Showing papers in "Scientific Programming in 2020"

Object Detection through Modified YOLO Neural Network

Abstract: In the field of object detection, recently, tremendous success is achieved, but still it is a very challenging task to detect and identify objects accurately with fast speed. Human beings can detect and recognize multiple objects in images or videos with ease regardless of the object’s appearance, but for computers it is challenging to identify and distinguish between things. In this paper, a modified YOLOv1 based neural network is proposed for object detection. The new neural network model has been improved in the following ways. Firstly, modification is made to the loss function of the YOLOv1 network. The improved model replaces the margin style with proportion style. Compared to the old loss function, the new is more flexible and more reasonable in optimizing the network error. Secondly, a spatial pyramid pooling layer is added; thirdly, an inception model with a convolution kernel of 1 1 is added, which reduced the number of weight parameters of the layers. Extensive experiments on Pascal VOC datasets 2007/2012 showed that the proposed method achieved better performance.

Image Classification Algorithm Based on Deep Learning-Kernel Function

Abstract: Although the existing traditional image classification methods have been widely applied in practical problems, there are some problems in the application process, such as unsatisfactory effects, low classification accuracy, and weak adaptive ability. This method separates image feature extraction and classification into two steps for classification operation. The deep learning model has a powerful learning ability, which integrates the feature extraction and classification process into a whole to complete the image classification test, which can effectively improve the image classification accuracy. However, this method has the following problems in the application process: first, it is impossible to effectively approximate the complex functions in the deep learning model. Second, the deep learning model comes with a low classifier with low accuracy. So, this paper introduces the idea of sparse representation into the architecture of the deep learning network and comprehensively utilizes the sparse representation of well multidimensional data linear decomposition ability and the deep structural advantages of multilayer nonlinear mapping to complete the complex function approximation in the deep learning model. And a sparse representation classification method based on the optimized kernel function is proposed to replace the classifier in the deep learning model, thereby improving the image classification effect. Therefore, this paper proposes an image classification algorithm based on the stacked sparse coding depth learning model-optimized kernel function nonnegative sparse representation. The experimental results show that the proposed method not only has a higher average accuracy than other mainstream methods but also can be good adapted to various image databases. Compared with other deep learning methods, it can better solve the problems of complex function approximation and poor classifier effect, thus further improving image classification accuracy.

A Fortran-Keras Deep Learning Bridge for Scientific Computing

Abstract: Implementing artificial neural networks is commonly achieved via high-level programming languages such as Python and easy-to-use deep learning libraries such as Keras. These software libraries come preloaded with a variety of network architectures, provide autodifferentiation, and support GPUs for fast and efficient computation. As a result, a deep learning practitioner will favor training a neural network model in Python, where these tools are readily available. However, many large-scale scientific computation projects are written in Fortran, making it difficult to integrate with modern deep learning methods. To alleviate this problem, we introduce a software library, the Fortran-Keras Bridge (FKB). This two-way bridge connects environments where deep learning resources are plentiful with those where they are scarce. The paper describes several unique features offered by FKB, such as customizable layers, loss functions, and network ensembles. The paper concludes with a case study that applies FKB to address open questions about the robustness of an experimental approach to global climate simulation, in which subgrid physics are outsourced to deep neural network emulators. In this context, FKB enables a hyperparameter search of one hundred plus candidate models of subgrid cloud and radiation physics, initially implemented in Keras, to be transferred and used in Fortran. Such a process allows the model’s emergent behavior to be assessed, i.e., when fit imperfections are coupled to explicit planetary-scale fluid dynamics. The results reveal a previously unrecognized strong relationship between offline validation error and online performance, in which the choice of the optimizer proves unexpectedly critical. This in turn reveals many new neural network architectures that produce considerable improvements in climate model stability including some with reduced error, for an especially challenging training dataset.

Improved Chaos-Based Cryptosystem for Medical Image Encryption and Decryption

Abstract: In the medical sector, the digital image is multimedia data that contain secret information. However, designing an efficient secure cryptosystem to protect the confidential images in sharing is a challenge. In this work, we propose an improved chaos-based cryptosystem to encrypt and decrypt rapidly secret medical images. A complex chaos-based PRNG is suggested to generate a high-quality key that presents high randomness behaviour, high entropy, and high complexity. An improved architecture is proposed to encrypt the secret image that is based on permutation, substitution, and diffusion properties. In the first step, the image’s pixels are randomly permuted through a matrix generated using the PRNG. Next, pixel’s bits are permuted using an internal condition. After that, the pixels are substituted using two different S-boxes with an internal condition. In the final step, the image is diffused by XORing pixels with the key stream generated by the PRNG in order to acquire an encrypted image. R rounds of encryption can be performed in a loop to increase the complexity. The cryptosystem is evaluated in depth by his application on several medical images with different types, contents, and sizes. The obtained simulation results demonstrate that the system enables high-level security and performance. The information entropy of the encrypted image has achieved an average of 7.9998 which is the most important feature of randomness. The algorithm can take full advantage of parallelism and pipeline execution in hardware implementation to meet real-time requirements. The PRNG was tested by NIST 800-22 test suit, which indicates that it is suitable for secure image encryption. It provides a large key space of 2192 which resists the brute-force attack. However, the cryptosystem is appropriate for medical image securing.

An Intelligent, Secure, and Smart Home Automation System

Abstract: The idea of a smart home is getting attention for the last few years. The key challenges in a smart home are intelligent decision making, secure identification, and authentication of the IoT devices, continuous connectivity, data security, and privacy issues. The existing systems are targeting one or two of these issues whereas a smart home automation system that is not only secure but also has intelligent decision making and analytical abilities is the need of time. In this paper, we present a novel idea of a smart home that uses a machine learning algorithm (Support Vector Machine) for intelligent decision making and also uses blockchain technology to ensure identification and authentication of the IoT devices. Emerging blockchain technology plays a vital role by providing a reliable, secure, and decentralized mechanism for identification and authentication of the IoT devices used in the proposed home automation system. Moreover, the SVM classifier is applied to classify the status of devices used in the proposed smart home automation system into one of the two categories, i.e., “ON” and “OFF.” This system is based on Raspberry Pi, 5 V relay circuit, and some sensors. A mobile application is developed using the Android platform. Raspberry Pi acting as the server maintains the database of each appliance. The HTTP web interface and apache server are used for communication among the Android app and Raspberry Pi. The proposed idea is tested in the lab and real life to validate its effectiveness and usefulness. It is also ensured that the hardware and technology used in the proposed idea are cheap, easily available, and replicable. The experimental results highlight its significance and validate the proof of the concept.

Android Malware Detection Using Fine-Grained Features

Abstract: Nowadays, Android applications declare as many permissions as possible to provide more function for the users, which also poses severe security threat to them. Although many Android malware detection methods based on permissions have been developed, they are ineffective when malicious applications declare few dangerous permissions or when the dangerous permissions declared by malicious applications are similar with those declared by benign applications. This limitation is attributed to the use of too few information for classification. We propose a new method named fine-grained dangerous permission (FDP) method for detecting Android malicious applications, which gathers features that better represent the difference between malicious applications and benign applications. Among these features, the fine-grained feature of dangerous permissions applied in components is proposed for the first time. We evaluate 1700 benign applications and 1600 malicious applications and demonstrate that FDP achieves a TP rate of 94.5%. Furthermore, compared with other related detection approaches, FDP can detect more malware families and only requires 15.205 s to analyze one application on average, which demonstrates its applicability for practical implementation.

Machine learning for the preliminary diagnosis of dementia

Abstract: Objective. The reliable diagnosis remains a challenging issue in the early stages of dementia. We aimed to develop and validate a new method based on machine learning to help the preliminary diagnosis of normal, mild cognitive impairment (MCI), very mild dementia (VMD), and dementia using an informant-based questionnaire. Methods. We enrolled 5,272 individuals who filled out a 37-item questionnaire. In order to select the most important features, three different techniques of feature selection were tested. Then, the top features combined with six classification algorithms were used to develop the diagnostic models. Results. Information Gain was the most effective among the three feature selection methods. The Naive Bayes algorithm performed the best (accuracy = 0.81, precision = 0.82, recall = 0.81, and F-measure = 0.81) among the six classification models. Conclusion. The diagnostic model proposed in this paper provides a powerful tool for clinicians to diagnose the early stages of dementia.

An Intelligent IoT Based Healthcare System Using Fuzzy Neural Networks

Abstract: Healthcare facilities in modern age are key challenge especially in developing countries where remote areas face lack of high-quality hospitals and medical experts. As artificial intelligence has revolutionized various fields of life, health has also benefited from it. The existing architecture of store-and-forward method of conventional telemedicine is facing some problems, some of which are the need for a local health center with dedicated staff, need for medical equipment to prepare patient reports, time constraint of 24–48 hours in receiving diagnosis and medication details from a medical expert in a main hospital, cost of local health centers, and need for Wi-Fi connection. In this paper, we introduce a novel and intelligent healthcare system that is based on modern technologies like Internet of things (IoT) and machine learning. This system is intelligent enough to sense and process a patient’s data through a medical decision support system. This system is low-cost solution for the people of remote areas; they can use it to find out whether they are suffering from a serious health issue and cure it accordingly by contacting near hospitals. The results of the experiments also show that the proposed system is efficient and intelligent enough to provide health facilities. The results presented in this paper are the proof of the concept.

Fingerspelling Identification for Chinese Sign Language via AlexNet-Based Transfer Learning and Adam Optimizer

Abstract: As an important component of universal sign language and the basis of other sign language learning, finger sign language is of great significance. This paper proposed a novel fingerspelling identification method for Chinese Sign Language via AlexNet-based transfer learning and Adam optimizer, which tested four different configurations of transfer learning. Besides, in the experiment, Adam algorithm was compared with stochastic gradient descent with momentum (SGDM) and root mean square propagation (RMSProp) algorithms, and comparison of using data augmentation (DA) against not using DA was executed to pursue higher performance. Finally, the best accuracy of 91.48% and average accuracy of 89.48 ± 1.16% were yielded by configuration M1 (replacing the last FCL8) with Adam algorithm and using 181x DA, which indicates that our method can identify Chinese finger sign language effectively and stably. Meanwhile, the proposed method is superior to other five state-of-the-art approaches.

CenterFace: Joint Face Detection and Alignment Using Face as Point

Abstract: Face detection and alignment in unconstrained environment is always deployed on edge devices which have limited memory storage and low computing power This paper proposes a one-stage method named CenterFace to simultaneously predict facial box and landmark location with real-time speed and high accuracy The proposed method also belongs to the anchor-free category This is achieved by (a) learning face existing possibility by the semantic maps, (b) learning bounding box, offsets, and five landmarks for each position that potentially contains a face Specifically, the method can run in real time on a single CPU core and 200 FPS using NVIDIA 2080TI for VGA-resolution images and can simultaneously achieve superior accuracy (WIDER FACE Val/Test-Easy: 0935/0932, Medium: 0924/0921, Hard: 0875/0873, and FDDB discontinuous: 0980 and continuous: 0732)

Detecting Citrus in Orchard Environment by Using Improved YOLOv4

Abstract: Real-time detection of fruits in orchard environments is one of crucial techniques for many precision agriculture applications, including yield estimation and automatic harvesting. Due to the complex conditions, such as different growth periods and occlusion among leaves and fruits, detecting fruits in natural environments is a considerable challenge. A rapid citrus recognition method by improving the state-of-the-art You Only Look Once version 4 (YOLOv4) detector is proposed in this paper. Kinect V2 camera was used to collect RGB images of citrus trees. The Canopy algorithm and the K-Means++ algorithm were then used to automatically select the number and size of the prior frames from these RGB images. An improved YOLOv4 network structure was proposed to better detect smaller citrus under complex backgrounds. Finally, the trained network model was used for sparse training, pruning unimportant channels or network layers in the network, and fine-tuning the parameters of the pruned model to restore some of the recognition accuracy. The experimental results show that the improved YOLOv4 detector works well for detecting different growth periods of citrus in a natural environment, with an average increase in accuracy of 3.15% (from 92.89% to 96.04%). This result is superior to the original YOLOv4, YOLOv3, and Faster R-CNN. The average detection time of this model is 0.06 s per frame at 1920 × 1080 resolution. The proposed method is suitable for the rapid detection of the type and location of citrus in natural environments and can be applied to the application of citrus picking and yield evaluation in actual orchards.

A Systematic Review of Healthcare Big Data

Abstract: Over the past decade, data recorded (due to digitization) in healthcare sectors have continued to increase, intriguing the thought about big data in healthcare. There already exists plenty of information, ready for analysis. Researchers are always putting their best effort to find valuable insight from the healthcare big data for quality medical services. This article provides a systematic review study on healthcare big data based on the systematic literature review (SLR) protocol. In particular, the present study highlights some valuable research aspects on healthcare big data, evaluating 34 journal articles (between 2015 and 2019) according to the defined inclusion-exclusion criteria. More specifically, the present study focuses to determine the extent of healthcare big data analytics together with its applications and challenges in healthcare adoption. Besides, the article discusses big data produced by these healthcare systems, big data characteristics, and various issues in dealing with big data, as well as how big data analytics contributes to achieve a meaningful insight on these data set. In short, the article summarizes the existing literature based on healthcare big data, and it also helps the researchers with a foundation for future study in healthcare contexts.

A Neural Network Based Intelligent Support Model for Program Code Completion

Abstract: In recent years, millions of source codes are generated in different languages on a daily basis all over the world. A deep neural network-based intelligent support model for source code completion would be a great advantage in software engineering and programming education fields. Vast numbers of syntax, logical, and other critical errors that cannot be detected by normal compilers continue to exist in source codes, and the development of an intelligent evaluation methodology that does not rely on manual compilation has become essential. Even experienced programmers often find it necessary to analyze an entire program in order to find a single error and are thus being forced to waste valuable time debugging their source codes. With this point in mind, we proposed an intelligent model that is based on long short-term memory (LSTM) and combined it with an attention mechanism for source code completion. Thus, the proposed model can detect source code errors with locations and then predict the correct words. In addition, the proposed model can classify the source codes as to whether they are erroneous or not. We trained our proposed model using the source code and then evaluated the performance. All of the data used in our experiments were extracted from Aizu Online Judge (AOJ) system. The experimental results obtained show that the accuracy in terms of error detection and prediction of our proposed model approximately is 62% and source code classification accuracy is approximately 96% which outperformed a standard LSTM and other state-of-the-art models. Moreover, in comparison to state-of-the-art models, our proposed model achieved an interesting level of success in terms of error detection, prediction, and classification when applied to long source code sequences. Overall, these experimental results indicate the usefulness of our proposed model in software engineering and programming education arena.

Yeme Tutum Testi Kısa Formunun (YTT-26) Üniversite Örnekleminde Türkçeye Uyarlanması ve Psikometrik Özelliklerinin Değerlendirilmesi

Abstract: Determining risk groups is an essential element of preventive studies in eating disorders. In this regard, the Eating Attitudes Test Short Form developed by Garner, Olmstad, Bohr, & Garfinkel (1982) is the most commonly used scale all around the world. Hence, the aim of this study is to investigate the psychometric properties of the Turkish version of Eating Attitudes Test-26 (EAT-26). A total of fifteen hundred voluntary college students (1000 in the first phase for exploratory factor analyses and 500 in the second phase for confirmatory factor analyses and other validity and reliability analyses) enrolled in the study. The Eating Attitudes Test-40 (EAT-40), Brief Symptom Inventory, and Eating Disorders Examination Questionnaire were used for analyzing the validity of EAT-26. Concurrent validity, discriminant validity, and factor analyses were calculated. In terms of reliability, Cronbach’s Alpha Coefficient Analyses and test-retest methods were used. Exploratory factor analyses showed that the items of EAT-26 loaded on three factors that explained 38.5% of total variance. These factors are Preoccupation with eating, Restriction, and Social Pressure. Confirmatory factor analyses of these three factors yielded close to acceptable goodness of fit values. EAT-26 was significantly correlated with Eating Attitudes Test-40, EAT-26, and Brief Symptom Inventory in a positive direction. Participants with a higher score in EAT-26 reported significantly higher scores in the Eating Disorder Examination Questionnaire and Brief Symptom Inventory. The Turkish version of Eating Attitudes Test-26 demonstrated good internal consistency (Cronbach’s Alpha = .84), and the test re-test reliability was .78. The study provides initial support for the reliability and validity of the Turkish version of EAT-26. Nevertheless, future research is needed for the crossvalidation of Eating Attitudes Test-26 in clinical samples.

Fuzzy Multicriteria Decision-Making Approach for Measuring the Possibility of Cloud Adoption for Software Testing

Abstract: To reduce costs and improve organizational efficiency, the adoption of innovative services such as Cloud services is the current trend in today’s highly competitive global business venture. The aim...

AIoT-Based Smart Bin for Real-Time Monitoring and Management of Solid Waste

Abstract: In the current time, the immense growth in population creates unhygienic environment for the citizen of a society with respect to waste generation. This rapid generation of waste leads to various infectious diseases in the environment. As followed by the traditional municipal system, in our surroundings, we can see over flooding of solid waste in the garbage bins. Solid waste management is a pivotal aspect in traditional systems and it is becoming dangerous in most populated areas. Arduous labor works and costs are required to manage and monitor garbage bins in real time. To maintain the cleanliness of a city and for real-time monitoring of trash bins, a smart bin mechanism (SBM) for smart cities is proposed in this paper, which is based on Artificial Intelligent of Things (AIoT). The SBM works on the 3R concept, that is, Reduce, Recycle, and Reuse. The SBM has the access to get real-time information about each bin and avoid overloading of these bins. The proposed framework reduces the labor cost and saves time and energy of the system. It also reduces the rate of disease infections by keeping the cities clean. Fuzzy logic is used for decision-making in selecting appropriate locations in the cities to install trash bins. The framework is implemented in the multiagent modeling environment, that is, NetLogo.

Deep RetinaNet for Dynamic Left Ventricle Detection in Multiview Echocardiography Classification

Abstract: Background. Currently, echocardiography has become an essential technology for the diagnosis of cardiovascular diseases. Accurate classification of apical two-chamber (A2C), apical three-chamber (A3C), and apical four-chamber (A4C) views and the precise detection of the left ventricle can significantly reduce the workload of clinicians and improve the reproducibility of left ventricle segmentation. In addition, left ventricle detection is significant for the three-dimensional reconstruction of the heart chambers. Method. RetinaNet is a one-stage object detection algorithm that can achieve high accuracy and efficiency at the same time. RetinaNet is mainly composed of the residual network (ResNet), the feature pyramid network (FPN), and two fully convolutional networks (FCNs); one FCN is for the classification task, and the other is for the border regression task. Results. In this paper, we use the classification subnetwork to classify A2C, A3C, and A4C images and use the regression subnetworks to detect the left ventricle simultaneously. We display not only the position of the left ventricle on the test image but also the view category on the image, which will facilitate the diagnosis. We used the mean intersection-over-union (mIOU) as an index to measure the performance of left ventricle detection and the accuracy as an index to measure the effect of the classification of the three different views. Our study shows that both classification and detection effects are noteworthy. The classification accuracy rates of A2C, A3C, and A4C are 1.000, 0.935, and 0.989, respectively. The mIOU values of A2C, A3C, and A4C are 0.858, 0.794, and 0.838, respectively.

Online Path Generation and Navigation for Swarms of UAVs

Abstract: With the growing popularity of unmanned aerial vehicles (UAVs) for consumer applications, the number of accidents involving UAVs is also increasing rapidly. Therefore, motion safety of UAVs has become a prime concern for UAV operators. For a swarm of UAVs, a safe operation cannot be guaranteed without preventing the UAVs from colliding with one another and with static and dynamically appearing, moving obstacles in the flying zone. In this paper, we present an online, collision-free path generation and navigation system for swarms of UAVs. The proposed system uses geographical locations of the UAVs and of the successfully detected, static, and moving obstacles to predict and avoid the following: (1) UAV-to-UAV collisions, (2) UAV-to-static-obstacle collisions, and (3) UAV-to-moving-obstacle collisions. Our collision prediction approach leverages efficient runtime monitoring and complex event processing (CEP) to make timely predictions. A distinctive feature of the proposed system is its ability to foresee potential collisions and proactively find best ways to avoid predicted collisions in order to ensure safety of the entire swarm. We also present a simulation-based implementation of the proposed system along with an experimental evaluation involving a series of experiments and compare our results with the results of four existing approaches. The results show that the proposed system successfully predicts and avoids all three kinds of collisions in an online manner. Moreover, it generates safe and efficient UAV routes, efficiently scales to large-sized problem instances, and is suitable for cluttered flying zones and for scenarios involving high risks of UAV collisions.

A Task Scheduling Strategy in Edge-Cloud Collaborative Scenario Based on Deadline

Abstract: Task scheduling plays a critical role in the performance of the edge-cloud collaborative. Whether the task is executed in the cloud and how it is scheduled in the cloud is an important issue. On the basis of satisfying the delay, this paper will schedule tasks on edge devices or cloud and present a task scheduling algorithm for tasks that need to be transferred to the cloud based on the catastrophic genetic algorithm (CGA) to achieve global optimum. The algorithm quantifies the total task completion time and the penalty factor as a fitness function. By improving the roulette selection strategy, optimizing mutation and crossover operator, and introducing cataclysm strategy, the search scope is expanded. Furthermore, the premature problem of the evolutionary algorithm is effectively alleviated. The experimental results show that the algorithm can address the optimal local issue while significantly shortening the task completion time on the basis of satisfying tasks delays.

Named Entity Recognition in Chinese Medical Literature Using Pretraining Models

Abstract: The medical literature contains valuable knowledge, such as the clinical symptoms, diagnosis, and treatments of a particular disease. Named Entity Recognition (NER) is the initial step in extracting this knowledge from unstructured text and presenting it as a Knowledge Graph (KG). However, the previous approaches of NER have often suffered from small-scale human-labelled training data. Furthermore, extracting knowledge from Chinese medical literature is a more complex task because there is no segmentation between Chinese characters. Recently, the pretraining models, which obtain representations with the prior semantic knowledge on large-scale unlabelled corpora, have achieved state-of-the-art results for a wide variety of Natural Language Processing (NLP) tasks. However, the capabilities of pretraining models have not been fully exploited, and applications of other pretraining models except BERT in specific domains, such as NER in Chinese medical literature, are also of interest. In this paper, we enhance the performance of NER in Chinese medical literature using pretraining models. First, we propose a method of data augmentation by replacing the words in the training set with synonyms through the Mask Language Model (MLM), which is a pretraining task. Then, we consider NER as the downstream task of the pretraining model and transfer the prior semantic knowledge obtained during pretraining to it. Finally, we conduct experiments to compare the performances of six pretraining models (BERT, BERT-WWM, BERT-WWM-EXT, ERNIE, ERNIE-tiny, and RoBERTa) in recognizing named entities from Chinese medical literature. The effects of feature extraction and fine-tuning, as well as different downstream model structures, are also explored. Experimental results demonstrate that the method of data augmentation we proposed can obtain meaningful improvements in the performance of recognition. Besides, RoBERTa-CRF achieves the highest F1-score compared with the previous methods and other pretraining models.

A comparative analysis of NSGA-II and NSGA-III for autoscaling parameter sweep experiments in the cloud

Abstract: Fil: Yannibelli, Virginia Daniela. Consejo Nacional de Investigaciones Cientificas y Tecnicas. Centro Cientifico Tecnologico Conicet - Tandil. Instituto Superior de Ingenieria del Software. Universidad Nacional del Centro de la Provincia de Buenos Aires. Instituto Superior de Ingenieria del Software; Argentina

Detection and Classification of Early Decay on Blueberry Based on Improved Deep Residual 3D Convolutional Neural Network in Hyperspectral Images

Abstract: Recently, the automatic detection of decayed blueberries is still a challenge in food industry. Early decay of blueberries happens on surface peel, which may adopt the feasibility of hyperspectral imaging mode to detect decayed region of blueberries. An improved deep residual 3D convolutional neural network (3D-CNN) framework is proposed for hyperspectral images classification so as to realize fast training, classification, and parameter optimization. Rich spectral and spatial features can be rapidly extracted from samples of complete hyperspectral images using our proposed network. This combines the tree structured Parzen estimator (TPE) adaptively and selects the super parameters to optimize the network performance. In addition, aiming at the problem of few samples, this paper proposes a novel strategy to enhance the hyperspectral image sample data, which can improve the training effect. Experimental results on the standard hyperspectral blueberry datasets show that the proposed framework improves the classification accuracy compared with AlexNet and GoogleNet. In addition, our proposed network reduces the number of parameters by half and the training time by about 10%.

Face Detection and Recognition Based on Visual Attention Mechanism Guidance Model in Unrestricted Posture

Abstract: Performance of face detection and recognition is affected and damaged because occlusion often leads to missed detection. To reduce the recognition accuracy caused by facial occlusion and enhance the accuracy of face detection, a visual attention mechanism guidance model is proposed in this paper, which uses the visual attention mechanism to guide the model highlight the visible area of the occluded face; the face detection problem is simplified into the high-level semantic feature detection problem through the improved analytical network, and the location and scale of the face are predicted by the activation map to avoid additional parameter settings. A large number of simulation experiment results show that our proposed method is superior to other comparison algorithms for the accuracy of occlusion face detection and recognition on the face database. In addition, our proposed method achieves a better balance between detection accuracy and speed, which can be used in the field of security surveillance.

QuPiD Attack: Machine Learning-Based Privacy Quantification Mechanism for PIR Protocols in Health-Related Web Search

Abstract: With the advancement in ICT, web search engines have become a preferred source to find health-related information published over the Internet. Google alone receives more than one billion health-related queries on a daily basis. However, in order to provide the results most relevant to the user, WSEs maintain the users’ profiles. These profiles may contain private and sensitive information such as the user’s health condition, disease status, and others. Health-related queries contain privacy-sensitive information that may infringe user’s privacy, as the identity of a user is exposed and may be misused by the WSE and third parties. This raises serious concerns since the identity of a user is exposed and may be misused by third parties. One well-known solution to preserve privacy involves issuing the queries via peer-to-peer private information retrieval protocol, such as useless user profile (UUP), thereby hiding the user’s identity from the WSE. This paper investigates the level of protection offered by UUP. For this purpose, we present QuPiD (query profile distance) attack: a machine learning-based attack that evaluates the effectiveness of UUP in privacy protection. QuPiD attack determines the distance between the user’s profile (web search history) and upcoming query using our proposed novel feature vector. The experiments were conducted using ten classification algorithms belonging to the tree-based, rule-based, lazy learner, metaheuristic, and Bayesian families for the sake of comparison. Furthermore, two subsets of an America Online dataset (noisy and clean datasets) were used for experimentation. The results show that the proposed QuPiD attack associates more than 70% queries to the correct user with a precision of over 72% for the clean dataset, while for the noisy dataset, the proposed QuPiD attack associates more than 40% queries to the correct user with 70% precision.

A Statistical Tool to Generate Potential Future Climate Scenarios for Hydrology Applications

Abstract: Global warming associated with greenhouse emissions will modify the availability of water resources in the future Methodologies and tools to assess the impacts of climate change are useful for policy making In this work, a new tool to generate potential future climate scenarios in a water resources system from historical and regional climate models’ information has been developed The GROUNDS tool allows generation of the future series of precipitation, temperature (minimum, mean, and maximum), and potential evapotranspiration It is a valuable tool for assessing the impacts of climate change in hydrological applications since these variables play a significant role in the water cycle, and it can be applicable to any case study The tool uses different approaches and statistical correction techniques to generate individual local projections and ensembles of them The non-equifeasible ensembles are created by combining the individual projections whose control or corrected control simulation has a better fit to the historical series in terms of basic and droughts statistics In this work, the tool is presented, and the methodology implemented is described It is also applied to a case study to illustrate how the tool works The tool was previously tested in different typologies of water resources systems that cover different spatial scales (river basin, aquifer, mountain range, and country), obtaining satisfactory results The local future scenarios can be propagated through appropriate hydrological models to study the impacts on other variables (eg, aquifer recharge, chloride concentration in coastal aquifers, streamflow, snow cover area, and snow depth) The tool is also useful in quantifying the uncertainties of the future scenarios by combining them with stochastic weather generators

Adaptive CU Split Decision Based on Deep Learning and Multifeature Fusion for H.266/VVC

Abstract: With the development of technology, the hardware requirement and expectations of user for visual enjoyment are getting higher and higher. The multitype tree (MTT) architecture is proposed by the Joint Video Experts Team (JVET). Therefore, it is necessary to determine not only coding unit (CU) depth but also its split mode in the H.266/Versatile Video Coding (H.266/VVC). Although H.266/VVC achieves significant coding performance on the basis of H.265/High Efficiency Video Coding (H.265/HEVC), it causes significantly coding complexity and increases coding time, where the most time-consuming part is traversal calculation rate-distortion (RD) of CU. To solve these problems, this paper proposes an adaptive CU split decision method based on deep learning and multifeature fusion. Firstly, we develop a texture classification model based on threshold to recognize complex and homogeneous CU. Secondly, if the complex CUs belong to edge CU, a Convolutional Neural Network (CNN) structure based on multifeature fusion is utilized to classify CU. Otherwise, an adaptive CNN structure is used to classify CUs. Finally, the division of CU is determined by the trained network and the parameters of CU. When the complex CUs are split, the above two CNN schemes can successfully process the training samples and terminate the rate-distortion optimization (RDO) calculation for some CUs. The experimental results indicate that the proposed method reduces the computational complexity and saves 39.39% encoding time, thereby achieving fast encoding in H.266/VVC.

Survey of Methodologies, Approaches, and Challenges in Parallel Programming Using High-Performance Computing Systems

Abstract: This paper provides a review of contemporary methodologies and APIs for parallel programming, with representative technologies selected in terms of target system type (shared memory, distributed, and hybrid), communication patterns (one-sided and two-sided), and programming abstraction level. We analyze representatives in terms of many aspects including programming model, languages, supported platforms, license, optimization goals, ease of programming, debugging, deployment, portability, level of parallelism, constructs enabling parallelism and synchronization, features introduced in recent versions indicating trends, support for hybridity in parallel execution, and disadvantages. Such detailed analysis has led us to the identification of trends in high-performance computing and of the challenges to be addressed in the near future. It can help to shape future versions of programming standards, select technologies best matching programmers’ needs, and avoid potential difficulties while using high-performance computing systems.

Identifying Ethnics of People through Face Recognition: A Deep CNN Approach

Abstract: The interest in face recognition studies has grown rapidly in the last decade. One of the most important problems in face recognition is the identification of ethnics of people. In this study, a new deep learning convolutional neural network is designed to create a new model that can recognize the ethnics of people through their facial features. The new dataset for ethnics of people consists of 3141 images collected from three different nationalities. To the best of our knowledge, this is the first image dataset collected for the ethnics of people and that dataset will be available for the research community. The new model was compared with two state-of-the-art models, VGG and Inception V3, and the validation accuracy was calculated for each convolutional neural network. The generated models have been tested through several images of people, and the results show that the best performance was achieved by our model with a verification accuracy of 96.9%.

The Literature Review of Platform Economy

Abstract: Since the 1990s, the increasing development of digital-driven technologies such as the Internet, cloud computing, big data, and the Internet of Things and the popularization of computers and mobile electronic devices have accelerated the evolution of global business organizations, thus making a new form of business organization, platform economy. As the most important form of industrial organization in the new economic era, the development of the platform has received extensive attention from the academia. Through literature analysis and inductive deduction, this paper reviews the connotation of platform economy, the historical context of development, the competition and monopoly (differentiation) of multilateral platforms, the evaluation mechanism of platform, antimonopoly governance, and research methods, and provides theoretical references and new ideas for future research directions.

A Novel Linguistic Z-Number QUALIFLEX Method and Its Application to Large Group Emergency Decision Making

Abstract: After an unconventional emergency event occurs, a reasonable and effective emergency decision should be made within a short time period In the emergency decision making process, decision makers’ opinions are often uncertain and imprecise, and determining the optimal solution to respond to an emergency event is a complex group decision making problem In this study, a novel large group emergency decision making method, called the linguistic Z-QUALIFLEX method, is developed by extending the QUALIFLEX method using linguistic Z-numbers The evaluations of decision makers on the alternative solutions are first expressed as linguistic Z-numbers, and the group decision matrix is then constructed by aggregating the evaluations of all subgroups The QUALIFLEX method is used to rank the alternative solutions for the unconventional emergency event Besides, a real-life example of emergency decision making is presented, and a comparison with existing methods is performed to validate the effectiveness and practicability of the proposed method The results show that the proposed linguistic Z-QUALIFLEX can accurately express the evaluations of the decision makers and obtain a more reasonable ranking result of solutions for emergency decision making