Hasil Pencarian  ::  Simpan CSV :: Kembali

"The book also surveys various soft computing tools, fuzzy relational calculus (FRC), genetic algorithm (GA) and multilayer perceptron (MLP) to provide a strong foundation for the reader. The supervised approach to pattern classification and model-based approach to occluded object recognition are treated in one framework , one based on either a conventional interpretation or a new interpretation of multidimensional fuzzy implication (MFI) and a novel notion of fuzzy pattern vector (FPV). By combining practice and theory, a completely independent design methodology was developed in conjunction with this supervised approach on a unified framework, and then tested thoroughly against both synthetic and real-life data. In the field of soft computing, such an application-oriented design study is unique in nature. The monograph essentially mimics the cognitive process of human decision making, and carries a message of perceptual integrity in representational diversity. "

"Teknologi telah membantu manusia untuk menyelesaikan berbagai masalah. Salah satu perkembangan yang paling penting adalah perkembangan teknologi penglihatan komputer. Bagi tuna netra yang hidup di kawasan perkotaan, hidup mandiri bukan pilihan yang mustahil. Dan bertransaksi dengan menggunakan uang kertas merupakan bagian dari kemandirian tersebut. Teknologi pengenalan citra melalui penglihatan komputer dapat membantu tuna netra untuk mengenali uang kertas. Sistem pengenalan uang kertas pada penelitian ini menggunakan metode Bag of Word sebagai metode klasifikasi denominasi uang kertas. Geometric Verification diimplementasikan untuk mengatasi kelemahan metode Bag of Words di sisi konsistensi spasial dari fitur citra pada saat pengenalan. Untuk mengetahui performa dari sistem, sistem diuji dengan menggunakan empat parameter uji. Parameter uji yang digunakan adalah variasi resolusi citra uji, variasi salt and pepper noise, variasi gaussian noise, dan variasi jumlah citra yang digunakan pada proses voting untuk klasifikasi. Berdasarkan hasil pengujian, sistem bekerja dengan baik dengan akurasi mencapai 82.86% dengan dataset sejumlah 714 citra.

---

Technology has helped people to solve various problems. One of the most important development is computer vision technology. For blind people who live in urban areas, to live independently is not an impossible option. And transaction using physical banknote is part of the independence. Image recognition technology through computer vision can help blind people to recognize the banknote. The banknote recognition system in this study is using Bag of Word as a method for classifying banknotes denomination. Geometric Verification is implemented to overcome the shortcomings of Bag of Words method in spatial consistency of image features during recognition. To determine the performance of the system, the system was tested by using four test parameters. Test parameters used is a variation of test image resolution, salt and pepper noise variations, gaussian noise variations, and variations in the number of images selected for the voting process of the classification. Based on test results, the system works well with the accuracy up to 82.86% with a 714 images dataset."

"Build deep learning applications, such as computer vision, speech recognition, and chatbots, using frameworks such as TensorFlow and Keras. This book helps you to ramp up your practical know-how in a short period of time and focuses you on the domain, models, and algorithms required for deep learning applications. Deep Learning with Applications Using Python covers topics such as chatbots, natural language processing, and face and object recognition. The goal is to equip you with the concepts, techniques, and algorithm implementations needed to create programs capable of performing deep learning. This book covers intermediate and advanced levels of deep learning, including convolutional neural networks, recurrent neural networks, and multilayer perceptrons. It also discusses popular APIs such as IBM Watson, Microsoft Azure, and scikit-learn. You will: Work with various deep learning frameworks such as TensorFlow, Keras, and scikit-learn. Build face recognition and face detection capabilities Create speech-to-text and text-to-speech functionality Make chatbots using deep learning. "

"Topics include: ways modern statistical procedures can yield estimates of pi more precisely than the original Buffon procedure traditionally used; the question of density and measure for random geometric elements that leave probability and expectation statements invariant under translation and rotation; the number of random line intersections in a plane and their angles of intersection; developments due to W. L. Stevens's ingenious solution for evaluating the probability that n random arcs of size a cover a unit circumference completely; the development of M. W. Crofton's mean value theorem and its applications in classical problems; and an interesting problem in geometrical probability presented by a karyograph."

"Tesis ini menelusuri agensi objek pada self generating sebagai metode desain untuk menghasilkan arsitektur. Pada umumnya, hasil karya arsitektur berupa bangunan. Kebutuhan akan bangunan dipertanyakan ketika arsitektur bisa terealisasikan melalui media seperti objek. Tulisan ini mempertanyakan kapabilitas objek sebagai metode perancangan arsitektur yang bisa terbentuk dengan sendirinya. Lingkungan terpisah yang disebabkan oleh objek menghasilkan reaksi dari makhluk hidup. Objek bisa memiliki agensi di luar intensi awal perancang. Agensi objek akan melebihi ekspektasi perancang ketika objek memiliki kegunaan di luar dari fungsi inisial. Potensi objek untuk membentuk ruang dengan kapabilitas di luar fungsi yang ditentukan pada awalnya dieksplorasi dalam tesis ini. Melalui operasi combine dan substitute pada objek, proses self generating makhluk hidup dapat berubah menjadi initiate, inhibit atau redirect. Merancang dengan objek yang dialihkan fungsinya oleh makhluk hidup mewujudkan arsitektur. Agensi objek dirancang agar memberikan dampak pada lingkungan sekitar melalui self generating. Tesis ini menelusuri pembuatan bahan makanan tempe sebagai proses yang membutuhkan objek agar terealisasi. Dari studi proses tersebut, rancangan yang dihasilkan adalah susunan objek yang dapat melangsungkan fermentasi tempe dengan sendirinya melalui kapabilitas peralihan fungsi untuk membentuk ruang berspora.

---

This thesis explores the agency of objects in self-generating as a method of design in architecture. In general, architectural projects are in the form of buildings. The need for buildings is questioned when architecture can be realized through media such as objects. This writing questions the capability of objects as a method of architectural design that can be formed by itself. A separate environment that is caused by objects creates a reaction from living beings. Objects can have agency outside of the initial intention of the designer. The agency of objects will exceed the expectations of the designer when objects have a use outside of its initial function. The potential of objects to create space with the capability outside of its determined function is explored in this thesis. Through the operation of combine and substitute towards objects, the process of self generating from living beings can change to initiate, inhibit or redirect. Designing with objects that have been redirected functionally by living beings produces architecture. The agency of object is designed to provide impact towards its environment through self generating. This thesis explores the production of food as a process that needs objects to be realized. From the study of its process, the design is an arrangement of objects that can carry out tempeh fermentation by itself through the capability of functional redirection to create a spore space."

"Sitem pengenal aksi manusia saat ini sudah mulai menarik perhatian bannyak orang. Salah satu modalitas yang digunakan dalam sistem pengenal aksi manusia adalah sistem pengenal aksi manusia berbasis kerangka manusia. Banyak pendekatan yang menggunakan metode GCNs untuk melakukan klasifikasi aksi yang mana ini merupakan salah satu bagian terpenting dari sistem pengenal aksi mansia. Walaupun banyak hasil positif yang telah dihasilkan dari penelitian yang menggunakan pendekatan berbasis GCNs, GCNs memiliki keterbatasan dalam ketahanan, interoperabilitas, dan skalabilitas. Penelitian ini menggunakan PoseConv3D dalam sistem pengenal aksi manusia untuk bagian aksi klasifikasi. PoseConv3D yang berbasis 3D-CNN dapat mengatasi keterbatasan yang terjadi pada pendekatan berbasis GCNs. Sistem pada penelitian yang telah ada sebelumnya memiliki kekurangan dimana sistem tidak dapat melakukan ekstraksi pose terhadap video dengan ketinggian dan sudut kamera pengambilan video thermal yang berbeda. Kekurangan sistem juga terjadi pada kemampuan pengenalan aksi, sistem tidak dapat mengenali aksi masing-masing manusia yang berada dalam video thermal. Pada penelitian kali ini, penulis mengembangkan model sistem pengenal aksi manusia penelitian yang telah dilakukan sebelumnya, dengan menggabungan metode spasial-temporal dan PoseConv3D pada tahapan klasifikasi aksi. Penelitian ini juga menggunakan metode CenterNet pada tahapan ekstraksi pose. Model hasil pelatihan memiliki akurasi yang bagus dalam melakukan pengenalan aksi masing-masing aksi dan ekstraksi pose terhadap video dengan ketinggian dan sudut kamera pengambilan video yang bervariasi.

---

Human action recognition systems have started to attract the attention of many people. One of the modalities used in human action recognition systems is the human skeleton-based human action recognition system. Many approaches use GCNs method to perform action classification which is one of the most important parts of human action recognition system. Although many positive results have been generated from research using GCNs-based approaches, GCNs have limitations in robustness, interoperability, and scalability. This research uses PoseConv3D in the human action recognition system for the action classification part. PoseConv3D which is based on 3D-CNN can overcome the limitations that occur in GCNs-based approaches. The system in previous research has shortcomings where the system cannot extract poses from videos with different heights and camera angles of thermal video capture. System deficiencies also occur in action recognition capabilities, the system cannot recognize the actions of each human in a thermal video. In this research, the author develops a human action recognition system model of research that has been done before, by combining spatial-temporal methods and PoseConv3D at the action classification stage. This research also uses the CenterNet method in the pose extraction stage. The trained model has good accuracy in performing action recognition and pose extraction for videos with varying heights and camera angles."

"Klasifikasi aksi multi-objek berdasarkan video RGB aerial merupakan tantangan kompleks yang dapat berguna untuk pengembangan sistem keamanan. Terdapat dua pendekatan jaringan saraf tiruan yang umum digunakan dalam sistem pengenal berbasis kerangka, Convolutional Neural Network (CNN) dan Graph Convolutional Network (GCN). Pendekatan CNN lebih efektif dalam mempelajari fitur spatio-temporal, lebih kuat terhadap noise dalam estimasi pose, dan dapat menangani skenario multi-objek dengan komputasi yang lebih ringan. Penelitian ini meliputi pengembangan pengenal aksi manusia dengan pendeteksi spatio-temporal berbasis kerangka menggunakan pendekatan 3D Convolutional Neural Network (3D-CNN). Pendeteksi spatio-temporal memungkinkan sistem untuk mengenali tiap-tiap aksi yang simultan dilakukan oleh multi-objek dalam satu rekaman video. Percobaan dilakukan menggunakan sejumlah pre-trained dataset dan menggunakan dataset video RGB aerial primer yang dilatih terhadap model pengenal aksi berbasis video frontal, dengan menerapkan metode transfer learning. Proses tranfer learning dilakukan dengan dataset khusus untuk menghasilkan model pelatihan yang memiliki akurasi tinggi. Pelatihan memberi keluaran berupa model jaringan saraf tiruan dengan nilai akurasinya. Pengujian dilakukan menggunakan data video untuk mengetahui ketepatan model. Dari model yang diperoleh, akan dilakukan analisis terhadap keberhasilan dan keakuratan metode dalam mengenali aksi manusia.

---

Multi-object action recognition based on aerial RGB video is a complex challenge that can be useful for security system development. There are two commonly used artificial neural network approaches in skeleton-based recognition systems, Convolutional Neural Network (CNN) and Graph Convolutional Network (GCN). CNN approach is more effective in learning spatio-temporal features, more robust to noise in pose estimation, and can handle multi-object scenarios with lighter computation. This research involves developing a human action recognition with skeleton-based spatio-temporal detection using a 3D Convolutional Neural Network (3D-CNN) approach. Spatio-temporal detection allows the system to recognize each simultaneous action performed by multiple objects in a single video footage. Experiments were conducted using a number of pre-trained datasets and using a primary aerial RGB video dataset trained on a frontal video-based action recognition model, by applying the transfer learning method. The transfer learning process is performed with a specific dataset to produce a high-accuracy training model. The training outputs an artificial neural network model with its accuracy value. Testing is done using video data to determine the accuracy of the model. From the model obtained, the success and accuracy of the method in recognizing human actions will be analyzed."