Wyniki wyszukiwania - BazTech

1

Artificial intelligence versus natural intelligence in mineral processing

Özkan Şafak Gökhan

Physicochemical Problems of Mineral Processing

|

2023

|

Vol. 59, iss. 5

art. no. 167501

EN

This article aims to introduce the terms NI-Natural Intelligence, AI-Artificial Intelligence, ML-Machine Learning, DL-Deep Learning, ES-Expert Systems and etc. used by modern digital world to mining and mineral processing and to show the main differences between them. As well known, each scientific and technological step in mineral industry creates huge amount of raw data and there is a serious necessity to firstly classify them. Afterwards experts should find alternative solutions in order to get optimal results by using those parameters and relations between them using special simulation software platforms. Development of these simulation models for such complex operations is not only time consuming and lacks real time applicability but also requires integration of multiple software platforms, intensive process knowledge and extensive model validation. An example case study is also demonstrated and the results are discussed within the article covering the main inferences, comments and decision during NI use for the experimental parameters used in a flotation related postgraduate study and compares with possible AI use.

2

Hybrid end-to-end approach integrating online learning with face-identification system

Nguyene Dat Van, Nguyen Son Trung, Pham Thi Hong Anh, Pham Van Toan, Hoang Thao Thu, Thanh Ta Minh

Computer Science

|

2023

|

T. 24 (2)

141--161

EN

Facial recognition has been one of the most intriguing and exciting research topics over the last few years. It involves multiple face-based algorithms such asfacial detection, facial alignment, facial representation, and facial recognition. However, all of these algorithms are derived from large deep-learning architectures, leading to limitations in development, scalability, accuracy, and deployment for public use with mere CPU servers. Also, large data sets that contain hundreds of thousands of records are often required for training purposes. In this paper, we propose a complete pipeline for an effective face-recognition application that requires only a small data set of Vietnamese celebrities and a CPU for training, solving the problem of data leakage, and the need for GPU devices. The pipeline is based on the combination of a conversion algorithm from face vectors to string tokens and the indexing & retrieval process by Elasticsearch, thereby tackling the problem of online learning in facial recognition. Compared with other popular algorithms on the same data set, our proposed pipeline not only outperforms the counterpart in terms of accuracy but also delivers faster inference, which is essential to real-time applications.

3

Esi in the supply chain of modular products

Wieteska G.

Problemy Transportu i Logistyki

|

2017

|

nr 3 (39)

129--140

EN

Discussion around the product development collaborations is very actual today because of growing pace of technological change. However, there are still few qualitative papers on product development in the perspective of more than one supply chain link. The aim of this paper is to recognize the role of an internal and external cooperation in product development process as well as identify the determinants of Early Supplier Involvement in supply chain of modular products. The paper consists of following sections: introduction, methodology, research results, conclusions and the proposal of future research. Author used in-depth interview and case study methods. There are many factors that are of importance while deciding on ESI (e.g. product characteristics, production environment, the company’s responsibility for detailed product specification). Based on conclusions, three hypothesis were formed. They can be an input to the further (quantitative) research: H1: Modularization strategy positively influences ESI, H2: Partnership positively influences ESI, H3: Modularization strategy positively influences partnership.

PL

Dyskusja na temat współpracy nad rozwojem produktów jest dziś bardzo aktualna z powodu rosnącego tempa zmian technologicznych. Jednak wciąż zbyt mało jest artykułów dotyczących rozwoju produktu w perspektywie więcej niż jednego ogniwa łańcucha dostaw. Celem tego artykułu jest rozpoznanie roli wewnętrznej i zewnętrznej współpracy w procesie opracowywania produktu, a także określenie czynników warunkujących wczesne zaangażowanie dostawców w łańcuch dostaw produktów modułowych. Artykuł składa się z następujących części: wprowadzenie, metodologia, wyniki badań, wnioski i propozycja przyszłych badań. Autorka wykorzystała pogłębione wywiady i metody studium przypadku. Na podstawie wniosków sformułowano trzy hipotezy. Mogą być one wkładem do dalszych (ilościowych) badań: H1: Strategia modularyzacji pozytywnie wpływa na ESI, H2: Partnerstwo pozytywnie wpływa na ESI, H3: Strategia modularyzacji pozytywnie wpływa na partnerstwo.

4

EV with duration forecasting. Case study

Ziółkowska A.

Czasopismo Techniczne. Budownictwo

|

2014

|

R. 111, z. 2-B

299--307

EN

This paper presents development of the earned value concept regarding forecasting project duration time. On the basis of the calculations carried out for an implemented investment project, consisting of development of the sanitary sewage and municipal water supply system, individual methods and their assumptions were presented and discussed.

PL

W artykule przedstawione zostało rozwinięcie wartości wypracowanej w aspekcie prognozowania terminu końcowego realizacji. Na podstawie obliczeń przeprowadzonych dla zrealizowanej inwestycji obejmującej swoim zakresem rozbudowę kanalizacji sanitarnej i wodociągu wiejskiego przedstawione i omówione zostały poszczególne metody i ich założenia.

5

Historia atomowej analizy spektralnej. Cz. III. Rozwój analizy ilościowej

Godlewska-Żyłkiewicz B.

Analityka : nauka i praktyka

|

2007

|

nr 4

36-38