arXiv subjects

Muhammad Haris

Publications and source records attributed to Muhammad Haris.

At least 19 recordsLinked to original sources

arXiv2026

Efficient MILP-based Urban Network Traffic Control in Mixed Autonomy with Dynamic Saturation Rates

This paper introduces a novel control strategy to optimize urban network traffic in mixed autonomy settings, featuring Connected and Automated Vehicles (CAVs) alongside Human-Driven Vehicles (HDVs). Unlike previous control strategies, where the impact of driver behaviour of CAVs and HDVs is not explicitly considered, we propose a dynamic, queue-responsive saturation rate to account for autonomy-driven variations in traffic flow characteristics. The proposed method is based on an extended multi-commodity store-and-forward model to a mixed autonomy environment, integrating optimized routing for CAVs via infrastructure-linked connectivity, and signal timings at every signalized intersection. The problem is formulated as a Non-Convex Quadratic Program (NQP), which accounts for queue evolution, spillback, green time allocation, and CAVs routing. To enable computational efficiency for real-time applications, we transform the NQP into a sequence of convex subproblems, leveraging under- and over-estimators to reformulate it as a Mixed Integer Linear Program (MILP). Experimental results via microscopic simulations validate the efficiency and robustness of the proposed methodology. The results reflect that the proposed model outperforms the existing multi-commodity approach, thus demonstrating its potential for real-time traffic optimization in future urban mobility systems.

eess.SY↗

arXiv2026

Nested Named Entity Recognition in Plasma Physics Research Articles

Named Entity Recognition (NER) is an important task in natural language processing that aims to identify and extract key entities from unstructured text. We present a novel application of NER in plasma physics research articles and address the challenges of extracting specialized entities from scientific text in this domain. Research articles in plasma physics often contain highly complex and context-rich content that must be extracted to enable, e.g., advanced search. We propose a lightweight approach based on encoder-transformers and conditional random fields to extract (nested) named entities from plasma physics research articles. First, we annotate a plasma physics corpus with 16 classes specifically designed for the nested NER task. Second, we evaluate an entity-specific model specialization approach, where independent BERT-CRF models are trained to recognize individual entity types in plasma physics text. Third, we integrate an optimization process to systematically fine-tune hyperparameters and enhance model performance. Our work contributes to the advancement of entity recognition in plasma physics and also provides a foundation to support researchers in navigating and analyzing scientific literature.

cs.CL↗

arXiv2025

Managing Comprehensive Research Instrument Descriptions within a Scholarly Knowledge Graph

In research, measuring instruments play a crucial role in producing the data that underpin scientific discoveries. Information about instruments is essential in data interpretation and, thus, knowledge production. However, if at all available and accessible, such information is scattered across numerous data sources. Relating the relevant details, e.g. instrument specifications or calibrations, with associated research assets (data, but also operating infrastructures) is challenging. Moreover, understanding the (possible) use of instruments is essential for researchers in experiment design and execution. To address these challenges, we propose a Knowledge Graph (KG) based approach for representing, publishing, and using information, extracted from various data sources, about instruments and associated scholarly artefacts. The resulting KG serves as a foundation for exploring and gaining a deeper understanding of the use and role of instruments in research, discovering relations between instruments and associated artefacts (articles and datasets), and opens the possibility to quantify the impact of instruments in research.

cs.DL↗

arXiv2024

Rethinking the production and publication of machine-reusable expressions of research findings

Literature is the primary expression of scientific knowledge and an important source of research data. However, scientific knowledge expressed in narrative text documents is not inherently machine reusable. To facilitate knowledge reuse, e.g. for synthesis research, scientific knowledge must be extracted from articles and organized into databases post-publication. The high time costs and inaccuracies associated with completing these activities manually has driven the development of techniques that automate knowledge extraction. Tackling the problem with a different mindset, we propose a pre-publication approach, known as reborn, that ensures scientific knowledge is born reusable, i.e. produced in a machine-reusable format during knowledge production. We implement the approach using the Open Research Knowledge Graph infrastructure for FAIR scientific knowledge organization. We test the approach with three use cases, and discuss the role of publishers and editors in scaling the approach. Our results suggest that the proposed approach is superior compared to classical manual and semi-automated post-publication extraction techniques in terms of knowledge richness and accuracy as well as technological simplicity.

cs.DL↗

arXiv2023

Beyond Line of Sight Defense Communication Systems: Recent Advances and Future Challenges

Beyond Line of Sight (BLOS) communication stands as an indispensable element within defense communication strategies, facilitating information exchange in scenarios where traditional Line of Sight (LOS) methodologies encounter obstruction. This article delves into the forefront of technologies driving BLOS communication, emphasizing advanced systems like phantom networks, nanonetworks, aerial relays, and satellite-based defense communication. Moreover, we present a practical use case of UAV path planning using optimization techniques amidst radar-threat war zones that add concrete relevance, underscoring the tangible applications of BLOS defense communication systems. Additionally, we present several future research directions for BLOS communication in defense systems, such as resilience enhancement, the integration of heterogeneous networks, management of contested spectrums, advancements in multimedia communication, adaptive methodologies, and the burgeoning domain of the Internet of Military Things (IoMT). This exploration of BLOS technologies and their applications lays the groundwork for synergistic collaboration between industry and academia, fostering innovation in defense communication paradigms.

eess.SP↗

arXiv2023

Scholarly Knowledge Graph Construction from Published Software Packages

The value of structured scholarly knowledge for research and society at large is well understood, but producing scholarly knowledge (i.e., knowledge traditionally published in articles) in structured form remains a challenge. We propose an approach for automatically extracting scholarly knowledge from published software packages by static analysis of their metadata and contents (scripts and data) and populating a scholarly knowledge graph with the extracted knowledge. Our approach is based on mining scientific software packages linked to article publications by extracting metadata and analyzing the Abstract Syntax Tree (AST) of the source code to obtain information about the used and produced data as well as operations performed on data. The resulting knowledge graph includes articles, software packages metadata, and computational techniques applied to input data utilized as materials in research work. The knowledge graph also includes the results reported as scholarly knowledge in articles.

cs.DL↗

arXiv2022

Scholarly Knowledge Extraction from Published Software Packages

A plethora of scientific software packages are published in repositories, e.g., Zenodo and figshare. These software packages are crucial for the reproducibility of published research. As an additional route to scholarly knowledge graph construction, we propose an approach for automated extraction of machine actionable (structured) scholarly knowledge from published software packages by static analysis of their (meta)data and contents (in particular scripts in languages such as Python). The approach can be summarized as follows. First, we extract metadata information (software description, programming languages, related references) from software packages by leveraging the Software Metadata Extraction Framework (SOMEF) and the GitHub API. Second, we analyze the extracted metadata to find the research articles associated with the corresponding software repository. Third, for software contained in published packages, we create and analyze the Abstract Syntax Tree (AST) representation to extract information about the procedures performed on data. Fourth, we search the extracted information in the full text of related articles to constrain the extracted information to scholarly knowledge, i.e. information published in the scholarly literature. Finally, we publish the extracted machine actionable scholarly knowledge in the Open Research Knowledge Graph (ORKG).

cs.DL↗

arXiv2022

Persistent Identification and Interlinking of FAIR Scholarly Knowledge

We leverage the Open Research Knowledge Graph - a scholarly infrastructure that supports the creation, curation, and reuse of structured, semantic scholarly knowledge - and present an approach for persistent identification of FAIR scholarly knowledge. We propose a DOI-based persistent identification of ORKG Papers, which are machine-actionable descriptions of the essential information published in scholarly articles. This enables the citability of FAIR scholarly knowledge and its discovery in global scholarly communication infrastructures (e.g., DataCite, OpenAIRE, and ORCID). While publishing, the state of the ORKG Paper is saved and cannot be further edited. To allow for updating published versions, ORKG supports creating new versions, which are linked in provenance chains. We demonstrate the linking of FAIR scholarly knowledge with digital artefacts (articles), agents (researchers) and other objects (organizations). We persistently identify FAIR scholarly knowledge (namely, ORKG Papers and ORKG Comparisons as collections of ORKG Papers) by leveraging DataCite services. Given the existing interoperability between DataCite, Crossref, OpenAIRE and ORCID, sharing metadata with DataCite ensures global findability of FAIR scholarly knowledge in scholarly communication infrastructures.

cs.DL↗

arXiv2022

The Digitalization of Bioassays in the Open Research Knowledge Graph

Background: Recent years are seeing a growing impetus in the semantification of scholarly knowledge at the fine-grained level of scientific entities in knowledge graphs. The Open Research Knowledge Graph (ORKG) https://www.orkg.org/ represents an important step in this direction, with thousands of scholarly contributions as structured, fine-grained, machine-readable data. There is a need, however, to engender change in traditional community practices of recording contributions as unstructured, non-machine-readable text. For this in turn, there is a strong need for AI tools designed for scientists that permit easy and accurate semantification of their scholarly contributions. We present one such tool, ORKG-assays. Implementation: ORKG-assays is a freely available AI micro-service in ORKG written in Python designed to assist scientists obtain semantified bioassays as a set of triples. It uses an AI-based clustering algorithm which on gold-standard evaluations over 900 bioassays with 5,514 unique property-value pairs for 103 predicates shows competitive performance. Results and Discussion: As a result, semantified assay collections can be surveyed on the ORKG platform via tabulation or chart-based visualizations of key property values of the chemicals and compounds offering smart knowledge access to biochemists and pharmaceutical researchers in the advancement of drug development.

cs.DL↗

arXiv2022

Enriching Scholarly Knowledge with Context

Leveraging a GraphQL-based federated query service that integrates multiple scholarly communication infrastructures (specifically, DataCite, ORCID, ROR, OpenAIRE, Semantic Scholar, Wikidata and Altmetric), we develop a novel web widget based approach for the presentation of scholarly knowledge with rich contextual information. We implement the proposed approach in the Open Research Knowledge Graph (ORKG) and showcase it on three kinds of widgets. First, we devise a widget for the ORKG paper view that presents contextual information about related datasets, software, project information, topics, and metrics. Second, we extend the ORKG contributor profile view with contextual information including authored articles, developed software, linked projects, and research interests. Third, we advance ORKG comparison faceted search by introducing contextual facets (e.g. citations). As a result, the devised approach enables presenting ORKG scholarly knowledge flexibly enriched with contextual information sourced in a federated manner from numerous technologically heterogeneous scholarly communication infrastructures.

cs.DL↗

arXiv2021

Federating Scholarly Infrastructures with GraphQL

A plethora of scholarly knowledge is being published on distributed scholarly infrastructures. Querying a single infrastructure is no longer sufficient for researchers to satisfy information needs. We present a GraphQL-based federated query service for executing distributed queries on numerous, heterogeneous scholarly infrastructures (currently, ORKG, DataCite and GeoNames), thus enabling the integrated retrieval of scholarly content from these infrastructures. Furthermore, we present the methods that enable cross-walks between artefact metadata and artefact content across scholarly infrastructures, specifically DOI-based persistent identification of ORKG artefacts (e.g., ORKG comparisons) and linking ORKG content to third-party semantic resources (e.g., taxonomies, thesauri, ontologies). This type of linking increases interoperability, facilitates the reuse of scholarly knowledge, and enables finding machine actionable scholarly knowledge published by ORKG in global scholarly infrastructures. In summary, we suggest applying the established linked data principles to scholarly knowledge to improve its findability, interoperability, and ultimately reusability, i.e., improve scholarly knowledge FAIR-ness.

cs.DL↗

arXiv2021

Low Light Image Enhancement via Global and Local Context Modeling

Images captured under low-light conditions manifest poor visibility, lack contrast and color vividness. Compared to conventional approaches, deep convolutional neural networks (CNNs) perform well in enhancing images. However, being solely reliant on confined fixed primitives to model dependencies, existing data-driven deep models do not exploit the contexts at various spatial scales to address low-light image enhancement. These contexts can be crucial towards inferring several image enhancement tasks, e.g., local and global contrast, brightness and color corrections; which requires cues from both local and global spatial extent. To this end, we introduce a context-aware deep network for low-light image enhancement. First, it features a global context module that models spatial correlations to find complementary cues over full spatial domain. Second, it introduces a dense residual block that captures local context with a relatively large receptive field. We evaluate the proposed approach using three challenging datasets: MIT-Adobe FiveK, LoL, and SID. On all these datasets, our method performs favorably against the state-of-the-arts in terms of standard image fidelity metrics. In particular, compared to the best performing method on the MIT-Adobe FiveK dataset, our algorithm improves PSNR from 23.04 dB to 24.45 dB.

cs.CV↗

arXiv2020

Image Super-Resolution using Explicit Perceptual Loss

This paper proposes an explicit way to optimize the super-resolution network for generating visually pleasing images. The previous approaches use several loss functions which is hard to interpret and has the implicit relationships to improve the perceptual score. We show how to exploit the machine learning based model which is directly trained to provide the perceptual score on generated images. It is believed that these models can be used to optimizes the super-resolution network which is easier to interpret. We further analyze the characteristic of the existing loss and our proposed explicit perceptual loss for better interpretation. The experimental results show the explicit approach has a higher perceptual score than other approaches. Finally, we demonstrate the relation of explicit perceptual loss and visually pleasing images using subjective evaluation.

eess.IV↗

arXiv2020

Space-Time-Aware Multi-Resolution Video Enhancement

We consider the problem of space-time super-resolution (ST-SR): increasing spatial resolution of video frames and simultaneously interpolating frames to increase the frame rate. Modern approaches handle these axes one at a time. In contrast, our proposed model called STARnet super-resolves jointly in space and time. This allows us to leverage mutually informative relationships between time and space: higher resolution can provide more detailed information about motion, and higher frame-rate can provide better pixel alignment. The components of our model that generate latent low- and high-resolution representations during ST-SR can be used to finetune a specialized mechanism for just spatial or just temporal super-resolution. Experimental results demonstrate that STARnet improves the performances of space-time, spatial, and temporal video super-resolution by substantial margins on publicly available datasets.

cs.CV↗

arXiv2019

Deep Back-Projection Networks for Single Image Super-resolution

Previous feed-forward architectures of recently proposed deep super-resolution networks learn the features of low-resolution inputs and the non-linear mapping from those to a high-resolution output. However, this approach does not fully address the mutual dependencies of low- and high-resolution images. We propose Deep Back-Projection Networks (DBPN), the winner of two image super-resolution challenges (NTIRE2018 and PIRM2018), that exploit iterative up- and down-sampling layers. These layers are formed as a unit providing an error feedback mechanism for projection errors. We construct mutually-connected up- and down-sampling units each of which represents different types of low- and high-resolution components. We also show that extending this idea to demonstrate a new insight towards more efficient network design substantially, such as parameter sharing on the projection module and transition layer on projection step. The experimental results yield superior results and in particular establishing new state-of-the-art results across multiple data sets, especially for large scaling factors such as 8x.

cs.CV↗

arXiv2019

Recurrent Back-Projection Network for Video Super-Resolution

We proposed a novel architecture for the problem of video super-resolution. We integrate spatial and temporal contexts from continuous video frames using a recurrent encoder-decoder module, that fuses multi-frame information with the more traditional, single frame super-resolution path for the target frame. In contrast to most prior work where frames are pooled together by stacking or warping, our model, the Recurrent Back-Projection Network (RBPN) treats each context frame as a separate source of information. These sources are combined in an iterative refinement framework inspired by the idea of back-projection in multiple-image super-resolution. This is aided by explicitly representing estimated inter-frame motion with respect to the target, rather than explicitly aligning frames. We propose a new video super-resolution benchmark, allowing evaluation at a larger scale and considering videos in different motion regimes. Experimental results demonstrate that our RBPN is superior to existing methods on several datasets.

cs.CV↗

arXiv2018

Task-Driven Super Resolution: Object Detection in Low-resolution Images

We consider how image super resolution (SR) can contribute to an object detection task in low-resolution images. Intuitively, SR gives a positive impact on the object detection task. While several previous works demonstrated that this intuition is correct, SR and detector are optimized independently in these works. This paper proposes a novel framework to train a deep neural network where the SR sub-network explicitly incorporates a detection loss in its training objective, via a tradeoff with a traditional detection loss. This end-to-end training procedure allows us to train SR preprocessing for any differentiable detector. We demonstrate that our task-driven SR consistently and significantly improves accuracy of an object detector on low-resolution images for a variety of conditions and scaling factors.

cs.CV↗

arXiv2018

Deep Back-Projection Networks For Super-Resolution

The feed-forward architectures of recently proposed deep super-resolution networks learn representations of low-resolution inputs, and the non-linear mapping from those to high-resolution output. However, this approach does not fully address the mutual dependencies of low- and high-resolution images. We propose Deep Back-Projection Networks (DBPN), that exploit iterative up- and down-sampling layers, providing an error feedback mechanism for projection errors at each stage. We construct mutually-connected up- and down-sampling stages each of which represents different types of image degradation and high-resolution components. We show that extending this idea to allow concatenation of features across up- and down-sampling stages (Dense DBPN) allows us to reconstruct further improve super-resolution, yielding superior results and in particular establishing new state of the art results for large scaling factors such as 8x across multiple data sets.

cs.CV↗