Information, Volume 15, Issue 2 (February 2024) – 54 articles

Background: Degenerative spinal pathologies are highly prevalent among the elderly population. Timely diagnosis of osteoporotic fractures and other degenerative deformities enables proactive measures to mitigate the risk of severe back pain and disability. Methods: We explore the use of shape auto-encoders for vertebrae, advancing the state of the art through robust automatic segmentation models trained without fracture labels and recent geometric deep learning techniques. Our shape auto-encoders are pre-trained on a large set of vertebrae surface patches. This pre-training step addresses the label scarcity problem faced when learning the shape information of vertebrae for fracture detection from image intensities directly. We further propose a novel shape decoder architecture: the point-based shape decoder. Results: Employing segmentation masks that were generated using the TotalSegmentator, our proposed method achieves an AUC of 0.901 on the VerSe19 testset. This outperforms image-based and surface-based end-to-end trained models. Our results demonstrate that pre-training the models in an unsupervised manner enhances geometric methods like PointNet and DGCNN. Conclusion: Our findings emphasize the advantages of explicitly learning shape features for diagnosing osteoporotic vertebrae fractures. This approach improves the reliability of classification results and reduces the need for annotated labels. Full article

The development and implementation of information systems strategy in multi-national corporations (MNCs) faces particular challenges—cultural differences and variations in work values and practices across different countries, numerous technology landscapes and legacy issues, language and accounting particularities, and differing business models. This article builds upon the existing literature and in-depth interviews with eighteen industry practitioners employed in six MNCs to construct an operational model to address these challenges. The research design is based on an inductive, qualitative approach that develops an initial conceptual framework—derived from the literature—into an operational model, which is then applied and refined in a case study company. The final model consists of change components and process phases. Six change components are identified that drive and underpin IS strategy—business strategy, systems projects, technology infrastructure, process change, skills and competencies, and costs and benefits. Five core process phases are recognized—review, align, engage, execute, and control. The model is based on the interaction between these two dimensions—change components and process phases—and an action list is also developed to support the application of the model, which contributes to the theory and practice of information systems deployment in MNCs. Full article

This paper presents a formal security analysis of the ISA100.11a standard protocol using the Colored Petri Net (CPN) modeling approach. Firstly, we establish a security threat model for the ISA100.11a protocol and provide a detailed description and analysis of the identified security threats. Secondly, we use the CPN tool to model the protocol formally and conduct model checking and security analysis. Finally, we analyze and discuss the results of the model checking, which demonstrate that the ISA100.11a standard protocol may have vulnerabilities when certain security threats exist, and provide some suggestions to enhance the security of the protocol. This research provides a certain level of security assurance for the ISA100.11a standard protocol and serves as a reference for similar security research on protocols. Full article

As the demand for cybersecurity experts in the industry grows, we face a widening shortage of skilled professionals. This pressing concern has spurred extensive research within academia and national bodies, who are striving to bridge this skills gap through refined educational frameworks, including the integration of innovative information applications like remote laboratories and virtual classrooms. Despite these initiatives, current higher education models for cybersecurity, while effective in some areas, fail to provide a holistic solution to the root causes of the skills gap. Our study conducts a thorough examination of established cybersecurity educational frameworks, with the goal of identifying crucial learning outcomes that can mitigate the factors contributing to this skills gap. Furthermore, by analyzing six different educational models, for each one that can uniquely leverage technology like virtual classrooms and online platforms and is suited to various learning contexts, we categorize these contexts into four distinct categories. This categorization introduces a holistic dimension of context awareness enriched by digital learning tools into the process, enhancing the alignment with desired learning outcomes, a consideration sparsely addressed in the existing literature. This thorough analysis further strengthens the framework for guiding education providers in selecting models that most effectively align with their targeted learning outcomes and implies practical uses for technologically enhanced environments. This review presents a roadmap for educators and institutions, offering insights into relevant teaching models, including the opportunities for the utilization of remote laboratories and virtual classrooms, and their contextual applications, thereby aiding curriculum designers in making strategic decisions. Full article

The COVID-19 pandemic heightened concerns about health and safety, leading people to seek information to protect themselves from infection. Even before the pandemic, false health information was spreading on social media. We conducted a review of recent literature in health and social sciences and proposed a theoretical model to understand the factors influencing the spread of false health information. Our focus was on how false health information circulated before and during the pandemic, impacting people’s perceptions of believing information on social media. We identified four possible strategies to counteract the negative effects of false health information: prebunking, refuting, legislation, and media literacy. We argue that improving people’s social media literacy skills is among the most effective ways to address this issue. Our findings provide a basis for future research and the development of policies to minimize the impact of false health information on society. Full article

The Provincial Health Services Authority (PHSA) of British Columbia suggested that a paradigm shift from weight to well-being could address the unintended consequences of focusing on obesity and improve the outcomes of efforts to address the challenges facing both individuals and our healthcare system. In this paper, we jointly used artificial intelligence (AI) and participatory modeling to examine the possible consequences of this paradigm shift. Specifically, we created a conceptual map with 19 experts to understand how obesity and physical and mental well-being connect to each other and other factors. Three analyses were performed. First, we analyzed the factors that directly connect to obesity and well-being, both in terms of causes and consequences. Second, we created a reduced version of the map and examined the connections between categories of factors (e.g., food production, and physiology). Third, we explored the themes in the interviews when discussing either well-being or obesity. Our results show that obesity was viewed from a medical perspective as a problem, whereas well-being led to broad and diverse solution-oriented themes. In particular, we found that taking a well-being perspective can be more comprehensive without losing the relevance of the physiological aspects that an obesity-centric perspective focuses on. Full article

Self-supervised learning (SSL) has emerged as a promising paradigm for learning flexible speech representations from unlabeled data. By designing pretext tasks that exploit statistical regularities, SSL models can capture useful representations that are transferable to downstream tasks. Barlow Twins (BTs) is an SSL technique inspired by theories of redundancy reduction in human perception. In downstream tasks, BTs representations accelerate learning and transfer this learning across applications. This study applies BTs to speech data and evaluates the obtained representations on several downstream tasks, showing the applicability of the approach. However, limitations exist in disentangling key explanatory factors, with redundancy reduction and invariance alone being insufficient for factorization of learned latents into modular, compact, and informative codes. Our ablation study isolated gains from invariance constraints, but the gains were context-dependent. Overall, this work substantiates the potential of Barlow Twins for sample-efficient speech encoding. However, challenges remain in achieving fully hierarchical representations. The analysis methodology and insights presented in this paper pave a path for extensions incorporating further inductive priors and perceptual principles to further enhance the BTs self-supervision framework. Full article

The development of autonomous driving models through reinforcement learning has gained significant traction. However, developing obstacle avoidance systems remains a challenge. Specifically, optimising path completion times while navigating obstacles is an underexplored research area. Amazon Web Services (AWS) DeepRacer emerges as a powerful infrastructure for engineering and analysing autonomous models, providing a robust foundation for addressing these complexities. This research investigates the feasibility of training end-to-end self-driving models focused on obstacle avoidance using reinforcement learning on the AWS DeepRacer autonomous race car platform. A comprehensive literature review of autonomous driving methodologies and machine learning model architectures is conducted, with a particular focus on object avoidance, followed by hands-on experimentation and the analysis of training data. Furthermore, the impact of sensor choice, reward function, action spaces, and training time on the autonomous obstacle avoidance task are compared. The results of the best configuration experiment demonstrate a significant improvement in obstacle avoidance performance compared to the baseline configuration, with a 95.8% decrease in collision rate, while taking about 79% less time to complete the trial circuit. Full article

Given a social network modelled by a graph, the goal of the influence maximization problem is to find k vertices that maximize the number of active vertices through a process of diffusion. For this diffusion, the linear threshold model is considered. A new algorithm, called ClusterGreedy, is proposed to solve the influence maximization problem. The ClusterGreedy algorithm creates a partition of the original set of nodes into small subsets (the clusters), applies the SimpleGreedy algorithm to the subgraphs induced by each subset of nodes, and obtains the seed set from a combination of the seed set of each cluster by solving an integer linear program. This algorithm is further improved by exploring the submodularity property of the diffusion function. Experimental results show that the ClusterGreedy algorithm provides, on average, higher influence spread and lower running times than the SimpleGreedy algorithm on Watts–Strogatz random graphs. Full article

Attentional orienting is a crucial process in perceiving our environment and guiding human behavior. Recent studies have suggested a forward attentional bias, where faster reactions are observed to spatial cues indicating information appearing in the forward rather than the rear direction. This study investigated how the body position affects attentional orienting, using a modified version of the Posner cueing task within a virtual reality environment. Participants, seated at a 90° angle or reclined at 45°, followed arrows directing their attention to one of four spatial positions where a spaceship will appear, visible either through transparent windows (front space) or in mirrors (rear space). Their task was to promptly identify the spaceship’s color as red or blue. The results indicate that participants reacted more swiftly when the cue correctly indicated the target’s location (valid cues) and when targets appeared in the front rather than the rear. Moreover, the “validity effect”—the advantage of valid over invalid cues—on early eye movements, varied based on both the participant’s body position and the target’s location (front or rear). These findings suggest that the body position may modulate the forward attentional bias, highlighting its relevance in attentional orienting. This study’s implications are further discussed within contexts like aviation and space exploration, emphasizing the necessity for precise and swift responses to stimuli across diverse spatial environments. Full article

Digital transformation in the public sector provides digital services to the citizens aiming at increasing their quality of life, as well as the transparency and accountability of a public administration. Since adaptation to the citizens changing needs is central for its success, Agile methodologies seem best suited for the software development of digital services in that area. However, as well documented by an attempt to use Scrum for an important Public Administration in Italy, substantial modifications to standard Agile were needed, giving rise to a new proposal called improved Agile (in short, iAgile). Another notable example is the Scrum@IMI method developed by the City of Barcelona for the deployment of its digital services. However, given the importance of digital transformation in the public sector and the scarcity of efforts (documented in the scholarly literature) to effectively bring Agile within it, a strategically important contribution that Computer Science can offer is a general paradigm describing how to tailor Agile methodologies and, in particular, Scrum, for such a specific context. Our proposal, called Scrum@PA, addresses this strategic need. Based on it, a public administration has a technically sound avenue to follow to adopt Scrum rather than a generic set of guidelines as in the current state of the art. We show the validity of our proposal by describing how the quite successful Scrum@IMI approach can be derived from Scrum@PA. Although iAgile can also be derived from our paradigm, we have chosen Scrum@IMI as a pilot example since it is publicly available on GitHub. Full article

In the domain of computer forensics, ensuring the integrity of operations like preservation, acquisition, analysis, and documentation is critical. Discrepancies in these processes can compromise evidence and lead to potential miscarriages of justice. To address this, we developed a generic methodology integrating each forensic transaction into an immutable blockchain entry, establishing transparency and authenticity from data preservation to final reporting. Our framework was designed to manage a wide range of forensic applications across different domains, including technology-focused areas such as the Internet of Things (IoT) and cloud computing, as well as sector-specific fields like healthcare. Centralizing our approach are smart contracts that seamlessly connect forensic applications to the blockchain via specialized APIs. Every action within the forensic process triggers a verifiable transaction on the blockchain, enabling a comprehensive and tamper-proof case presentation in court. Performance evaluations confirmed that our system operates with minimal overhead, ensuring that the integration bolsters the judicial process without hindering forensic investigations. Full article

With the exponential growth of remote sensing images in recent years, there has been a significant increase in demand for micro-target detection. Recently, effective detection methods for small targets have emerged; however, for micro-targets (even fewer pixels than small targets), most existing methods are not fully competent in feature extraction, target positioning, and rapid classification. This study proposes an enhanced detection method, especially for micro-targets, in which a combined loss function (consisting of NWD and CIOU) is used instead of a singular CIOU loss function. In addition, the lightweight Content-Aware Reassembly of Features (CARAFE) replaces the original bilinear interpolation upsampling algorithm, and a spatial pyramid structure is added into the network model’s small target layer. The proposed algorithm undergoes training and validation utilizing the benchmark dataset known as AI-TOD. Compared to speed-oriented YOLOv7-tiny, the mAP0.5 and mAP0.5:0.95 of our improved algorithm increased from 42.0% and 16.8% to 48.7% and 18.9%, representing improvements of 6.7% and 2.1%, respectively, while the detection speed was almost equal to that of YOLOv7-tiny. Furthermore, our method was also tested on a dataset of multi-scale targets, which contains small targets, medium targets, and large targets. The results demonstrated that mAP0.5:0.95 increased from “9.8%, 54.8%, and 68.2%” to “12.6%, 55.6%, and 70.1%” for detection across different scales, indicating improvements of 2.8%, 0.8%, and 1.9%, respectively. In summary, the presented method improves detection metrics for micro-targets in various scenarios while satisfying the requirements of detection speed in a real-time system. Full article

Conventional spatiotemporal methods take frequentist or density-based approaches to map event clusters over time. While these methods discern hotspots of varying continuity in space and time, their findings overlook locations of routine occurrences where the geographic context may contribute to the regularity of event occurrences. Hence, this research aims to recognize the routine occurrences of point events and relate site characteristics and situation dynamics around these locations to explain the regular occurrences. We developed an algorithm, Location Analytics of Routine Occurrences (LARO), to determine an appropriate temporal unit based on event periodicity, seek locations of routine occurrences, and geographically contextualize these locations through spatial association mining. We demonstrated LARO in a case study with over 250,000 reported traffic accidents from 2010 to 2018 in Dallas, Texas, United States. LARO identified three distinctive locations, each exhibiting varying frequencies of traffic accidents at each weekly hour. The findings indicated that locations with routine traffic accidents are surrounded by high densities of stores, restaurants, entertainment, and businesses. The timing of traffic accidents showed a strong relationship with human activities around these points of interest. Besides the LARO algorithm, this study contributes to the understanding of previously overlooked periodicity in traffic accidents, emphasizing the association between periodic human activities and the occurrence of street-level traffic accidents. The proposed LARO algorithm is applicable to occurrences of point-based events, such as crime incidents or animal sightings. Full article

Purpose: The purpose of this research paper was to analyse the counterstrategies to mitigate cybersecurity challenges using organisational learning loops amidst major crises in the Higher Education and Research Sector (HERS). The authors proposed the learning loop framework revealing several counterstrategies to mitigate cybersecurity issues in HERS. The counterstrategies are explored, and their implications for research and practice are discussed. Methodology: The qualitative methodology was adopted, and semi-structured interviews with cybersecurity experts and top managers were conducted. Results: This exploratory paper proposed the learning loop framework revealing introducing new policies and procedures, changing existing systems, partnership with other companies, integrating new software, improving employee learning, enhancing security, and monitoring and evaluating security measures as significant counterstrategies to ensure the cyber-safe working environment in HERS. These counterstrategies will help to tackle cybersecurity in HERS, not only during the current major crisis but also in the future. Implications: The outcomes provide insightful implications for both theory and practice. This study proposes a learning framework that prioritises counterstrategies to mitigate cybersecurity challenges in HERS amidst a major crisis. The proposed model can help HERS be more efficient in mitigating cybersecurity issues in future crises. The counterstrategies can also be tested, adopted, and implemented by practitioners working in other sectors to mitigate cybersecurity issues during and after major crises. Future research can focus on addressing the shortcomings and limitations of the proposed learning framework adopted by HERS. Full article

Although there have been some studies on the success factors for IT software projects, there is still a lack of coherent research on the success factors for IT service projects. Therefore, this study aimed to identify and understand the factors and their relationships that contribute to the success of IT service projects. For this purpose, multivariate regressions and structural equation models (SEMs) were developed and analyzed. The regression models included six project management success criteria used as dependent variables (quality of the delivered product, scope realization and requirements, timeliness of delivery, delivery within budget, customer satisfaction, and provider satisfaction) and four independent variables (agile techniques and change management, organization and people, stakeholders and risk analysis, work environment), which had been identified through exploratory factor analysis. The results showed that not all success factors were relevant to all success criteria, and there were differences in their importance. An additional series of exploratory and confirmatory factor analyses along with appropriate statistical measures were employed to evaluate the quality of these four factors. The SEM approach was based on five latent constructs with a total of twenty components. The study suggests that investing in improving people’s knowledge and skills, using agile methodologies, creating a supportive work environment, and involving stakeholders in regular risk analysis are important for project management success. The results also suggest that the success factors for IT service projects depend on both traditional and agile approaches. The study extensively compared its findings with similar research and discussed common issues and differences in both the model structures and methodologies applied. The investigation utilized mathematical methods and techniques that are not commonly applied in the field of project management success modeling. The comprehensive methodology that was applied may be helpful to other researchers who are interested in this topic. Full article

Effective collision risk reduction in autonomous vehicles relies on robust and straightforward pedestrian tracking. Challenges posed by occlusion and switching scenarios significantly impede the reliability of pedestrian tracking. In the current study, we strive to enhance the reliability and also the efficacy of pedestrian tracking in complex scenarios. Particularly, we introduce a new pedestrian tracking algorithm that leverages both the YOLOv8 (You Only Look Once) object detector technique and the StrongSORT algorithm, which is an advanced deep learning multi-object tracking (MOT) method. Our findings demonstrate that StrongSORT, an enhanced version of the DeepSORT MOT algorithm, substantially improves tracking accuracy through meticulous hyperparameter tuning. Overall, the experimental results reveal that the proposed algorithm is an effective and efficient method for pedestrian tracking, particularly in complex scenarios encountered in the MOT16 and MOT17 datasets. The combined use of Yolov8 and StrongSORT contributes to enhanced tracking results, emphasizing the synergistic relationship between detection and tracking modules. Full article

Grasping the concerns of customers is paramount, serving as a foundation for both attracting and retaining a loyal customer base. While customer satisfaction has been extensively explored across diverse industries, there remains a dearth of insights into how distinct rural bed and breakfasts (RB&Bs) can effectively cater to the specific needs of their target audience. This research utilized latent semantic analysis and text regression techniques on online reviews, uncovering previously unrecognized factors contributing to RB&B customer satisfaction. Furthermore, the study demonstrates that certain factors wield distinct impacts on guest satisfaction within varying RB&B market segments. The implications of these findings extend to empowering RB&B owners with actionable insights to enhance the overall customer experience. Full article

This research addresses a critical need in the ongoing battle against malware, particularly in the form of obfuscated malware, which presents a formidable challenge in the realm of cybersecurity. Developing effective antivirus (AV) solutions capable of combating packed malware remains a crucial endeavor. Packed malicious programs employ encryption and advanced techniques to obfuscate their payloads, rendering them elusive to AV scanners and security analysts. The introduced research presents an innovative malware packer classifier specifically designed to adeptly identify packer families and detect unknown packers in real-world scenarios. To fortify packer identification performance, we have curated a meticulously crafted dataset comprising precisely packed samples, enabling comprehensive training and validation. Our approach employs a sophisticated feature engineering methodology, encompassing multiple layers of analysis to extract salient features used as input to the classifier. The proposed packer identifier demonstrates remarkable accuracy in distinguishing between known and unknown packers, while also ensuring operational efficiency. The results reveal an impressive accuracy rate of 99.60% in identifying known packers and 91% accuracy in detecting unknown packers. This novel research not only significantly advances the field of malware detection but also equips both cybersecurity practitioners and AV engines with a robust tool to effectively counter the persistent threat of packed malware. Full article

GPT (Generative Pre-trained Transformer) represents advanced language models that have significantly reshaped the academic writing landscape. These sophisticated language models offer invaluable support throughout all phases of research work, facilitating idea generation, enhancing drafting processes, and overcoming challenges like writer’s block. Their capabilities extend beyond conventional applications, contributing to critical analysis, data augmentation, and research design, thereby elevating the efficiency and quality of scholarly endeavors. Strategically narrowing its focus, this review explores alternative dimensions of GPT and LLM applications, specifically data augmentation and the generation of synthetic data for research. Employing a meticulous examination of 412 scholarly works, it distills a selection of 77 contributions addressing three critical research questions: (1) GPT on Generating Research data, (2) GPT on Data Analysis, and (3) GPT on Research Design. The systematic literature review adeptly highlights the central focus on data augmentation, encapsulating 48 pertinent scholarly contributions, and extends to the proactive role of GPT in critical analysis of research data and shaping research design. Pioneering a comprehensive classification framework for “GPT’s use on Research Data”, the study classifies existing literature into six categories and 14 sub-categories, providing profound insights into the multifaceted applications of GPT in research data. This study meticulously compares 54 pieces of literature, evaluating research domains, methodologies, and advantages and disadvantages, providing scholars with profound insights crucial for the seamless integration of GPT across diverse phases of their scholarly pursuits. Full article

To support pathologists in breast tumor diagnosis, deep learning plays a crucial role in the development of histological whole slide image (WSI) classification methods. However, automatic classification is challenging due to the high-resolution data and the scarcity of representative training data. To tackle these limitations, we propose a deep learning-based breast tumor gigapixel histological image multi-classifier integrated with a high-resolution data augmentation model to process the entire slide by exploring its local and global information and generating its different synthetic versions. The key idea is to perform the classification and augmentation in feature latent space, reducing the computational cost while preserving the class label of the input. We adopt a deep learning-based multi-classification method and evaluate the contribution given by a conditional generative adversarial network-based data augmentation model on the classifier’s performance for three tumor classes in the BRIGHT Challenge dataset. The proposed method has allowed us to achieve an average F1 equal to 69.5, considering only the WSI dataset of the Challenge. The results are comparable to those obtained by the Challenge winning method (71.6), also trained on the annotated tumor region dataset of the Challenge. Full article

Alzheimer’s disease (AD) is a neurodegenerative disorder that leads to the loss of cognitive functions due to the deterioration of brain tissue. Current diagnostic methods are often invasive or costly, limiting their widespread use. Developing non-invasive and cost-effective screening methods is crucial, especially for identifying patients with mild cognitive impairment (MCI) at the risk of developing Alzheimer’s disease. This study employs a Machine Learning (ML) approach, specifically K-means clustering, on a subset of pixels common to all magnetic resonance imaging (MRI) images to rapidly classify subjects with AD and those with normal Normal Cognitive (NC). In particular, we benefited from defining significant pixels, a narrow subset of points (in the range of 1.5% to 6% of the total) common to all MRI images and related to more intense degeneration of white or gray matter. We performed K-means clustering, with k = 2, on the significant pixels of AD and NC MRI images to separate subjects belonging to the two classes and detect the class centroids. Subsequently, we classified subjects with MCI using only the significant pixels. This approach enables quick classification of subjects with AD and NC, and more importantly, it predicts MCI-to-AD conversion with high accuracy and low computational cost, making it a rapid and effective diagnostic tool for real-time assessments. Full article

As a typical intelligent device, magnetorheological (MR) dampers have been widely applied in vibration control and mitigation. However, the inherent hysteresis characteristics of magnetic materials can cause significant time delays and fluctuations, affecting the controllability and damping performance of MR dampers. Most existing mathematical models have not considered the adverse effects of magnetic hysteresis characteristics, and this study aims to consider such effects in MR damper models. Based on the magnetic circuit analysis of MR dampers, the Jiles–Atherton (J-A) model is adopted to characterize the magnetic hysteresis properties. Then, a weight adaptive particle swarm optimization algorithm (PSO) is introduced to the J-A model for efficient parameter identifications of this model, in which the differential evolution and the Cauchy variation are combined to improve the diversity of the population and the ability to jump out of the local optimal solution. The results obtained from the improved J-A model are compared with the experimental data under different working conditions, and it shows that the proposed J-A model can accurately predict the damping performance of MR dampers with magnetic hysteresis characteristics. Full article

In the realm of Parkinson’s Disease (PD) research, the integration of wearable sensor data with personal health records (PHR) has emerged as a pivotal avenue for patient alerting and monitoring. This study delves into the complex domain of PD patient care, with a specific emphasis on harnessing the potential of wearable sensors to capture, represent and semantically analyze crucial movement data and knowledge. The primary objective is to enhance the assessment of PD patients by establishing a robust foundation for personalized health insights through the development of Personal Health Knowledge Graphs (PHKGs) and the employment of personal health Graph Neural Networks (PHGNNs) that utilize PHKGs. The objective is to formalize the representation of related integrated data, unified sensor and PHR data in higher levels of abstraction, i.e., in a PHKG, to facilitate interoperability and support rule-based high-level event recognition such as patient’s missing dose or falling. This paper, extending our previous related work, presents the Wear4PDmove ontology in detail and evaluates the ontology within the development of an experimental PHKG. Furthermore, this paper focuses on the integration and evaluation of PHKG within the implementation of a Graph Neural Network (GNN). This work emphasizes the importance of integrating PD-related data for monitoring and alerting patients with appropriate notifications. These notifications offer health experts precise and timely information for the continuous evaluation of personal health-related events, ultimately contributing to enhanced patient care and well-informed medical decision-making. Finally, the paper concludes by proposing a novel approach for integrating personal health KGs and GNNs for PD monitoring and alerting solutions. Full article

Integrated photonic chips leverage the recent developments in integrated circuit technology, along with the control and manipulation of light signals, to realize the integration of multiple optical components onto a single chip. By exploiting the power of light, integrated photonic chips offer numerous advantages over traditional optical and electronic systems, including miniaturization, high-speed data processing and improved energy efficiency. In this review, we survey the current status of quantum computation, optical neural networks and the realization of some algorithms on integrated optical chips. Full article

This paper aims to provide discernment toward establishing a general framework, dedicated to data analysis and forecasting in smart buildings. It constitutes an industrial return of experience from an industrialist specializing in IoT supported by the academic world. With the necessary improvement of energy efficiency, discernment is paramount for facility managers to optimize daily operations and prioritize renovation work in the building sector. With the scale of buildings and the complexity of Heating, Ventilation, and Air Conditioning (HVAC) systems, the use of artificial intelligence is deemed the cheapest tool, holding the highest potential, even if it requires IoT sensors and a deluge of data to establish genuine models. However, the wide variety of buildings, users, and data hinders the development of industrial solutions, as specific studies often lack relevance to analyze other buildings, possibly with different types of data monitored. The relevance of the modeling can also disappear over time, as buildings are dynamic systems evolving with their use. In this paper, we propose to study the forecasting ability of the widely used Long Short-Term Memory (LSTM) network algorithm, which is well-designed for time series modeling, across an instrumented building. In this way, we considered the consistency of the performances for several issues as we compared to the cases with no prediction, which is lacking in the literature. The insight provided let us examine the quality of AI models and the quality of data needed in forecasting tasks. Finally, we deduced that efficient models and smart choices about data allow meaningful insight into developing time series modeling frameworks for smart buildings. For reproducibility concerns, we also provide our raw data, which came from one “real” smart building, as well as significant information regarding this building. In summary, our research aims to develop a methodology for exploring, analyzing, and modeling data from the smart buildings sector. Based on our experiment on forecasting temperature sensor measurements, we found that a bigger AI model (1) does not always imply a longer time in training and (2) can have little impact on accuracy and (3) using more features is tied to data processing order. We also observed that providing more data is irrelevant without a deep understanding of the problem physics. Full article

The popularization of the internet and the widespread use of smartphones have led to a rapid growth in the number of social media users. While information technology has brought convenience to people, it has also given rise to cyberbullying, which has a serious negative impact. The identity of online users is hidden, and due to the lack of supervision and the imperfections of relevant laws and policies, cyberbullying occurs from time to time, bringing serious mental harm and psychological trauma to the victims. The pre-trained language model BERT (Bidirectional Encoder Representations from Transformers) has achieved good results in the field of natural language processing, which can be used for cyberbullying detection. In this research, we construct a variety of traditional machine learning, deep learning and Chinese pre-trained language models as a baseline, and propose a hybrid model based on a variant of BERT: XLNet, and deep Bi-LSTM for Chinese cyberbullying detection. In addition, real cyber bullying remarks are collected to expand the Chinese offensive language dataset COLDATASET. The performance of the proposed model outperforms all baseline models on this dataset, improving 4.29% compared to SVM—the best performing method in traditional machine learning, 1.49% compared to GRU—the best performing method in deep learning, and 1.13% compared to BERT. Full article

This study investigates self-assessment tendencies in Large Language Models (LLMs), examining if patterns resemble human cognitive biases like the Dunning–Kruger effect. LLMs, including GPT, BARD, Claude, and LLaMA, are evaluated using confidence scores on reasoning tasks. The models provide self-assessed confidence levels before and after responding to different questions. The results show cases where high confidence does not correlate with correctness, suggesting overconfidence. Conversely, low confidence despite accurate responses indicates potential underestimation. The confidence scores vary across problem categories and difficulties, reducing confidence for complex queries. GPT-4 displays consistent confidence, while LLaMA and Claude demonstrate more variations. Some of these patterns resemble the Dunning–Kruger effect, where incompetence leads to inflated self-evaluations. While not conclusively evident, these observations parallel this phenomenon and provide a foundation to further explore the alignment of competence and confidence in LLMs. As LLMs continue to expand their societal roles, further research into their self-assessment mechanisms is warranted to fully understand their capabilities and limitations. Full article

Keyword extraction from Knowledge Bases underpins the definition of relevancy in Digital Library search systems. However, it is the pertinent task of Joint Relation Extraction, which populates the Knowledge Bases from which results are retrieved. Recent work focuses on fine-tuned, Pre-trained Transformers. Yet, F1 scores for scientific literature achieve just 53.2, versus 69 in the general domain. The research demonstrates the failure of existing work to evidence the rationale for optimisations to finetuned classifiers. In contrast, emerging research subjectively adopts the common belief that Natural Language Processing techniques fail to derive context and shared knowledge. In fact, global context and shared knowledge account for just 10.4% and 11.2% of total relation misclassifications, respectively. In this work, the novel employment of semantic text analysis presents objective challenges for the Transformer-based classification of Joint Relation Extraction. This is the first known work to quantify that pipelined error propagation accounts for 45.3% of total relation misclassifications, the most poignant challenge in this domain. More specifically, Part-of-Speech tagging highlights the misclassification of complex noun phrases, accounting for 25.47% of relation misclassifications. Furthermore, this study identifies two limitations in the purported bidirectionality of the Bidirectional Encoder Representations from Transformers (BERT) Pre-trained Language Model. Firstly, there is a notable imbalance in the misclassification of right-to-left relations, which occurs at a rate double that of left-to-right relations. Additionally, a failure to recognise local context through determiners and prepositions contributes to 16.04% of misclassifications. Furthermore, it is highlighted that the annotation scheme of the singular dataset utilised in existing research, Scientific Entities, Relations and Coreferences (SciERC), is marred by ambiguity. Notably, two asymmetric relations within this dataset achieve recall rates of only 10% and 29%. Full article