Limited Contextual Information Research Articles

Integration of multiscale fusion of residual neural network with 2-D gramian angular fields for lower limb movement recognition based on multi-channel sEMG signals

The human lower limb movements recognition (LLMR) plays a pivotal role in active lower limb exoskeleton robots. Employing surface electromyography (sEMG) signals for LLMR allows for the convenient, rapid and stable capture of signal variations, facilitating efficient identification of lower limb motion patterns. However, current sEMG-based LLMR methods face challenges such as incomplete feature extraction, limited contextual information and restricted feature extraction scales during feature extraction. This paper proposed a LLMR method based on Gramian Angular Fields (GAF) and multiscale fusion of Residual Neural Network (MS-ResNet). The denoised sEMG time series was transformed into Gramian Angular Difference Field (GADF) matrix based on GAF. The MS-ResNet model, incorporating ResNet and multiscale feature fusion concepts, was proposed to comprehensively capture global and local information through different-scale feature extraction and fusion, so as to improve recognition performance. sEMG signals from 11 muscles of the preferred leg of 15 healthy subjects were recorded during six common lower limb movements. Experimental analysis investigated the impact of the convolutional kernel size (k × k) in Stream 2 of MS-ResNet and the number of muscles involved on recognition performance. The study revealed that selecting k as 13, coupled with 11 muscles, yielded optimal model performance with the average cross-individual recognition accuracy reaching 97.62 %, demonstrating the model’s efficiency in LLMR. This method could provide a viable solution for developing more efficient and reliable LLMR systems, applicable to lower limb exoskeleton robots and intelligent prosthetics.

Exploring Learning experiences of Black Asian and Minority Ethnic (BAME) students in a Public Health Undergraduate Degree.

Whilst university data highlights that BAME students are awarded up to 33% lower assessment outcomes than their white counterparts, there is limited contextual information to explain why the situation arises. A small scale qualitative project sought to explore the barriers and enablers to Public Health students' learning experiences through semi-structured interviews. Emerging themes included the role of the family in their learning; the influence of peer groups and others in their motivation to study and becoming an independent student and these themes are viewed from a critical intercultural and intersectional perspective.

Adaptive Scale and Correlative Attention PointPillars: An Efficient Real-Time 3D Point Cloud Object Detection Algorithm

Recognizing 3D objects from point clouds is a crucial technology for autonomous vehicles. Nevertheless, LiDAR (Light Detection and Ranging) point clouds are generally sparse, and they provide limited contextual information, resulting in unsatisfactory recognition performance for distant or small objects. Consequently, this article proposes an object recognition algorithm named Adaptive Scale and Correlative Attention PointPillars (ASCA-PointPillars) to address this problem. Firstly, an innovative adaptive scale pillars (ASP) encoding method is proposed, which encodes point clouds using pillars of varying sizes. Secondly, ASCA-PointPillars introduces a feature enhancement mechanism called correlative point attention (CPA) to enhance the feature associations within each pillar. Additionally, a data augmentation algorithm called random sampling data augmentation (RS-Aug) is proposed to solve the class imbalance problem. The experimental results on the KITTI 3D object dataset demonstrate that the proposed ASCA-PointPillars algorithm significantly boosts the recognition performance and RS-Aug effectively enhances the training effects on an imbalanced dataset.

M 3 Rec: A Context-aware Offline Meta-level Model-based Reinforcement Learning Approach for Cold-Start Recommendation

Reinforcement learning (RL) has shown great promise in optimizing long-term user interest in recommender systems. However, existing RL-based recommendation methods need a large number of interactions for each user to learn the recommendation policy. The challenge becomes more critical when recommending to new users who have a limited number of interactions. To that end, in this paper, we address the cold-start challenge in the RL-based recommender systems by proposing a novel context-aware offline meta-level model-based reinforcement learning approach for user adaptation. Our proposed approach learns to infer each user's preference with a user context variable that enables recommendation systems to better adapt to new users with limited contextual information. To improve adaptation efficiency, our approach learns to recover the user choice function and reward from limited contextual information through an inverse reinforcement learning method, which is used to assist the training of a meta-level recommendation agent. To avoid the need for online interaction, the proposed method is trained using historically collected offline data. Moreover, to tackle the challenge of offline policy training, we introduce a mutual information constraint between the user model and recommendation agent. Evaluation results show the superiority of our developed offline policy learning method when adapting to new users with limited contextual information. In addition, we provide a theoretical analysis of the recommendation performance bound.

Edge-enhanced minimum-margin graph attention network for short text classification

With the rapid advancement of the internet, there has been a dramatic increase in short-text data. Due to the brevity of short texts, sparse features, and limited contextual information, short-text classification has become a challenging task in natural language processing. However, current methods primarily capture semantic information from locally-sequenced words in short text, which ignores the intricate feature relationships that pervade both the intra-text and inter-text. Therefore, this paper proposes a novel Edge-Enhanced Minimum-Margin Graph Attention Network (EMGAN) for short text classification to address this issue. Specifically, we construct a Heterogeneous Information Graph (HIG) to represent complex relationships among short text features. HIG mainly considers the relationship between document features and three attribute features, such as entities, topics, and keywords, and can represent short text features from multiple dimensions and levels. Then, to enhance the connectivity and expressiveness of the HIG for more effective propagation of feature information within it, we present a novel X-shaped structure edge-enhancement method. It enriches their relationships by reconstructing the edge structures. Furthermore, we design a Minimum Margin Graph Attention Network (MMGAN) for short text classification. Specifically, this method aims to explore the minimum margin between high-order neighbors and central nodes at the minimum cost, efficiently extracting and aggregating feature information. Extensive experimental results demonstrate that our proposed EMGAN model outperforms existing methods on five datasets, validating its effectiveness in short-text classification. Our code is submitted at https://github.com/w123yy/EMGAN.

Clinical Evidence, Triangulation of Perspectives and Contextualization. Part 1: The Beginning of Carla’s Treatment

We propose to critically evaluate and strengthen the level of clinical evidence in psychoanalysis, using a strategy of triangulating clinical phenomena from different perspectives and increasing contextual knowledge. Insufficient discussion of alternative hypotheses and limited contextual information are two Achilles heels of psychoanalytic case presentations. We examine the concept and quality standards of clinical evidence in psychoanalysis and related disciplines, with particular attention to the contribution of the three-level model (3-LM). We analyze the case of a patient treated with transference-focused psychotherapy (TFP), making explicit the theoretical-clinical agreements and disagreements of the authors. We discuss the strengths and limitations of triangulation and contextualization, concluding that they make clinical work and psychoanalytic writing more reliable, transparent, auditable, and replicable.

Dual Causes Generation Assisted Model for Multimodal Aspect-Based Sentiment Classification.

Multimodal aspect-based sentiment classification (MABSC) aims to identify the sentiment polarity toward specific aspects in multimodal data. It has gained significant attention with the increasing use of social media platforms. Existing approaches primarily focus on analyzing the content of posts to predict sentiment. However, they often struggle with limited contextual information inherent in social media posts, hindering accurate sentiment detection. To overcome this issue, we propose a novel multimodal dual cause analysis (MDCA) method to track the underlying causes behind expressed sentiments. MDCA can provide additional reasoning cause (RC) and direct cause (DC) to explain why users express certain emotions, thus helping improve the accuracy of sentiment prediction. To develop a model with MDCA, we construct MABSC datasets with RC and DC by utilizing large language models (LLMs) and visual-language models. Subsequently, we devise a multitask learning framework that leverages the datasets with cause data to train a small generative model, which can generate RC and DC, and predict the sentiment assisted by these causes. Experimental results on MABSC benchmark datasets demonstrate that our MDCA model achieves the state-of-the-art performance, and the small fine-tuned model exhibits superior adaptability to MABSC compared to large models like ChatGPT and BLIP-2.

Analysis of urban visitor walkability based on mobile data: The case of Daejeon, Korea

The walkability of destinations plays a decisive role in obtaining a sense of place for urban visitors. For an improved walkability-based visit experience, the city structure can be analyzed by dividing it into small units, starting with the destination. However, existing studies focus on the walkability of residents by administrative district and use limited contextual information and structural analysis tools. Therefore, this study aims to structurally understand walkability through network analysis with mobile-based visitor data collected from 822 point-of-interest (POI) in Daejeon. In this study, the actual walking distance between 95,817 cells with visitors and POIs was measured to calculate the edge weight and influence of cells on POI. We analyzed the POI-cell network through edge weight and extracted nine communities to understand the city context through POI analysis and derived the following findings. First, it is possible to determine the potential demand by visitors' walkability-based division. Second, our walkability measurement method follows a bottom-up approach, starting with a small unit cell, understanding the entire city as a community extraction model, and possibly extending to other cities in Korea. Third, POI-centered structural analysis is possible using the number of visitors and distance in the proposed network analysis method.

Investigating changes in mental health services utilisation in England and their impact on health outcomes and wellbeing during the COVID-19 pandemic: Protocol for a health data-linkage study.

Linking routinely collected health care system data records for the same individual across different services and over time has enormous potential for the NHS and its patients. The aims of this data linkage study are to quantify the changes to mental health services utilisation in responses to the COVID-19 pandemic and determine whether these changes were associated with health-related outcomes and wellbeing among people living in the most deprived communities in North East and North Cumbria, England. We will assemble a retrospective cohort of people having referred or self-referred to NHS-funded mental health services or Improving Access to Psychological Therapies (IAPT) services between 23rd March 2019 and 22nd March 2020 in the most deprived areas in England. We will link together data from retrospective routinely collected healthcare data including local general practitioner (GP) practice data, Hospital Episode Statistics admitted patient care outpatients, and A&E, Community Services Data Set, Mental Health Services Data Set, and Improving Access to Psychological Therapies Data Set. We will use these linked patient-level data to 1) describe the characteristics of the cohort prior to the lockdown; 2) investigate changes to mental health services utilised between multiple time periods of the COVID-19 lockdown including out of lockdown; 3) explore the relationship between these changes and health outcomes/wellbeing and factors that confound and mediate this relationship among this cohort. This study comprises a deprived population-based cohort of people having referred or self-referred to NHS-funded secondary mental health services or Improving Access to Psychological Therapies (IAPT) services over an extended period of the lockdown in England (2019-2022).This study will utilise a new longitudinal data resource that will link together detailed data from a cohort of individual participants and retrospective administrative data relating to the use of primary, secondary, and community care services.The study period covers pre-lockdown, different lockdown and post-lockdown, and out of lockdown periods up to March 2022.Routinely collected administrative data contain limited contextual information and represent an underestimate of total health outcomes for these individuals.Routinely collected datasets can often been incomplete or contain missing data, which can make it difficult to accurately analyse the data and draw meaningful conclusions.Intervention and treatment for mental health conditions are not wholly captured across these data sources and may impact health outcomes.

Egocentric Early Action Prediction via Adversarial Knowledge Distillation

Egocentric early action prediction aims to recognize actions from the first-person view by only observing a partial video segment, which is challenging due to the limited context information of the partial video. In this article, to tackle the egocentric early action prediction problem, we propose a novel multi-modal adversarial knowledge distillation framework. In particular, our approach involves a teacher network to learn the enhanced representation of the partial video by considering the future unobserved video segment, and a student network to mimic the teacher network to produce the powerful representation of the partial video and based on that predicting the action label. To promote the knowledge distillation between the teacher and the student network, we seamlessly integrate adversarial learning with latent and discriminative knowledge regularizations encouraging the learned representations of the partial video to be more informative and discriminative toward the action prediction. Finally, we devise a multi-modal fusion module toward comprehensively predicting the action label. Extensive experiments on two public egocentric datasets validate the superiority of our method over the state-of-the-art methods. We have released the codes and involved parameters to benefit other researchers. 1

INPHOVIS: Interactive visual analytics for smartphone-based digital phenotyping

Digital phenotyping is the characterization of human behavior patterns based on data from digital devices such as smartphones in order to gain insights into the users’ state and especially to identify ailments. To support supervised machine learning, digital phenotyping requires gathering data from study participants’ smartphones as they live their lives. Periodically, participants are then asked to provide ground truth labels about their health status. Analyzing such complex data is challenging due to limited contextual information and imperfect health/wellness labels. We propose INteractive PHOne-o-typing VISualization (INPHOVIS), an interactive visual framework for exploratory analysis of smartphone health data to study phone-o-types. Prior visualization work has focused on mobile health data with clear semantics such as steps or heart rate data collected using dedicated health devices and wearables such as smartwatches. However, unlike smartphones which are owned by over 85 percent of the US population, wearable devices are less prevalent thus reducing the number of people from whom such data can be collected. In contrast, the “low-level” sensor data (e.g., accelerometer or GPS data) supported by INPHOVIS can be easily collected using smartphones. Data visualizations are designed to provide the essential contextualization of such data and thus help analysts discover complex relationships between observed sensor values and health-predictive phone-o-types. To guide the design of INPHOVIS, we performed a hierarchical task analysis of phone-o-typing requirements with health domain experts. We then designed and implemented multiple innovative visualizations integral to INPHOVIS including stacked bar charts to show diurnal behavioral patterns, calendar views to visualize day-level data along with bar charts, and correlation views to visualize important wellness predictive data. We demonstrate the usefulness of INPHOVIS with walk-throughs of use cases. We also evaluated INPHOVIS with expert feedback and received encouraging responses.

Carrying Inundation Blessings: A Discussion of Pilgrim Flask Amulets in Ancient Egypt

Abstract Pilgrim flasks were a ceramic form that first appeared in Egypt in the Eighteenth Dynasty. A small quantity of faience amulets in the shape of pilgrim flasks are known in several museum collections, but have not been studied in detail. The amulets are standardized in material and shape and, based on the limited contextual information, likely reflect a specific aspect of local belief, especially since their worn surface and bail for stringing suggests they were worn and touched regularly. It is suggested that these amulets are chronologically restricted and date between the Third Intermediate Period and Late Period, and are related to the contemporary appearance of New Year’s Flasks – a type of pilgrim flask predominantly made in faience and thought to be for celebration of the Nile inundation. By presenting a macro-focus on a little-known amulet type, it is hoped this study will expand our understanding of religious ideology, symbolic meaning, and the changing socio-cultural context in the Third Intermediate Period.

On-device modeling of user’s social context and familiar places from smartphone-embedded sensor data

Context modeling and recognition represent complex tasks that allow mobile and ubiquitous computing applications to adapt to the user’s situation. The real advantage of context-awareness in mobile environments mainly relies on the prompt system’s and applications’ reaction to context changes. Current solutions mainly focus on limited context information generally processed on centralized architectures, potentially exposing users’ personal data to privacy leakage, and missing personalization features. For these reasons on-device context modeling and recognition represent the current research trend in this area. Among the different information characterizing the user’s context in mobile environments, social interactions and visited locations remarkably contribute to the characterization of daily life scenarios. In this paper we propose a novel, unsupervised and lightweight approach to model the user’s social context and her locations based on ego networks directly on the user mobile device. Relying on this model, the system is able to extract high-level and semantic-rich context features from smartphone-embedded sensors data. Specifically, for the social context it exploits data related to both physical and cyber social interactions among users and their devices. As far as location context is concerned, we assume that it is more relevant to model the familiarity degree of a specific location for the user’s context than the raw location data, both in terms of GPS coordinates and proximity devices. We demonstrate the effectiveness of the proposed approach with 3 different sets of experiments by using 5 real-world datasets collected from a total of 956 personal mobile devices. Specifically, we assess the structure of the social and location ego networks, we provide a semantic evaluation of the proposed models and a complexity evaluation in terms of mobile computing performance. Finally, we demonstrate the relevance of the extracted features by showing the performance of 3 different machine learning algorithms to recognize daily-life situations, obtaining an improvement of 3% of AUROC, 9% of Precision, and 5% in terms of Recall with respect to use only features related to physical context.

Global–Local Enhancement Network for Short Text Classification

Because of the limited context information, it is a challenging task to classify short texts. Most existing methods only focus on extracting high-quality local features or global features from text to construct text representations, which is not comprehensive enough. This article proposes a global–local enhancement network (GLEN), which can construct a high-quality text representation by integrating the global and local features of the text. To improve the quality of global and local features, a group-wise enhancement mechanism is introduced, which can effectively enhance the important features while weakening the unimportant features. For the information-loss problem of traditional pooling operation, we designed a global–local pooling mechanism, which can filter out local features that are more relevant to the whole information of the text. Seven benchmark datasets of text classification were selected to test the performance of the model, and GLEN obtained the best results on most datasets. The ablation experiment on GLEN shows that both the group-wise enhancement mechanism and the global–local pooling mechanism can effectively improve the performance of the model.

Boundary-aware context neural network for medical image segmentation.

Medical image segmentation can provide a reliable basis for further clinical analysis and disease diagnosis. With the development of convolutional neural networks (CNNs), medical image segmentation performance has advanced significantly. However, most existing CNN-based methods often produce unsatisfactory segmentation masks without accurate object boundaries. This problem is caused by the limited context information and inadequate discriminative feature maps after consecutive pooling and convolution operations. Additionally, medical images are characterized by high intra-class variation, inter-class indistinction and noise, extracting powerful context and aggregating discriminative features for fine-grained segmentation remain challenging. In this study, we formulate a boundary-aware context neural network (BA-Net) for 2D medical image segmentation to capture richer context and preserve fine spatial information, which incorporates encoder-decoder architecture. In each stage of the encoder sub-network, a proposed pyramid edge extraction module first obtains multi-granularity edge information. Then a newly designed mini multi-task learning module for jointly learning segments the object masks and detects lesion boundaries, in which a new interactive attention layer is introduced to bridge the two tasks. In this way, information complementarity between different tasks is achieved, which effectively leverages the boundary information to offer strong cues for better segmentation prediction. Finally, a cross feature fusion module acts to selectively aggregate multi-level features from the entire encoder sub-network. By cascading these three modules, richer context and fine-grain features of each stage are encoded and then delivered to the decoder. The results of extensive experiments on five datasets show that the proposed BA-Net outperforms state-of-the-art techniques.

The use of patient experience data for quality improvement in hospitals: A scoping review

In this paper we identified what was reported in the literature on qualitative and quantitative approaches used to capture and improve patient experiences in a hospital setting. For inclusion, articles were required to describe an embedded strategy for capturing patient experiences that was used to inform quality improvement in a hospital setting. Articles also had to be published in English between January 2004 and December 2020. Six databases (MEDLINE, EMBASE, PsycINFO, CINAHL, Health and Psychosocial Instruments and Cochrane Library) and grey literature (relevant hospital and government websites) were searched. All articles were screened by two reviewers and any disagreements were resolved through consensus. Data were extracted from the included articles using a study-specific form in Microsoft Excel and synthesized using descriptive qualitative and quantitative approaches. Thirty articles were included in this scoping review. Patient experience data were captured through a variety of methods including surveys, focus groups, patient complaints and informal feedback, with the majority using formal, paper-based surveys. A wide range of quality improvement initiatives were implemented as a result of hospitals’ patient experience data, but there was limited contextual information regarding the hospital settings and population characteristics. Initiatives implemented by a dedicated and multidisciplinary quality improvement team (nurses, administrators, physicians, etc.) generally demonstrated positive outcomes. We conclude that more work is needed to better understand how best to capture and use patient experience data for quality improvement, the contexts in which initiatives are successful and how to integrate patients and families in the ongoing implementation and evaluation processes.

An integrated cyber security risk management framework and risk predication for the critical infrastructure protection

Cyber security risk management plays an important role for today’s businesses due to the rapidly changing threat landscape and the existence of evolving sophisticated cyber attacks. It is necessary for organisations, of any size, but in particular those that are associated with a critical infrastructure, to understand the risks, so that suitable controls can be taken for the overall business continuity and critical service delivery. There are a number of works that aim to develop systematic processes for risk assessment and management. However, the existing works have limited input from threat intelligence properties and evolving attack trends, resulting in limited contextual information related to cyber security risks. This creates a challenge, especially in the context of critical infrastructures, since attacks have evolved from technical to socio-technical and protecting against them requires such contextual information. This research proposes a novel integrated cyber security risk management (i-CSRM) framework that responds to that challenge by supporting systematic identification of critical assets through the use of a decision support mechanism built on fuzzy set theory, by predicting risk types through machine learning techniques, and by assessing the effectiveness of existing controls. The framework is composed of a language, a process, and it is supported by an automated tool. The paper also reports on the evaluation of our work to a real case study of a critical infrastructure. The results reveal that using the fuzzy set theory in assessing assets' criticality, our work supports stakeholders towards an effective risk management by assessing each asset's criticality. Furthermore, the results have demonstrated the machine learning classifiers’ exemplary performance to predict different risk types including denial of service, cyber espionage and crimeware.

What is the future of illicit drug profiling in Switzerland? Condemned to disappear or forgotten treasure.

Illicit drug profiling bears a long history. Developments in the field from mid‐90s have led to several international profiling programs. Several countries have put their efforts to develop and implement the routine use of illicit drug profiling in the investigation and prosecution of illicit drug‐related crimes. For more than 20 years, the School of Criminal Sciences (ESC) at the University of Lausanne has, through its illicit drug expertise laboratory, played a main role in promoting the use of illicit drug profiling. In Switzerland, there is no national illicit drug profiling practice and the ESC laboratory is the only one offering such service. However, only a limited number of Swiss jurisdictions send regularly all or part of their seized specimens for analysis to the ESC laboratory. Profiling results are furnished to investigators and prosecutors regardless if they have been requested or not and are stored in a database with limited contextual information with no further data treatment. In 2020, the interruption of a project intended to develop and implement an intercantonal database gathering traditional police data, forensic data (e.g., DNA, fingerprints, etc.), and physical and chemical links, to produce intelligence and support investigation, led to the fundamental question: Is illicit drug profiling in Switzerland condemned to disappear or is it a forgotten treasure, a neglected approach that deserves to be revalued? This paper reports the Swiss situation regarding illicit drug profiling practices and discusses some factors that are thought to impact its use in day‐to‐day work.

2D medical image segmentation via learning multi-scale contextual dependencies.

Automatic medical image segmentation plays an important role as a diagnostic aid in the identification of diseases and their treatment in clinical settings. Recently proposed methods based on Convolutional Neural Networks (CNNs) have demonstrated their potential in image processing tasks, including some medical image analysis tasks. Those methods can learn various feature representations with numerous weight-shared convolutional kernels, however, the missed diagnosis rate of regions of interest (ROIs) is still high in medical image segmentation. Two crucial factors behind this shortcoming, which have been overlooked, are small ROIs from medical images and the limited context information from the existing network models. In order to reduce the missed diagnosis rate of ROIs from medical images, we propose a new segmentation framework which enhances the representative capability of small ROIs (particularly in deep layers) and explicitly learns global contextual dependencies in multi-scale feature spaces. In particular, the local features and their global dependencies from each feature space are adaptively aggregated based on both the spatial and the channel dimensions. Moreover, some visualization comparisons of the learned features from our framework further boost neural networks' interpretability. Experimental results show that, in comparison to some popular medical image segmentation and general image segmentation methods, our proposed framework achieves the state-of-the-art performance on the liver tumor segmentation task with 91.18% Sensitivity, the COVID-19 lung infection segmentation task with 75.73% Sensitivity and the retinal vessel detection task with 82.68% Sensitivity. Moreover, it is possible to integrate (parts of) the proposed framework into most of the recently proposed Fully CNN-based models, in order to improve their effectiveness in medical image segmentation tasks.

Detecting Text Baselines in Historical Documents With Baseline Primitives

Previous deep learning based approaches to text baseline detection in historical documents usually take it as a semantic segmentation task. These methods adopt a fully convolutional neural network to predict baseline pixels first and then group them into lines by heuristic post-processing steps, which tends to suffer from a wrongly merged or wrongly split problem owing to limited context information provided by pixels. To address these issues, we introduce the concept of a baseline primitive, which is defined as a virtual bounding box centered at each baseline pixel. After baseline primitive detection, a relation network is used to predict a link relationship for each pair of primitives. Consequently, text baselines are generated by detecting baseline primitives and grouping them with the corresponding link relationships. Owing to the design of baseline primitives, wider context information can be leveraged to improve link prediction accuracy. Therefore, our approach can effectively detect text baselines with small inter-line or large inter-word spacing. Quantitative experimental results demonstrate the effectiveness of the proposed baseline primitive design. Our approach achieves state-of-the-art performance on two public benchmarks, namely cBAD 2017 and cBAD 2019.