Edlira Kalemi Vakaj

• PhD
• Associate Professor at Birmingham City University

In today's technology-driven world, databases are everywhere-they power everything from business systems to mobile apps. But interacting with them still requires knowledge of SQL, a technical language that many everyday users don't understand. This creates a barrier for people who need data but lack programming skills. Natural Language Interfaces t...

Introduction: This research investigates the integration of natural language processing (NLP) techniques with eye-tracking data to gain deeper insights into cognitive processes during reading. By analyzing eye movements, such as saccades and fixations, the study aims to enhance NLP models' accuracy and efficiency in processing text complexity and c...

IFC data has become the general building information standard for collaborative work in the construction industry. However, IFC data can be very complicated because it allows for multiple ways to represent the same product information. In this research, we utilise the capabilities of LLMs to parse the IFC data with Graph Retrieval-Augmented Generat...

This paper introduces a novel approach to handling unknown intents in dialogue systems by proposing a custom intent discovery pipeline using Z-BERT-A. Developed in Python, this pipeline is specifically designed to address intents that are not predefined within the system. The development of this solution is guided by a comprehensive literature revi...

Within the construction and design engineering sphere, integrating advanced technologies has become indispensable for streamlining processes and enhancing productivity. This paper explores the development and implementation of a design assist tool, combining Natural Language Processing (NLP) methodologies to extract semantic information from digita...

Chest X-ray interpretation is essential for diagnosing cardiac and respiratory diseases. This study introduces a deep learning ensemble approach that integrates Convolutional Neural Networks (CNNs), including ResNet-152, VGG19, EfficientNet, and a Vision Transformer (ViT), to enhance diagnostic accuracy. Using the NIH Chest X-ray dataset, the metho...

The architecture, engineering, and construction (AEC) industry still heavily relies on information stored in drawings for building construction, maintenance, compliance and error checks. However, information extraction (IE) from building drawings is often time-consuming and costly, especially when dealing with historical buildings. Drawing search c...

Automatic Compliance Checking (ACC) within the Architecture, Engineering, and Construction (AEC) sector necessitates automating the interpretation of building regulations to achieve its full potential. Converting textual rules into machine-readable formats is challenging due to the complexities of natural language and the scarcity of resources for...

This research presents a novel approach to automated competency question generation by integrating Large Language Models (LLMs) with Knowledge Graphs (KGs), particularly within the context of sustainability assessment standards like BREEAM. The study develops a comprehensive methodology combining natural language processing and knowledge representa...

Knowledge Graphs (KG) are emerging and becoming increasingly popular. Building a domain knowledge graph from a large amount of text is a challenging task which requires a tremendous amount of work, including entity recognition, entity disambiguation, and relationship extraction. In this context, the 3rd NLP4KGC workshop brings together academics, i...

The Architecture, Engineering and Construction (AEC) sector faces severe sustainability and efficiency challenges. In recent years, various initiatives have demonstrated how artificial intelligence can effectively address these challenges and improve sustainability and efficiency in the sector. In the context of retrofit projects, there is a contin...

Metastatic breast cancer (MBC) continues to be a leading cause of cancer-related deaths among women. This work introduces an innovative non-invasive breast cancer classification model designed to improve the identification of cancer metastases. While this study marks the initial exploration into predicting MBC, additional investigations are essenti...

Automatic Compliance Checking (ACC) is a promising response to the challenges involved in meeting building and planning regulations, and increasingly utilised by researchers in the context of Building Information Modelling (BIM) and the Industry Foundation Classes (IFC). However, engineers often use computational methods, such as Finite Element Ana...

Automatic Compliance Checking (ACC) within the Architecture, Engineering, and Construction (AEC) sector necessitates automating the interpretation of building regulations to achieve its full potential. However, extracting information from textual rules to convert them to a machine-readable format has been a challenge due to the complexities associa...

Breast cancer is a major health problem worldwide, and accurate prediction of its recurrence is crucial to early detection of recurrence and personalised treatment. In recent years, various AI techniques have been applied to predict cancer recurrence with increasingly high accuracy. Graph Neural Networks (GNNs) have emerged as powerful tools for an...

Automated compliance checking (ACC) in the Architecture, Engineering, and Construction (AEC) sector represents a pivotal task which is traditionally executed manually, demanding significant time and labor. This work investigates the automation of the Requirement, Applicability, Selection, and Exception (RASE) methodology for building regulatory com...

Currently climate change poses a significant challenge to us, both now and as we head into the future. Several individuals endeavour to adopt more sustainable lifestyles, ensuring that our daily choices do not have adverse impact on our planet. Under the umbrella of sustainability, food stands out as an area of specific emphasis, specifically regar...

This book constitutes the proceedings of the First International Conference, AI4S 2023, held in Pune, India, during September 4-5, 2023. The 14 full papers and the 2 short papers included in this volume were carefully reviewed and selected from 72 submissions. This volume aims to open discussion on trustworthy AI and related topics, trying to brin...

Safeguarding for healthcare involves working together to protect adults, children, and young people at risk of harm. Despite global research and national guidance outlining health professionals’ roles in this regard, there is limited knowledge about the type of strategies used to mobilise safeguarding research to practitioners in England. Our criti...

Internet of Things (IoT) data has the potential to be utilized in many domain-specific applications to enable smart sensing in areas that were not initially covered during the conceptualization phase of these applications. Typically, data collected in IoT scenarios serve a specific purpose and follow heterogeneous data models and domain-specific on...

The surge in Covid-19 cases seen in 2020 has caused the UK government to enact regulations to stop the virus’s spread. Along with other aspects like altered customer confidence and activity, the financial effects of these actions must be taken into account. This later can be studied from the user generated content posted on social networks such as...

Large Language Models (LLMs) have taken Knowledge Representation -- and the world -- by storm. This inflection point marks a shift from explicit knowledge representation to a renewed focus on the hybrid representation of both explicit knowledge and parametric knowledge. In this position paper, we will discuss some of the common debate points within...

Businesses have sought out new solutions to provide support and improve customer satisfaction as more products and services have become interconnected digitally. There is an inherent need for businesses to provide or outsource fast, efficient and knowledgeable support to remain competitive. Support solutions are also advancing with technologies, in...

Businesses have sought out new solutions to provide support and improve customer satisfaction as more products and services have become interconnected digitally. There is an inherent need for businesses to provide or outsource fast, efficient and knowledgeable support to remain competitive. Support solutions are also advancing with technologies, in...

Climate change is one of the biggest issues we face, besides Covid [6], we head into the future. Many strive to live more sustainably so that the choices made in our daily lives don’t adversely impact our planet. Food is one area of sustainability that is focused on, especially the impact of what we eat and how we can make choices that do not negat...

Contact centres have been highly valued by organizations for a long time. However, the COVID-19 pandemic has highlighted their critical importance in ensuring business continuity, economic activity, and quality customer support. The pandemic has led to an increase in customer inquiries related to payment extensions, cancellations, and stock inquiri...

The Architecture, Engineering, and Construction (AEC) industry is subject to numerous regulations and standards that govern the design, construction, and maintenance of buildings and infrastructure. These regulations often involve complex language and technical jargon, which can be difficult to understand and apply in practice. Semantisation, or th...

The Covid-19 pandemic is a universal problem that has caused significant outbreaks in every country and region, affecting men and women of all ages around the world. The automatic detection of lung infection is a major challenge that poses a limitation to the potential medical imaging offers to augment patient treatments and strategies for tackling...

Human communication is predominantly expressed through speech and writing, which are powerful mediums for conveying thoughts and opinions. Researchers have been studying the analysis of human sentiments for a long time, including the emerging area of bimodal sentiment analysis in natural language processing (NLP). Bimodal sentiment analysis has gai...

International Conference on Sustainbility

Design for manufacturing and assembly (DfMA) has been widely applied to support the decision-making process in offsite construction. With a DfMA approach, cost estimation requires taking product design and production processes into consideration. Current studies conduct cost estimation built upon quantity take-offs. However, they do not provide a v...

Communication is a key method of expressing one's thoughts and opinions. Amongst many 1 modalities, speech and writing are the most powerful and common forms of human communication. 2 Analysing what and how people think has inherently been an interesting and progressive research 3 domain. This includes bimodal sentiment analysis which is an emergin...

The current digital fabrication workflow requires many iterations between design and manufacturing. Automated manufacturability analysis can reduce the number of iterations at the design stage. However, existing approaches that leverage design for manufacturing and assembly (DfMA) do not consider detailed product features and production capabilitie...

The COVID-19 pandemic represents a global public health emergency that is becoming an economic crisis, a social crisis and a well-being crisis. Countries around the world have taken unprecedented precautionary measures against COVID-19 to control the spread of the disease and to ensure the well-being of their people. This study investigates the hea...

Model reusability and integration with datasets are major contributors towards their interoperability, the concepts that follows process established by computer aided process engineering (CAPE) community (Belaud & Pons 2002). This paper proposes a semantic approach which enables model/data registration, their discovery and concomitantly model their...

Cloud manufacturing is an emerging manufacturing paradigm to enable rapid production for mass customization. Industrialized construction shares a similar production environment with manufacturing products, so it has a great potential to utilize the paradigm. Previous studies never examined cloud manufacturing in the construction context. This work...

Offsite Manufacturing (OSM) is a modern and innovative method of construction with the potential to adopt advanced factory production system through a more structured workflow, standardised products, and the use of robotics for automation. However, there have been challenges in quantifying improvements from the conventional method, which leads to t...

Nowadays, Online Social Networks (OSNs) has created a breeding ground for criminals to engage in cyber–crime activities, and the legal enforcement agencies (LEAs) are facing significant challenges since there is no consistent and generalized framework built specifically to analyse users’ misbehaviour and their social activity on these platforms. Da...

Nowadays, online social networks (OSNs) are being used as a hosting ground for criminal activities, and the legal enforcement agencies (LEAs) are struggling to process and analyse the huge amount of data coming from these sources. OSNs generate a huge massive volume of unstructured data making it difficult for the LEAs to ‘patrol the facts’ and to...

Architecture, Engineering and Construction (AEC) is a fragmented industry dealing with heterogeneous data formats coming from different domains. Building Information Modelling (BIM) is one of the most important efforts to manage information collaboratively within the AEC industry. The Industry Foundation Classes (IFC) can be used as a data format t...

Online Social Networks (OSNs) have fundamentally and permanently altered the arena of digital and classical crime. Recently, law enforcement agencies (LEAs) have been using OSNs as a data source to collect Open Source Intelligence for fighting and preventing crime. However, most existing technological developments for LEAs to fight and prevent crim...

Online Social Networks (OSNs) have fundamentally and permanently altered the arena of digital and classical crime. Recently, law enforcement agencies (LEAs) have been using OSNs as a data source to collect Open Source Intelligence for fighting and preventing crime. However, most existing technological developments for LEAs to fight and prevent crim...

Pre-processing of large scale datasets in order to ensure data quality is a very important task in data mining. One of the serious threats to data quality is the lack of data collected during field experiments, which negatively affects the data quality. The missing data usually have significant effects in many real-life pattern classification scena...

Process modelling and simulation is a vital tool to plan, evaluate, assess, and develop different alternatives for the design of products and processes. The complexity of problems as well as heterogeneity of modelling methods make process modelling and simulation challenging, time consuming and often tedious process requiring a wide range of expert...

Biorefining is a dynamic field with ever growing number of computer models developed, heterogeneous data acquired and generally new knowledge generated in large volumes, all to serve functions at different scales and for different purposes. Sharing and reusing of these resources, especially models and data, inherently saves developing time, but als...

The increasing availability of biorefining models and the heterogeneity characterising them necessitates efficient acquisition, discovery and integration tools to enable their reuse. This has been addressed by the CAPE-OPEN standard which significantly facilitates model reusability and interoperability (Braunschweig et al., 2004). Still, efficiency...

Pre-processing of large scale datasets in order to ensure data quality is a very important task in data mining. One of the serious threats to data quality is the lack of data collected during field experiments, which negatively affects the data quality. The missing data usually have significant effects in many real-life pattern classification scena...

There are numerous social networks such as Facebook, LinkedIn, Google Plus and Twitter whose data sources are becoming larger every day holding an abundance of valuable information. Among these data, digital crime evidence can be collected from on-line social networks (OSNs) for crime detection and further analysis. This paper describes the SMONT o...

There are numerous social networks such as Facebook, LinkedIn, Google Plus and Twitter whose data sources are becoming larger every day holding an abundance of valuable information. Among these data, digital crime evidence can be collected from online social networks (OSNs) for crime detection and further analysis. This paper describes the SMONT on...

A design of InterCAPEmodel ontology, which contains a comprehensive description to represent the knowledge of models and data in the biorefining domain, is presented. Primarily, the InterCAPEmodel ontology aims at providing implicit knowledge that reflects process synthesis logic, and explicit knowledge including a complete set of input/output type...

Solving complex problems in biorefining associated with the process or unit design, process synthesis and analysis, or pure understanding the potential, heavily rely on modelling and simulation, the activity which remains implicit to the engineers who built them and hence limited to their use. The importance of model reusability, therefore, has bee...

Online Social Networks (OSNs) are nowadays being used widely and intensively for crime investigation and prevention activities. As they provide a lot of information they are used by the law enforcement and intelligence. An extensive review on existing solutions and models for collecting intelligence from this source of information and making use of...

Digital Imaging and Communications in Medicine (DICOM) is a standard for handling, storing, printing and transmitting information in medical imaging. It includes: the file format and the networking protocol. The image consists of a list of attributes which contains a) metadata for image like size, dimensions, resolution etc. and b) patient metadata...

In everyday life the production and broadcast of material goods, computer and management in global communication cannot be realized without an electrical power source, the output of which is associated with environmental and safety problems. Current methods for providing electricity departing from limited natural resources, such as oil, gas, coal,...

Formal Representation of Knowledge deals with the construction of real world models taken from a certain domain, which enables automatic reasoning and interpretation. These formal models, called also ontologies, are used to offer formal semantics (forms interpretable by machine) to all kinds of information. Ontology building in Computer Science is...

With the expansion of global communication the commercial world has changed its proceedings. The Internet has played a crucial role in the development of new ways of doing business, by creating a major global market. E-commerce is one of the main subjects discussed in legal environments last years. The need to develop legal elaboration with the sam...

The aim of Semantic Web is to add machineprocessable information to the Web. Our focus is on information related to people. This problem in Semantic Web is addressed by the FOAF Vocabulary. FOAF Vocabulary describes people, their activities and the people they know. The terms defined in this vocabulary let us say general things about us and people...

The main objective of our study is to determine the challenges faced during the process of teaching Computer Science in a university of a country in transition and make suggestions to improve this teaching process by perfecting the necessary conditions. Our survey builds on the thesis that we live in an information age; information technology is an...