Active Classification With Uncertainty Comparison Queries

Noisy pairwise comparison feedback has been incorporated to improve the overall query complexity of interactively learning binary classifiers. The positivity comparison oracle is extensively used to provide feedback on which is more likely to be positive in a pair of data points. Because it is impossible to determine accurate labels using this oracle alone without knowing the classification threshold, existing methods still rely on the traditional explicit labeling oracle, which explicitly answers the label given a data point. The current method conducts sorting on all data points and uses explicit labeling oracle to find the classification threshold. However, it has two drawbacks: (1) it needs unnecessary sorting for label inference and (2) it naively adapts quick sort to noisy feedback. In order to avoid these inefficiencies and acquire information of the classification threshold at the same time, we propose a new pairwise comparison oracle concerning uncertainties. This oracle answers which one has higher uncertainty given a pair of data points. We then propose an efficient adaptive labeling algorithm to take advantage of the proposed oracle. In addition, we address the situation where the labeling budget is insufficient compared to the data set size. Furthermore, we confirm the feasibility of the proposed oracle and the performance of the proposed algorithm theoretically and empirically.

Implementation Of Bubble Sort Algorithm On 2 Fruit Models Of Data Selection Using The Java Program Language

There are various kinds of data sorting methods that we know of which are the Bubble Sort, Selection Sort, Insertion Sort, Quick Sort, Shell Sort, Heap Sort, and Radix Sort methods. All of these methods have advantages and disadvantages of each, whose use is determined based on needs. Each method has a different algorithm, where different algorithms affect the execution time. One interesting algorithm to be implemented on 2 variant models of data sorting is the Bubble Sort algorithm, the reason is that this algorithm has a fairly long and detailed process flow to produce an ordered data sequence from a previously unordered data sequence. Two (2) data sorting variant models that will be implemented using the Bubble Sort algorithm are: Ascending data sorting variants moving from left to right, and Descending data sorting variants moving from left to right. And the device used in implementing the Bubble Sort algorithm is the Java programming language.

ANALISIS PERBANDINGAN PERFORMA PEMROGRAMAN SEKUENSIAL DAN PARALEL DENGAN SKEMA UJI MATRIX, FILTER DAN QUICK SORT

Komputasi sekuensial merupakan sebuah proses untuk melakukan pemecahan masalah dengan melakukan setiap langkah secara berurutan. Konsekuensi pemecahan sebuah masalah dengan menggunakan komputasi sekuensial adalah sebuah hasil akan muncul apabila langkah pengerjaan telah dilakukan. Pengembangan teknologi dari komputasi sekuensial adalah kom-putasi paralel yang melibatkan penggunaan sumber daya secara bersamaan. Khusus pada bidang IT, sumber daya tersebut dapat berupa core processor atau juga dimungkinkan untuk melibatkan graphical unit. Skema uji yang dilakukan yaitu ber-fokus pada perbandingan performa komputasi sekuensial dan komputasi paralel. Skema uji tersebut terdiri dari pengujian perkalian matrix, proses filter sebuah gambar, dan proses quick sort. Hasil skema uji 1 menunjukkan bahwa komputasi paralel dapat melakukan perkalian dengan dimensi 2000x2000 dengan hasil berkisar 4x lebih cepat dibandingkan komputasi serial. Berikutnya, hasil skema uji 2 menunjukkan proses filter dapat dilakukan oleh komputasi paralel dengan efisiensi 50% lebih baik menggunakan 4 buah core. Terakhir, hasil skema uji 3 menghasilkan nilai efektivitas tertinggi menggunakan CUDA yaitu berkisar 96% dengan proses quick sort pada data sebesar 32Mb.

Attribute Reduction Method Based on Sample Extraction and Priority

Attribute reduction is a key issue in the research of rough sets. Aiming at the shortcoming of attribute reduction algorithm based on discernibility matrix, an attribute reduction method based on sample extraction and priority is presented. Firstly, equivalence classes are divided using quick sort for computing compressed decision table. Secondly, important samples are extracted from compressed decision table using iterative self-organizing data analysis technique algorithm(ISODATA). Finally, attribute reduction of sample decision table is conducted based on the concept of priority. Experimental results show that the attribute reduction method based on sample extraction and priority can significantly reduce the overall execution time and improve the reduction efficiency.

Analisis Perbandingan Efisiensi Algoritma Brute Force dan Divide and Conquer dalam Proses Pengurutan Angka

Abstrak— Perbandingan algoritma dibutuhkan untuk mengetahui tingkat efisiensi suatu algoritma. Penelitian ini membandingkan efisiensi dari dua strategi algoritma sort yang sudah ada yaitu brute force dan divide and conquer. Algoritma brute force yang akan diuji adalah bubble sort dan selection sort. Algoritma divide and conquer yang akan diuji adalah quick sort dan merge sort. Cara yang dilakuakn dalam penelitian ini adalah melakukan tes dengan data sebanyak 50 sampai 100000 untuk setiap algoritma. Tes dilakukan dengan menggunakan bahasa pemrograman JavaScript. Hasil dari penelitian ini adalah algoritma quick sort dengan strategi divide and conquer memiliki efisiensi yang baik serta running time yang cepat dan algoritma bubble sort dengan strategi brute force memiliki efisiensi yang buruk serta running time yang lama. Kata Kunci – Efisiensi, algoritma, brute force, divide and conquer, bubble sort, selection sort, quick sort, merge sort

Optimal group based testing strategy for detecting infected individuals: comparison of algorithms

We investigate group based testing strategy targeted to identify infected patients by making use of a medical test which equally well applies to single and pooled samples. We demonstrate that, under assumed setting, quick sort grounded testing algorithm allows to reduce average costs, and the reduction is very significant when the infection percentage is low. Although the basic idea of test sampling is known, our major novelty is the rigorous treatment of the model. Another interesting insight following rigorous analysis is that an average number of tests per one individual scales like entropy of the prevalence of infection. One more reason for the paper is the context: taking into account the current situation with the coronavirus, dissemination of renowned ideas and the optimisation of algorithms can be of a great importance and of economical benefit.

Analisis Kinerja Algoritma Quick Double Merge Sort Paralel Menggunakan openMP

Processor technology currently tends to increase the number of cores more than increasing the clock speed. This development is very useful and becomes an opportunity to improve the performance of sequential algorithms that are only done by one core. This paper discusses the sorting algorithm that is executed in parallel by several logical CPUs or cores using the openMP library. This algorithm is named QDM Sort which is a combination of sequential quick sort algorithm and double merge algorithm. This study uses a data parallelism approach to design parallel algorithms from sequential algorithms. The data used in this study are the data that have not been sorted and also the data that has been sorted is integer type which is stored in advance in a file. The parameter measured to determine the performance of the QDM Sort algorithm is speedup. In a condition where a large amount of data is above 4096 and the number of threads in QDM Sort is the same as the number of logical CPUs, the QDM Sort algorithm has a better speedup compared to the other parallel sorting algorithms discussed in this study. For small amounts of data it is still better to use sequential sorting algorithm.