Goran Delac

• PhD
• Professor (Associate) at University of Zagreb Faculty of Electrical Engineering and Computing

While constructing QoS-aware composite work-flows based on service oriented systems, it is necessary to assess nonfunctional properties of potential service selection candidates. In this paper, we present CLUS, a model for reliability prediction of atomic web services that estimates the reliability for an ongoing service invocation based on the dat...

As SOA gains more traction through various implementations, building reliable service compositions remains one of the principal research concerns. Widely researched reliability assurance methods, often rely on applying redundancy or complex optimization strategies that can make them less applicable when it comes to designing service compositions on...

Development of Web technologies has pushed forward a wide array of tools which can be used by the end-users to customize their own environment. Mashup development frameworks stand out as means to create Web applications by combining the existing content or functionality provided by various, disparate, providers on the Web. Like for all composite sy...

In recent years, the ubiquitous demands for cross-protocol application access are driving the need for deeper integration between SIP and SOAP. In this article we present a novel methodology for integrating these two protocols. Through an analysis of properties of SIP and SOAP we show that integration between these protocols should be based on appl...

Contemporary web applications are often designed as composite services built by coordinating atomic services with the aim of providing the appropriate functionality. Although functional properties of each atomic service assure correct functionality of the entire application, nonfunctional properties such as availability, reliability, or security mi...

Large Language Models (LLMs) have demonstrated remarkable performance across diverse domains. However, effectively leveraging their vast knowledge for training smaller downstream models remains an open challenge, especially in domains like tabular data learning, where simpler models are often preferred due to interpretability and efficiency. In thi...

Recent advancement in deep-neural network performance led to the development of new state-of-the-art approaches in numerous areas. However, the black-box nature of neural networks often prohibits their use in areas where model explainability and model transparency are crucial. Over the years, researchers proposed many algorithms to aid neural netwo...

Software defect prediction aims to identify potentially defective software modules to better allocate limited quality assurance resources. Practitioners often do this by utilizing supervised models trained using historical data. This data is gathered by mining version control and issue tracking systems. Version control commits are linked to issues...

In this paper, several model architectures are explored in order to design a high-performing named entity recognition model for addresses which deals with challenges such as diversity, ambiguity and complexity of the address entity. Different types of neural networks are used for training the classifier, including the bidirectional LSTM network in...

This paper proposes two natural language processing models for extracting useful information from multilingual, unstructured (free form) CV documents. The model identifies the relevant document sections (personal information, education, employment, etc.) and the corresponding specific information at the lower hierarchy level (names, addresses, role...

We describe a CV recommender system built for the purpose of connecting candidates with projects that are relevant to their skills. Each candidate and each project is described by a textual document (CV or a project description) from which we extract a set of skills and convert this set to a numeric representation using two known models: Latent Sem...

In this paper, we describe a CV recommender system with a focus on two properties. The first property is the ability to classify candidates into roles based on automatic processing of their CV documents. The second property is the ability to recommend skills to a candidate which are not listed in their CV, but the candidate is likely to have them....

As cloud computing becomes the prevailing aspect of software engineering, paradigms such as Service-Based Systems (SBSs) or Software as a Service (SaaS) are coming into focus. They are based on cloud services responding to numerous client requests. Selecting the actual service instance for request can be an issue, if requirements for multiple Quali...

Many problems in smart solution development make use of discrete optimization techniques. It is expected that smart cities will have a constant need for parcel delivery and vehicle routing which is heavily reliant on discrete optimization. In this paper we present an improvement to the Variable neighborhood descent (VND) algorithm for discrete opti...

In this paper we present a greedy randomized adaptive search procedure (GRASP) for solving a vehicle routing problem (VRP) for package delivery with delivery place selection. The problem can be solved by stepwise optimization, i.e., first selecting delivery sites and then defining routes based on that selection. Alternatively, it can be solved by j...

Modern service selection in a cloud has to consider multiple requests to various service classes by multiple users. Taking into account quality-of-service requirements such as response time, throughput, and reliability, as well as the processing capacities of the service instances, we devise an efficient algorithm for minimum-cost mapping of mutual...

Recommender systems based on collaborative filtering (CF) rely on datasets containing users' taste preferences for various items. Accuracy of various prediction approaches depends on the amount of similarity between users and items in a dataset. As a heuristic estimate of this data quality aspect, which could serve as an indicator of the prediction...

Due to proliferation of digital publishing, e-book catalogs are abundant but noisy and unstructured. Tools for the digital librarian rely on ISBN, metadata embedded into digital files (without accepted standard) and cryptographic hash functions for the identification of coderivative or nearduplicate content. However, unreliability of metadata and s...

The aim of this paper is to show that an accurate and efficient text classifier for relatively simple problem domains can be created in only a few hours of development time. The motivating example discussed in the paper is a recent HackerRank competition problem that tasked competitors with creating a classifier for questions from the popular quest...

The modern information systems on the Internet are often implemented as composite services built from multiple atomic services. These atomic services have their interfaces publicly available while their inner structure is unknown. The quality of the composite service is dependent on both the availability of each atomic service and their appropriate...

Service-oriented architecture (SOA) is a popular paradigm for development of distributed systems by composing the functionality provided by the services exposed on the network. In effect, the services can use functionalities of other services to accomplish their own goals. Although such an architecture provides an elegant solution to simple constru...

Representational State Transfer (REST), as an architectural style for distributed hyper-media systems, enables scalable operation of the World Wide Web and is the foundation for its future evolution. However, although described over 10 years ago, no formal model for representing RESTful systems exists that is comprehensive in following REST princip...

Representational State Transfer (REST), as an architectural style for distributed hypermedia systems, enables scalable operation of the World Wide Web (WWW) and is the foundation for its future evolution. However, although described over 10 years ago, no comprehensive formal model for representing RESTful systems exists. The lack of a formal model...

The proliferation of smart-phone devices, with ever advancing technological features, has brought the issue of mobile device security back into focus. Mobile devices are rapidly becoming attractive targets for malicious attacks due to significant advances in both hardware and operating systems. The modern mobile platforms, like Android, iOS and Sym...

The Web today has become the most used and popular platform for application development. In the beginnings of the Web, applications provided users just the ability to browse and read content. The expansion and adoption of new web technologies has led to a significant increase in development and, more importantly, usage of web applications that allo...

The proliferation of smart-phone devices, with ever advancing technological features, has brought the issue of mobile device security back into focus. Mobile devices are rapidly becoming attractive targets for malicious attacks due to significant advances in both hardware and operating systems. The modern mobile platforms, like Android, iOS and Sym...