Nikola Lopac

Prof. Dr. Nikola Lopac

Department of Electrical Engineering, Automation and Computing, University of Rijeka, Faculty of Maritime Studies, Rijeka, Primorsko-Goranska Županija, Croatia
+1
orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 August 2022 in Sensors
Verified
Journal Article
Open access
PDF file
Nikola LopacNikola Lopac
Nikola Lopac
IJIrena Jurdana
Irena Jurdana
ABAdrian Brnelić
Adrian Brnelić
Tomislav KrljanTomislav Krljan
Tomislav Krljan
The development of light detection and ranging (lidar) technology began in the 1960s, following the invention of the laser, which represents the central component of this system, integrating laser scanning with an inertial measurement unit (IMU) and Global Positioning System (GPS). Lidar technology is spreading to many different areas of application, from those in autonomous vehicles for road detection and object recognition, to those in the maritime sector, including object detection for autonomous navigation, monitoring ocean ecosystems, mapping coastal areas, and other diverse applications. This paper presents lidar system technology and reviews its application in the modern road transportation and maritime sector. Some of the better-known lidar systems for practical applications, on which current commercial models are based, are presented, and their advantages and disadvantages are described and analyzed. Moreover, current challenges and future trends of application are discussed. This paper also provides a systematic review of recent scientific research on the application of lidar system technology and the corresponding computational algorithms for data analysis, mainly focusing on deep learning algorithms, in the modern road transportation and maritime sector, based on an extensive analysis of the available scientific literature.

30 December 2021 in IEEE Access
Verified
Journal Article
Open access
Nikola LopacNikola Lopac
Nikola Lopac
FHFranko Hržić
Franko Hržić
IVIrena Petrijevcanin Vuksanovic
Irena Petrijevcanin Vuksanovic
JLJonatan Lerga
Jonatan Lerga
Analysis of non-stationary signals in a noisy environment is a challenging research topic in many fields often requiring simultaneous signal decomposition in the time and frequency domain. This paper proposes a method for the classification of noisy non-stationary time-series signals based on Cohen’s class of their time-frequency representations (TFRs) and deep learning algorithms. We demonstrated the proposed approach on the example of detecting gravitational-wave (GW) signals in intensive real-life, non-stationary, non-white, and non-Gaussian noise. For this purpose, we prepared a dataset based on the actual data from the Laser Interferometer Gravitational-Wave Observatory (LIGO) detector and the synthetic GW signals obtained by realistic simulations. Next, 12 different TFRs from Cohen’s class were calculated from the original noisy time-series data and used to train three state-of-the-art convolutional neural network (CNN) architectures: ResNet-101, Xception, and EfficientNet. The obtained classification results are compared to those achieved by the base model trained on the original time series. Analysis of the results suggests that the proposed approach combining deep CNN architectures with Cohen’s class TFRs yields high values of performance metrics and significantly improves the classification performance compared to the base model. The TFR-CNN models achieve the values of the classification accuracy of up to 97.10%, the area under the receiver operating characteristic curve (ROC AUC) of up to 0.9885, the recall of up to 95.87%, the precision of up to 99.51%, the F1 score of up to 97.03%, and the area under the precision-recall curve (PR AUC) of up to 0.9920. This classification performance is obtained on the dataset in which the signal-to-noise ratio (SNR) values of the raw, noisy time-series signals range from −123.46 to −2.27 dB. Therefore, this study suggests that using alternative TFRs of Cohen’s class can improve the deep learning-based detection of non-stationary GW signals in an intensive noise environment. Moreover, the proposed approach can also be a viable solution for deep learning-based analysis of numerous other noisy non-stationary signals in different practical applications.

23 July 2021 in Sustainability
Verified
Journal Article
Open access
PDF file
IJIrena Jurdana
Irena Jurdana
Nikola LopacNikola Lopac
Nikola Lopac
Nobukazu WakabayashiNobukazu Wakabayashi
Nobukazu Wakabayashi
HLHONGZE LIU
HONGZE LIU
Due to the ever-increasing amount of data collected and the requirements for the rapid and reliable exchange of information across many interconnected communication devices, land-based communications networks are experiencing continuous progress and improvement of existing infrastructures. However, maritime communications are still characterized by slow communication speeds and limited communication capacity, despite a similar trend of increasing demand for information exchange. These limitations are particularly evident in digital data exchange, which is still limited to relatively slow and expensive narrowband satellite transmission. Furthermore, with the increasing digitalization of ships and introducing the sustainable concept of autonomous ship operation, large amounts of collected data need to be transmitted in real-time to enable remote voyage monitoring and control, putting additional pressure on the already strained means of maritime communications. In this paper, an adaptive shipboard data compression method based on differential binary encoding is proposed for real-time maritime data transmission. The proposed approach is verified on the actual data collected on board a training ship equipped with the latest data acquisition system. The obtained results show that the proposed data encoding method efficiently reduces the transmitted data size to an average of 3.4% of the original shipboard data, thus significantly reducing the required data transmission rate. Moreover, the proposed method outperforms several other tested competing methods for shipboard data encoding by up to 69.6% in terms of compression efficiency. Therefore, this study suggests that the proposed data compression approach can be a viable and efficient solution for transmitting large amounts of digital shipboard data in sustainable maritime real-time communications.

14 February 2022 in Sustainability
Verified
Journal Article
Open access
PDF file
HLHONGZE LIU
HONGZE LIU
IJIrena Jurdana
Irena Jurdana
Nikola LopacNikola Lopac
Nikola Lopac
Nobukazu WakabayashiNobukazu Wakabayashi
Nobukazu Wakabayashi
Traditional methods of marine navigation are undergoing a revolution brought about by the almost universal adoption of the Automatic Identification System (AIS). AIS exchanges a wealth of navigational information among vessels and between ships to shore through Very High Frequency (VHF). With AIS data integrated into the Electronic Chart Display and Information System (ECDIS), the identification and navigational information of surrounding vessels as well as aids to navigation can be reflected on the electronic charts in real time, despite some problems such as the low AIS carriage rate on small vessels where it is not mandatory and the high cost of ECDIS preventing such vessels from installing it. In this paper, we introduce BlueNavi, a lower cost but sustainable maritime information providing platform built with microservices architecture allowing flexible on-demand scalability and cross-platform adaptability. Applications served by BlueNavi can provide users with data either stored in a remote data center through the internet or received locally by devices connected to the station without the need for the internet. From our land test, we show that users with only an internet connection but without any AIS equipment can also obtain live AIS data collected by other stations. Conversely, with access to the internet, BlueNavi can also send data back to the land stations, enabling other ships to identify non-AIS ships as well. Through the live-ship test, we demonstrate that BlueNavi works well offline in cooperation with shipborne AIS equipment. We also look at some possible application scenarios for BlueNavi with other data sources and means of communication other than AIS and VHF that can be expanded to the platform. BlueNavi will enable inexpensive ship identification for small vessels and provide an extension of functionality to ECDIS for large ships.

Verified
Journal Article
Open access
PDF file
JDJosip Dujmović
Josip Dujmović
Tomislav KrljanTomislav Krljan
Tomislav Krljan
Nikola LopacNikola Lopac
Nikola Lopac
SŽSrđan Žuškin
Srđan Žuškin
Carbon emissions generated by the transportation sector represent a large part of total greenhouse gas emissions and are thus subject to various policies and initiatives for emission reduction and the development of sustainable transportation networks. Furthermore, passenger transportation generates a significant amount of emissions within this sector, especially in those countries with large and developed tourist sectors. Examples of such countries are Italy and Croatia, located in the Adriatic region, with a large portion of passengers between them being transported utilizing mainly maritime and/or road transportation modes. A proper analysis of the impact of these transportation mode choices on carbon emissions is essential to enable the selection of the optimal transportation mode for the particular transportation route with respect to the generated emissions. Therefore, this study determines the carbon emissions of the maritime and/or road transportation modes on the existing cross-border passenger transportation routes between Italy and Croatia. For the analysis, the Adriatic region was divided into three sections—the Northern, Middle, and Southern regions—each characterized by specific transportation routes defined by geographical features and distances. The results obtained from this research are presented as total carbon emissions for each transportation mode separately, based on each of three chosen routes in different regions. In addition, a carbon emission comparison between each transportation mode in regard to occupancy rate is performed and presented separately for each chosen route based on its specific distances, transportation means, and features. Finally, by providing an analysis of the existing state, this study can serve as a basis for Italy–Croatia cross-border passenger mobility network modernization and the introduction of new, sustainable, and multimodal transportation routes.

20 April 2023 in Sensors
Verified
Journal Article
Open access
PDF file
Vedran JurdanaVedran Jurdana
Vedran Jurdana
Nikola LopacNikola Lopac
Nikola Lopac
MVMiroslav Vrankic
Miroslav Vrankic
Compressive sensing (CS) of the signal ambiguity function (AF) and enforcing the sparsity constraint on the resulting signal time-frequency distribution (TFD) has been shown to be an efficient method for time-frequency signal processing. This paper proposes a method for adaptive CS-AF area selection, which extracts the magnitude-significant AF samples through a clustering approach using the density-based spatial clustering algorithm. Moreover, an appropriate criterion for the performance of the method is formalized, i.e., component concentration and preservation, as well as interference suppression, are measured utilizing the information obtained from the short-term and the narrow-band Rényi entropies, while component connectivity is evaluated using the number of regions with continuously-connected samples. The CS-AF area selection and reconstruction algorithm parameters are optimized using an automatic multi-objective meta-heuristic optimization method, minimizing the here-proposed combination of measures as objective functions. Consistent improvement in CS-AF area selection and TFD reconstruction performance has been achieved without requiring a priori knowledge of the input signal for multiple reconstruction algorithms. This was demonstrated for both noisy synthetic and real-life signals.