Integration Of Information Research Articles

A graph-based method for automatic graded diagnosis of depression using EEG signals

Depression is a common psychological disorder typically categorized into four grades according to the symptom severity. Accurately diagnosing different grades of depression is significant for taking appropriate treatment strategies to prevent the condition from worsening. Electroencephalography (EEG) has the potential to mirror the prevailing mental state of patients, providing a possible way to diagnose depression. However, it is still a challenge to extract EEG features that reflect varying degrees of depression for automatic grading diagnosis. It has been pointed out that depression involves the intensification of abnormal interactions among distinct brain regions as it advances, which suggests that brain spatial information may play a key role in tracking different grades of depression. Based on this, combined with deep learning models, this paper proposes a new graph-based method for automatic grading diagnosis of depression. A novel graph-based brain network (BN) construction method is first proposed to convert EEG into graph structure containing brain spatial information, where the individual-level (IBN) and group-level brain networks (GBN) are constructed respectively. Next, a new deep learning model P-I-GAT is built based on graph attention networks (GAT) for identifying EEG signals from depression patients with different severity. In specific, the “P” represents the prior information integration capability, synthesizing attribute information from the IBN and structural information from the GBN. The resulting synthesized brain network contains prior information from these two different scales, referred to as the prior brain network (PBN). “I” denotes the multi-rhythm interaction capability, which adaptively assigns learning weights to each rhythmic PBN to fully exploit the information embedded within the PBNs. Ultimately, the proposed method is validated on the open dataset MODMA, achieving an accuracy of 88.57% and a specificity of 91.97%.

CE-MS-Based Clinical Metabolomics of Human Plasma.

Capillary electrophoresis coupled to mass spectrometry (CE-MS) has emerged as a powerful analytical technique with significant implications for clinical research and diagnostics. The integration of information from CE and MS strengthens confidence in the identification of compounds present in clinical samples. The ability of CE to separate molecules based on their electrophoretic mobility coupled to MS enables the accurate identification and quantification of analytes, even in complex biological matrices such as human plasma.Here, we present a detailed protocol for an untargeted metabolomics study using CE-MS and its application in a study on human plasma from patients suffering Long COVID syndrome. The protocol ranges from sample preparation to biological interpretation, detailing a workflow enabling the analysis of cationic and anionic compounds, metabolite identification, and data processing.

Adaptive search for broad attention based vision transformers

Vision Transformer (ViT) has prevailed among computer vision tasks for its powerful capability of image representation recently. Frustratingly, the manual design of efficient architectures for ViTs can be laborious, often involving repetitive trial and error processes. Furthermore, the exploration of lightweight ViTs remains limited, resulting in inferior performance compared to convolutional neural networks. To tackle these challenges, we propose Adaptive Search for Broad attention based Vision Transformers, called ASB, which automates the design of efficient ViT architectures by utilizing the broad search space and an adaptive evolutionary algorithm. The broad search space facilitates the exploration of a novel connection paradigm, enabling more comprehensive integration of attention information to improve ViT performance. Additionally, an efficient adaptive evolutionary algorithm is developed to efficiently explore architectures by dynamically learning the probability distribution of candidate operators. Our experimental results demonstrate that the adaptive evolution in ASB efficiently learns excellent lightweight models, achieving a 55% improvement in convergence speed over traditional evolutionary algorithms. Moreover, the effectiveness of ASB is validated across several visual tasks. For instance, on ImageNet classification, the searched model attains a performance of 77.8% with 6.5M parameters and outperforms state-of-the-art models, including EfficientNet and EfficientViT networks. On mobile COCO panoptic segmentation, our approach delivers 43.7% PQ. On mobile ADE20K semantic segmentation, our method attains 40.9% mIoU. The code and pre-trained models will be available soon in ASB-Code.

Are women's breast cancer risk appraisals in line with updated clinical risk estimates communicated? Results from a UK Family History Risk and Prevention Clinic.

The incorporation of breast density and a polygenic risk score (PRS) into breast cancer risk prediction models can alter previously communicated risk estimates. Previous research finds that risk communication does not usually change personal risk appraisals. This study aimed to examine how women from the Family History Risk (FH-Risk) study appraise their breast cancer risk following communication of an updated risk estimate. In the FH-Risk study 323 women attended a consultation to receive an updated breast cancer risk estimate. A subset (n=190) completed a questionnaire, assessing their subjective breast cancer risk appraisals, satisfaction with the information provided and cancer related worry. One hundred and three were notified of a decrease risk, 34 an increase and 53 an unchanged risk. Women's subjective risk appraisals were in line with the updated risk estimates provided, with age, a PRS and breast density explaining most of the variance in these appraisals. Those notified of an increased risk demonstrated higher subjective risk perceptions compared to those whose risk remained unchanged or decreased. Women's subjective breast cancer risk appraisals are amenable to change following updated risk feedback, with new information breast density and a PRS accepted and integrated into existing risk appraisals. Trust in the service, the analogies and visual communication strategies used may have positively influenced the integration of this new information. Further research is warranted to assess whether similar patterns emerge for other illnesses and in different clinical contexts to determine the best strategies for communicating updated risk estimates.

Cross‐Domain Information Integration in Government: Hierarchies and Responsibilities

ABSTRACTCross‐domain integration of information is increasingly identified as a priority across public sector contexts because (in theory) it enables the use of more information, including information from groups and communities historically excluded from public sector decision making. In this paper, we reject the tendency to take ‘integration’ for granted, arguing the need to position cross‐domain integration as an information practice, and conducting mixed methods thematic analysis of government strategic documents to validate the utility of this approach. We find that depending on the type of information proposed to be integrated — digital data versus the knowledge of peoples and communities — our sample of Canadian government institutions treats cross‐domain integration with differing levels of procedural rigour and detail. Reflecting ASIS&T 2024 themes of prioritizing responsibility and reflexivity in information practice, and of cultivating community partnerships through practice, not merely in name, we discuss the information hierarchies that emerge in the cross‐domain information integration in government and the associated impacts on stakeholder communities.

Bayesian feedback in the framework of ecological sciences

In ecological studies, it is not uncommon to encounter scenarios where the same phenomenon (e.g., species occurrence, species abundance) is observed using two different types of samplers. For example, species data can be collected from scientific sampling with a completely random sample pattern, but also from opportunistic sampling (e.g., whale watching from commercial fishing vessels or bird watching from citizen science), where observers tend to look for particular species in areas where they expect to find them.Species Distribution Models (SDMs) are widely used tools for analysing this type of ecological data. In particular, two models are available for the aforementioned data: a geostatistical model (GM) for data collected where the sampling design is not directly related to the observations, and a preferential model (PM) for data obtained from opportunistic sampling.The integration of information from disparate sources can be addressed through the use of expert elicitation and integrated models. This paper focuses on a sequential Bayesian procedure for linking two models by updating prior distributions. The Bayesian paradigm is implemented together with the integrated nested Laplace approximation (INLA) methodology, which is an effective approach for making inference and predictions in spatial models with high performance and low computational cost. This sequential approach has been evaluated through the simulation of various scenarios and the subsequent comparison of the results from sharing information between models using a variety of criteria. The procedure has also been exemplified on a real dataset.The primary findings indicate that, in general, it is preferable to transfer information from the independent (with a completely random sampling) model to the preferential model rather than in the alternative direction. However, this depends on several factors, including the spatial range and the spatial arrangement of the sampling locations.

Industrial information integration in deep space exploration and exploitation: Architecture and technology

Recently, China and the United States have achieved remarkable success in aerospace science and technology over the years. Space has become another field of competition in the technological advancement of various countries. Through space missions, space tourism, moon and Mars exploration, China and the United States can demonstrate the sophistication of their technologies to the public and audiences around the world. Despite the competitiveness between the big countries, space missions and deep space exploration and exploitation have provided a lot of deep and orbital space information that is beneficial not only for the next space mission but also for enhancing technological development for other domestic uses. Therefore, space industrial information integration (III), or Space III, connecting IoT to form the Internet of Planets, is critically important for deep space explorations. However, few articles have reviewed the existing technologies of space. We are one of the few groups to perform an extensive review, research the space explorations and divide the space information integration systematically based on the information architecture and technologies in the space industries. In this paper, we propose that III can be divided into three different architectures: data, technology, and application, whereas space technology can be divided into six areas. This review is important not only in formulating research in technological integration but also in determining the proposed architecture to facilitate a further extension of applications to large-scale and complex problems in the space industries in the future.

TE-LSTM: A Prediction Model for Temperature Based on Multivariate Time Series Data

In the era of big data, prediction has become a fundamental capability. Current prediction methods primarily focus on sequence elements; however, in multivariate time series forecasting, time is a critical factor that must not be overlooked. While some methods consider time, they often neglect the temporal distance between sequence elements and the predicted target time, a relationship essential for identifying patterns such as periodicity, trends, and other temporal dynamics. Moreover, the extraction of temporal features is often inadequate, and discussions on how to comprehensively leverage temporal data are limited. As a result, model performance can suffer, particularly in prediction tasks with specific time requirements. To address these challenges, we propose a new model, TE-LSTM, based on LSTM, which employs a temporal encoding method to fully extract temporal features. A temporal weighting strategy is also used to optimize the integration of temporal information, capturing the temporal relationship of each element relative to the target element, and integrating it into the LSTM. Additionally, this study examines the impact of different time granularities on the model. Using the Beijing International Airport station as the study area, we applied our method to temperature prediction. Compared to the baseline model, our model showed an improvement of 0.7552% without time granularity, 1.2047% with a time granularity of 3, and 0.0953% when addressing prediction tasks with specific time requirements. The final results demonstrate the superiority of the proposed method and highlight its effectiveness in overcoming the limitations of existing approaches.

FE-CFNER: Feature Enhancement-based approach for Chinese Few-shot Named Entity Recognition

Although significant progress has been made in Chinese Named Entity Recognition (NER) methods based on deep learning, their performance often falls short in few-shot scenarios. Feature enhancement is considered a promising approach to address the issue of Chinese few-shot NER. However, traditional feature fusion methods tend to lead to the loss of important information and the integration of irrelevant information. Despite the benefits of incorporating BERT for improving entity recognition, its performance is limited when training data is insufficient. To tackle these challenges, this paper proposes a Feature Enhancement-based approach for Chinese Few-shot NER called FE-CFNER. FE-CFNER designs a double cross neural network to minimize information loss through the interaction of feature cross twice. Additionally, adaptive weights and a top-k mechanism are introduced to sparsify attention distributions, enabling the model to prioritize important information related to entities while excluding irrelevant information. To further enhance the quality of BERT embeddings, FE-CFNER employs a contrastive template for contrastive learning pre-training of BERT, enhancing BERT’s semantic understanding capability. We evaluate the proposed method on four sampled Chinese NER datasets: Weibo, Resume, Taobao, and Youku. Experimental results validate the effectiveness and superiority of FE-CFNER in Chinese few-shot NER tasks.

Disentangling the spinal mechanisms of illusory heat and burning sensations in the thermal grill illusion.

The thermal grill illusion (TGI), a phenomenon in which the juxtaposition of innocuous warm and cold temperatures on the skin elicits a burning sensation, offers a unique perspective to how pain occurs in response to harmless stimuli. We investigated the role of the spinal cord in the generation of the TGI across 2 experiments (total n = 80). We applied heat and cold stimuli to dermatomes, areas of skin innervated by a single spinal nerve, that mapped onto adjacent or nonadjacent spinal segments. Enhanced warm and burning ratings during the TGI were observed when cold and warm stimuli were confined within the same dermatome. Furthermore, we found the spatial organisation of warm and cold stimuli within and across dermatomes affected TGI perception. Perceived warmth and burning intensity increased when the cold stimulus projected to the segment more caudal to the warm stimulus, whereas perceived cold during the TGI decreased compared with the opposite spatial arrangement. This suggests that the perception of TGI is enhanced when cold afferents are projected to spinal segments positioned caudally in relation to those receiving warm afferents. Our results indicate distinct interaction of sensory pathways based on the segmental arrangement of afferent fibres and are consistent with current interpretations of the spread and integration of thermosensory information along the spinal cord.

GraphCVAE: Uncovering cell heterogeneity and therapeutic target discovery through residual and contrastive learning.

Advancements in Spatial Transcriptomics (ST) technologies in recent years have transformed the analysis of tissue structure and function within spatial contexts. However, accurately identifying spatial domains remains challenging due to data sparsity and noise. Traditional clustering methods often fail to capture spatial dependencies, while spatial clustering methods struggle with batch effects and data integration. We introduce GraphCVAE, a model designed to enhance spatial domain identification by integrating spatial and morphological information, correcting batch effects, and managing heterogeneous data. GraphCVAE employs a multi-layer Graph Convolutional Network (GCN) and a variational autoencoder to improve the representation and integration of spatial information. Through contrastive learning, the model captures subtle differences between cell types and states. Extensive testing on various ST datasets demonstrates GraphCVAE's robustness and biological contributions. In the dorsolateral prefrontal cortex (DLPFC) dataset, it accurately delineates cortical layer boundaries. In glioblastoma, GraphCVAE reveals critical therapeutic targets such as TF and NFIB. In colorectal cancer, it explores the role of the extracellular matrix in colorectal cancer. The model's performance metrics consistently surpass existing methods, validating its effectiveness. GraphCVAE's advanced visualization capabilities further highlight its precision in resolving spatial structures, making it a powerful tool for spatial transcriptomics analysis and offering new insights into disease studies.

USING TED TALKS IN ENGLISH LANGUAGE TEACHING

The results of a quantitative investigation on how incorporating TED Talks media into language training affects students' speaking abilities are presented in this article. The purpose of the study was to evaluate how well students' verbal expression and communication skills may be improved by using TED Talks videos as a resource. After incorporating TED Talks, students' speaking abilities significantly improved, according to an examination of pre- and post-test results. The integration of genuine and captivating information from TED Talks introduced students to a diverse range of subjects, accomplished presenters, and everyday language usage, resulting in improved pronunciation, vocabulary, and fluency. These findings highlight the TED Talks' potential as a useful educational resource for enhancing students' speaking abilities during language training. It is highly recommended that language instructors use TED Talks into their instructional strategies to establish engaging and interactive learning environments that promote language proficiency and proficient communication. The study adds to the body of knowledge already available on the use of multimedia materials in language instruction and provides teachers looking for creative ways to improve their students' speaking skills with useful advice.

Sustainable Performance: Unraveling the Nexus between ESG and Performance Management Systems

In the current highly competitive environment, firms are devoting growing levels of attention towards environmental, social, and governance (ESG) standards as a response to external pressure from stakeholders. Consequently, scholars are cur-rently displaying heightened interest in examining the integration of financial and non-financial information, including ESG, within performance measurement sys-tems (PMSs). Adopting broader PMSs would provide companies with a more holis-tic comprehension of their performance, consequently avoiding prioritizing solely financial and economic indicators while neglecting sustainability and social re-sponsibility. We employed the Systematic Literature Review (SLR) protocol to car-ry out the research and conducted a comprehensive exploration of the subject un-der investigation. Specifically, we first constructed the research profile of the sam-ple, offering an overview of the existing knowledge in the field. Subsequently, we performed a meticulous and qualitative examination of the prevalent emerging themes discovered in the sample. Finally, the review concludes by presenting a structured research agenda that outlines various avenues for future research.

Fake News Detection Using Optimized Convolutional Neural Network and Bidirectional Long Short-Term Memory

The spread of fake news in the digital age threatens the integrity of online information, influences public opinion, and creates confusion. This study developed and tested a fake news detection model using an enhanced CNN-BiLSTM architecture with GloVe word embedding techniques. The WELFake dataset comprising 72,000 samples was used, with training and testing data ratios of 90:10, 80:20, and 70:30. Preprocessing involved GloVe 100-dimensional word embedding, tokenization, and stopword removal. The CNN-BiLSTM model was optimized with hyperparameter tuning, achieving an accuracy of 96%. A larger training data ratio demonstrated better performance. Results indicate the effectiveness of this model in distinguishing fake news from real news. This study shows that the CNN-BiLSTM architecture with GloVe embedding can achieve high accuracy in fake news detection, with recommendations for further research to explore preprocessing techniques and alternative model architectures for further improvement.

Матрица когнитивных фильтров – инструмент анализа лингвокреатем в современном онлайн-дискурсе на английском языке

The article introduces the matrix of cognitive filters as a research method that makes it possible to model the process of inferring the meaning of lingua-createmes in multimodal online discourse. Multimodal linguistic systems are based on a complex interaction of multimodal components. These components combine with basic cognitive mechanisms in decoding various complex phenomena in digital Internet discourse. The research revealed a classification of key cognitive mechanisms that generate the meaning of creative multimodal elements: banner blindness, evaluative categorization, conceptualization, (de)compression of information, profiling, conceptual metaphor, conceptual metaphthonymy, and conceptual integration. The research material involved 18,000 monomodal verbal and multimodal lingua-createmes selected by continuous sampling from English-language Internet resources, as well as visual and verbal corpora. The method proved effective in modelling the general cognitive resonance of lingua-createmes and predicting cognitive resonance / dissonance (positive or negative) in communication. The practical lingua-cognitive experiment involved 335 English-speaking respondents from eleven countries. They were asked to use the matrix of cognitive filters to perform a step-by-step decoding of several creative multimodal elements. The method proved highly effective for detecting cognitive resonance or mental tension, i.e., positive or negative cognitive dissonance. The method demonstrated good prospects for obtaining additional data on reactions to lingua-creative discursive elements.

Nigerian Secondary Physics Teachers’ Perceptions of Factors That Challenge Information and Communication Technology Integration

Nigerian Secondary Physics Teachers’ Perceptions of Factors That Challenge Information and Communication Technology Integration

Transfer graph feature alignment guided multi-source domain adaptation network for machinery fault diagnosis

In recent years, the application of unsupervised multi-source domain adaptation (MSDA) techniques for fault diagnosis has gained significant traction. Current research typically overlooks or fails to effectively capture critical data structure information during feature extraction. Another challenge is optimising the integration of information from multiple source domains to diagnose the target domain while avoiding negative transfer. To address these challenges, this study proposes a transfer graph feature alignment guided multi-source domain adaptation network (MDTGAL). In the proposed method, a transfer graph sample generator module (GSG) is constructed to model the data structure between source and target domains, and multiple graph feature extractors are employed to learn the data structure information from different domain combinations. A regularisation technique is introduced to extract the domain-invariant features by aligning the parameters across multiple independent graph feature extractors. In addition, a weighted soft-voting mechanism based on the polynomial kernel-induced maximum mean difference metric (PK-MMD) is designed to fuse the outputs from multiple classifiers, to comprehensively account for the influence of each source domain. The proposed method was tested on multi-source domain transfer tasks involving various operating conditions of rotating machinery. The experimental results demonstrate that the MDTGAL exhibits superior cross-domain diagnostic performance, outperforming existing mainstream methods. In addition, this study explored the impact of varying numbers of source domains on the diagnostic accuracy of the target domain, providing insights into selecting the correct number of source domains for specific MSDA tasks.

Examining The Integration Of ICT Tools In English Language Teaching: Comparative Analysis Of High School Teachers' Practices In India And Vietnam

This study explores the integration of Information and Communication Technology (ICT) tools in English language teaching practices of high school teachers in India and Vietnam. A survey with chart-based responses was distributed to 60 teachers(30 from each country) from nearby districts. The research investigates howteachers utilize ICT tools, their assessment practices, and perceived effects on student engagement and learning. The findings reveal that both countries employ ICT tools, with a focus on social media platforms, language learning applications, and online dictionaries. Vietnamese teachers demonstrated a slightly higher adoption rate, particularly for virtual reality (VR) and augmented reality (AR) technologies. While paper-based assessments remain prevalent, online tools like Google Forms and online assessment platforms are gaining traction. Teachers reported positive perceptions of ICT tools, believing they enhance student engagement and learning outcomes. However, challenges were identified, including limited access to technology resources and a lack of training on effective ICT integration. This study highlights the need for further research to directly measure the impact of ICT tools on student achievement. Additionally, it emphasizes the importance of addressing teacher training needs to unlock the full potential of ICT tools and create more engaging and effective English language learning experiences for students.

Enhancing Black Hole Attack Detection in VANETs: A Hybrid Approach Integrating DBSCAN Clustering with Decision Trees

Ensuring the security of communication is crucial in Vehicular Ad Hoc Networks (VANETs) to protect the integrity of information sharing among cars. To implement VANET communication as an answer for the different uses, secure communication is necessary. The unreliability of VANET environments is caused by message delays or tampering in VANET applications. Finding the sweet spot between VANET security and performance and dependability is the primary goal. This project’s overarching goal is to fortify VANETs against Blackhole Routing Attacks and, by identifying and blocking harmful nodes, to mitigate the blackhole impact. This paper proposes a robust hybrid approach for the detection of black hole attacks in VANETs, leveraging the synergy between DBSCAN (Density-Based Spatial Clustering of Applications with Noise) clustering and Decision Trees. DBSCAN, a density-based clustering algorithm, is employed to identify spatial clusters of vehicles, while Decision Trees are utilized to discern normal communication patterns from malicious ones within these clusters. The integration of these two techniques enhances the accuracy and efficiency of black hole attack detection in the dynamic and resource-constrained VANET environment. Experimental results demonstrate the effectiveness of the proposed hybrid approach, providing a promising solution for bolstering the security of VANETs against emerging threats. Here in result 73.89% improvement is received in Packet Drop Rate using DBSCAN, also minor improvement over Throughput and Average end to end delay and major improvement in terms of Network Routing Load.

A portable test system for the radar

Abstract In order to adapt to the increasingly fierce battlefield confrontation scenarios, a portable, fast deployment and folding test system for the radar is proposed. The corresponding key test items of radar such as spectrum, waveform, lobe, target tracking and data analysis can be completed on the test system. After the Built-in-Test (BIT) information and test system results are integrated, the corresponding evaluation report and implementation recommendations can be provided to the maintenance personnel. This paper expounds the design of each subsystem step by step. The Main Control Unit (MCU) is the task scheduling and information integration center for the system. The corresponding high frequency components, processing components, storage components have been implemented systematic and miniaturized design. In the end, the improvement direction and prospect of the test system are given.