High-volume Data Research Articles

Improved Detection and Analysis of Wheat Spikes U sing Multi-Stage Convolutional Neural Network

High throughput plant phenotyping is the advanced scientific approach for rapid phenotyping of plant traits, especially high consumable grains or crops, which is designed to process a high volume of data in a short time for plant breeders and cultivars to utilize. Detection and counting of crop traits such as plants, fruits, wheat or rice spikes, sorghum head, and plant diseases is more advanced research in this field, where real-world data are collected using aerial and land-based imaging platforms equipped with a variety of geospatial sensors, and their statistical analysis is conducted using Artificial Intelligence (AI) and Deep Learning-based solutions. In this paper, we contributed to solving such a challenge of phenotyping by detecting and counting wheat spikes from land-based imaging by applying a Region-based Convolutional Neural Network (CNN) model. Our method employs the use of CNN to extract features from the imaging platform and the learning model is trained to detect and count wheat spikes in field images based on these extracted features. Using the publicly available SPIKE dataset to train and test our model, our proposed method achieved 98% average precision and 91% average F1 score on the test set. Our results show a significant improvement of 2.9% and 11.2% in detection accuracy as well as 1% and 3% in average precision metric over state-of-the-art Faster Regionbased Convolutional Neural Network (Faster-RCNN), and RetinaNet, respectively, and have the potential to significantly benefit plant breeders by facilitating the selection of wheat varieties with high yields. DUJASE Vol. 7 (2) 21-30, 2022 (July)

Association mining-based method for enterprise’s technological innovation intelligent decision making under big data

Technological innovation is vital for the survival and development of enterprises. In the era of intelligent information interconnection and knowledge-driven economy, there is a growing interest in how to manage high-volume data, unlock its potential value, and provide intelligent analysis and decision-making support for enterprise’s technological innovation. This paper proposes an improved knowledge association analysis method based on the semantic concept model. This approach enables the discovery of potential correlations and interaction modes between the influencing factors of enterprise’s technological innovation, and provides a useful reference for decision-making by combining the analysis with the enterprise’s own situation.

Frugal Gaussian clustering of huge imbalanced datasets through a bin-marginal approach

Clustering conceptually reveals all its interest when the dataset size considerably increases since there is the opportunity to discover tiny but possibly high value clusters which were out of reach with more modest sample sizes. However, clustering is practically faced to computer limits with such high data volume, since possibly requiring extremely high memory and computation resources. In addition, the classical subsampling strategy, often adopted to overcome these limitations, is expected to heavily failed for discovering clusters in the highly imbalanced cluster case. Our proposal first consists in drastically compressing the data volume by just preserving its bin-marginal values, thus discarding the bin-cross ones. Despite this extreme information loss, we then prove generic identifiability property for the diagonal mixture model and also introduce a specific EM-like algorithm associated to a composite likelihood approach. This latter is extremely more frugal than a regular but unfeasible EM algorithm expected to be used on our bin-marginal data, while preserving all consistency properties. Finally, numerical experiments highlight that this proposed method outperforms subsampling both in controlled simulations and in various real applications where imbalanced clusters may typically appear, such as image segmentation, hazardous asteroids recognition and fraud detection.

Fuzzy Rule Based Adaptive Block Compressive Sensing for WSN Application

Transmission of high volume of data in a restricted wireless sensor network (WSN) has come up as a challenge due to high-energy consumption and larger bandwidth requirement. To address the issues of high-energy consumption and efficient data transmission adaptive block compressive sensing (ABCS) is one of the optimum solution. ABCS framework is well capable to adapt the sampling rate depending on the block’s features information that offers higher sampling rate for less compressible blocks and lower sampling rate for more compressible blocks In this paper, we have proposed a novel fuzzy rule based adaptive compressive sensing approach by leveraging the saliency and the edge features of the image making the sampling rate selection completely automatic. Adaptivity of the block sampling ratio has been decided based on the fuzzy logic system (FLS) by considering two important features i.e., edge and saliency information. The proposed framework is experimented on standard dataset, Kodak data set, CCTV images and the Set5 data set images. It achieved an average PSNR of 34.26 and 33.2 and an average SSIM of 0.87 and 0.865 for standard images and CCTV images respectively. Again for high resolution Kodak data set and Set 5 dataset images, it achieved an average PSNR of 32.95 and 31.72 and SSIM of 0.832 and 0.8 respectively. The experiments and the result analysis show that proposed method is efficacious than the state of the art methods in both subjective and objective evaluation metrics.

A metaheuristic-based ensemble feature selection framework for cyber threat detection in IoT-enabled networks

Internet of Things (IoT) enabled networks are highly vulnerable to cyber threats due to insecure wireless communication, resource constraint architecture, different types of IoT devices, and a high volume of sensor data being transported across the network. Therefore, IoT-compatible cybersecurity solutions are required. An intrusion detection system is one of the most common solutions for detecting cyber threats in IoT-enabled networks. However, most of the existing solutions for cyber threat detection suffer from many issues like poor accuracy, high learning complexity, low scalability, and high false positive rate (FPR). We propose a metaheuristic-based intelligent and novel framework for cyber threat detection using ensemble feature selection and classification approaches to overcome these issues. First, a metaheuristic-based ensemble feature selection framework is designed using Binary Gravitational Search Algorithm (BGSA) and Binary Grey Wolf Optimization (BGWO) to get an optimized set of features to avoid the curse of dimensionality for efficient learning. Next, Decision Tree and ensemble learning-based classification techniques such as AdaBoost and Random Forest (RF) are employed separately to detect and classify cyber threats. The UNSW-NB15 dataset assesses the effectiveness of the proposed framework, and its performance is evaluated against recent state-of-the-art frameworks. Based on the result analysis, it is found that the RF outperforms existing modern cyber threats detection methods due to the optimized feature subset (4 features out of 42), maximum accuracy (99.41%), maximum detection rate (99.09%), and maximum F1-score (99.33%) with the lowest FPR (0.03%).

Tracking Population-Level Anxiety Using Search Engine Data: Ecological Study.

Anxiety disorders are the most prevalent mental disorders globally, with a substantial impact on quality of life. The prevalence of anxiety disorders has increased substantially following the COVID-19 pandemic, and it is likely to be further affected by a global economic recession. Understanding anxiety themes and how they change over time and across countries is crucial for preventive and treatment strategies. The aim of this study was to track the trends in anxiety themes between 2004 and 2020 in the 50 most populous countries with high volumes of internet search data. This study extends previous research by using a novel search-based methodology and including a longer time span and more countries at different income levels. We used a crowdsourced questionnaire, alongside Bing search query data and Google Trends search volume data, to identify themes associated with anxiety disorders across 50 countries from 2004 to 2020. We analyzed themes and their mutual interactions and investigated the associations between countries' socioeconomic attributes and anxiety themes using time-series linear models. This study was approved by the Microsoft Research Institutional Review Board. Query volume for anxiety themes was highly stable in countries from 2004 to 2019 (Spearman r=0.89) and moderately correlated with geography (r=0.49 in 2019). Anxiety themes were predominantly long-term and personal, with "having kids," "pregnancy," and "job" the most voluminous themes in most countries and years. In 2020, "COVID-19" became a dominant theme in 27 countries. Countries with a constant volume of anxiety themes over time had lower fragile state indexes (P=.007) and higher individualism (P=.003). An increase in the volume of the most searched anxiety themes was associated with a reduction in the volume of the remaining themes in 13 countries and an increase in 17 countries, and these 30 countries had a lower prevalence of mental disorders (P<.001) than the countries where no correlations were found. Internet search data could be a potential source for predicting the country-level prevalence of anxiety disorders, especially in understudied populations or when an in-person survey is not viable.

Brain-machine interface based on transfer-learning for detecting the appearance of obstacles during exoskeleton-assisted walking.

Brain-machine interfaces (BMIs) attempt to establish communication between the user and the device to be controlled. BMIs have great challenges to face in order to design a robust control in the real field of application. The artifacts, high volume of training data, and non-stationarity of the signal of EEG-based interfaces are challenges that classical processing techniques do not solve, showing certain shortcomings in the real-time domain. Recent advances in deep-learning techniques open a window of opportunity to solve some of these problems. In this work, an interface able to detect the evoked potential that occurs when a person intends to stop due to the appearance of an unexpected obstacle has been developed. First, the interface was tested on a treadmill with five subjects, in which the user stopped when an obstacle appeared (simulated by a laser). The analysis is based on two consecutive convolutional networks: the first one to discern the intention to stop against normal walking and the second one to correct false detections of the previous one. The results were superior when using the methodology of the two consecutive networks vs. only the first one in a cross-validation pseudo-online analysis. The false positives per min (FP/min) decreased from 31.8 to 3.9 FP/min and the number of repetitions in which there were no false positives and true positives (TP) improved from 34.9% to 60.3% NOFP/TP. This methodology was tested in a closed-loop experiment with an exoskeleton, in which the brain-machine interface (BMI) detected an obstacle and sent the command to the exoskeleton to stop. This methodology was tested with three healthy subjects, and the online results were 3.8 FP/min and 49.3% NOFP/TP. To make this model feasible for non-able bodied patients with a reduced and manageable time frame, transfer-learning techniques were applied and validated in the previous tests, and were then applied to patients. The results for two incomplete Spinal Cord Injury (iSCI) patients were 37.9% NOFP/TP and 7.7 FP/min.

Using Geospatial Information to Map Yield Gain from the Use of Azospirillum brasilense in Furrow

The application of biological products in agricultural crops has become increasingly prominent. The growth-promoting bacterium Azospirillum brasilense has been used as an alternative to promote greater yield in maize crops. In the context of precision agriculture, interpreting geospatial data has allowed for monitoring the effect of the application of products that increase the yield of corn crops. The objective of this work was to evaluate the potential of Kriging techniques and spectral models through images in estimating the gain in yield of maize crop after applying A. brasilense. Analyses were carried out in two commercial areas treated with A. brasilense. The results revealed that models of yield prediction by Kriging with a high volume of training data estimated the yield gain with a root-mean-square error deviation (RMSE%), mean absolute percentage error (MAPE%), and R2 to be 6.67, 5.42, and 0.88, respectively. For spectral models with a low volume of training data, yield gain was estimated with RMSE%, MAPE%, and R2 to be 9.3, 7.71, and 0.80, respectively. The results demonstrate the potential to map the spatial distribution of productivity gains in corn crops following the application of A. brasilense.

Application of artificial intelligence techniques in the intensive care unit

Intensive care unit deals with data that are dynamic in nature like real time measurement of health condition to laboratory test data that are continuously changes accordingly with time. Artificial intelligence (AI’s) potential ability to perform complex pattern analyses using large volumes of data. Generated pattern discovers the new symptoms of the disease in the Intensive care units (ICUs), helps the doctors to prescribe the new drug discovery which is helpful to intelligent use. Currently research work has been focused in the ICU making more efficient clinical workflow by generation of high-risk patterns from improved high volumes of data. Emerging area of AI in the ICU includes mortality prediction, uses of powerful sensors, new drug discovery, prediction of length of stay and legal role in uses of drugs for severity of disease. This review focuses latest application of AI drugs and other relevant issues for the ICU.

Can barely winning lead to losing? Gender and past performance

We use high-volume data from professional tennis to estimate the causal effect of past on current performance for women and men. To identify this effect, we exploit double faults as exogenous shocks to past performance. We estimate that men do not react to near setbacks in the past. In contrast, women perform considerably worse after near setbacks. Heterogeneity analysis reveals different effects depending on experience, ability, and the intermediate score. Our results are robust to a number of sensitivity checks. A potential explanation for our findings are gender differences in negative psychological momentum.

Reaching for the Sky: Maximizing Deep Learning Inference Throughput on Edge Devices with AI Multi-Tenancy

The wide adoption of smart devices and Internet-of-Things (IoT) sensors has led to massive growth in data generation at the edge of the Internet over the past decade. Intelligent real-time analysis of such a high volume of data, particularly leveraging highly accurate deep learning (DL) models, often requires the data to be processed as close to the data sources (or at the edge of the Internet) to minimize the network and processing latency. The advent of specialized, low-cost, and power-efficient edge devices has greatly facilitated DL inference tasks at the edge. However, limited research has been done to improve the inference throughput (e.g., number of inferences per second) by exploiting various system techniques. This study investigates system techniques, such as batched inferencing, AI multi-tenancy, and cluster of AI accelerators, which can significantly enhance the overall inference throughput on edge devices with DL models for image classification tasks. In particular, AI multi-tenancy enables collective utilization of edge devices’ system resources (CPU, GPU) and AI accelerators (e.g., Edge Tensor Processing Units; EdgeTPUs). The evaluation results show that batched inferencing results in more than 2.4× throughput improvement on devices equipped with high-performance GPUs like Jetson Xavier NX. Moreover, with multi-tenancy approaches, e.g., concurrent model executions (CME) and dynamic model placements (DMP), the DL inference throughput on edge devices (with GPUs) and EdgeTPU can be further improved by up to 3× and 10×, respectively. Furthermore, we present a detailed analysis of hardware and software factors that change the DL inference throughput on edge devices and EdgeTPUs, thereby shedding light on areas that could be further improved to achieve high-performance DL inference at the edge.

Implementing Artificial Intelligence to Reduce Marine Ecosystem Pollution

Industrial growth has a positive impact because it brings prosperity to humans. But on the other hand, it also has a negative effect, mainly due to industrial pollution produced. The pollution impacts environmental damage, one of which is the marine environment. This damage can be reduced by increasing understanding of the marine environment by monitoring it using technology. Although efforts have been made to monitor the marine environment, there are difficulties interpreting the large amount of data collected. To overcome these obstacles, we need technology that can process big data. One of the technologies that can be used is Artificial Intelligence which will be discussed in this study. This study aims to provide further understanding regarding the application of Artificial Intelligence to monitor the marine environment. This study uses a literature review method from several studies related to Artificial Intelligence. The final result of this study explains the potential and impact of applying Artificial Intelligence in reducing pollution of the marine environment sustainably. Although there have been many efforts to monitor the ocean for pollutants remotely, classifying the data is challenging because of the high volume of data. Therefore, the novelty of this research is to discuss a use case of a new approach to monitoring the ocean with the help of Artificial Intelligence. This research is expected to be motivated to develop better solutions in overcoming marine environment pollution using Artificial Intelligence technology.

Privacy-preserving cancer type prediction with homomorphic encryption

Cancer genomics tailors diagnosis and treatment based on an individual’s genetic information and is the crux of precision medicine. However, analysis and maintenance of high volume of genetic mutation data to build a machine learning (ML) model to predict the cancer type is a computationally expensive task and is often outsourced to powerful cloud servers, raising critical privacy concerns for patients’ data. Homomorphic encryption (HE) enables computation on encrypted data, thus, providing cryptographic guarantees to protect privacy. But restrictive overheads of encrypted computation deter its usage. In this work, we explore the challenges of privacy preserving cancer type prediction using a dataset consisting of more than 2 million genetic mutations from 2713 patients for several cancer types by building a highly accurate ML model and then implementing its privacy preserving version in HE. Our solution for cancer type inference encodes somatic mutations based on their impact on the cancer genomes into the feature space and then uses statistical tests for feature selection. We propose a fast matrix multiplication algorithm for HE-based model. Our final model achieves 0.98 micro-average area under curve improving accuracy from 70.08 to 83.61% , being 550 times faster than the standard matrix multiplication-based privacy-preserving models. Our tool can be found at https://github.com/momalab/octal-candet.

Crowdsourcing in Plastic and Reconstructive Surgery: A Systematic Review with Reporting Recommendations.

Crowdsourcing uses online platforms to collect large data from laypersons and has been increasingly used over the past 5 years to answer questions about aesthetic and functional outcomes following plastic and reconstructive surgery. This systematic review evaluates crowdsourcing articles in plastic and reconstructive surgery based on study topic, participants, and effect size in the hopes of describing best practices. A systematic search strategy was developed with a licensed librarian and attending plastic surgeon to query all articles using crowdsourcing in plastic and reconstructive surgery. Covidence systematic review manager was used by two independent reviewers to import articles, screen abstracts, evaluate full texts, and extract data. A search run on October 8, 2021, yielded 168 studies, of which 45 were ultimately included. Craniofacial surgery and aesthetic surgery collectively constituted over half of studies. Participants in plastic surgery crowdsourcing studies are more commonly from the United States, female, straight, 25 to 35 years old; have completed college; and earn $20,000 to $50,000 per year. Studies typically assessed aesthetic perceptions, cost approximately $350, ran a median of 9 days, included approximately 60 unique survey items, and included approximately 40 unique human images. Crowdsourcing is a relatively new, low-cost method of garnering high-volume data from laypersons that may further our understanding of public perception in plastic and reconstructive surgery. As with other nascent fields, there is significant variability in number of subjects used, subject compensation, and methodology, indicating an opportunity for quality improvement.

Design De-Identification of Thermal History for Collaborative Process-Defect Modeling of Directed Energy Deposition Processes

Abstract There is an urgent need for developing collaborative process-defect modeling in metal-based additive manufacturing (AM). This mainly stems from the high volume of training data needed to develop reliable machine learning models for in-situ anomaly detection. The requirements for large data are especially challenging for small-to-medium manufacturers (SMMs), for whom collecting copious amounts of data is usually cost prohibitive. The objective of this research is to develop a secured data sharing mechanism for directed energy deposition (DED) based AM without disclosing product design information, facilitating secured data aggregation for collaborative modeling. However, one major obstacle is the privacy concerns that arise from data sharing, since AM process data contain confidential design information, such as the printing path. The proposed adaptive design de-identification for additive manufacturing (ADDAM) methodology integrates AM process knowledge into an adaptive de-identification procedure to mask the printing trajectory information in metal-based AM thermal history, which otherwise discloses substantial printing path information. This adaptive approach applies a flexible data privacy level to each thermal image based on its similarity with the other images, facilitating better data utility preservation while protecting data privacy. A real-world case study was used to validate the proposed method based on the fabrication of two cylindrical parts using a DED process. These results are expressed as a Pareto optimal solution, demonstrating significant improvements in privacy gain and minimal utility loss. The proposed method can facilitate privacy improvements of up to 30% with as little as 0% losses in dataset utility after de-identification.

Power System Transient Stability Assessment Based on Machine Learning Algorithms and Grid Topology

This work employs machine learning methods to develop and test a technique for dynamic stability analysis of the mathematical model of a power system. A distinctive feature of the proposed method is the absence of a priori parameters of the power system model. Thus, the adaptability of the dynamic stability assessment is achieved. The selected research topic relates to the issue of changing the structure and parameters of modern power systems. The key features of modern power systems include the following: decreased total inertia caused by integration of renewable sources energy, stricter requirements for emergency control accuracy, highly digitized operation and control of power systems, and high volumes of data that describe power system operation. Arranging emergency control in these new conditions is one of the prominent problems in modern power systems. In this study, the emergency control algorithms based on ensemble machine learning algorithms (XGBoost and Random Forest) were developed for a low-inertia power system. Transient stability of a power system was analyzed as the base function. Features of transmission line maintenance were used to increase accuracy of estimation. Algorithms were tested using the test power system IEEE39. In the case of the test sample, accuracy of instability classification for XGBoost was 91.5%, while that for Random Forest was 81.6%. The accuracy of algorithms increased by 10.9% and 1.5%, respectively, when the topology of the power system was taken into account.

Data-based drivers of big data analytics utilization: moderating role of IT proactive climate

PurposeThis study uses the resource-based view (RBV) and isomorphism to investigate the influence of data-based resources (i.e. bigness of data, data accessibility (DA) and data completeness (DC)) on big data analytics (BDA) use under the moderation effect of organizational culture (i.e. IT proactive climate). It also analyzes the possible relationship between BDA implementation and value creation.Design/methodology/approachThe empirical validation of the research model was performed through a cross-sectional procedure to gather survey-based responses. The data obtained from a sample of 190 IT executives having relevant educational backgrounds and experienced in the field of big data and business analytics were analyzed using structural equation modeling.FindingsBDA usage can generate significant value if supported by proper levels of DA and DC, which are benefits obtained from the bigness of data (high volume, variety and velocity of data). In addition, data-driven benefits have stronger impacts on BDA usage in firms with higher levels of IT proactive climate.Originality/valueThe present paper has extended the existing literature as it demonstrates facilitating characteristic of data-based resources (i.e. DA and DC) on BDA implementation which can be intensified with an established IT proactive climate in the firm. Additionally, it provides further theoretical and practical insights which are illustrated ahead.

Surgeons’ perspectives on artificial intelligence to support clinical decision-making in trauma and emergency contexts: results from an international survey

BackgroundArtificial intelligence (AI) is gaining traction in medicine and surgery. AI-based applications can offer tools to examine high-volume data to inform predictive analytics that supports complex decision-making processes. Time-sensitive trauma and emergency contexts are often challenging. The study aims to investigate trauma and emergency surgeons’ knowledge and perception of using AI-based tools in clinical decision-making processes.MethodsAn online survey grounded on literature regarding AI-enabled surgical decision-making aids was created by a multidisciplinary committee and endorsed by the World Society of Emergency Surgery (WSES). The survey was advertised to 917 WSES members through the society’s website and Twitter profile.Results650 surgeons from 71 countries in five continents participated in the survey. Results depict the presence of technology enthusiasts and skeptics and surgeons' preference toward more classical decision-making aids like clinical guidelines, traditional training, and the support of their multidisciplinary colleagues. A lack of knowledge about several AI-related aspects emerges and is associated with mistrust.DiscussionThe trauma and emergency surgical community is divided into those who firmly believe in the potential of AI and those who do not understand or trust AI-enabled surgical decision-making aids. Academic societies and surgical training programs should promote a foundational, working knowledge of clinical AI.

Predicting Bike Usage and Optimizing Operations at Repair Shops in Bike Sharing Systems

Supply chain responsiveness and big data analytics (BDA) have garnered considerable interest in academia and among practitioners. BDA helps researchers understand the current challenges in data management, including the high volume, velocity, and variety of data. This study is concerned with improving the responsiveness of supply chain networks to bike-sharing systems (BSS), which exhibit BDA characteristics. To address the challenges of forecasting bike usage and accordingly optimizing repair shop operations, we analyze multi-factor BSS data (Data from Washington D.C. BSS available to public), wherein attributes, such as weather conditions, registration, humidity, date, and time, are present. We use machine learning algorithms, such as neural networks, decision-tree-based regression, K-nearest neighbor, support vectors, and ensemble random forest, to predict bike usage and repair. This work contests the results and demonstrates the effectiveness of combining machine learning with supply chain network design. Supply chain networks model bike repairs by means of capacity extensions, which entails a nonlinear problem. In this study, we utilize a gradient search to solve a nonlinear supply chain network model. By enabling capacity extension, bike repair shops within the BSS exhibit a promising 50 % reduction in lead repair time. Furthermore, a 25 % overall throughput increase in BSS is achieved. Ultimately, this study demonstrates the importance of operational flexibility in responding to big data challenges.

Adaptive Sampling Approach Exploiting Spatio-Temporal Correlation and Residual Energy in Periodic Wireless Sensor Networks

Energy limitation is a major issue in wireless sensor networks where a high volume of redundant data is collected periodically and transmitted through the network. Therefore, efficient energy consumption is the key solution to maximize the network lifetime. This paper proposes an adaptive sampling approach based on spatio-temporal correlation of collected data and on nodes residual energy. This approach aims to optimize sampling rates of sensor nodes while ensuring a high quality of the collected data. In addition, a data reconstruction method based on linear regression is adopted in the sink to reconstruct the missing samples due to the sampling rate reduction and adaptation compared to the case of a constant maximal sampling rate. We compared our approach with recently proposed adaptive sampling benchmark methods in different scenarios of data temporal correlation. Simulation results demonstrate the effectiveness of our proposed method in optimizing energy consumption by reducing the sampling rate while maintaining data quality. Our contribution can be applied to several fields, particularly, the field of water resources management.