Intensive Feature Research Articles

Evaluation of Physico-Chemical Characteristics of Cement Superplasticizer Based on Polymelamine Sulphonate.

Cementitious materials are used to construct an engineered barrier in repositories for radioactive waste. The cement matrix may contain a variety of organic compounds, some of which are polymeric admixtures used as plasticizers. Superplasticizers (SPs) are highly effective organic cement additives for reducing water amount, increasing workability, homogeneity, plasticity and the non-segregation of mortars and grouts, improving mechanical properties and resistance to destructive environments. SPs in cement could have an impact on the long-term safety of the disposals of radioactive waste. These organic agents can leach from the cementitious matrix into groundwater and may affect the migration behaviour of radionuclides. The detailed chemical composition and other characteristics of the cement (CEM I 42.5 R, Sweden) used for the leaching experiments were evaluated. It contained mainly CaO (52.51 ± 1.37, %), and the surface area of the cement particles was 13.2 ± 1.3 m2/g. An insignificant increase in pH (from 12.6 ± 0.1 to 12.8 ± 0.1) was observed for the leachates over 10 days. A commercially available cement superplasticizer based on polymelamine sulphonate (PMS) Peramin SMF10 (Peramin AB, Sweden) was chosen for the research. The product's chemical composition was analysed using wavelength-dispersive X-ray fluorescence (WD-XRF) spectroscopy, while other physico-chemical properties of the PMS superplasticizer were assessed by Raman spectroscopy and thermo-gravimetric analysis. In aqueous solutions and powders of PMS, the same most intensive features were observed at 774 cm-1 (ring out-of-plane deformation), 977 cm-1 (C-N-C bending, SO stretching) and 1055 cm-1 (C-N=C bending) in the Raman spectra. At up to 270 °C, the polymer was thermally stable. Raman and UV/Vis spectroscopies were used to assess the rate of the alkaline degradation of PMS superplasticizer in different aqueous solutions. No changes were observed in the hydrolytic solutions with any of the above analytical methods over a period of 3 years. The results obtained revealed a good thermal and chemical stability (in highly alkaline media, pH = 9.9-12.9) of the PMS polymer.

Analysis and Benchmarking of feature reduction for classification under computational constraints

Machine learning is most often expensive in terms of computational and memory costs due to training with large volumes of data. Current computational limitations of many computing systems motivate us to investigate practical approaches, such as feature selection and reduction, to reduce the time and memory costs while not sacrificing the accuracy of classification algorithms. In this work, we carefully review, analyze, and identify the feature reduction methods that have low costs/overheads in terms of time and memory. Then, we evaluate the identified reduction methods in terms of their impact on the accuracy, precision, time, and memory costs of traditional classification algorithms. Specifically, we focus on the least resource intensive feature reduction methods that are available in Scikit-Learn library. Since our goal is to identify the best performing low-cost reduction methods, we do not consider complex expensive reduction algorithms in this study. In our evaluation, we find that at quadratic-scale feature reduction, the classification algorithms achieve the best trade-off among competitive performance metrics. Results show that the overall training times are reduced 61%, the model sizes are reduced 6×, and accuracy scores increase 25% compared to the baselines on average with quadratic scale reduction.

A common data model for the standardization of intensive care unit medication features.

Common data models provide a standard means of describing data for artificial intelligence (AI) applications, but this process has never been undertaken for medications used in the intensive care unit (ICU). We sought to develop a common data model (CDM) for ICU medications to standardize the medication features needed to support future ICU AI efforts. A 9-member, multi-professional team of ICU clinicians and AI experts conducted a 5-round modified Delphi process employing conference calls, web-based communication, and electronic surveys to define the most important medication features for AI efforts. Candidate ICU medication features were generated through group discussion and then independently scored by each team member based on relevance to ICU clinical decision-making and feasibility for collection and coding. A key consideration was to ensure the final ontology both distinguished unique medications and met Findable, Accessible, Interoperable, and Reusable (FAIR) guiding principles. Using a list of 889 ICU medications, the team initially generated 106 different medication features, and 71 were ranked as being core features for the CDM. Through this process, 106 medication features were assigned to 2 key feature domains: drug product-related (n = 43) and clinical practice-related (n = 63). Each feature included a standardized definition and suggested response values housed in the electronic data library. This CDM for ICU medications is available online. The CDM for ICU medications represents an important first step for the research community focused on exploring how AI can improve patient outcomes and will require ongoing engagement and refinement.

The Critical Role of Anharmonic Lattice Dynamics for Macroscopic Properties of the Visible Light Absorbing Nitride Semiconductor CuTaN2

AbstractTernary nitride semiconductors are rapidly emerging as a promising class of materials for energy conversion applications, offering an appealing combination of strong light absorption in the visible range, desirable charge transport characteristics, and good chemical stability. In this work, it is shown that finite‐temperature lattice dynamics in CuTaN2 – a prototypical ternary nitride displaying particularly strong visible light absorption – exhibit a pronounced anharmonic character that plays an essential role in defining its macroscopic optoelectronic and thermal properties. Low‐frequency vibrational modes that are Raman‐inactive from symmetry considerations of the average crystal structure and unstable in harmonic phonon calculations are found to appear as intensive Raman features near room temperature. The atomic contributions to the anharmonic vibrations are characterized by combining Raman measurements with molecular dynamics and density functional theory calculations. This analysis reveals that anharmonic lattice dynamics have large ramifications on the fundamental properties of this compound, resulting in uniaxial negative thermal expansion and the opening of its bandgap to a near‐optimal value for solar energy harvesting. The atomic‐level understanding of anharmonic lattice dynamics, as well as the finding that they strongly influence key properties of this semiconductor at room temperature, have important implications for design of new functional materials, especially within the emerging class of ternary nitride semiconductors.

Imperatives for integrated weed management in vegetable production: Evaluating research and adoption

AbstractWeeds have a significant impact on vegetable production worldwide. These intensive cropping systems feature frequent tillage, fertilization and irrigation, providing ideal growing conditions for crops as well as certain weeds. Integrated weed management (IWM) can reduce reliance on herbicides by encouraging a systems approach to weed management. Using insights from global research and industry literature, we investigated the effectiveness of prevailing weed control methods, and evaluated emerging management practices and technologies for ongoing research and adoption. Weed control relies primarily on a relatively narrow range of herbicides as well as frequent tillage. Herbicides have negative impacts on soil, water and human health, while tillage impacts soil quality and function. Intensive cropping on smaller plots facilitates IWM, relying on multiple strategies including hand weeding, mulches, cover crops and cultural methods (e.g., crop rotations, timing). New herbicide options are suggested as an industry priority but are constrained by the lack of new chemistry and potential herbicide resistance. Refinement and adoption of non‐herbicide and emerging precision control methods into farm IWM in vegetables is more likely to be sustainable. This review is relevant to advanced vegetable production systems globally, but also to smallholder vegetable production in developing economies.

Intensive Multi-order Feature Extraction for Incipient Fault Detection of Inverter System

Intensive Multi-order Feature Extraction for Incipient Fault Detection of Inverter System

Interpretable, data-driven models for predicting shaft power, fuel consumption, and speed considering the effects of hull fouling and weather conditions

In response to the global call for action to reduce CO2 emissions, operational measures such as speed, route optimization, and hull cleaning play a significant role in the maritime industry. These measures can be implemented immediately without significant investment in both newbuilding ships and existing ships. To make accurate decisions regarding operational measures, reliable and precise models of environmental conditions and effects of hull fouling are required. In this study, a data-driven approach using linear regression was applied to predict shaft power, fuel consumption, and speed after intensive data preparation and feature engineering. First, a shaft power prediction model was developed by combining three independent submodels: the RPM-power model, hull fouling model, and environmental effect model. Subsequently, fuel consumption and speed prediction models were developed based on the shaft power prediction model. Model validation was performed on a 174K LNG carrier, and the results showed good accuracy even in long-term ship operations of more than two years. The mean absolute percentage errors (MAPEs) of the prediction models were 1.60%, 1.70%, and 2.68% for the shaft power, fuel consumption, and speed, respectively. The validated models were applied to two LNG carriers, and satisfactory results were obtained. This study contributes to greenhouse gas (GHS) reduction by providing interpretable, flexible, and accurate models that can help make correct decisions regarding optimal operational measures.

Transformer-Enhanced CNN Based on Intensive Feature for Hyperspectral Unmixing

Transformer-Enhanced CNN Based on Intensive Feature for Hyperspectral Unmixing

MEDICAL IMAGING ENHANCEMENT WITH AI MODELS FOR AUTOMATIC DISEASE DETECTION AND CLASSIFICATION BASED ON MEDICAL IMAGES

The development of artificial intelligence (AI) in the healthcare industry has recently been of utmost importance. Early discovery, diagnosis, categorization, analysis, and treatment options are always positive medical breakthroughs. In making diagnoses and strategic decisions for healthcare, precise and consistent picture classification is essential. The semantic gap has emerged as the main problem with picture sorting. To bridge the gap, traditional machine learning techniques for classification mainly depend on low-level features rather than high-level ones, use some hand-crafted features, but compel intensive feature extraction and classification procedures. Deep convolution neural networks (CNNs), a potent technique that has significantly advanced in recent years, are successful in classifying images. A thorough assessment of pertinent studies is required to further assist readers in understanding the research and its main concepts captured. This study highlights the various AI models for automatic disease detection and classification based on medical images. This can include identifying tumors, lesions, fractures, or other abnormalities. The models discussed in this article include Convolutional Neural Networks (CNNs), Generative Adversarial Networks (GANs), One-Class Learning Models, Recurrent Neural Networks (RNNs), and 3D and Multimodal Models. Since these models work with various modalities, there are numerous instances where computed tomography (CT), positron emission computed tomography (PET), X-ray, magnetic resonance imaging (MRI), and ultrasound (US). Are mentioned to help complement the research.

Enhanced lower-limb motor imagery by kinesthetic illusion.

Brain-computer interface (BCI) based on lower-limb motor imagery (LMI) enables hemiplegic patients to stand and walk independently. However, LMI ability is usually poor for BCI-illiterate (e.g., some stroke patients), limiting BCI performance. This study proposed a novel LMI-BCI paradigm with kinesthetic illusion(KI) induced by vibratory stimulation on Achilles tendon to enhance LMI ability. Sixteen healthy subjects were recruited to carry out two research contents: (1) To verify the feasibility of induced KI by vibrating Achilles tendon and analyze the EEG features produced by KI, research 1 compared the subjective feeling and brain activity of participants during rest task with and without vibratory stimulation (V-rest, rest). (2) Research 2 compared the LMI-BCI performance with and without KI (KI-LMI, no-LMI) to explore whether KI enhances LMI ability. The analysis methods of both experiments included classification accuracy (V-rest vs. rest, no-LMI vs. rest, KI-LMI vs. rest, KI-LMI vs. V-rest), time-domain features, oral questionnaire, statistic analysis and brain functional connectivity analysis. Research 1 verified that induced KI by vibrating Achilles tendon might be feasible, and provided a theoretical basis for applying KI to LMI-BCI paradigm, evidenced by oral questionnaire (Q1) and the independent effect of vibratory stimulation during rest task. The results of research 2 that KI enhanced mesial cortex activation and induced more intensive EEG features, evidenced by ERD power, topographical distribution, oral questionnaire (Q2 and Q3), and brain functional connectivity map. Additionally, the KI increased the offline accuracy of no-LMI/rest task by 6.88 to 82.19% (p < 0.001). The simulated online accuracy was also improved for most subjects (average accuracy for all subjects: 77.23% > 75.31%, and average F1_score for all subjects: 76.4% > 74.3%). The LMI-BCI paradigm of this study provides a novel approach to enhance LMI ability and accelerates the practical applications of the LMI-BCI system.

A novel deep learning-based approach for malware detection

Malware detection approaches can be classified into two classes, including static analysis and dynamic analysis. Conventional approaches of the two classes have their respective advantages and disadvantages. For example, static analysis is faster but cannot detect the malware variants generated through code obfuscation, whereas dynamic analysis can effectively detect variants generated through code obfuscation but is slower and requires intensive resources. This paper proposes a novel deep learning-based approach for malware detection. It delivers better performance than conventional approaches by combining static and dynamic analysis advantages. First, it visualises a portable executable (PE) file as a coloured image. Second, it extracts deep features from the colour image using fine-tuned deep learning model. Third, it detects malware based on the deep features using support vector machines (SVM). The proposed method combines deep learning with machine learning and eliminates the need for intensive feature engineering tasks and domain knowledge. The proposed approach is scalable, cost-effective, and efficient. The detection effectiveness of the proposed method is validated through 12 machine learning models and 15 deep learning models. The generalisability of the proposed framework is validated on various benchmark datasets. The proposed approach outperformed with an accuracy of 99.06% on the Malimg dataset. The Wilcoxon signed-rank test is used to show the statistical significance of the proposed framework. The detailed experimental results demonstrate the superiority of the proposed method over the other state-of-the-art approaches, with an average increase in accuracy of 16.56%. Finally, to tackle the problems of imbalanced data and the shortage of publicly available datasets for malware detection, various data augmentation techniques are proposed, which lead to improved performance. It is evident from the results that the proposed framework can be useful to the defence industry, which will be helpful in devising more efficient malware detection solutions.

Improvement of Human Pose Estimation and Processing With the Intensive Feature Consistency Network

The modeling of human body kye-points is the most significant aspect of pose estimation appropriately. Computer vision algorithm identifies human pose, body-movement, and action in many ways. Most of the previous works taken advantage for finding accuracy or efficiency in terms of speed. However, many techniques suffer for intensive computational demands with low-latency or higher proceeding speed. We have designed a unique approach for single-person pose estimation and action recognition which is well suited for fitness application and mobility activities. The proposed framework has been developed with a base network that provides an initial pose to further refinement through Intensive Feature Consistency (IFC) network. The IFC network enforces high-level constraints on the global body intensity correction and local body part adjustments. The proposed module reduces the impact of body joint movement diversity by interpreting long-term consistent view. We have illustrated the effectiveness of proposed framework through pose estimation accuracy improvement with two benchmark datasets. Which is specified state-of the- art performance of IFC network under the required real-time processing speed on the CPU platform. The IFC network has improved 99.1% of PCK body and 94.7% of PCK torso accuracy under 31 FPS, which is comparatively higher than the existing work.

Fenomena Pembatalan Permohonan Paspor dalam Implementasi Kebijakan M-Paspor pada Kantor Imigrasi Tanjung Perak

This article is a study of the phenomenon of cancellation of passport applications in the implementation of M-Paspor policy at Tanjung Perak Immigration Office. The implementation of M-Paspor policy was released in early 2022 led to the phenomenon of cancellation of passport application with many reasons. Some of the reasons for cancelling the application are because the passport applicant is not attend on the specified schedule, the applicant can’t complete the required documents that need to be attached or the mistake in applying passport application. This study uses a qualitative method with case study approach Analyzis uses public policy’s theory and consept of public policy’s implementation. The result of the study stated that the M-Passport policy requires more socialization and additional information regarding the detailed application requirements that need to be completed by the applicant in accordance with the purpose of the passport application as well as a more intensive notification feature to minimize error in submitting a passport application by the passport applicant.

Tea-cake CBIR: a tea-cake content-based image retrieval model with rich and intensive feature extraction

Tea-cake CBIR: a tea-cake content-based image retrieval model with rich and intensive feature extraction

Preterm Babies: At the Hospital

Preterm Babies: At the Hospital

Conceptual replication of an evidence-based peer learning programme to enhance career preparation — a cluster randomized controlled trial (RCT)

Previous randomized-controlled trials have shown that a peer learning group intervention for career preparation can have positive effects on adolescent career management and the transition to post-comprehensive education in secondary schools. However, this earlier evidence of efficacy has been found by intervention studies that have implemented the method intensively. Earlier studies suggest that tailoring implementation strategies to fit organizational processes may offer opportunities to improve the sustainability and scalability of evidence-based practices. In this study, the implementation of the career preparation intervention was integrated into the school curriculum as a part of regular career counselling, lengthening the delivery timeframe of the intervention programme and using the schools’ own guidance counsellors as intervention providers. We conducted a conceptual replication study to investigate how effectively the adapted intervention programme enhanced perceived career preparation skills by carrying out a new cluster randomized-controlled trial among 1068 pupils. Linear mixed models showed that the effect of peer learning sessions on career choice preparedness was positive in comparison to that in the control group. The result suggests that the adapted intervention programme preserved its identifiable positive effects, although dismissing intensive delivery features somewhat reduced the effect size. These study results have implications for school-based career counselling interventions as schools seek to identify evidence-based methods that are cost-efficient and may be integrated into regular school routines.

RTSDM: A Real-Time Semantic Dense Mapping System for UAVs

Intelligent drones or flying robots play a significant role in serving our society in applications such as rescue, inspection, agriculture, etc. Understanding the scene of the surroundings is an essential capability for further autonomous tasks. Intuitively, knowing the self-location of the UAV and creating a semantic 3D map is significant for fully autonomous tasks. However, integrating simultaneous localization, 3D reconstruction, and semantic segmentation together is a huge challenge for power-limited systems such as UAVs. To address this, we propose a real-time semantic mapping system that can help a power-limited UAV system to understand its location and surroundings. The proposed approach includes a modified visual SLAM with the direct method to accelerate the computationally intensive feature matching process and a real-time semantic segmentation module at the back end. The semantic module runs a lightweight network, BiSeNetV2, and performs segmentation only at key frames from the front-end SLAM task. Considering fast navigation and the on-board memory resources, we provide a real-time dense-map-building module to generate an OctoMap with the segmented semantic map. The proposed system is verified in real-time experiments on a UAV platform with a Jetson TX2 as the computation unit. A frame rate of around 12 Hz, with a semantic segmentation accuracy of around 89% demonstrates that our proposed system is computationally efficient while providing sufficient information for fully autonomous tasks such as rescue, inspection, etc.

Shallow Deep Learning using Space-filling Curves for Malware Classification

The incidents of malware attacks are continually increasing at a rapid rate, thanks to the lucrative potential in schemes such as ransomware, credential stealing Trojans and cryptominers. Their explosive growth is compounded by the ease with which variants can be created from original strains. As a result, anti-virus organisations are struggling to keep up, with some reporting upwards of 14 million samples processed per month. These sheer volumes have caused a shift towards machine learning and artificial intelligence in an effort to alleviate the manual burden of analysis and classification. This research presents a novel framework for the classification of malware into distinct family classes through computer vision and deep learning. In the proposed framework, malware binaries are represented in an abstract form as images mapped through mathematical constructs known as space-filling curves. Convolutional neural networks were constructed and applied to the malware images to build predictive models for classification. The models were optimised using an auto-tuning function for the hyper parameters, which included Bayesian Optimisation, Random search and HyperBand, providing an exhaustive search on the hyper parameters. On a training dataset of 13k malware samples from 23 distinct families, the models yielded an average score of 95% for precision, recall and f1-score. The final deep learning model was validated for robustness against a dataset of more recent variants, comprising 12,816 samples from 16 malware families, returning classification scores of 95%, 86% and 90% for precision, recall and f1-score. The final model was demonstrated to outperform a similar benchmark model considerably. The results show the potential of the deep learning framework as a viable solution to the classification of malware, without the need for manually intensive feature generation or invasive processing techniques.

Horizontal and Vertical Collaboration for VR Delivery in MEC-Enabled Small-Cell Networks

Due to the large bandwidth, low latency and computationally intensive features of virtual reality (VR) video applications, the current resource-constrained wireless and edge networks cannot meet the requirements of on-demand VR delivery. In this letter, we propose a joint horizontal and vertical collaboration architecture in multi-access edge computing (MEC)-enabled small-cell networks for downlink VR delivery. In the proposed architecture, multiple MEC servers can jointly provide VR head-mounted devices (HMDs) with edge caching and viewpoint computation services, i.e., horizontal collaboration (HC), while the caching and computation strategies can collaborate among vertical layers, i.e., vertical collaboration (VC). Power allocation at base stations (BSs) is considered in coordination with HC and VC of MEC servers to obtain lower end-to-end latency of VR delivery. A joint caching, power allocation and task offloading problem is then formulated. By exploiting the hidden monotonicity of the problem, a discrete branch-reduce-and-bound (DBRB) algorithm is proposed to obtain the optimal solution efficiently. Simulation results demonstrate the advantage of the proposed architecture and algorithm in terms of existing ones.

Air trapping in COVID-19 patients following hospital discharge: retrospective evaluation with paired inspiratory/expiratory thin-section CT

ObjectivesThe study reports our experience with paired inspiration/expiration thin-section computed tomographic (CT) scans in the follow-up of COVID-19 patients with persistent respiratory symptoms.MethodsFrom August 13, 2020, to May 31, 2021, 48 long-COVID patients with respiratory symptoms (27 men and 21 women; median age, 62.0 years; interquartile range: 54.0–69.0 years) underwent follow-up paired inspiration-expiration thin-section CT scans. Patient demographics, length of hospital stay, intensive care unit admission rate, and clinical and laboratory features of acute infection were also included. The scans were obtained on a median of 72.5 days after onset of symptoms (interquartile range: 58.5–86.5) and at least 30 days after hospital discharge. Thin-section CT findings included ground-glass opacity, mosaic attenuation pattern, consolidation, traction bronchiectasis, reticulation, parenchymal bands, bronchial wall thickening, and air trapping. We used a quantitative score to determine the degree of air trapping in the expiratory scans.ResultsParenchymal abnormality was found in 50% (24/48) of patients and included air trapping (37/48, 77%), ground-glass opacities (19/48, 40%), reticulation (18/48, 38%), parenchymal bands (15/48, 31%), traction bronchiectasis (9/48, 19%), mosaic attenuation pattern (9/48, 19%), bronchial wall thickening (6/48, 13%), and consolidation (2/48, 4%). The absence of air trapping was observed in 11/48 (23%), mild air trapping in 20/48 (42%), moderate in 13/48 (27%), and severe in 4/48 (8%). Independent predictors of air trapping were, in decreasing order of importance, gender (p = 0.0085), and age (p = 0.0182).ConclusionsOur results, in a limited number of patients, suggest that follow-up with paired inspiratory/expiratory CT in long-COVID patients with persistent respiratory symptoms commonly displays air trapping.Key Points• Our experience indicates that paired inspiratory/expiratory CT in long-COVID patients with persistent respiratory symptoms commonly displays air trapping.• Iterative reconstruction and dose-reduction options are recommended for demonstrating air trapping in long-COVID patients.