Search

Machine learning (ML) has increasingly been adopted in safety-critical systems such as autonomous vehicles (AVs) and industrial robotics. In these domains, reliability and safety are important considerations, and hence it is critical to ensure the resilience of ML systems to faults and errors. On the other hand, soft errors are becoming more frequent in commodity computer systems due to the effects of technology scaling and reduced supply voltages. Further, traditional solutions for masking hardware faults such as Triple-Modular Redundancy (TMR) are prohibitively expensive in terms of their energy and performance overheads. Therefore, there is a compelling need to ensure the resilience of ML applications to soft errors on commodity hardware platforms.We first experimentally assess the resilience of safety-critical ML applications to soft errors. We demonstrate through fault injection experiments that even a single bit flip due to a soft error can lead to misclassification in Deep Neural Network (DNN) applications deployed in AVs, leading to safety violations. However, not all the errors in an DNN will result in serve consequences such as safety violations, and hence it is sufficient to protect the DNN from the ones that do. Unfortunately, finding all possible errors that result in safety violations is a very compute intensive task. We propose BinFI, a fault injection approach that efficiently injects critical faults that are highly likely to result in safety violations, based on the unique properties of DNNs. Finally, we propose Ranger, an approach to protect DNNs from critical faults with minimal performance overheads and no accuracy loss. We will conclude by presenting some of our ongoing work, and the future challenges in this area.

The purpose of this work is to explore the applicability and effectiveness of deep learning methods for the task------moves recognition in abstract of research paper. We firstly build a large corpus for moves recognition. Then we choose the traditional machine learning method SVM as a benchmark, and develop four moves recognition methods based on DNN, LSTM, Attention-BiLSTM and BERT. Finally, we design two groups of experiments with sample size 10,000 and 50,000 and then compare experimental results. The results show that most of the deep learning methods outperform the traditional machine learning method SVM especially in large-scale sample experiments, in which the BERT with a re-pre-trained model achieves the best results in both groups of experiments. Deep learning methods are proved applicable and effective for moves recognition in research paper abstracts.

In modern academic social network, it is very difficult for scholars to find academic papers consistent with their research direction. Time is a critical factor in paper recommendation. As time goes on, the impact of an academic paper would gradually fade. Likewise, the research interests of users may also change. Therefore, we propose a temporal perceptual neural collaborative filtering model that integrates the multi-dimensional features of papers. We conducted our experiments on the dataset from CiteULike, comparing the recommended results by using four time-decay functions and evaluating our model with multiple evaluation indicators. The satisfactory results show that our model is effective in filtering out the expired papers by considering the characteristics of papers and the changes of scholars' interests.

The written exam is a universal tool for evaluating student performance in the field of education. The written exam provides a mechanism by which instructors and organizations ensure the consistency of the assessment process. Human effort required for the assessment is very high and it depends on several factors such as knowledge of the teacher, application level understanding of the teacher, criteria of the marking and time allotted. However, traditional evaluation processes consume very costly efforts and take huge time for the completion of the complete evaluation, verification and publishing of the result process. This research introduces the design and implementation of Handwritten Answer Evaluation (HAES) system for student exam papers. The HAES is an automatic response assessment system that enables the identification of text in answer sheets and can evaluate the grade of each answer based on the previous knowledge of the model. In this study, Optical Character Recognition (OCR) tool is used to extract the text from human written scanned answer script and machine learning/natural language processing (NLP) techniques are used for grading the answer sheets. The scores are based on cosine set similarity measures, where each sentence in the evaluated answer paper carries their corresponding mark. The developed model can be used to evaluate the marks of the unscored descriptive answers.

As Machine Learning (ML) becomes pervasive in the era of artificial intelligence, ML specific tools and frameworks are required for architectural research. This paper introduces NeuroMeter, an integrated power, area, and timing modeling framework for ML accelerators. NeuroMeter models the detailed architecture of ML accelerators and generates a fast and accurate estimation on power, area, and chip timing. Meanwhile, it also enables the runtime analysis of system-level performance and efficiency when the runtime activity factors are provided. NeuroMeter’s micro-architecture model includes fundamental components of ML accelerators, including systolic array based tensor units (TU), reduction trees (RT), and 1D vector units (VU). NeuroMeter has accurate modeling results, with the average power and area estimation errors below 10% and 17% respectively when validated against TPU-v1, TPU-v2, and Eyeriss.Leveraging the NeuroMeter’s new capabilities on architecting manycore ML accelerators, this paper presents the first in-depth study on the design space and tradeoffs of “Brawny and Wimpy” inference accelerators in datacenter scenarios with the insights that are otherwise difficult to discover without NeuroMeter. Our study shows that brawny designs with 64x64 systolic arrays are the most performant and efficient for inference tasks in the 28nm datacenter architectural space with a 500mm2 die area budget. Our study also reveals important tradeoffs between performance and efficiency. For datacenter accelerators with low batch inference, a small $(\sim 16$%) sacrifice of system performance (in achieved Tera OPerations per Second, aka TOPS) can lead to more than a 2x efficiency improvement (in achieved TOPS/TCO). To showcase NeuroMeter’s capability to model a wide range of diverse ML accelerator architectures, we also conduct a followon mini-case study on implications of sparsity on different ML accelerators, demonstrating wimpier accelerator architectures benefit more readily from sparsity processing despite their lower achievable raw energy efficiency.

Due to the increasingly growing demand for user identification on cell phones, PCs, laptops, and so on, face anti-spoofing has risen to significance and is an active research area in academia and industry. The detection of the real face then recognize it present an important challenge regarding the techniques that can be used to spoof any recognition system like masks, printed photos. This paper we present an anti-spoofing face method to solve the real-world scenario that learns the target domain classifier based on samples used for training in a particular source domain. Specifically, with the conventional regression CNN, the Spatial/Channel-wise Attention Modules were introduced. Two modules, namely the Spatial-wise Attention Module and the Channel-wise Attention Module, were used at spatial and channel levels to improve local features and ignore the irrelevant features. Extensive experiments on current collections with benchmarks datasets verifies that the recommended solution will significantly benefit from the two modules and better generalization capability by providing significantly improved results in anti-spoofing.

Drowsiness can be dangerous when performing tasks that require constant attention, such as driving a vehicle. Sleepiness is correlated with a variety of physiological variables, such as eye closing, head movements, pulse rate, eye twitch rate, etc. Also, the yawn can be considered as an accurate indicator of drowsiness and fatigue. Yawning detection is very important for the safety purpose of drivers as it will let the driver know if he/she is getting drowsy. Driving at that moment may not be safe. Several automatic yawning detection techniques have been developed for driver's drowsiness monitoring system. Nevertheless, correctly detecting the yawning of the driver and predicting exhaustion in real-time situations is still a crucial challenge. In this paper, we will be reviewing various existing machine learning approaches for driver's yawning detection. In previous approaches, various classical machine learning algorithms such as viola-Jones, contour activation algorithm and SVM have been used for yawning detection, but these approaches failed to predict yawning in realtime situations. Using Deep learning techniques, we can make a real-time yawn detection system with high accuracy. We find that some precious Deep learning algorithms like CNN, RNN, LSTM, Bi-LSTM can detect the patterns with high accuracy. After the comparison of various algorithms and techniques, we find that with the help of Deep learning algorithms the yawning can be detected in real time with high accuracy.

Human recogntion technologies are gaining significant research attention, where the model can be trained to be more precise to recognize the poses performed by objects. Activity identification is a kind of problem, which needs more research consideration and improvement. There is also an increasing need to detect different poses of objects. To tackle the issue, different sensors like Gyroscope and Accelerometer are required to classify the data in the form of images using machine learning algorithms like SVM and CNN. These approaches help us in implementing real-time applicaions such as health monitoring, tracking sports activity and security. The paper also discusses about its benefits, limitations and prominent approach for human activity recognition.

Machine learning (ML) components are increasingly adopted in many automated systems. Their ability to learn and work with novel input/incomplete knowledge and their generalization capabilities make them highly desirable solutions for complex problems. This has motivated the inclusion of ML techniques/components in products for many industrial domains including automotive systems. Such systems are safety-critical systems since their failure may cause death or injury to humans. Therefore, their safety must be ensured before they are used in their operational environment. However, existing safety standards and Verification and Validation (V&V) techniques do not properly address the special characteristics of ML-based components such as non-determinism, non-transparency, instability. This position paper presents the authors' view on the safety of automotive systems incorporating ML-based components, and it is intended to motivate and sketch a research agenda for extending a safety standard, namely ISO 26262, to address challenges posed by incorporating ML-based components in automotive systems.

In this invited paper, applications for Machine Learning (ML) in several areas of semiconductor manufacturing and test are reviewed and potential opportunities are discussed.

The rapid growth of Internet technologies and further dependence on online services, increase the demand for keeping these networks and data secure. The protection of online information is becoming even more vital to the national security and economic stability. Recently, network security has become one of the most concerning subjects in the current research and industry fields. Intrusion Detection Systems (IDSs) are considered as the backbone for network and data protection. Throughout time, different IDS approaches have been implemented to attain maximum detection accuracy. Machine learning IDS is one of the promising IDS techniques that have been created to detect known as well as unknown attacks. This paper investigates various machine learning techniques used to deploy Network-based Intrusion Detection System (NIDS). This survey could provide a more robust understanding of the existing techniques and assists intrigued researchers to identify research opportunities and investigate more in this direction.

In autonomous driving, 3D object detection is es-sential as it provides basic knowledge about the environment. However, as deep learning based 3D detection methods are usually computation intensive, it is challenging to support realtime 3D object detection on edge-computing devices in selfdriving cars with limited computation and memory resources. To facilitate this, we propose a compiler-aware pruning search framework, to achieve real-time inference of 3D object detection on the resource-limited mobile devices. Specifically, a generator is applied to sample better pruning proposals in the search space based on current proposals with their performance, and an evaluator is adopted to evaluate the sampled pruning proposal performance. To accelerate the search, the evaluator employs Bayesian optimization with an ensemble of neural predictors. We demonstrate in experiments that for the first time, the pruning search framework can achieve real-time 3D object detection on mobile (Samsung Galaxy S20 phone) with state-of-the-art detection performance.

Graph neural networks (GNN) have achieved state-of-the-art performance on various industrial tasks. However, the poor efficiency of GNN inference and frequent Out-of-Memory (OOM) problem limit the successful application of GNN on edge computing platforms. To tackle these problems, a feature decomposition approach is proposed for memory efficiency optimization of GNN inference. The proposed approach could achieve outstanding optimization on various GNN models, covering a wide range of datasets, which speeds up the inference by up to 3×. Furthermore, the proposed feature decomposition could significantly reduce the peak memory usage (up to 5× in memory efficiency improvement) and mitigate OOM problems during GNN inference.

Nowadays, there is a rapidly increasing number of conferences and journals in computer science that make a lot of challenges for researchers to find an appropriate venue to submit their scientific work. There is a need for a recommendation system that can support researchers for a better process of paper submission. In this paper, we present an efficient approach for building such a recommendation model by using embedding methods, Global Vector (GloVe) 1 created by Pennington et al. [1] and FastText 2 proposed by Facebook [2], Convolutional Neural Network (CNN) [3], and LSTM. The experimental results show that the combination of CNNs and FastText, CNN + FastText, can achieve the best performance in terms of the Top 1 Accuracy compared with other techniques, including the S2RSCS model, as presented in [4]. Moreover, the performance by using GloVe or FastText is much better, faster, and more stable than S2RSCS in most cases.

Prior work on texture analysis of historic, photographic papers has focused primarily on measures of texture similarity. However, automated grouping or clustering of photographic paper textures in a way that is meaningful to art conservators remains an open problem. In this work a deep learning approach to automated classification is presented, for clusters derived from a human sorting experiment conducted by 19 art conservators and paper experts and subsequently extended through crowd-sourcing. The proposed approach uses a deep convolutional neural network, and results are presented on the performance in automatically classifying images when compared to human experts.

Currently, anomaly detection is receiving a great deal of attention due to its importance in many real-world applications especially in data analytics. Anomaly detection has two important purposes in data pre-processing stages: one is to detect and attempts to eliminate them if and only if it is really outlier, while the other requires attention be paid to valid outlier (extreme value) because extreme value themselves carry the significant and critical information, such as extreme weather events. It will lead to significant harm if not detected and treated properly. This paper begins with the summary of anomaly detection, challenges, type of anomalies, extreme value followed by machine learning algorithms approach that deal with anomaly detection. Finally, we provide a conclusion that discusses about the important of detecting clearly between outlier or extreme value in data pre-processing stage, so that an effective and efficient prediction can be achieved later in modelling stage.

In this paper, machine learning approaches have been used to predict whether a scientific paper will be accepted in a top-tier AI conferences or not. This shall help authors identify the likelihood of their paper getting accepted in a top-tier AI conference. We have used the PeerRead dataset containing papers collected from major AI conferences that are publicly available. We have achieved an accuracy of 81% using Random Forest classifier. The novelty of the paper lies in accurately predicting whether a scientific paper will be accepted in the top AI conference.

In recent years, with the increasing investment in scientific research, the number of papers has proliferated, and the development of scientific research has also received widespread attention from scholars. Paper citations as an indicator to measure academic influence have essential reference value for future research directions. Aiming at the future paper citation number prediction problem, we propose a citation number prediction model based on the recurrent neural network method with gated recurrent unit(GRU-CPM). In this paper, we first extract features from real data sets that are useful for predicting the number of citations in papers, and then the features were input into GRU-CPM for prediction. Finally, the prediction results are compared with other regression models. Experimental results demonstrate that the GRU-CPM has higher prediction accuracy and faster convergence speed. The time series prediction of citation count is better than existing methods.

In many fields, a mass of algorithms with completely different hyperparameters have been developed to address the same type of problems. Choosing the algorithm and hyperparameter setting correctly can promote the overall performance greatly, but users often fail to do so due to the absence of knowledge. How to help users to effectively and quickly select the suitable algorithm and hyperparameter settings for the given task instance is an important research topic nowadays, which is known as the CASH problem. In this paper, we design the Auto-Model approach, which makes full use of known information in the related research paper and introduces hyperparameter optimization techniques, to solve the CASH problem effectively. Auto-Model tremendously reduces the cost of algorithm implementations and hyperparameter configuration space, and thus capable of dealing with the CASH problem efficiently and easily. To demonstrate the benefit of Auto-Model, we compare it with classical Auto-Weka approach. The experimental results show that our proposed approach can provide superior results and achieves better performance in a short time., 12 pages, 3 figures

In this work, different Machine Learning (ML) techniques are used and evaluated based on their performance of classifying peer reviewed published content. The ultimate objective is to extract meaningful information from published abstracts. In pursuing this objective, the ML techniques are utilized to classify different publications into three fields: Science, Business, and Social Science. The ML techniques applied in this work are Support Vector Machines, Naive Bayes, K-Nearest Neighbor, and Decision Tree. In addition to the description of the utilized ML algorithms, the methodology and algorithms for text recognition using the aforementioned ML techniques are provided. The comparative study based on four different performance measures suggests that – with the exception of Decision Tree algorithm – the proposed ML techniques with the detailed pre-processing algorithms work well for classifying publications into categories based on the text provided in the abstract.

Neural networks are increasingly used as data-driven models for a wide variety of physical systems such as ground vehicles, airplanes, human physiology and automobile engines. These models are in-turn used for designing and verifying autonomous systems. The advantages of using neural networks include the ability to capture characteristics of particular systems using the available data. This is particularly advantageous for medical systems, wherein the data collected from individuals can be used to design devices that are well-adapted to a particular individual's unique physiological characteristics. At the same time, neural network models remain opaque: their structure makes them hard to understand and interpret by human developers. One key challenge lies in checking that neural network models of processes are “conformant” to the well established scientific (physical, chemical and biological) laws that underlie these models. In this paper, we will show how conformance often fails in models that are otherwise accurate and trained using the best practices in machine learning, with potentially serious consequences. We motivate the need for learning and verifying key conformance properties in data-driven models of the human insulin-glucose system and data-driven automobile models. We survey verification approaches for neural networks that can hold the key to learning and verifying conformance.

Fiber nonlinearities from Kerr effect are considered as major constraints for enhancing the transmission capacity in current optical transmission systems. Digital nonlinearity compensation techniques such as digital backpropagation can perform well but require high computing resources. Machine learning can provide a low complexity capability especially for high-dimensional classification problems. Recently several supervised and unsupervised machine learning techniques have been investigated in the field of fiber nonlinearity mitigation. This paper offers a brief review of the principles, performance and complexity of these machine learning approaches in the application of nonlinearity mitigation.

With the proliferation of threats of leakage of sensitive information such as military classified documents, information guards have recently gained increased interest. An information guard is merely a filter than controls the content of the exchanged information between two domains where one of them has a higher confidentiality level than the other one. The main role of an information guard is to block leakage of the sensitive information from the higher confidentiality domain to the lower confidentiality domain. An example of a higher confidentiality domain is a military network while a subcontractor network is an example of a lower confidentiality domain. The common practice is to use an automatic information guard based on predefined list of words that is called "dirty word list" in order to decide the security level of a document and consequently release it to the lower confidentially domain or block it. Traditional information guards are configured manually based on the notion of "Dirty Lists". The classification logic of traditional information guards uses the occurrence of words from the "Dirty Lists". In this paper, we advocate the use of machine learning as a corner stone for building advanced information guards. Machine learning can also be used as a supplement to the decision obtained based on "Dirty Lists" classification. Machine learning has hardly been analysed for this problem, and the analysis on topical classification presented here provides new knowledge and a basis for further work within this area. Ten different machine learning algorithms were applied on real life data from a military context. Presented results are promising and demonstrates that machine learning can become a useful tool to assist humans in determining the appropriate security label of an information object.

In this survey paper, we point out a comparative study on different types of plant leaf diseases and all the techniques of machine learning which had been used to detect plant leaf disease. This was accomplished for two principle reasons: to restrain the length of the paper and in light of the fact that techniques managing roots, seeds and natural products have a few idiosyncrasies that would warrant a particular study. The chose proposition are isolated into three classes as indicated by their goal: recognition, seriousness measurement, and characterization. Every one of those classes, thus, are subdivided by the primary specialized arrangement utilized in the calculation. This paper is required to be helpful to specialists working both on vegetable pathology and example acknowledgment, giving a thorough and open outline of this significant field of research.

The usage of single-objective similarity functions in engineering tasks of service-oriented software may reduce their effectiveness, since a single similarity value can be misleading. In particular, a single similarity value cannot be clearly interpreted, since it hides the values of its individual objectives. The state-of-the-art approaches, which use service similarity functions, typically rely on single-objective functions. Going in a complementary direction, we propose the usage of multi-objective functions for calculating service similarity. We formally define such a function and we provide emerging results, which show that the effectiveness of service engineering tasks can be improved by using multi-objective functions.

According to the characteristics of the online test paper composition, the genetic algorithm is preferred as the core algorithm. However, there are some problems in the traditional genetic algorithm when it is being used, such as low efficiency in the later search period and easy to fall into the local optimal solution. To solve this problem, this paper makes some optimizations for the traditional genetic algorithm's coding scheme, initial population, fitness function and genetic operator. After the improvement, the composing test paper module based on genetic algorithm was finally implemented in java language through seven parts.

Agriculture plays an important role in farmer’s life. Sometimes manual identification of disease is time consuming and need of labor is more. One of the most important facts that reduce the growth of plants is disease attack. Overall study about agriculture shows that quality and quantity of agricultural products may be reduced due to various factors of plant diseases. These diseases can be more easily identified by using machine learning approach as compared to manual method. Hence machine learning method can be used to identify the affected leaf images.Images captured by camera will be processed using different image processing technique. These techniques will help in identifying plant diseases thereby increasing the yield of plants. This survey paper describes plant disease identification using Machine Learning Approach and study in detail about various techniques for disease identification and classification is also done.

A code clone is a pair of code fragments, within or between software systems that are similar. Since code clones often negatively impact the maintainability of a software system, a great many numbers of code clone detection techniques and tools have been proposed and studied over the last decade. To detect all possible similar source code patterns in general, the clone detection tools work on syntax level (such as texts, tokens, AST and so on) while lacking user-specific preferences. This often means the reported clones must be manually validated prior to any analysis in order to filter out the true positive clones from task or user-specific considerations. This manual clone validation effort is very time-consuming and often error-prone, in particular for large-scale clone detection. In this paper, we propose a machine learning based approach for automating the validation process. In an experiment with clones detected by several clone detectors in several different software systems, we found our approach has an accuracy of up to 87.4% when compared against the manual validation by multiple expert judges. The proposed method shows promising results in several comparative studies with the existing related approaches for automatic code clone validation. We also present our experimental results in terms of different code clone detection tools, machine learning algorithms and open source software systems.

The problem of classifying a research article into one or more fields of science is of particular importance for the academic search engines and digital libraries. A robust classification algorithm offers the users a wide variety of useful tools, such as the refinement of their search results, the browsing of articles by category, the recommendation of other similar articles, etc. In the current literature we encounter approaches which attempt to address this problem without taking into consideration important parameters such as the previous history of the authors and the categorization of the scientific journals which publish the articles. In addition, the existing works overlook the huge volume of the involved academic data. In this paper, we expand an existing effective algorithm for research articles classification, and we parallelize it on Apache Spark –a parallelization framework which is capable of sharing large amounts of data into the main memory of the nodes of a cluster– to enable the processing of large academic datasets. Furthermore, we present data manipulation methodologies which are useful not only for this particular problem, but also for most parallel machine learning approaches. In our experimental evaluation, we demonstrate that our proposed algorithm is considerably more accurate than the supervised learning approaches implemented within the machine learning library of Spark, whereas it outperforms them in terms of execution speed by a significant margin.

This paper presents a methodology for selecting best groups of predictor variables based on regression trees. Test results of the developed methodology applied to industrial pilot paper machine data are presented. Specifically, the results list process variable groups, which are more valuable in predicting paper quality variables. The benefit of paper quality prediction based on process variables is the timely reaction to changes happening during production process and, thus, the reduced operational costs. The proposed regression trees based group variable ranking methodology shows stable results on both data sets used in this study.

With today’s eye-tracking technologies, it is possible to analyze cognitive processes such as reading. There are many studies on that topic. We have studied some of these studies that analyze eye movements recording during reading by various machine learning algorithms.

Precise prediction of severe diseases resulting in mortality is one of the main issues in medical fields. Even if pathological and radiological measurements provide competitive precision, they usually require large costs of time and expense to obtain and analyze the data for prediction. Recently, end-to-end approaches based on deep neural networks have been proposed, however, they still suffer from the low classification performance and difficulties of interpretation. In this study, we propose a novel disease prediction method, EHAN (EHR History-based prediction using Attention Network), based on the recurrent neural network (RNN) and attention mechanism. The proposed method incorporates (1) a bidirectional gated recurrent units (GRU) for automated sequential modeling, (2) attention mechanism for improving long-term dependence modeling, (3) RNN-based gradient-weighted class activation mapping (Grad-CAM) to visualize the class specific attention-weights. We conducted the experiments to predict the occurrence of risky disease containing cardiovascular and cerebrovascular diseases from more than 40,000 hypertension patients' electronic health records (EHR). The results showed that the proposed method outperformed the state-of-the-art model with respect to the various performance metrics. Furthermore, we confirmed that the proposed visualizing methods can be used to assist data-driven discovery.

In the new era of genetic epidemiology, there have been growing interest in studying genetic variants and their associations to complex diseases. Advances in modern computational approaches have led to the search for useful interacting genetic variants that are associated to the manifestation of a disease. However, these conventional strategies face number of challenges in predicting interesting interactions when data acquisition and dimensionality increases. Deep learning promises empirical success in number of applications including bioinformatics to drive insights of biological complexities. A deep neural network was previously proposed to identify true causative two-locus SNP interactions. The method was evaluated on various simulated and real datasets. In this study, the performance of the previously proposed deep learning method is maximized by improving network learning and avoiding overfitting. The method is further extended for performing sensitivity analysis. The performance of the method is evaluated on chronical dialysis patient's data for identifying higher-order interactions. It was observed that the highly ranked two-locus and three-locus SNP interactions in mitochondrial D-loop has the highest risk for the manifestation of disease.

Whole-genome multiple alignments are widely used in genomics and evolution, and yet their accuracy is imperfect, due in part to the computational complexity of the task at hand. Identifying portions of these alignments that are likely to be incorrect would allow researchers to either work on improving them or flagging them for exclusion from downstream analyses. We introduce MSA-ED, a machine learning tool for the detection of errors in whole-genome multiple alignments. MSA-ED uses random forests or artificial neural networks to identify and classify several types of alignment errors. It is trained on labeled data obtained by using an evolution simulator to generate fake orthologous sequences and their correct alignment, and comparing it to the alignment produced by Multiz, a popular whole-genome aligner. Key to the success of MSA-ED is the engineering of several types of evolutionarily-inspired features that boost prediction accuracy. MSA-ED is shown to be able to detect certain types of errors with good accuracy. It is then applied to actual genomic alignments to identify putative alignment errors. Availability: https://github.com/jaspal1329/MSA-ED

Biometric identification systems must be able to distinguish between individuals in various conditions. This paper presents a review paper on face matchers between commercial and open source SDK and techniques available for face recognition. This paper also presents experiments done in performance comparisons between a commercial face matcher, VeriLook 5.6 and an open source matcher OpenBR 0.5 from a set of images collected from those who work in the offices in various situations including the different poses, and various illuminants. The experiment results taken from those officers in NECTEC have shown that a commercial face matcher performs better but this requires proper set up of face extraction parameters to ensure the optimal results. Further improvements would require other face detection algorithms to enhance the performance of both free and commercial face matchers according to their own particular shortcomings.

This paper presents an information-theoretic approach to variable selection for prediction of laboratory measurements of paper quality. Along with a well-known Principal Component Analysis we considered techniques for variable selection based on the classical Shannon Mutual Information and a novel Maximal Information Coefficient. A multilayer perceptron neural model was used to predict quality measurements and compare feature selection techniques. The suggested approach was tested on real industrial data obtained form a pilot paper machine. The presented results show that information-theoretic techniques perform better compared to Principal Component Analysis, providing higher accuracy results.

As the complexity and scale of circuits keep growing, clocking architectures of FPGAs have become more complex to meet the timing requirement. In this paper, to optimize wirelength and meanwhile meet emerging clocking architectural constraints, we propose several detailed placement techniques, i.e., two-step clock constraint legalization and chain move. After integrating these techniques into our FPGA placement framework, experimental results on ISPD 2017 benchmarks show that our proposed approach yields 2.3% shorter routed wirelength and the running time is 2x faster compared to the first place winner in the ISPD 2017 contest. Moreover, we explore the possibilities to use machine learning-based methods to predict routing congestion in UltraScale FPGAs. Experimental results on both ISPD 2016 and ISPD 2017 benchmarks show that our proposed congestion estimation model is a good approximation to the one obtained from Vivado and can lead to good placement results compared to the previous methods.

The process of mining comprises of supervised learning and unsupervised learning. It includes various approaches out of which data classification is one of the beneficial and constructive methods. This paper explores the effective functioning of the whole process. There are several cases in classification where the important data is missed during the process. It can hence be concluded that the process of mining is greatly affected by the absence of such kind of data. The process of extraction of unknown and new data from the huge dataset that has been left during the classification process is known as novelty detection. It aims to cover the most commonly used ideas in modeling the novelty data, to classify them as well as to provide useful methods which need to be used in order to identify novelty data for temporal data time series. Novelty detection generally focuses on the identification of shapes or patterns, space, density, distance and learning models. This paper mainly aims to identify the important data which is typically missed during the process of training. This research explains the overall concept to detect the novelty data that is used in the taxonomy of level set methods.

Automation plays an important role in production industry for improving the quality and throughput of the end product. In most of the textile industries, manual inspection of the manufactured product is done for identification of quality parameters such as dimensions and features. Manual assessment is costly, time-consuming and sometimes inaccurate for color analysis and matching. As a solution to this problem, we can use image processing techniques for color analysis and matching by using Microsoft Visual Studio, OpenCV, Python and C#. The GigE camera is used for acquiring the image of the fabric and analyzed for color matching using the above software platforms. The objective of this project is to perform color matching in fabrics for quality measures and to increase the efficiency of the process. Euclidian distance method and k-means color clustering method are performed for getting the required output and increasing throughput. It is found after experimentation that k-means color clustering method gives better results as compared to the normal Euclidian distance method. This is due to machine learning involved in k-means color clustering method, which helps in the identification of different color clusters in a fabric piece and setting standard values for color match of a fabric, thereby increasing the chance of getting a perfect color match.

Environmental parameters like humidity, temperature, rainfall, wind flow, light intensity, soil pH are main factors for precision agriculture. Fluctuations in weather parameters like humidity, temperature and so on along with the inappropriate management result into a decrease in crop productivity. Therefore disease prediction is more important to beat these problems. The real-time update will alert the farmer by indicating which crop is in trouble, so the expenses on insecticides, pesticides will reduce and overall economic condition of farmers will improve. The proposed system gives more emphasis to predict diseases of the crop with the use of the Internet of Things and machine learning algorithms. Different sensors collect the real-time data of environmental parameters like temperature, humidity, rainfall, light intensity. Utilizing these data, crop diseases are predicted using machine learning algorithms. Such predictions would warn the farmers about crop diseases through text message or web browser. This work can be extended in the future to help farmers in other ways like which fertilizer can be used to overcome this disease problem.

Platforms for publishing research papers are increasing largely that contribute to big data as their volume is humongous and are unstandardized. Classification of this huge chunk of data is one of the biggest challenges in Information Retrieval. In this paper we discuss a scoring based unsupervised learning approach to extract relevant features and classify the research papers according to their content on a two class dataset. Feature extraction is carried out by analyzing the sections of a research paper and scoring them, followed by a two level hybrid classification technique based on title and conceptual summary using graph clustering. Promising experimental results are observed for data set using our research paper classification method. We present the experimental results of our proposed algorithm for feature extraction and clustering and compare the same with different approaches reported in literature.

This paper discusses the identification of extend relation in scientific papers based on supervised machine learning. Identification of extend relations is conducted by classifying each sentence in scientific papers into extend category. Extend relation is one type of papers' relations that obtained by using the citation context based approach. Citation context is a set of words or phrases in a sentence collection that citing or discussing other papers. Citation context based approach use the semantic of citation sentence to identify the relationship between scientific papers and can identify more varied relationship than two other approaches i.e. content-based and citation analysis. The recently research in papers' relations used a rule-based approach to identify extend relations. In this paper, supervised learning approached with proposed features set was used to identify extend relations. The learning of classifier model is explored by using Naive Bayes, Decision Tree, Ibk and Logistic Regression. Experimental results show that the performance of extend sentence classification based on supervised machine learning with proposed features is superior compared to the baseline. Feature selection based on correlation value is also effective to improve the performance of the extend sentence classification.

A large amount of information is continuously generated in intensive health care. An analysis of these data streams can supply valuable insights to improve the monitoring of the patients. The volume, frequency and complexity of data, which come unlabeled, make their analysis a challenging task. Machine learning (ML) techniques have been successfully employed for mining data streams to extract useful knowledge for health care monitoring. It includes the detection of changes in the behavior of sensors, failures on machines or systems, and data anomalies. Anomaly (or outlier) detection is a ML task that aims to find exceptions or abnormalities in a dataset. These exceptions, in a medical context, can represent a new disease pattern, an event to be further investigated, behavior changes or potential health complications. Despite of its analysis in data streams is a challenging task, temporal abstractions techniques should help due to they deal with the management and abstraction of time based data, offering high level of visualization of each data object in its context. The aim of this paper is to review recent research in anomaly detection and temporal abstractions and discuss the application of their combination to intensive care data streams.

This short paper contains a skeletal overview of papers presented on this topic. We briefly explain what fuzzy intervals are, why they naturally appear in the description of uncertainty, and show that their usage is helpful on all the stages of real-life problem-solving. >

Presents a novel approach for the modelling of typical nonlinear systems at the wet end of the paper machines. Due to the complicated nature of the process, at first a pure multilayer perceptron (MLP) neural network is applied to establish the nonlinear model for the system. Instead of using standard backpropagation (BP) algorithms, genetic algorithm-based training is applied during the weight optimization phase. This is then followed by a logical combination of the so-formed neural network with a physical modelling exercise, leading to an improved semi-physical model which combines the advantages of physical and neural network modelling. The effectiveness of the proposed modelling techniques is illustrated by their applications in the establishment of two models, paper sizing and dry strength, for the wet-end chemical processes of the UMIST pilot paper machine.

Advanced map-matching algorithms use location and heading of GPS points along with geometrical and topological features of digital road networks to find the road segment on which the vehicle is moving. However, GPS errors sometimes impede map-matching algorithms in finding the correct segment, especially in dense and complicated parts of the network, such as near intersections with acute angles or on close parallel roads. In this paper an artificial neural network (ANN) approach is explored to improve the segment identification accuracy of map-matching algorithms. The proposed ANN is continuously trained by using the horizontal shift imposed on GPS points and once it is trained, it will be used to correct raw GPS points before inputting them into the map-matching algorithm. Integrating the proposed ANN enabled an existing map-matching algorithm to find the correct segments for some of the GPS points where the original map-matching algorithm had failed to do so.

Most works covering the topic of transfer learning propose an algorithm to solve a given domain adaptation problem, then test the algorithm using real-world datasets. A test with a real-world dataset represents a single transfer learning test condition, which partially measures an algorithm's performance. Previous research has placed little emphasis on developing a comprehensive and uniform test for transfer learning algorithms. With this in mind, a test framework is proposed, comprising of distortion profiles which define a comprehensive test suite. The unique contribution of this paper is the definition of a test framework that measures a more complete profile of a transfer learning algorithm's capability, facilitating the identification of relative poor and good performance areas. As a proof of concept, the test framework is used to test a homogeneous transfer learning algorithm. The test framework will be the basis for a number of future applications.

The effective bandwidth management in multi-service computer networks such as university networks has become a challenge in recent years. The growth of internet traffic and limitation of bandwidth resources persuade the information technology (IT) managers to focus on effective bandwidth allocation policies. One of the important issues discussed in this domain is how to assign the bandwidth fairly based on the priority levels. In this paper, focusing on the "priority-based bandwidth allocation", a hybrid data mining method is developed to manage the limited bandwidth in a university network more effectively. This method is composed of two main steps and uses the clustering and classification techniques. The main purpose is to detect, analyze and predict students' behavioral patterns in a university network and identify the main factors that affect their tendency in using internet. The proposed method is applied on a real data of a network university. The results indicate that "degree level" and "age" are the most important factors that influence students' tendency to use internet. The results would be also useful for prediction purposes. It helps the IT managers to predict a new student's tendency to use internet given his/her characteristics. By analyzing the results, the IT managers can make better decisions to optimize the allocation of bandwidth resources.