Hasil Pencarian  ::  Simpan CSV :: Kembali

Abstrak :
[Data fusion in information retrieval This book offers a theoretical and empirical approach to data fusion, used in information retrieval in complex, diverse settings such as web and social networks, legal, enterprise and others. Discusses, analyzes and ealuates typical data fusion algorithms., Data fusion in information retrieval This book offers a theoretical and empirical approach to data fusion, used in information retrieval in complex, diverse settings such as web and social networks, legal, enterprise and others. Discusses, analyzes and ealuates typical data fusion algorithms.]

Abstrak :
This book provides a comprehensive introduction to the concepts and idea of multisensor data fusion. The reader is made familiar with tools taken from a wide range of diverse subjects including, neural networks, signal processing, statistical estimation, tracking algorithms, computer vision and control theory which are combined by using a common statistical framework. The book is illustrated with many real-life examples taken from a diverse range of applications and contains an extensive list of modern references.

Abstrak :
The purpose of this paper is to classification of three main types of Malaysian honey (Acacia, Kelulut and Tualang) according to their botanical origin using UV–Vis Spectroscopy and digital camera. This paper presented the classification of the honey based on two characteristics from three (3) types of local honey, namely the antioxidant contents and colour variations. The former uses the UV spectroscopy of selected wavelength range, and the latter using RGB digital camera. Principal Component Analysis (PCA) was used for both methods to reduce the dimension of extracted data. The Support Vector Machine (SVM) was used for the classification of honey. The assessment was done separately for each of the methods, and also on the fusion of both data after features extraction and association. This paper shows that classification of the fusion method improved significantly compared to single modality Honey classification based on the fusion method was able to achieve 94% accuracy. Hence, the proposed methods have the ability to provide accurate and rapid classification of honey products in terms of origin. The proposed system can be applied in Malaysia honey industry and further improve the quality assessment and provide traceability.

Abstrak :
Pelacakan objek dengan menggunakan metode penggabungan dari citra visual RGB dan termal inframerah (TIR) menjadi bidang yang menarik untuk dipelajari oleh para peneliti dalam beberapa tahun terakhir karena kemampuannya untuk bertahan pada situasi dan kondisi sulit yang berkaitan dengan iluminasi cahaya seperti dalam keadaan gelap dan cuaca buruk yang tidak dapat dideteksi dengan hanya menggunakan citra RGB saja. Pada kondisi normal pelacakan objek dengan menggunakan citra RGB akan memiliki akurasi yang bagus, namun pada kondisi gelap dan cuaca buruk citra termal inframerah dapat membantu untuk tetap dapat melakukan pelacakan objek. Penggabungan keunggulan dari citra RGB dan termal inframerah diharapkan akan saling membantu untuk menutupi kelemahan dari masing-masing metode. Namun pencarian metode penggabungan terbaik dari kedua masukan tersebut masih merupakan tantangan tersendiri. Pada penelitian ini metode High Level Fusion dengan arsitektur DeepSORT dan Kalman Filter Hierarchical Estimator digunakan untuk menggabungkan citra RGB dan termal inframerah yang berfokus pada penggabungan hasil estimasi pelacakan objek dari kedua masukan. Dari hasil penelitian ini didapatkan sebuah arsitektur penggabungan metode pelacakan yang dapat mengoptimalkan hasil pelacakan dari kedua masukan dan tetap dapat bekerja ketika salah satu masukan tidak berfungsi. ......RGBT object tracking has become an interesting field study for many researchers because of the robustness to overcome adverse conditions related to illumination like total darkness and bad weather where RGB detection could not perform well. Object tracking with RGB images could have excellent performance in normal conditions, but in dark and difficult weather conditions thermal infrared images could help to maintain the tracking process. This integration from RGB and thermal infrared is expected to complement each other’s strengths and weaknesses. However, it is still challenging to find the best method that can combine those two different input information. In this research, high-level data fusion method and DeepSORT architecture were used as a baseline tracking with Kalman filter Hierarchical Estimator to combine RGB and Thermal estimates for object tracking. The study results presented the combination architecture to optimize the tracking result that can perform with both inputs and maintain function if one of the inputs falls through.

Abstrak :
This book introduces resource-aware data fusion algorithms to gather and combine data from multiple sources (e.g., sensors) in order to achieve inferences. These techniques can be used in centralized and distributed systems to overcome sensor failure, technological limitation, and spatial and temporal coverage problems. The algorithms described in this book are evaluated with simulation and experimental results to show they will maintain data integrity and make data useful and informative.

Abstrak :
Dalam desain sistem pemantauan dan pengontrolan parameter lingkungan secara otomatis, selain desain sistem serta implementasi algoritma di dalamnya, pemilihan media tanam merupakan faktor penting yang menjadi pertimbangan. Pertimbangan akan jenis media tanam mengarah kepada suatu media terisolasi yang memungkinkan terjadinya pengontrolan langsung oleh aktuator. Sedangkan pertimbangan akan desain sistem mengarah kepada bagaimana arsitektur fisik alat dan protokol pemantauan dan pengontrol dapat dieksekusi secara efektif dan efisien. Pertimbangan pada implementasi algoritma mengarah kepada bagaimana proses pemantauan dan pengontrolan bersifat komplementer. Dalam skripsi ini, peneliti mengusulkan rancang sistem pemantau dan pengontrol tanaman dengan media terarium tertutup berbasis IoT dengan menggunakan algoritma novel yang memanfaatkan integrasi data, yakni data fusion, dan adaptive hysteresis regime. Tujuan dari sistem yang diusulkan ialah untuk mengontrol setiap parameter lingkungan ke dalam rentang optimum dengan mempertimbangkan coupling relationship antar parameter untuk mempercepat pertumbuhan tanaman. Hasil pengukuran menunjukkan bahwa sistem yang diusulkan menghasilkan kondisi optimum yang berkelanjutan dan stabil. Hal ini dibuktikan pada saat implementasi sistem di mana kecepatan pertumbuhan tanaman yang dikontrol di dalam sistem yang diusulkan rata-rata lebih cepat 23,83 % daripada tanaman yang tidak dikontrol.

---

In the design of autonomous monitoring and controlling environmental parameters, in addition to the system design and algorithm implementation, the choice of planting media is an important factor to be considered. Consideration of the type of planting media leads to an isolated medium that allows direct control by actuators. While the consideration of the system design leads to how the physical architecture and monitoring and controlling tools and protocols can be executed effectively and efficiently. Consideration on the implementation of algorithm leads to how the monitoring and controlling process is complementary to each other. In this thesis, the researcher proposes the design of plant monitoring and controlling system with IoT-based terrarium medium using novel algorithms that utilize data integration, namely data fusion, and the adaptive hysteresis regime. The purpose of the proposed system is to control each environmental parameter into the optimum range by considering coupling relationship between parameters to accelerate plant growth. The measurement results show that the proposed system produces optimum conditions that are more sustain and stable. This is evidenced at the time of the implementation of the system where the plant growth controlled in the proposed system is on average 23,83 % faster than uncontrolled ones.