Search

In this article, we review and compare different methods for the localization of an illuminator of opportunity for passive radar systems employing cooperative targets. For assessment and comparison, we use numerical simulations and real-world radar measurements. To achieve reliable operation under real-world conditions, a correct and robust association of the bistatic radar target observations with ground truth information is necessary. We introduce a novel solution to this issue with an efficient preprocessing algorithm based on a planar approximation.

While a range of models have been proposed for the multiperiod blend scheduling problem (MBSP), solving even medium-size MBSP instances remains challenging due to the presence of bilinear terms and binary variables. To address this challenge, we develop solution methods for MBSP focusing on the cost minimization objective. We develop a novel preprocessing algorithm to calculate lower bounds on stream flows. We define product dedicated flow variables to address product specific features involved in MBSP. Bounds on stream flows and new product dedicated flow variables are then used to generate tightening constraints which significantly improve the solution time of the mixed integer nonlinear programming models as well as models based on linear approximations.

Alzheimer's disease (AD) is the most common neurodegenerative disease in older people. Despite considerable efforts to find a cure for AD, there is a 99.6% failure rate of clinical trials for AD drugs, likely because AD patients cannot easily be identified at early stages. This project investigated machine learning approaches to predict the clinical state of patients in future years to benefit AD research. Clinical data from 1737 patients was obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database and was processed using the "All-Pairs" technique, a novel methodology created for this project involving the comparison of all possible pairs of temporal data points for each patient. This data was then used to train various machine learning models. Models were evaluated using 7-fold cross-validation on the training dataset and confirmed using data from a separate testing dataset (110 patients). A neural network model was effective (mAUC = 0.866) at predicting the progression of AD on a month-by-month basis, both in patients who were initially cognitively normal and in patients suffering from mild cognitive impairment. Such a model could be used to identify patients at early stages of AD and who are therefore good candidates for clinical trials for AD therapeutics., Comment: 10 pages; updated acknowledgements

This paper addresses the design of a parcel delivery system using drones, which includes the strategic planning of the system and operational planning for a given region. The amount of payload affects the battery consumption rate (BCR), which can cause a disruption in delivery of goods if the BCR was under-estimated in the planning stage or cause unnecessarily higher expenses if it was over-estimated. Hence, a reliable parcel delivery schedule using drones is proposed to consider the BCR as a function of payload in the operational planning optimization. A minimum set covering approach is used to model the strategic planning and a mixed integer linear programming problem (MILP) is used for operational planning. A variable preprocessing algorithm and primal and dual bound generation methods are developed to improve the computational time for solving the operational planning model. The optimal solution provides the least number of drones and their flight paths to deliver parcels while ensuring the safe return of the drones with respect to the battery charge level. Experimental data show that the BCR is a linear function of the payload amount. The results indicate the impact of including the BCR in drone scheduling, 3 out of 5 (60%) flight paths are not feasible if the BCR is not considered. The numerical results show that the sequence of visiting customers impacts the remaining charge.

In this work we focus on an extension of the minimum cost flow problem in layered networks. Feasible arc flows must satisfy a specific compatibility restriction in addition to flow balance and capacity restrictions. Namely, at most one of the crossing arcs is allowed to have positive flow on it. This variant of the minimum cost flow problem, which we call the minimum cost noncrossing flow problem, can frequently be encountered in real life. The determination of optimal temporal quay crane allocations to berthed vessels in container terminals, and optimal train schedules through the stations on the same railroad line are two examples. We first analyze the complexity of the problem and show that the noncrossing flow problem is in fact N P -complete in a layered network. Then, we introduce mixed-integer linear programming formulations and discuss a polynomially solvable special case. Next we show a sufficient condition for the existence of a crossing in an optimal solution, which can be used for preprocessing the arcs in order to reduce the problem size. Our computational experiments on a large test set show that our preprocessing algorithm can significantly reduce the number of arcs.

It is important to distinguish ALK positive lung cancer from ALK negative lung cancer and to monitor the efficacy of targeted drugs. This paper applies a microscopic hyperspectral imaging technique to identify ALK positive lung cancer cells and evaluate the therapeutic effect. The hyperspectral images of five groups of lung tissues are captured by the home-made microscopic hyperspectral imaging system. A preprocessing algorithm is proposed to reduce obvious banding noise and noise particles from original data. Then a segmentation algorithm, which assembles Supported Vector Machine (SVM) and Majority analysis together with the Clumping processing, is presented. The ALK positive and negative lung cancers can be distinguished by both the fluctuation of spectral curves and the relative proportion between cytoplasm and cell nucleus. In addition, the treatment efficacy can be surveyed in the same way. The experimental results show that the relative proportion of cytoplasm in Group ALK-neg is 77.3%, while that in Group ALK-pos is 40.6%. It is obvious that there exist differences in contents and spectra between Group ALK-neg and Group ALK-pos. Moreover, the experimental results of quantitative analysis and spectral curves analysis show that ALK positive lung cancer cells treated with the low concentration of targeted drugs will be developed towards the ALK negative lung cancer. This paper shows the potential of using hyperspectral images to detect the ALK positive lung cancer cells and evaluate the therapeutic effect of targeted drugs.

Various applications like face analysis, recognition, reidentification exist where the use of Face Detection is necessary as their preprocessing algorithm in the pipeline. There has been extensive studies done in the domain of Face Detection in the past, and various robust algorithms have been proposed and evaluated on different datasets. Such techniques are also deployed in various applications. Although it may seem that this domain is very old and much work must have been done in it, there is still room for improvement. Previous studies have targeted issues like facial poses, expressions, scales of images and occlusions, and have achieved good accuracy. In recent years, work on advanced issues like low-resolution images, usage of proposed anchors, scale-invariance of models, minimization of model size, have been explored and various solutions have been proposed. In this paper, we will discuss the state-of-the-art publications in this domain, what issues they are targeting and what technologies they are using.

Reproducibility is a cornerstone of scientific communication without which one cannot build upon each other’s work. Because modern human brain imaging relies on many integrated steps with a variety of possible algorithms, it has, however, become impossible to report every detail of a data processing workflow. In response to this analytical complexity, community recommendations are to share data analysis pipelines (scripts that implement workflows). Here we show that this can easily be done using EEGLAB and tools built around it. BIDS tools allow importing all the necessary information and create a study from electroencephalography (EEG)-Brain Imaging Data Structure compliant data. From there preprocessing can be carried out in only a few steps using EEGLAB and statistical analyses performed using the LIMO EEG plug-in. Using Wakeman and Henson (2015) face dataset, we illustrate how to prepare data and build different statistical models, a standard factorial design (faces ∗ repetition), and a more modern trial-based regression approach for the stimulus repetition effect, all in a few reproducible command lines.

Security incidents such as natural disasters and power outages can cause inter-domain routing system regional failures, significantly impact the Internet’s safety. Reducing the impact of security incidents is essential for maintaining the stability of the Internet. One of the major impacts of security incidents is that many UPDATE messages will generate, which may easily cause network oscillations. This paper presents the UPDATE messages analysis during the six security incidents and finds that many duplicates and invalid messages are the leading cause of network instability. To effectively process these UPDATE messages, this paper proposes an UPDATE message preprocessing algorithm by analyzing the UPDATE operating mechanism to remove duplicate and invalid messages. Aiming at the problem of slow route search in existing route update methods using software-defined networking (SDN), this paper designs a RIB hierarchical structure for multi-level retrieval and proposes SMSEI-SDN combination with current route update strategies. Experimental results show that when a security incident occurs, by removing duplicate and invalid messages, SMSEI-SDN can reduce the total number of messages by an average of 19% and a maximum of 34.9% within the 60 s of caching time. Besides, SMSEI-SDN can reduce the routing update time by more than 99.98% compared to existing methods. This work provides insights for network operators and researchers interested in security incident impact suppression in the inter-domain routing system.

Because of its high research value, action recognition has become a very popular research direction in recent years. However, the research on the combination of motion recognition technology and dance movements is still in its infancy. At the same time, due to the high complexity of dance movements and the problems of human body self-occlusion when performing dances, research on dance video action recognition has been caused. Progress is relatively slow. This article mainly introduces the research of sports dance action recognition system oriented to human motion monitoring and sensing, fully considers the abovementioned problems, and makes in-depth research and analysis on the current excellent action recognition research content in this field. This paper proposes a research method of sports dance movement recognition for human movement monitoring and sensing, including sports dance movement classification algorithm and sports dance movement preprocessing algorithm, which is used to conduct research experiments on sports dance movement recognition for human movement monitoring and sensing. The experimental results of this article show that the average recognition accuracy of the sports dance action recognition system for human motion monitoring and sensing is 92%, which can be used in daily sports dance training and competition.

One of the significant challenges in machine learning is the classification of imbalanceddata. In many situations, standard classifiers cannot learn how to distinguish minority classexamples from the others. Since many real problems are unbalanced, this problem has becomevery relevant and deeply studied today. This paper presents a new preprocessing method based onDelaunay tessellation and the preprocessing algorithm SMOTE (Synthetic Minority Over-samplingTechnique), which we call DTO-SMOTE (Delaunay Tessellation Oversampling SMOTE). DTO-SMOTEconstructs a mesh of simplices (in this paper, we use tetrahedrons) for creating synthetic examples.We compare results with five preprocessing algorithms (GEOMETRIC-SMOTE, SVM-SMOTE,SMOTE-BORDERLINE-1, SMOTE-BORDERLINE-2, and SMOTE), eight classification algorithms,and 61 binary-class data sets. For some classifiers, DTO-SMOTE has higher performance than othersin terms of Area Under the ROC curve (AUC), Geometric Mean (GEO), and Generalized Index ofBalanced Accuracy (IBA).

Stroke is a high-risk disease causing death, permanent disability in patients, and is the leading cause of death worldwide. Stroke can be quickly examined for disease through CT, an imaging diagnostic tool. However, the diagnosis of Ischemic Stroke using a CT image has the advantage of being able to take a picture in a short time with less restrictions in place, but there is a problem that diagnosis through an image is very difficult. In this paper, we propose a deep learning system capable of learning and classifying ischemic stroke diseases that are small datasets and difficult to learn about image data. We propose a preprocessing algorithm optimized for ischemic stroke based on Non-Contrast CT data in Middle Cerebral Artery (MCA) area.

This paper presents a novel method for automatically selecting the highest quality image sections for an underwater optical mosaic. We have constructed an image quality measure, which is used to determine the optimal seam between two overlapping images. We also present our preprocessing algorithm, which is a novel combination of existing methods. The full mosaic processing chain is demonstrated on images collected with a HUGIN autonomous underwater vehicle (AUV), using a camera system consisting of a high-sensitivity, still-image camera and a synchronized strobe with multiple light emitting diodes (LEDs).

Background A big-data-driven and artificial intelligence (AI) with machine learning (ML) approach has never been integrated with the hospital information system (HIS) for predicting major adverse cardiac events (MACE) in patients with chest pain in the emergency department (ED). Therefore, we conducted the present study to clarify it. Methods In total, 85,254 ED patients with chest pain in three hospitals between 2009 and 2018 were identified. We randomized the patients into a 70%/30% split for ML model training and testing. We used 14 clinical variables from their electronic health records to construct a random forest model with the synthetic minority oversampling technique preprocessing algorithm to predict acute myocardial infarction (AMI) Results Predicting MACE using the random forest model produced areas under the curves (AUC) of 0.915 for AMI Conclusions An AI real-time prediction model is a promising method for assisting physicians in predicting MACE in ED patients with chest pain. Further studies to evaluate the impact on clinical practice are warranted.

We study edit distance computation with preprocessing: the preprocessing algorithm acts on each string separately, and then the query algorithm takes as input the two preprocessed strings. This model is inspired by scenarios where we would like to compute edit distance between many pairs in the same pool of strings. Our results include: Permutation-LCS: If the LCS between two permutations has length $n-k$, we can compute it \textit{ exactly} with $O(n \log(n))$ preprocessing and $O(k \log(n))$ query time. Small edit distance: For general strings, if their edit distance is at most $k$, we can compute it \textit{ exactly} with $O(n\log(n))$ preprocessing and $O(k^2 \log(n))$ query time. Approximate edit distance: For the most general input, we can approximate the edit distance to within factor $(7+o(1))$ with preprocessing time $\tilde{O}(n^2)$ and query time $\tilde{O}(n^{1.5+o(1)})$. All of these results significantly improve over the state of the art in edit distance computation without preprocessing. Interestingly, by combining ideas from our algorithms with preprocessing, we provide new improved results for approximating edit distance without preprocessing in subquadratic time.

In this chapter, we extend the integrated timetabling and passenger routing problem by additionally considering line planning. This allows for a passenger focused approach to line planning where travel times can be evaluated exactly instead of approximately as in many passenger focused line planning models. In addition to the integrated problem, we present an exact preprocessing algorithm as well as two heuristics to reduce the problem size. In the computational evaluation the integrated problem as well as the methods for reducing the problem size is discussed.

In this work, we have proposed a simple overlapping community detection algorithm based on a distributed neighbourhood threshold method (DNTM). DNTM uses pre-partitioned disjoint communities and then analyzes the neighbourhood distribution of boundary nodes in disjoint communities to detect overlapping communities. It is a form of seed-based global method since boundary nodes are considered as seeds and become the starting point for detecting overlapping communities. Threshold value for each boundary node is used as minimum influence by the neighbours of a node in order to determine its belongingness to any community. The effectiveness of the DNTM algorithm has been demonstrated by testing on fifteen real-world datasets and compared with seven overlapping community detection algorithms. DNTM outperforms comparable algorithms with 10 out of 15 datasets and gives comparable results for the remaining 5 datasets in terms of the extended modularity \(Q_{ov}\) measure. Experiments with various disjoint algorithms on 15 datasets reveal that DNTM with tolerance community detection (TCD) as a preprocessing algorithm gives the best result.

Ціла низка екзогенних та ендогенних факторів чинить комплексний синергічний негативний вплив на стан серцево-судинної системи як основного адаптогена. Для його ранньої діагностики, зокрема у системах віддаленого моніторування, запропоновано використати фонокардіосигнал (синхронно зареєстрований з електрокардіосигналом), який у термінах системно-сигнальної концепції є переносником відомостей про морфофункціональний стан серця. Як модель фонокардіосигналу використано періодично корельований випадковий процес (оскільки ця модель є адекватною до природи породження сигналу) та синфазний метод опрацювання, що дало змогу врахувати вплив нервової регуляції (синусового вузла як водія ритму). Синфазний метод вимагає забезпечення однорідності статистичного матеріалу та визначення періоду корельованості вхідної послідовності, який у випадку фонокардіосигналу може бути представленим як середня тривалість серцевого циклу. Визначення його за тривалістю R-R інтервалу не дає змоги забезпечити вибірку однієї окремої реалізації, тобто інтервалу між моментами прояву дії синусового вузла, що на електрокардіограмі виявляється P-зубцем. Тому запропоновано визначати одну реалізацію серцевого циклу як інтервал P-P. Наведено процедуру попереднього опрацювання зареєстрованого сигналу за алгоритмом: детрендінг сигналу (позбавлення від тренду, постійної складової сигналу), згладжування (позбавлення від високочастотних шумів з мінімальним спотворенням спектру та зміщенням локалізацій P-зубців), знаходження періоду повторюваності за P-зубцями. Така модель фонокардіосигналу дає можливість удосконалення існуючих систем віддаленого кардіомоніторингу для виявлення змін у роботі серця на ранніх стадіях розвитку патологічного процесу шляхом упровадження нового класу інформативно-інваріантних ознак – спектральних компонент, отриманих у результаті опрацювання сигналу синфазним методом.

This research is to design an effective hybrid main memory structure for graph processing applications, because it is quite expensive to use only high-speed DRAM for such applications. Thus, we propose a DRAM-PCM hybrid main memory structure to reduce the cost and energy consumption and design regression prefetch scheme to cope with irregular access patterns in large graph processing workloads. In addition, the prefetch includes preprocessing algorithm to maximize prefetching performance. Our experimental evaluation shows a performance improvement of 36 percent over a conventional DRAM model, 15 percent over existing prefetch models such as GHB/PC, SMS, and AMPM, and 6 percent over the latest model.

The Synthetic Minority Oversampling Technique (SMOTE) preprocessing algorithm is considered "de facto" standard in the framework of learning from imbalanced data. This is due to its simplicity in the design of the procedure, as well as its robustness when applied to different type of problems. Since its publication in 2002, SMOTE has proven successful in a variety of applications from several different domains. SMOTE has also inspired several approaches to counter the issue of class imbalance, and has also significantly contributed to new supervised learning paradigms, including multilabel classification, incremental learning, semi-supervised learning, multi-instance learning, among others. It is standard benchmark for learning from imbalanced data. It is also featured in a number of different software packages - from open source to commercial. In this paper, marking the fifteen year anniversary of SMOTE, we reflect on the SMOTE journey, discuss the current state of affairs with SMOTE, its applications, and also identify the next set of challenges to extend SMOTE for Big Data problems.

Time Reversal (TR) imaging methods have recently generated considerable interest due to their robustness and ability to locate multiple targets. However, problems arise when the targets are behind an obstructing material. We develop a preprocessing algorithm for TR imaging methods to obtain images of targets hidden behind a wall, applying temporal and spatial windows on the full-Multistatic Data Matrix (MDM). By using temporal-windows, we divide the full-MDM into sub-MDMs. We further segment the sub-MDMs spatially by selecting its elements corresponding to a predetermined number of antennas in space.We take the singular value decomposition of the sub-MDMs to obtain singular value distributions as well as singular vectors which we analyse individually and use for the MUltiple SIgnal Classification (MUSIC) TR imaging method. The obtained images from the these localised sub-MDMs collectively yield to clearerimages of scenarios than we can obtain using the full-MDM.

Datasets are the backbone for data mining and knowledge engineering field to build an excellent classification model. However, the learning model usually follows a significantly biased distribution of classes. It is known as a class imbalance. The class imbalance problem exists in many real-time datasets. The main objective of this research is to fix an adaptive threshold based on class data and fit that data into models that can be understood and utilized by ordinal multiclass imbalanced scenario for improving the predictive accuracy. The methodology utilizes Laplace-Gauss based SMOTE method for synthesizing sophisticated objects of minority classes. Dynamic parameters are adapted for SMOTE algorithm by utilizing the underlying class information. On the whole, the dataset is divided into training and test data. Training dataset is updated with new synthetic patterns. The experimental analysis is performed on testing dataset to check the efficiency of the proposed methodology by comparing it with the existing methodology. The performance evaluation is conducted in terms of the measures called Mean Absolute Error (MAE), 154Maximum Mean Absolute Error (MMAE), Geometric Mean (GM), Kappa, and Average Accuracy. The Experimental results prove that the proposed methodology can produce authentic synthetic patterns than the existing method. The proposed method can synthesize the new effective patterns with the help of dynamic parameter setting. It upgrades the global precision and class-wise precision especially preserves rank order of the classes.

In this paper, we propose a structure of a portable cardiograph. Contents and functions of all blocks are overviewed. We describe two main structures of portable cardiographs, prepare a comparative table of characteristics for different analog front-ends. All individual features of the chips are listed as well. We register a test signal and try to improve its quality by means of digital filtration, taking the signal gained from certified Biopack equipment as a reference. We calculate device power consumption to compute required battery volume. Finally, energy efficient preprocessing algorithm is proposed.

In order to better assess the health of the human body and protect people from disease, this study designs a wearable glasses system based on pulse signal preprocessing algorithm, pulse rate calculation algorithm and motion recognition algorithm. The pulse data before and after exercise are used to analyze the health status of the human body. Finally, the performance in various aspects of the system was verified by relevant experiments. The results show that the system is feasible. It can be seen that the system can be used for the assessment of human health conditions, and it is expected to serve people well in the future and make people live a healthier life.

In this paper, a new preprocessing algorithm to qualify images of different pollen grains for further processing is proposed. This algorithm provides a score related to the sharpness of the image and will be used to automatically adjust the focal length of a microscope that magnifies the image. The obtained score has been compared to four quality metrics generally used to estimate the clarity of an image and to a reference made by a human. The results of the simulations show that the proposed algorithm combines better performance with low complexity on the set of images.

With the development of information society, biometrics technology has been paid more and more attention. Iris recognition is considered as the most promising biometric authentication technology in the 21st century because of its uniqueness, stability and non-creativity. However, due to the high cost of iris recognition equipment and some defects of the algorithm, iris recognition cannot be applied in real life on a large scale. In this paper, a fast localization iris recognition algorithm is proposed, which combines the iris segmentation algorithm with deep learning to quickly extract the iris region for recognition. Firstly, the pupil edge was extracted by dynamic threshold analysis and contour extraction, and then iris was located by edge detection and gray calculation. Finally, features of normalized images were learned by deep learning network. Experiments show that the method can guarantee the accuracy and efficiency of iris segmentation and has a high degree of recognition and matching.

Personal laser scanning (PLS) has significant potential for estimating the in-situ diameter of breast height (DBH) with high efficiency and precision, which improves the understanding of forest structure and aids in building carbon cycle models in the big data era. PLS collects more complete stem point cloud data compared with the present laser scanning technology. However, there is still no significant advantage of DBH estimation accuracy. Because the error caused by merging different point cloud fragments has not yet been eliminated, overlapping and inaccurate co-registered point cloud fragments are often inevitable, which are usually the leading error sources of PLS-based DBH estimation. In this study, a novel pre-processing algorithm named annular neighboring points distribution analysis (ANPDA) was developed to improve PLS-based DBH estimation accuracy. To reduce the impact of inaccurately co-registered point cloud fragments, ANPDA identified outliers through iterative removal of outermost points and analyzing the distribution of annular neighboring points. Six plots containing 247 trees under different forest conditions were selected to evaluate the ANPDA. Results showed that in the six plots, error reductions of 53.80&ndash, 87.13% for bias, 38.82&ndash, 57.30% for mean absolute error (MAE), and 27.17&ndash, 56.02% for root mean squared error (RMSE) were achieved after applying ANPDA. These results confirmed that ANPDA was generally effective for improving PLS-based DBH estimation accuracy. It appeared that ANPDA could be conveniently fused with an automatic PLS-based DBH estimation process as a preprocessing algorithm. Furthermore, it has the potential to predict and warn operators of potential large errors during hierarchical semi-automatic DBH estimation.