Papers by adhiguna mahendra
Airline industry has rapidly increased as many people prefer airplane as airlines offer inflight ... more Airline industry has rapidly increased as many people prefer airplane as airlines offer inflight meals and entertainment and comfortability. The in-flight materials---comfortability---are being laundered in an in-flight service company. This paper aimed to find an optimal schedule for an in-flight service company by minimizing the total operation time in a day. In addition, it helps the company for making decision on purchasing additional machines. The methodology used in this paper were linear programming with assignment and transportation model, scheduling, and simulation to prove the result of optimization. The optimization was conducted using Microsoft Excel Solver and the simulation used a program called as Tecnomatix Plant Simulation. After the optimization was finished, simulation model development was required to check the validity and whether it is applicable for the laundry system within the company. The result of this paper showed the company needs to buy one additional tumble dryer to meet the customers' requirement and the productivity level was increased
Penerbit BRIN eBooks, Mar 17, 2023
Sebagai penerbit ilmiah, Penerbit BRIN mempunyai tanggung jawab untuk terus berupaya menyediakan ... more Sebagai penerbit ilmiah, Penerbit BRIN mempunyai tanggung jawab untuk terus berupaya menyediakan terbitan ilmiah yang berkualitas. Upaya tersebut merupakan salah satu perwujudan tugas Penerbit BRIN untuk turut serta membangun sumber daya manusia unggul dan mencerdaskan kehidupan bangsa sebagaimana yang diamanatkan dalam pembukaan UUD 1945.
AI Startup Strategy
Audience: product/engineering/AI team. Delivery Outlines outcome or value delivered to the custom... more Audience: product/engineering/AI team. Delivery Outlines outcome or value delivered to the customer (end user and developer user) in each release. Outlines a detailed list of features delivered in each release, including internal features. Features Conceals internal features that do not directly impact customers. Every feature committed in each release will be visible. Reviewer Various stakeholders reviewed what to share, how much to share, and when to share. Reviewed and mutually agreed by both PM and engineering/AI team.
Penerbit BRIN eBooks, Mar 17, 2023
2022 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)
IEEE Access
Detecting a moving pedestrian is still a challenging task in a smart surveillance system due to d... more Detecting a moving pedestrian is still a challenging task in a smart surveillance system due to dynamic scenes. Locating and detecting the moving pedestrian simultaneously influences the development of an integrated but low-resource smart surveillance system. This paper proposes a novel approach to locating and detecting moving pedestrians in a video. Our proposed method first locates the region of interest (ROI) using a background subtraction algorithm based on guided filtering. This novel background subtraction algorithm allows our method to also filter unexpected noises at the same time, which could benefit the performance of our proposed method. Subsequently, the pedestrians are detected using YOLOv2, YOLOv3, and YOLOv4 within the provided ROI. Our proposed method resulted in more processing frames per second compared with previous approaches. Our experiments showed that the proposed method has a competitive performance in the CDNET2014 dataset with a fast-processing time. It costs around ~50 fps in CPU to classify moving pedestrians and maintain a highly accurate rate. Due to its fast processing, the proposed approach is suitable for IoT or smart surveillance device which has limited resource. INDEX TERMS moving object analysis; pedestrian localization and detection, convolutional neural network (CNN); integrated surveillance system; YOLO.
한국멀티미디어학회 학술발표논문집, May 1, 2010
Proceedings of the International Conference on Engineering and Information Technology for Sustainable Industry, 2020
Airline industry has rapidly increased as many people prefer airplane as airlines offer inflight ... more Airline industry has rapidly increased as many people prefer airplane as airlines offer inflight meals and entertainment and comfortability. The in-flight materials---comfortability---are being laundered in an in-flight service company. This paper aimed to find an optimal schedule for an in-flight service company by minimizing the total operation time in a day. In addition, it helps the company for making decision on purchasing additional machines. The methodology used in this paper were linear programming with assignment and transportation model, scheduling, and simulation to prove the result of optimization. The optimization was conducted using Microsoft Excel Solver and the simulation used a program called as Tecnomatix Plant Simulation. After the optimization was finished, simulation model development was required to check the validity and whether it is applicable for the laundry system within the company. The result of this paper showed the company needs to buy one additional t...
[...]L’inspection des surfaces considerees est basee sur la technique d’Inspection par Particules... more [...]L’inspection des surfaces considerees est basee sur la technique d’Inspection par Particules Magnetiques (Magnetic Particle Inspection (MPI)) qui revele les defauts de surfaces apres les traitements suivants : la surface est enduite d’une solution contenant les particules, puis magnetisees et soumise a un eclairage Ultra-Violet. La technique de controle non destructif MPI est une methode bien connue qui permet de reveler la presence de fissures en surface d’un materiau metallique. Cependant, une fois le defaut revele par le procede, ladetection automatique sans intervention de l’operateur en toujours problematique et a ce jour l'inspection basee sur le procede MPI des materiaux tubulaires sur les sites de production deVallourec est toujours effectuee sur le jugement d’un operateur humain. Dans cette these, nous proposons une approche par vision artificielle pour detecter automatiquement les defauts a partir des images de la surface de tubes apres traitement MPI. Nous avons developpe etape par etape une methodologie de vision artificielle de l'acquisition d'images a la classification.[...] La premiere etape est la mise au point d’un prototype d'acquisition d’images de la surface des tubes. Une serie d’images a tout d’abord ete stockee afin de produire une base de donnees. La version actuelle du logiciel permet soit d’enrichir la base de donnee soit d’effectuer le traitement direct d’une nouvelle image : segmentation et saisie de la geometrie (caracteristiques de courbure) des defauts. Mis a part les caracteristiques geometriques et d’intensite, une analyse multi resolution a ete realisee sur les images pour extraire des caracteristiques texturales. Enfin la classification est effectuee selon deux classes : defauts et de non-defauts. Celle ci est realisee avec le classificateur des forets aleatoires (Random Forest) dont les resultats sontcompares avec les methodes Support Vector Machine et les arbres de decision.La principale contribution de cette these est l'optimisation des parametres utilisees dans les etapes de segmentations dont ceux des filtres de morphologie mathematique, du filtrage lineaire utilise et de la classification avec la methode robuste des plans d’experiences (Taguchi), tres utilisee dans le secteur de la fabrication. Cette etape d’optimisation a ete completee par les algorithmes genetiques. Cette methodologie d’optimisation des parametres des algorithmes a permis un gain de temps et d’efficacite significatif. La seconde contribution concerne la methode d’extraction et de selection des caracteristiques des defauts. Au cours de cette these, nous avons travaille sur deux bases de donnees d’images correspondant a deux types de tubes : « Tool Joints » et « Tubes Coupling ». Dans chaque cas un tiers des images est utilise pour l’apprentissage. Nous concluons que le classifieur du type« Random Forest » combine avec les caracteristiques geometriques et les caracteristiques detexture extraites a partir d’une decomposition en ondelettes donne le meilleur taux declassification pour les defauts sur des pieces de « Tool Joints »(95,5%) (Figure 1). Dans le cas des « coupling tubes », le meilleur taux de classification a ete obtenu par les SVM avec l’analyse multiresolution (89.2%) (figure.2) mais l’approche Random Forest donne un bon compromis a 82.4%. En conclusion la principale contrainte industrielle d’obtenir un taux de detection de defaut de 100% est ici approchee mais avec un taux de l’ordre de 90%. Les taux de mauvaises detections (Faux positifs ou Faux Negatifs) peuvent etre ameliores, leur origine etant dans l’aspect de l’usinage du tube dans certaines parties, « Hard Bending ».De plus, la methodologie developpee peut etre appliquee a l’inspection, par MPI ou non, de differentes lignes de produits metalliques
Http Www Theses Fr, Nov 8, 2012
2015 International Conference on Data and Software Engineering (ICoDSE), 2015
Image Processing: Machine Vision Applications V, 2012
ABSTRACT Automatic industrial surface inspection methodology based on Magnetic Particle Inspectio... more ABSTRACT Automatic industrial surface inspection methodology based on Magnetic Particle Inspection is developed from image acquisition to defect classification. First the acquisition system is optimized, then tubular material images are acquired, reconstructed then stored. The characteristics of the crack-like defects with respect to its geometric model and curvature are used as a priori knowledge for mathematical morphology and linear filtering. After the segmentation and binarization of the image, vast amount of defect candidates exist. Finally classification is performed with decision tree learning algorithm due to its robustness and speed. The parameters for mathematical morphology, linear filtering and classification are analyzed and optimized with Design Of Experiments based on Taguchi approach. The most significant parameters obtained may be analyzed and tuned further. Experiments are performed on tubular materials and evaluated by its accuracy and robustness by comparing ground truth and processed images. The result is promising with 97 % True Positive and only 0.01 % False Positive rate on the testing set.
Uploads
Papers by adhiguna mahendra