of MOF-derived ZnO/C/SS catalyst provided abundant active centers and boosted an electron- rich environment to promote its future prosperity and facilitate practical applications for electrochemical water-splitting.