Abstract: Large amounts of data on the web can provide valuable information. For example, product reviews help business owners measure customer satisfaction. Sentiment analysis classifies texts into two polarities: positive and negative. This paper examines movie reviews and tweets using a new term weighting scheme, called one-over-sigma (1/sigma), on benchmark datasets for sentiment classification. The proposed method aims to improve the performance of sentiment classification. The results show that 1/sigma is more accurate than the popular term weighting schemes. In order to verify if the entropy reflects the discriminating power of terms, we report a comparison of entropy values for different term weighting schemes.
Abstract: Breadth-First Search (BFS) is a core graph algorithm that is widely used for graph analysis. As it is frequently used in many graph applications, improving the BFS performance is essential. In this paper, we present a graph ordering method that could reorder the graph nodes to achieve better data locality, thus, improving the BFS performance. Our method is based on an observation that the sibling relationships will dominate the cache access pattern during the BFS traversal. Therefore, we propose a frequency-based model to construct the graph order. First, we optimize the graph order according to the nodes’ visit frequency. Nodes with high visit frequency will be processed in priority. Second, we try to maximize the child nodes’ overlap layer by layer. As it is proved to be NP-hard, we propose a heuristic method that could greatly reduce the preprocessing overheads.We conduct extensive experiments on 16 real-world datasets. The result shows that our method could achieve comparable performance with the state-of-the-art methods while the graph ordering overheads are only about 1/15.
Abstract: Currently the most prevalent deep learning methods require a large amount of data for training, whereas few-shot learning tries to learn a model from limited data without extensive retraining. In this paper, we present a loss function based on triplet loss for solving few-shot problem using metric based learning. Instead of setting the margin distance in triplet loss as a constant number empirically, we propose an adaptive margin distance strategy to obtain the appropriate margin distance automatically. We implement the strategy in the deep siamese network for deep metric embedding, by utilizing an optimization approach by penalizing the worst case and rewarding the best. Our experiments on image recognition and co-segmentation model demonstrate that using our proposed triplet loss with adaptive margin distance can significantly improve the performance.
Abstract: The performance of a permanent magnet brushless direct current (BLDC) motor controlled by the Kalman filter based position-sensorless drive is studied in terms of its dependence from the system’s parameters variations. The effects of the system’s parameters changes on the dynamic behavior of state variables are verified. Simulated is the closed loop control scheme with Kalman filter in the feedback line. Distinguished are two separate data sampling modes in analyzing feedback output from the BLDC motor: (1) equal angular separation and (2) equal time intervals. In case (1), the data are collected via equal intervals of rotor’s angular position i, i.e. keeping = const. In case (2), the data collection time points ti are separated by equal sampling time intervals t = const. Demonstrated are the effects of the parameters changes on the sensorless control flow, in particular, reduction of the instability torque ripples, switching spikes, and torque load balancing. It is specifically shown that an efficient suppression of commutation induced instability torque ripples is an achievable selection of the sampling rate in the Kalman filter settings above a certain critical value. The computational cost of such suppression is shown to be higher for the motors with lower induction values of the windings.
Abstract: Kernelized Correlation Filter (KCF) based trackers have gained a lot of attention recently because of their accuracy and fast calculation speed. However, this algorithm is not robust in cases where the object is lost by a sudden change of direction, being obscured or going out of view. In order to improve KCF performance in long-term tracking, this paper proposes an anomaly detection method for target loss warning by analyzing the response map of each frame, and a classification algorithm for reliable target re-locating mechanism by using Random fern. Being tested with Visual Tracker Benchmark and Visual Object Tracking datasets, the experimental results indicated that the precision and success rate of the proposed algorithm were 2.92 and 2.61 times higher than that of the original KCF algorithm, respectively. Moreover, the proposed tracker handles occlusion better than many state-of-the-art long-term tracking methods while running at 60 frames per second.
Abstract: Tree-ring analysis is an important part of the quality assessment and the dating of (archaeological) wood samples. It provides quantitative data about the whole anatomical ring structure, which can be used, for example, to measure the impact of the fluctuating environment on the tree growth, for the dendrochronological analysis of archaeological wooden artefacts and to estimate the wood mechanical properties. Despite advances in computer vision and edge recognition algorithms, detection and counting of annual rings are still limited to 2D datasets and performed in most cases manually, which is a time consuming, tedious task and depends strongly on the operator’s experience. This work presents an image processing approach to detect the whole 3D tree-ring structure directly from X-ray computed tomography imaging data. The approach relies on a modified Canny edge detection algorithm, which captures fully connected tree-ring edges throughout the measured image stack and is validated on X-ray computed tomography data taken from six wood species.
Abstract: Analysis of the human microbiome using metagenomic
sequencing data has demonstrated high ability in discriminating
various human diseases. Raw metagenomic sequencing data require
multiple complex and computationally heavy bioinformatics steps
prior to data analysis. Such data contain millions of short sequences
read from the fragmented DNA sequences and stored as fastq files.
Conventional processing pipelines consist in multiple steps including
quality control, filtering, alignment of sequences against genomic
catalogs (genes, species, taxonomic levels, functional pathways,
etc.). These pipelines are complex to use, time consuming and
rely on a large number of parameters that often provide variability
and impact the estimation of the microbiome elements. Training
Deep Neural Networks directly from raw sequencing data is a
promising approach to bypass some of the challenges associated with
mainstream bioinformatics pipelines. Most of these methods use the
concept of word and sentence embeddings that create a meaningful
and numerical representation of DNA sequences, while extracting
features and reducing the dimensionality of the data. In this paper
we present an end-to-end approach that classifies patients into disease
groups directly from raw metagenomic reads: metagenome2vec. This
approach is composed of four steps (i) generating a vocabulary of
k-mers and learning their numerical embeddings; (ii) learning DNA
sequence (read) embeddings; (iii) identifying the genome from which
the sequence is most likely to come and (iv) training a multiple
instance learning classifier which predicts the phenotype based on
the vector representation of the raw data. An attention mechanism
is applied in the network so that the model can be interpreted,
assigning a weight to the influence of the prediction for each genome.
Using two public real-life data-sets as well a simulated one, we
demonstrated that this original approach reaches high performance,
comparable with the state-of-the-art methods applied directly on
processed data though mainstream bioinformatics workflows. These
results are encouraging for this proof of concept work. We believe
that with further dedication, the DNN models have the potential to
surpass mainstream bioinformatics workflows in disease classification
tasks.
Abstract: The built-up area is a significant proxy to measure regional economic growth and reflects the Gross Provincial Product (GPP). However, an up-to-date and reliable database of built-up areas is not always available, especially in developing countries. The cloud-based geospatial analysis platform such as Google Earth Engine (GEE) provides an opportunity with accessibility and computational power for those countries to generate the built-up data. Therefore, this study aims to extract the built-up areas in Eastern Economic Corridor (EEC), Thailand using day and nighttime satellite imagery based on GEE facilities. The normalized indices were generated from Landsat 8 surface reflectance dataset, including Normalized Difference Built-up Index (NDBI), Built-up Index (BUI), and Modified Built-up Index (MBUI). These indices were applied to identify built-up areas in EEC. The result shows that MBUI performs better than BUI and NDBI, with the highest accuracy of 0.85 and Kappa of 0.82. Moreover, the overall accuracy of classification was improved from 79% to 90%, and error of total built-up area was decreased from 29% to 0.7%, after night-time light data from the Visible and Infrared Imaging Suite (VIIRS) Day Night Band (DNB). The results suggest that MBUI with night-time light imagery is appropriate for built-up area extraction and be utilize for further study of socioeconomic impacts of regional development policy over the EEC region.
Abstract: Autonomous vehicles look set to drastically alter the way we move people and goods, in urban as well as rural areas. However, little has been written about Africa with this regard. Moreover, in order for this new technology to be adopted, user acceptance is vital. The current research examines the user acceptance of autonomous minibus shuttles, as a solution for first/last mile public transport in Pretoria, South Africa. Of the respondents surveyed, only 2.31% perceived them as not useful. Respondents showed more interest in using these shuttles in combination with the bus rapid transit system (75.4%) as opposed to other modes of public transportation (40%). The significance of these findings is that they can help ensure that the implementation of autonomous public transport in South Africa is adapted to the local user. Furthermore, these findings could be adapted for other South African cities and other cities across the continent.
Abstract: Air Defense Systems contain high-value assets that are
expected to fulfill their mission for several years - in many cases,
even decades - while operating in a fast-changing, technology-driven
environment. Thus, it is paramount that decision-makers can assess
how effective an Air Defense System is in the face of new developing
threats, as well as to identify the bottlenecks that could jeopardize
the security of the airspace of a country. Given the broad extent
of activities and the great variety of assets necessary to achieve
the strategic objectives, a systems approach was taken in order to
delineate the core requirements and the physical architecture of an
Air Defense System. Then, value-focused thinking helped in the
definition of the measures of effectiveness. Furthermore, analytical
methods were applied to create a formal structure that preliminarily
assesses such measures. To validate the proposed methodology, a
powerful simulation was also used to determine the measures of
effectiveness, now in more complex environments that incorporate
both uncertainty and multiple interactions of the entities. The results
regarding the validity of this methodology suggest that the approach
can support decisions aimed at enhancing the capabilities of Air
Defense Systems. In conclusion, this paper sheds some light on
how consolidated approaches of Systems Engineering and Operations
Research can be used as valid techniques for solving problems
regarding a complex and yet vital matter.
Abstract: The addition of a small amount of alumina cement to Portland cement results in immediate setting, a rapid increase in the compressive strength and a clear increase of the adhesion to concrete substrate. This phenomenon is used, among others, for the production of liquid floor self-levelling compounds. Alumina cement is several times more expensive than Portland cement and is a component having a significant impact on prices of products manufactured with its use. For the production of liquid floor self-levelling compounds, low-alumina cement containing approximately 40% Al2O3 is normally used. The aim of the study was to determine the impact of Portland cement with the addition of alumina cement on the basic physical and mechanical properties of cement slurries and mortars. CEM I 42.5R and three types of alumina cement containing 40%, 50% and 70% of Al2O3 were used for the tests. Mixes containing 4%, 6%, 8%, 10% and 12% of different varieties of alumina cement were prepared; for which, the time of initial and final setting, compressive and flexural strength and adhesion to concrete substrate were determined. The analysis of the obtained test results showed that a similar immediate setting effect and clearly better adhesion strength can be obtained using the addition of 6% of high-alumina cement than 12% of low-alumina cement. As the prices of these cements are similar, this can give significant financial savings in the production of liquid floor self-levelling compounds.
Abstract: Innovation is the key element of economic development and a key factor in social processes. Technical innovations can be identified as prerequisites and causes of social change and cannot be created without the renewal of society. The study of social innovation can be characterised as one of the significant research areas of our day. The study’s aim is to identify the process of social innovation, which can be defined by input, transformation, and output factors. This approach divides the social innovation process into three parts: situation analysis, implementation, follow-up. The methods associated with each stage of the process are illustrated by the chronological line of social innovation. In this study, we have sought to present methodologies that support long- and short-term decision-making that is easy to apply, have different complementary content, and are well visualised for different user groups. When applying the methods, the reference objects are different: county, district, settlement, specific organisation. The solution proposed by the study supports the development of a methodological combination adapted to different situations. Having reviewed metric and conceptualisation issues, we wanted to develop a methodological combination along with a change management logic suitable for structured support to the generation of social innovation in the case of a locality or a specific organisation. In addition to a theoretical summary, in the second part of the study, we want to give a non-exhaustive picture of the two counties located in the north-eastern part of Hungary through specific analyses and case descriptions.
Abstract: Additive Manufacturing processes are becoming increasingly established in the industry for the economic production of complex prototypes and functional components. Laser beam melting (LBM), the most frequently used Additive Manufacturing technology for metal parts, has been gaining in industrial importance for several years. The LBM process chain – from material storage to machine set-up and component post-processing – requires many manual operations. These steps often depend on the manufactured component and are therefore not standardized. These operations are often not performed in a standardized manner, but depend on the experience of the machine operator, e.g., levelling of the build plate and adjusting the first powder layer in the LBM machine. This lack of standardization limits the reproducibility of the component quality. When processing metal powders with inhalable and alveolar particle fractions, the machine operator is at high risk due to the high reactivity and the toxic (e.g., carcinogenic) effect of the various metal powders. Faulty execution of the operation or unintentional omission of safety-relevant steps can impair the health of the machine operator. In this paper, all the steps of the LBM process chain are first analysed in terms of their influence on the two aforementioned challenges: reproducibility and work safety. Standardization to avoid errors increases the reproducibility of component quality as well as the adherence to and correct execution of safety-relevant operations. The corresponding lean method 5S will therefore be applied, in order to develop approaches in the form of recommended actions that standardize the work processes. These approaches will then be evaluated in terms of ease of implementation and their potential for improving reproducibility and work safety. The analysis and evaluation showed that sorting tools and spare parts as well as standardizing the workflow are likely to increase reproducibility. Organizing the operational steps and production environment decreases the hazards of material handling and consequently improves work safety.
Abstract: The global sanitation workforce bridges the gap between sanitation infrastructure and the provision of sanitation services through essential public service work. Manual pit emptiers often perform the work at the cost of their dignity, safety, and health as their work requires repeated heavy physical activities such as lifting, carrying, pulling, and pushing. This exposes them to occupational and environmental health hazards and risking illness, injury, and death. The study will extend the studies by presenting occupational health risks and suggestions for improvement in informal settlements of Nairobi, Kenya. This is a qualitative study conducted among sanitation stakeholders in Korogocho, Mukuru and Kibera informal settlements in Nairobi. Data were captured using digital voice recorders, transcribed and thematically analysed. The discussion notes were further supported by observational notes made during the interviews. These formed the basis for a robust picture of occupational health of manual pit emptiers; a lack or inappropriate use of protective clothing, and prolonged duration of working hours were described to contribute to the occupational health hazard. To continue working, manual pit emptiers had devised coping strategies which include working in groups, improvised protective clothing, sharing the available protective clothing, working at night and consuming alcohol drinks while at work. Many of these strategies are detrimental to their health. Occupational health hazards among pit emptiers are key for effective working and is as a result of a lack of collaboration amongst stakeholders linked to health, safety and lack of PPE of pit emptiers. Collaborations amongst sanitation stakeholders is paramount for health, safety, and in ensuring the provision and use of personal protective devices.
Abstract: We present a decision-support tool to assist an operator in the detection and tracking of a suspect vehicle traveling to an unknown target destination. Multiple data sources, such as traffic cameras, traffic information, weather, etc., are integrated and processed in real-time to infer a suspect’s intended destination chosen from a list of pre-determined high-value targets. Previously, we presented our work in the detection and tracking of vehicles using traffic and airborne cameras. Here, we focus on the fusion and processing of that information to predict a suspect’s behavior. The network of cameras is represented by a directional graph, where the edges correspond to direct road connections between the nodes and the edge weights are proportional to the average time it takes to travel from one node to another. For our experiments, we construct our graph based on the greater Los Angeles subset of the Caltrans’s “Performance Measurement System” (PeMS) dataset. We propose a Bayesian approach where a posterior probability for each target is continuously updated based on detections of the suspect in the live video feeds. Additionally, we introduce the concept of ‘soft interventions’, inspired by the field of Causal Inference. Soft interventions are herein defined as interventions that do not immediately interfere with the suspect’s movements; rather, a soft intervention may induce the suspect into making a new decision, ultimately making their intent more transparent. For example, a soft intervention could be temporarily closing a road a few blocks from the suspect’s current location, which may require the suspect to change their current course. The objective of these interventions is to gain the maximum amount of information about the suspect’s intent in the shortest possible time. Our system currently operates in a human-on-the-loop mode where at each step, a set of recommendations are presented to the operator to aid in decision-making. In principle, the system could operate autonomously, only prompting the operator for critical decisions, allowing the system to significantly scale up to larger areas and multiple suspects. Once the intended target is identified with sufficient confidence, the vehicle is reported to the authorities to take further action. Other recommendations include a selection of road closures, i.e., soft interventions, or to continue monitoring. We evaluate the performance of the proposed system using simulated scenarios where the suspect, starting at random locations, takes a noisy shortest path to their intended target. In all scenarios, the suspect’s intended target is unknown to our system. The decision thresholds are selected to maximize the chances of determining the suspect’s intended target in the minimum amount of time and with the smallest number of interventions. We conclude by discussing the limitations of our current approach to motivate a machine learning approach, based on reinforcement learning in order to relax some of the current limiting assumptions.
Abstract: Composite structures become intriguing for the design of aerospace, automotive and marine applications due to weight reduction, corrosion resistance and radar signature reduction demands and requirements. Studies on piezoelectric ceramic transducers (PZT) for diagnostics and health monitoring have gained attention for their sensing capabilities, however PZT structures are prone to fail in case of heavy operational loads. In this paper, we develop a piezo-based Glass Fiber Reinforced Polymer (GFRP) composite finite element (FE) model, validate with experimental setup, and identify the applicability and limitations of PZTs for a marine application. A case study is conducted to assess the piezo-based sensing capabilities in a representative marine composite structure. A FE model of the composite structure combined with PZT patches is developed, afterwards the response and functionality are investigated according to the sea conditions. Results of this study clearly indicate the blockers and critical aspects towards industrialization and wide-range use of PZTs for marine composite applications.
Abstract: Data flow and the purpose of reporting the data are different and dependent on business needs. Different parameters are reported and transferred regularly during freight delivery. This business practices form the dataset constructed for each time point and contain all required information for freight moving decisions. As a significant amount of these data is used for various purposes, an integrating methodological approach must be developed to respond to the indicated problem. The proposed methodology contains several steps: (1) collecting context data sets and data validation; (2) multi-objective analysis for optimizing freight transfer services. For data validation, the study involves Grubbs outliers analysis, particularly for data cleaning and the identification of statistical significance of data reporting event cases. The Grubbs test is often used as it measures one external value at a time exceeding the boundaries of standard normal distribution. In the study area, the test was not widely applied by authors, except when the Grubbs test for outlier detection was used to identify outsiders in fuel consumption data. In the study, the authors applied the method with a confidence level of 99%. For the multi-objective analysis, the authors would like to select the forms of construction of the genetic algorithms, which have more possibilities to extract the best solution. For freight delivery management, the schemas of genetic algorithms' structure are used as a more effective technique. Due to that, the adaptable genetic algorithm is applied for the description of choosing process of the effective transportation corridor. In this study, the multi-objective genetic algorithm methods are used to optimize the data evaluation and select the appropriate transport corridor. The authors suggest a methodology for the multi-objective analysis, which evaluates collected context data sets and uses this evaluation to determine a delivery corridor for freight transfer service in the multi-modal transportation network. In the multi-objective analysis, authors include safety components, the number of accidents a year, and freight delivery time in the multi-modal transportation network. The proposed methodology has practical value in the management of multi-modal transportation processes.
Abstract: Machine learning is a new and exciting area of
artificial intelligence nowadays. Machine learning is the most
valuable, time, supervised, and cost-effective approach. It is not a
narrow learning approach; it also includes a wide range of methods
and techniques that can be applied to a wide range of complex realworld
problems and time domains. Biological image classification,
adaptive testing, computer vision, natural language processing, object
detection, cancer detection, face recognition, handwriting
recognition, speech recognition, and many other applications of
machine learning are widely used in research, industry, and
government. Every day, more data are generated, and conventional
machine learning techniques are becoming obsolete as users move to
distributed and real-time operations. By providing fundamental
knowledge of machine learning tools and research opportunities in
the field, the aim of this article is to serve as both a comprehensive
overview and a guide. A diverse set of machine learning resources is
demonstrated and contrasted with the key features in this survey.
Abstract: The use of laser beam welding for joining titanium and aluminum offers more advantages compared with conventional joining processes. Dissimilar metal combination is very much needed for aircraft structural industries and research activities. The quality of a weld joint is directly influenced by the welding input parameters. The common problem that is faced by the manufactures is the control of the process parameters to obtain a good weld joint with minimal detrimental. To overcome this issue, various parameters can be preferred to obtain quality of weld joint. In this present study an overall literature review on processing parameters such as offset distance, welding speed, laser power, shielding gas and filler metals are discussed with the effects on quality weldment. Additionally, mechanical properties of welds joint are discussed. The aim of the report is to review the recent progress in the welding of dissimilar titanium (Ti) and aluminum (Al) alloys to provide a basis for follow up research.
Abstract: Fingerprint Anti-Spoofing approaches have been actively developed and applied in real-world applications. One of the main problems for Fingerprint Anti-Spoofing is not robust to unseen samples, especially in real-world scenarios. A possible solution will be to generate artificial, but realistic fingerprint samples and use them for training in order to achieve good generalization. This paper contains experimental and comparative results with currently popular GAN based methods and uses realistic synthesis of fingerprints in training in order to increase the performance. Among various GAN models, the most popular StyleGAN is used for the experiments. The CNN models were first trained with the dataset that did not contain generated fake images and the accuracy along with the mean average error rate were recorded. Then, the fake generated images (fake images of live fingerprints and fake images of spoof fingerprints) were each combined with the original images (real images of live fingerprints and real images of spoof fingerprints), and various CNN models were trained. The best performances for each CNN model, trained with the dataset of generated fake images and each time the accuracy and the mean average error rate, were recorded. We observe that current GAN based approaches need significant improvements for the Anti-Spoofing performance, although the overall quality of the synthesized fingerprints seems to be reasonable. We include the analysis of this performance degradation, especially with a small number of samples. In addition, we suggest several approaches towards improved generalization with a small number of samples, by focusing on what GAN based approaches should learn and should not learn.