Rozdziały

Stały URI dla kolekcji

Przeglądaj

Ostatnie zgłoszenia

Teraz wyświetlane 1 - 15 z 15
  • Pozycja
    Prediction of Natural Image Saliency for Synthetic Images
    (Wydawnictwo Politechniki Łódzkiej, 2021) Rudak, Ewa; Rynkiewicz, Filip; Daszuta, Marcin; Sturgulewski, Łukasz; Lazarek, Jagoda
    Numerous saliency models are being developed with the use ofneural networks and are capable of combining various features and predicting the saliency values with great results. In fact, it might be difficult to replace the possibilities of artificial intelligence applied to algorithms responsible for predicting saliency. However, the low-level features are still important and should not be removed completely from new saliency models. This work shows that carefully chosen and integrated features, including a deep learning based one, can be used for saliency prediction. The integration is obtained by using Multiple Kernel Learning. This solution is quite effective, as compared to a few other models tested on the same dataset.
  • Pozycja
    Synergy of Convolutional Neural Networks and Geometric Active Contours
    (Wydawnictwo Politechniki Łódzkiej, 2021) Tomczyk, Arkadiusz; Pankiv, Oleksandr; Szczepaniak, Piotr S.
    Hybrid approach to machine learning techniques could potentially provide improvements in image segmentation results. In this paper, a model of cooperation of convolutional neural networks and geometric active contours is proposed and developed. The novelty of the approach lies in combining deep neural networks and active contour model in order to improve CNN output results. The method is examined on the image segmentation task and applied to the detection and extraction of nuclei of HL60 cell line. The model had been tested on both 2-D and 3-D images. Because of feature learning characteristics of convolutional neural networks, the proposed solution should perform well in multiple scenarios and can be considered generic.
  • Pozycja
    Simulation of photon emission by an excited atom in the quantum register
    (Wydawnictwo Politechniki Łódzkiej, 2021) Ostrowski, Marcin
    This paper investigates whether a quantum computer can efficiently simulate the atom deexcitation process with emission of photon. An algorithm is presented for simulating of the atom-photon interaction and photon free propagation, implemented on standard two-input gates. The paper examines the properties of the proposed algorithm and then compares the obtained results with the theoretical predictions.
  • Pozycja
    Search for outliers by fuzzy logic systems – general concepts
    (Wydawnictwo Politechniki Łódzkiej, 2021) Kacprowicz, Marcin
    This article presents both a review of the literature and research proposals on the use of artificial integration, in particular fuzzy logic and fuzzy logic systems to search for and find exceptions outlier.
  • Pozycja
    Postgraduate studies in the Institute of Information Technology of the Lodz University of Technology
    (Wydawnictwo Politechniki Łódzkiej, 2021) Krasiukianis, Roman; Smoliński, Mateusz; Kwapisz, Marcin; Karbowańczyk, Michał
    The article presents the assumptions, development path and key achievements of postgraduate studies at the Faculty of Technical Physics, Information Technology and Applied Mathematics of the Lodz University of Technology. The emphasis was placed on the role of cooperation with IT companies in developing postgraduate study programs related to the needs of the Lodz region as well as methods for assessing the quality of the learning process. In addition, problems related to changes in the labor market, as well as risks and opportunities resulting from the need to conduct classes differently during the COVID-19 pandemic, are discussed.
  • Pozycja
    Objects’ colors impact on scene image perception in immersive virtual environments
    (Wydawnictwo Politechniki Łódzkiej, 2021) Andrzejczak, Jarosław; Lenarczyk, Marcin
    Objects’ color perception, including these in virtual space, plays significant role in looking for information, rating content and navigating. Prepared research environment consist of five individual experiments focused on analysis of color (especially its contrast) impact on objects perception in virtual space. Both quantitative data from virtual environment and qualitative data from questionnaires have been acquired. Results from one task showed, that there is a correlation between high color contrast and memorization efficiency. At the same time, in accordance with verified results we can’t be certain, that colors having high contrast with surroundings are selected first, better noticed and chosen faster.
  • Pozycja
    IT law as an indispensable element of education
    (Wydawnictwo Politechniki Łódzkiej, 2021) Urbaniak-Mastalerz, Izabela
    The study presents the issues of selected aspects of IT law. The article indicates legal regulations and court decisions in the field of computer program protection. The author solve the problem of how to interpret various aspects of IT law, taking into account the current case law of the Supreme Court and common courts. Conclusions from the discussed regulations and judgments, based on the available statistics, will constitute a starting point for the evaluation and the possibility of computer programs protection.
  • Pozycja
    Hand gestures as a method of interaction in virtual reality HOPA games
    (Wydawnictwo Politechniki Łódzkiej, 2021) Lamus, Monika; Wiśniewska, Aneta; Szrajber, Rafał
    The main objective of the study was to implement the intuitive gesture set for movement and interaction in a virtual HOPA game. A review and analysis of existing solutions using the Leap Motion device to track gestures and hand movements was conducted. Two sets of movement modes were created and subjected to a series of tests to determine the best optimal movement and interaction technique. The tests were verified in terms of speed and accuracy of task performance.
  • Pozycja
    Gamification in Accounting Education- Evidence From Logistic Course Experience
    (Wydawnictwo Politechniki Łódzkiej, 2021) Fajczak-Kowalska, Anita; Misztal, Anna
    The study’s main goal is to indicate the possibility of using gamification in teaching the basics of accounting at a university. The authors implement the gamification model among logistics students at one of the universities in Lodz. The experiment involved the introduction of gamification during the pandemic in 2020 and 2021. The classes were conducted using MS Teams and the Moodle platform. The study is theoretical and empirical. The first part presents the basic theoretical issue related to gamification and gamification in education; the second part shows a case study. The results of the implementation of gamification in teaching accounting are positive. The students showed higher commitment, assessed the classes better, gained additional knowledge, established better interpersonal relationships.
  • Pozycja
    Educational infrastructures for IT teaching
    (Wydawnictwo Politechniki Łódzkiej, 2021) Kwapisz, Marcin; Karbowańczyk, Michał
    The basic problem of teaching information technologies is a proper infrastructure for classes and courses. This especially applies to remote and e-learning, when a student does not have access to “physical” laboratories. Technologies based on virtualization and containerization can help a lot to deliver the infrastructure. Unfortunately it requires a significant amount of administrative work, because many tasks simply have to be done manually. This article explains the current situation for Infrastructures and Network Applications (INA) specialization at Institute of Information Technology. It also describes how the educational infrastructure could or should be managed in the future.
  • Pozycja
    Comparison of Selected Algorithms Solving Vehicle Routing Problem with Simultaneous Delivery and Pickup
    (Wydawnictwo Politechniki Łódzkiej, 2021) Michalik, Maciej; Ochelska-Mierzejewska, Joanna
    The Vehicle Routing Problem is a widely known combinatorial optimization problem. A particular variant of this problem is Vehicle Routing Problem with Simultaneous Delivery and Pickup (VRPSDP). In this paper, two metaheuristics are compared in the context of solving the VRPSDP - the Genetic Algorithm (GA) and Ant Colony Optimization (ACO). Both implemented algorithms are hybridized using local search operators. Implemented algorithms are tested using well known Dethloff dataset. The final results show that, in general, ACO gives more accurate results than GA, but it is worse in terms of performance. The main reason for that is the difficulty of incorporating local search operators into the Genetic Algorithm.
  • Pozycja
    A Case Study based exam at Computer Science at Lodz University of Technology
    (Wydawnictwo Politechniki Łódzkiej, 2021) Sękalski, Przemysław; Pietrzak, Piotr
    This paper describes the process of introducing changes in diploma examination system in the Computer Science discipline at Lodz University of Technology, Poland. The main aim of this paper is to share the experience with other universities to speed up an introduction of modern examination techniques, to launch an open discussion and encourage business partners to support the examination system to improve the quality of education. It also includes a discussion on how to effectively check the students’ qualifications.
  • Pozycja
    Case-Based Reasoning for Pattern Recognition using Granular Information Generated by Active Hypercontours
    (Wydawnictwo Politechniki Łódzkiej, 2021) Szczepaniak, Piotr S.
    This paper presents a novel extension of the case-based reasoning (CBR) technique. In the proposed method, a case is defined using the concept of multidimensional information granule created by the active hypercontour. The granularity of information is expected to be justifiable. The paper explains the main principles of the method and discusses its usefulness with reference to the pattern recognition problem.
  • Pozycja
    The camera as a way of telling stories with images in 360 animations using VR technology
    (Wydawnictwo Politechniki Łódzkiej, 2021) Białek, Maciej; Wiśniewska, Aneta; Szrajber, Rafał
    VR technologies have found their place into the film industry, potentially revolutionizing standards of cinematography. Aim of this work was to investigate and compare the perception of space depending on the type of the camera. For this purpose, a special 360° animated film was created with two types of camera: one following the viewpoint of a character and another one defined by shots. As a result we can tell that the following camera seems to be more attractive to a recipient, which means a greater portion of a material was perceived and with a greater comfort of viewing experience.
  • Pozycja
    BBO in solving complex optimization problems– bullwhip effect reduction in logistics networks
    (Wydawnictwo Politechniki Łódzkiej, 2021) Dziomdziora, Adam; Ignaciuk, Przemysław
    This chapter addresses Biogeography-Based Optimization (BBO) implementation for counteracting the bullwhip effect in logistic systems influenced by uncertain demand. The considered class of systems comprises two types of actors – controlled nodes and external sources – connected by unidirectional links. In this paper, the application of BBO is proposed to support the optimization problem of proper channel allocation in transportation links. BBO allows one to perform simulation-based optimization and provide desirable operating conditions to answer a priori unknown, timevarying demand. The effectiveness of the goods distribution process governed under a base-stock policy includes the objective function of mitigating the bullwhip effect and minimizing transportation costs. The introduced optimization problem is solved using BBO to find an optimal channel allocation matrix for a given topology. The results are verified in extensive simulations of a real-world logistic network.