Abstract: This paper presents a method for single image dehazing based on dark channel prior (DCP). The property that the intensity of the dark channel gives an approximate thickness of the haze is used to estimate the transmission and atmospheric light. Instead of constant atmospheric light, the proposed method employs scene depth to estimate spatially varying atmospheric light as it truly occurs in nature. Haze imaging model together with the soft matting method has been used in this work to produce high quality haze free image. Experimental results demonstrate that the proposed approach produces better results than the classic DCP approach as color fidelity and contrast of haze free image are improved and no over-saturation in the sky region is observed. Further, lifting Haar wavelet transform is employed to reduce overall execution time by a factor of two to three as compared to the conventional approach.
Abstract: Engagement is one of the most important factors in determining successful outcomes and deep learning in students. Existing approaches to detect student engagement involve periodic human observations that are subject to inter-rater reliability. Our solution uses real-time multimodal multisensor data labeled by objective performance outcomes to infer the engagement of students. The study involves four students with a combined diagnosis of cerebral palsy and a learning disability who took part in a 3-month trial over 59 sessions. Multimodal multisensor data were collected while they participated in a continuous performance test. Eye gaze, electroencephalogram, body pose, and interaction data were used to create a model of student engagement through objective labeling from the continuous performance test outcomes. In order to achieve this, a type of continuous performance test is introduced, the Seek-X type. Nine features were extracted including high-level handpicked compound features. Using leave-one-out cross-validation, a series of different machine learning approaches were evaluated. Overall, the random forest classification approach achieved the best classification results. Using random forest, 93.3% classification for engagement and 42.9% accuracy for disengagement were achieved. We compared these results to outcomes from different models: AdaBoost, decision tree, k-Nearest Neighbor, naïve Bayes, neural network, and support vector machine. We showed that using a multisensor approach achieved higher accuracy than using features from any reduced set of sensors. We found that using high-level handpicked features can improve the classification accuracy in every sensor mode. Our approach is robust to both sensor fallout and occlusions. The single most important sensor feature to the classification of engagement and distraction was shown to be eye gaze. It has been shown that we can accurately predict the level of engagement of students with learning disabilities in a real-time approach that is not subject to inter-rater reliability, human observation or reliant on a single mode of sensor input. This will help teachers design interventions for a heterogeneous group of students, where teachers cannot possibly attend to each of their individual needs. Our approach can be used to identify those with the greatest learning challenges so that all students are supported to reach their full potential.
Abstract: The aim of this study is to develop a system which can identify and sort peaberries automatically at low cost for coffee producers in developing countries. In this paper, the focus is on the classification of peaberries and normal coffee beans using image processing and machine learning techniques. The peaberry is not bad and not a normal bean. The peaberry is born in an only single seed, relatively round seed from a coffee cherry instead of the usual flat-sided pair of beans. It has another value and flavor. To make the taste of the coffee better, it is necessary to separate the peaberry and normal bean before green coffee beans roasting. Otherwise, the taste of total beans will be mixed, and it will be bad. In roaster procedure time, all the beans shape, size, and weight must be unique; otherwise, the larger bean will take more time for roasting inside. The peaberry has a different size and different shape even though they have the same weight as normal beans. The peaberry roasts slower than other normal beans. Therefore, neither technique provides a good option to select the peaberries. Defect beans, e.g., sour, broken, black, and fade bean, are easy to check and pick up manually by hand. On the other hand, the peaberry pick up is very difficult even for trained specialists because the shape and color of the peaberry are similar to normal beans. In this study, we use image processing and machine learning techniques to discriminate the normal and peaberry bean as a part of the sorting system. As the first step, we applied Deep Convolutional Neural Networks (CNN) and Support Vector Machine (SVM) as machine learning techniques to discriminate the peaberry and normal bean. As a result, better performance was obtained with CNN than with SVM for the discrimination of the peaberry. The trained artificial neural network with high performance CPU and GPU in this work will be simply installed into the inexpensive and low in calculation Raspberry Pi system. We assume that this system will be used in under developed countries. The study evaluates and compares the feasibility of the methods in terms of accuracy of classification and processing speed.
Abstract: Conventional reservoir prediction methods ar not sufficient to explore the implicit relation between seismic attributes, and thus data utilization is low. In order to improve the predictive classification accuracy of reservoir lithology, this paper proposes a deep learning lithology prediction method based on ResNet (Residual Neural Network) and SENet (Squeeze-and-Excitation Neural Network). The neural network model is built and trained by using seismic attribute data and lithology data of Shengli oilfield, and the nonlinear mapping relationship between seismic attribute and lithology marker is established. The experimental results show that this method can significantly improve the classification effect of reservoir lithology, and the classification accuracy is close to 70%. This study can effectively predict the lithology of undrilled area and provide support for exploration and development.
Abstract: In this paper we develop a model that couples Two Concurrent Convolution Neural Network with different filters (TC*CNN) for face recognition and compare its performance to an existing sequential CNN (base model). We also test and compare the quality and performance of the models on three datasets with various levels of complexity (easy, moderate, and difficult) and show that for the most complex datasets, edges will produce the most accurate and efficient results. We further show that in such cases while Support Vector Machine (SVM) models are fast, they do not produce accurate results.
Abstract: Over-parameterized neural networks have attracted a
great deal of attention in recent deep learning theory research,
as they challenge the classic perspective of over-fitting when
the model has excessive parameters and have gained empirical
success in various settings. While a number of theoretical works
have been presented to demystify properties of such models, the
convergence properties of such models are still far from being
thoroughly understood. In this work, we study the convergence
properties of training two-hidden-layer partially over-parameterized
fully connected networks with the Rectified Linear Unit activation via
gradient descent. To our knowledge, this is the first theoretical work
to understand convergence properties of deep over-parameterized
networks without the equally-wide-hidden-layer assumption and
other unrealistic assumptions. We provide a probabilistic lower bound
of the widths of hidden layers and proved linear convergence rate of
gradient descent. We also conducted experiments on synthetic and
real-world datasets to validate our theory.
Abstract: The inability of organizations to put in place management control measures for Internet of Things (IoT) complexities persists to be a risk concern. Policy makers have been left to scamper in finding measures to combat these security and privacy concerns. IoT forensics is a cumbersome process as there is no standardization of the IoT products, no or limited historical data are stored on the devices. This paper highlights why IoT forensics is a unique adventure and brought out the legal challenges encountered in the investigation process. A quadrant model is presented to study the conflicting aspects in IoT forensics. The model analyses the effectiveness of forensic investigation process versus the admissibility of the evidence integrity; taking into account the user privacy and the providers’ compliance with the laws and regulations. Our analysis concludes that a semi-automated forensic process using machine learning, could eliminate the human factor from the profiling and surveillance processes, and hence resolves the issues of data protection (privacy and confidentiality).
Abstract: In the field of machine learning, the ensemble has been employed as a common methodology to improve the performance upon multiple base classifiers. However, the true predictions are often canceled out by the false ones during consensus due to a phenomenon called “curse of correlation” which is represented as the strong interferences among the predictions produced by the base classifiers. In addition, the existing practices are still not able to effectively mitigate the problem of imbalanced classification. Based on the analysis on our experiment results, we conclude that the two problems are caused by some inherent deficiencies in the approach of consensus. Therefore, we create an enhanced ensemble algorithm which adopts a designed rank-based chain-mode consensus to overcome the two problems. In order to evaluate the proposed ensemble algorithm, we employ a well-known benchmark data set NSL-KDD (the improved version of dataset KDDCup99 produced by University of New Brunswick) to make comparisons between the proposed and 8 common ensemble algorithms. Particularly, each compared ensemble classifier uses the same 22 base classifiers, so that the differences in terms of the improvements toward the accuracy and reliability upon the base classifiers can be truly revealed. As a result, the proposed rank-based chain-mode consensus is proved to be a more effective ensemble solution than the traditional consensus approach, which outperforms the 8 ensemble algorithms by 20% on almost all compared metrices which include accuracy, precision, recall, F1-score and area under receiver operating characteristic curve.
Abstract: This paper mainly studies the path planning method based on ant colony optimization (ACO), and proposes heuristic integration ant colony optimization (HIACO). This paper not only analyzes and optimizes the principle, but also simulates and analyzes the parameters related to the application of HIACO in path planning. Compared with the original algorithm, the improved algorithm optimizes probability formula, tabu table mechanism and updating mechanism, and introduces more reasonable heuristic factors. The optimized HIACO not only draws on the excellent ideas of the original algorithm, but also solves the problems of premature convergence, convergence to the sub optimal solution and improper exploration to some extent. HIACO can be used to achieve better simulation results and achieve the desired optimization. Combined with the probability formula and update formula, several parameters of HIACO are tested. This paper proves the principle of the HIACO and gives the best parameter range in the research of path planning.
Abstract: In this paper, a multiple-input/multiple-output (MIMO) antenna design with polarization and radiation pattern diversity is presented for future smartphones. The configuration of the design consists of four double-fed circular-ring antenna elements located at different edges of the printed circuit board (PCB) with an FR-4 substrate and overall dimension of 75×150 mm2. The antenna elements are fed by 50-Ohm microstrip-lines and provide polarization and radiation pattern diversity function due to the orthogonal placement of their feed lines. A good impedance bandwidth (S11 ≤ -10 dB) of 3.4-3.8 GHz has been obtained for the smartphone antenna array. However, for S11 ≤ -6 dB, this value is 3.25-3.95 GHz. More than 3 dB realized gain and 80% total efficiency are achieved for the single-element radiator. The presented design not only provides the required radiation coverage but also generates the polarization diversity characteristic.
Abstract: A design of beam-steerable antenna array for the future cellular communication (5G) is presented. The proposed design contains eight elements of compact end-fire antennas arranged on the top edge of smartphone printed circuit board (PCB). Configuration of the antenna element consists of the conductive patterns on the top and bottom copper foil layers and a substrate layer with a via-hole. The simulated results including input-impedance and also fundamental radiation properties have been presented and discussed. The impedance bandwidth (S11 ≤ -10 dB) of the antenna spans from 17.5 to 21 GHz (more than 3 GHz bandwidth) with a resonance at 19 GHz. The antenna exhibits end-fire (directional) radiation beams with wide-angle scanning property and could be used for the future 5G beam-forming. Furthermore, the characteristics of the array design in the vicinity of user-hand are studied.
Abstract: In this study, an automated building and tree detection
method is proposed using DSM data and true orthophoto image. A
multiscale matched filtering is used on DSM data. Therefore, first
watershed transform is applied. Then, Otsu’s thresholding method
is used as an adaptive threshold to segment each watershed region.
Detected objects are masked with NDVI to separate buildings and
trees. The proposed method is able to detect buildings and trees
without entering any elevation threshold. We tested our method on
ISPRS semantic labeling dataset and obtained promising results.
Abstract: Constant potometer is an important component of pipeline anti-corrosion systems in the chemical industry. Based on Internet of Things (IoT) technology, Programmable Logic Controller (PLC) technology and database technology, this paper developed a set of a constant potometer remote monitoring management system. The remote monitoring and remote adjustment of the working status of the constant potometer are realized. The system has real-time data display, historical data query, alarm push management, user permission management, and supporting Web access and mobile client application (APP) access. The actual engineering project test results show the stability of the system, which can be widely used in cathodic protection systems.
Abstract: This paper presents a wearable reconfigurable supernumerary robotic limb with differential actuated joints, which is lightweight, compact and comfortable for the wearers. Compared to the existing supernumerary robotic limbs which mostly adopted series structure with large movement space but poor carrying capacity, a prototype with the series-parallel configuration to better adapt to different task requirements has been developed in this design. To achieve a compact structure, two kinds of cable-driven mechanical structures based on guide pulleys and differential actuated joints were designed. Moreover, two different tension devices were also designed to ensure the reliability and accuracy of the cable-driven transmission. The proposed device also employed self-designed bearings which greatly simplified the structure and reduced the cost.
Abstract: Organizations, including governments, generate (big) data that are high in volume, velocity, veracity, and come from a variety of sources. Public Administrations are using (big) data, implementing base registries, and enforcing data sharing within the entire government to deliver (big) data related integrated services, provision of insights to users, and for good governance. Government (Big) data ecosystem actors represent distinct entities that provide data, consume data, manipulate data to offer paid services, and extend data services like data storage, hosting services to other actors. In this research work, we perform a systematic literature review. The key objectives of this paper are to propose a robust definition of government (big) data ecosystem and a classification of government (big) data ecosystem actors and their roles. We showcase a graphical view of actors, roles, and their relationship in the government (big) data ecosystem. We also discuss our research findings. We did not find too much published research articles about the government (big) data ecosystem, including its definition and classification of actors and their roles. Therefore, we lent ideas for the government (big) data ecosystem from numerous areas that include scientific research data, humanitarian data, open government data, industry data, in the literature.
Abstract: Radio Frequency Identification (RFID) is one of the most commonly used technologies in IoTs and Wireless Sensor Networks which makes the devices identification and tracking extremely easy to manage. Since RFID uses wireless channel for communication, which is open for all types of adversaries, researchers have proposed many Ultralightweight Mutual Authentication Protocols (UMAPs) to ensure security and privacy in a cost-effective manner. These UMAPs involve simple bitwise logical operators such as XOR, AND, OR & Rot, etc., to design the protocol messages. However, most of these UMAPs were later reported to be vulnerable against many malicious attacks. In this paper, we have presented a detailed overview of some eminent UMAPs and also discussed the many security attacks on them. Finally, some recommendations and suggestions have been discussed, which can improve the design of the UMAPs.
Abstract: Nowadays, physical processes are becoming digitized
by the evolution of communication, sensing and storage technologies
which promote the development of smart cities. The evolution of
this technology has generated multiple challenges related to the
generation of big data and the active participation of electronic
devices in society. Thus, devices can send information that is captured
and processed over large areas, but there is no guarantee that all
the obtained data amount will be effectively stored and correctly
persisted. Because, depending on the technology which is used,
there are parameters that has huge influence on the full delivery of
information. This article aims to characterize the project, currently
under development, of a platform that based on data science will
perform a performance and effectiveness evaluation of an industrial
network that implements LoRaWAN technology considering its main
parameters configuration relating these parameters to the information
Abstract: In the last few years, Automatic Number Plate Recognition (ANPR) systems have become widely used in the safety, the security, and the commercial aspects. Forethought, several methods and techniques are computing to achieve the better levels in terms of accuracy and real time execution. This paper proposed a computer vision algorithm of Number Plate Localization (NPL) and Characters Segmentation (CS). In addition, it proposed an improved method in Optical Character Recognition (OCR) based on Deep Learning (DL) techniques. In order to identify the number of detected plate after NPL and CS steps, the Convolutional Neural Network (CNN) algorithm is proposed. A DL model is developed using four convolution layers, two layers of Maxpooling, and six layers of fully connected. The model was trained by number image database on the Jetson TX2 NVIDIA target. The accuracy result has achieved 95.84%.
Abstract: Geographic Information Systems (GIS) is a multipurpose computer-based tool that provides a sophisticated ability to map and analyze data on different spatial layers. However, GIS is far more easily applied in some policy areas than others. This paper seeks to determine the areas of sustainable development, including environmental, economic, and social dimensions, where GIS has been used to date to support efforts to implement the United Nations Sustainable Development Goals (SDGs), and to discuss potential areas where it might be used more. Based on an extensive analysis of published literature, we ranked the SDGs according to how frequently GIS has been used to study related policy. We found that SDG#15 “Life on Land” is most often addressed with GIS, following by SDG#11 “Sustainable Cities and Communities”, and SDG#13 “Climate Action”. On the other hand, we determined that SDG#2 “Zero Hunger”, SDG#8 “Decent Work and Economic Growth”, and SDG#16 “Peace, Justice, and Strong Institutions” are least addressed with GIS. The paper outlines some specific ways that GIS might be applied to the SDGs least linked to this tool currently.
Abstract: The Versatile Video Coding standard (VVC) is actually under development by the Joint Video Exploration Team (or JVET). An Adaptive Multiple Transforms (AMT) approach was announced. It is based on different transform modules that provided an efficient coding. However, the AMT solution raises several issues especially regarding the complexity of the selected set of transforms. This can be an important issue, particularly for a future industrial adoption. This paper proposed an efficient hardware implementation of the most used transform in AMT approach: the DCT II. The developed circuit is adapted to different block sizes and can reach a minimum frequency of 192 MHz allowing an optimized execution time.