Search results for: feature noise

Authors: Luis Alvarado, Victor Poblete, Isaac Gonzalez, Yetzabeth Gonzalez

Abstract:

In MIREX 2016 (http://www.music-ir.org/mirex), the deep neural network (DNN)-Deep Chroma Extractor, proposed by Korzeniowski and Wiedmer, reached the highest score in an audio chord recognition task. In the present paper, this tool is assessed under acoustic reverberant environments and distinct source-microphone distances. The evaluation dataset comprises The Beatles and Queen datasets. These datasets are sequentially re-recorded with a single microphone in a real reverberant chamber at four reverberation times (0 -anechoic-, 1, 2, and 3 s, approximately), as well as four source-microphone distances (32, 64, 128, and 256 cm). It is expected that the performance of the trained DNN will dramatically decrease under these acoustic conditions with signals degraded by room reverberation and distance to the source. Recently, the effect of the bio-inspired Locally-Normalized Cepstral Coefficients (LNCC), has been assessed in a text independent speaker verification task using speech signals degraded by additive noise at different signal-to-noise ratios with variations of recording distance, and it has also been assessed under reverberant conditions with variations of recording distance. LNCC showed a performance so high as the state-of-the-art Mel Frequency Cepstral Coefficient filters. Based on these results, this paper proposes a variation of locally-normalized triangular filters called Locally-Normalized Quarter Tone (LNQT) filters. By using the LNQT spectrogram, robustness improvements of the trained Deep Chroma Extractor are expected, compared with classical triangular filters, and thus compensating the music signal degradation improving the accuracy of the chord recognition system.

Keywords: chord recognition, deep neural networks, feature extraction, music information retrieval

Procedia PDF Downloads 232

Authors: Aidan J. Bowes, Reaz Hasan

Abstract:

The automotive industry is continually aiming to develop the aerodynamics of car body design. This may be for a variety of beneficial reasons such as to increase speed or fuel efficiency by reducing drag. However recently there has been a greater amount of focus on wind noise produced while driving. Designers in this industry seek a combination of both simplicity of approach and overall effectiveness. This combined with the growing availability of commercial CFD (Computational Fluid Dynamics) packages is likely to lead to an increase in the use of RANS (Reynolds Averaged Navier-Stokes) based CFD methods. This is due to these methods often being simpler than other CFD methods, having a lower demand on time and computing power. In this investigation the effectiveness of turbulent flow and acoustic noise prediction using RANS based methods has been assessed for different wing mirror geometries. Three different RANS based models were used, standard k-ε, realizable k-ε and k-ω SST. The merits and limitations of these methods are then discussed, by comparing with both experimental and numerical results found in literature. In general, flow prediction is fairly comparable to more complex LES (Large Eddy Simulation) based methods; in particular for the k-ω SST model. However acoustic noise prediction still leaves opportunities for more improvement using RANS based methods.

Keywords: acoustics, aerodynamics, RANS models, turbulent flow

Procedia PDF Downloads 446

Authors: Chin-Chen Chang, I-Ta Lee, Tsung-Ta Ke, Wen-Kai Tai

Abstract:

Common methods for resizing image size include scaling and cropping. However, these two approaches have some quality problems for reduced images. In this paper, we propose an image resizing algorithm by separating the main objects and the background. First, we extract two feature maps, namely, an enhanced visual saliency map and an improved gradient map from an input image. After that, we integrate these two feature maps to an importance map. Finally, we generate the target image using the importance map. The proposed approach can obtain desired results for a wide range of images.

Keywords: energy map, visual saliency, gradient map, seam carving

Procedia PDF Downloads 476

Authors: Sung Un Kim, Ivana Martinović, Snježana Stanarević Katavić

Abstract:

As more and more youth use mobile devices, such as tablets and smartphones, for information seeking in their everyday lives, the purpose of this study is to understand the behaviors of youth seeking health information on mobile devices. The specific objective of this study is to examine 1) for what health issues youth use mobile devices, 2) for what reasons youth use mobile devices to obtain health information, 3) in what ways youth use mobile devices for health information, and 4) the features of health applications that youth find useful. The researchers devised a questionnaire for this study. Four hundred eight students from two high schools, located in Osijek, Croatia, participated by answering the questionnaire (281 girls and 127 boys). The collected data were analyzed using descriptive statistics and content analysis. The results show that among all participants, about 85 percent (n = 344) reported having used mobile devices for health information. The most frequent health topic for which they had been using mobile devices is physical activity (n = 273), followed by eating issues and nutrition (n = 224), mental health (n = 160), sexual health (n = 157), alcohol, drugs, and tobacco (n = 125), safety (n = 96) and particular diseases (n = 62). They use mobile devices to obtain health information due to the ease of use (n = 342), the ease of sharing health information (n = 281), portability (n = 215), timeliness (n = 162), and the ease of tracking/recording/monitoring health status (n = 147). Of those who have used mobile devices for health information, three-quarters (n = 261) use mobile devices to search health information, while 32.8% (n =113) use applications and 31.7% (n =109) browse information. Those who have used applications for health information (n = 113) consider the alert feature (n=107) as the most useful, followed by the tracking/recording/monitoring feature (n =92), the customized information feature (n = 86), the video feature (n = 58), and the sharing feature (n =39). It is notable that although health applications have been actively developed and studied, a majority of the participants search for or browse information on mobile devices, instead of using applications. The researchers will discuss reasons that some of them did not use mobile devices to obtain health information, students’ concerns about using health applications, and features that they wish to have in health applications.

Keywords: Croatia, health information, information seeking behaviors, mobile devices, youth

Procedia PDF Downloads 402

Authors: Hsu-Hui Cheng, Peng-Chian Chen, Shu-Yuan Chang, Jie-Ying Zhang

Abstract:

Activities in the music practice rooms range from playing, listening, rehearsing to music performing. The good room acoustics in a music practice room enables a music teacher to teach more effectively subtle concepts such as intonation, articulation, balance, dynamics and tone production. A poor acoustical environment would deeply affect the development of basic musical skills of music students. Practicing in the music practice room is an essential daily activity for music students; consequently, music practice rooms are very important facilities in a music school or department. The purpose of this survey is to measure and analyze the acoustic condition of piano practice rooms at the department of music in Zhaoqing University and accordingly apply a more effective teaching method to music students. The volume of the music practice room is approximately 25 m³, and it has existing curtains and some wood hole sound-absorbing panels. When all small music practice rooms are in constant use for teaching, it was found that the values of the background noise at 45, 46, 42, 46, 45 dB(A) in the small music practice room ( the doors and windows were close), respectively. The noise levels in the small music practice room to higher than standard levels (35dB(A)).

Keywords: acoustical performance, music practice room, noise level, piano room

Procedia PDF Downloads 226

Authors: Yuyan Yi, Jingyi Zheng, Nedret Billor

Abstract:

Independent component analysis (ICA) is one of the most commonly used blind source separation (BSS) techniques for signal pre-processing, such as noise reduction and feature extraction. The main parameter in the ICA method is the number of independent components (IC). Although there have been several methods for the determination of the number of ICs, it has not been given sufficient attentionto this important parameter. In this study, wereview the mostused methods fordetermining the number of ICs and providetheir advantages and disadvantages. Further, wepropose an improved version of column-wise ICAByBlock method for the determination of the number of ICs.To assess the performance of the proposed method, we compare the column-wise ICAbyBlock with several existing methods through different ICA methods by using simulated and real signal data. Results show that the proposed column-wise ICAbyBlock is an effective and stable method for determining the optimal number of components in ICA. This method is simple, and results can be demonstrated intuitively with good visualizations.

Keywords: independent component analysis, optimal number, column-wise, correlation coefficient, cross-validation, ICAByblock

Procedia PDF Downloads 99

Authors: Majid Pourahmadi

Abstract:

The performance of time-reversal MUSIC algorithm will be dramatically degrades in presence of strong noise and multiple scattering (i.e. when scatterers are close to each other). This is due to error in determining the number of scatterers. The present paper provides a new approach to alleviate such a problem using an information theoretic criterion referred as minimum description length (MDL). The merits of the novel approach are confirmed by the numerical examples. The results indicate the time-reversal MUSIC yields accurate estimate of the target locations with considerable noise and multiple scattering in the received signals.

Keywords: microwave imaging, time reversal, MUSIC algorithm, minimum description length (MDL)

Procedia PDF Downloads 337

Authors: Muhammad Afzal, Junaid Uzair Satti

Abstract:

The noise emanating from the ducting of heating, ventilation, and air-conditioning (HVAC) system is often attenuated by using the dissipative silencers. Such devices work well for the high-frequency noise but are less operative in the low-frequency noise range. The present study analyzes a reactive silencer comprising expansion chamber of the elastic membranes partitioned symmetrically by a rigid plate. The Mode-Matching scheme has been developed to solve the governing boundary value problem. The orthogonal and non-orthogonal duct modes of acoustic pressures and normal velocities are matched at interfaces. It enables to recast the differential system into the infinite system of linear algebraic of equations, which is, then truncated and inverted for the solution. The truncated solution is validated through the conservation of energy and reconstruction of matching conditions. The results for scattering energy flux and transmission loss are shown against frequency and the dimensions of the chamber. It is seen that the stop-band of the silencer can be shifted to the broadband by changing the dimensions of the chamber and the properties of the elastic membranes. The modeled reactive silencer is more efficient in low frequency regime where the passive devices are least effective.

Keywords: acoustic scattering, elastic membranes mode-matching, reactive silencer

Procedia PDF Downloads 146

Authors: Antoni Ivanov, Nikolay Dandanov, Nicole Christoff, Vladimir Poulkov

Abstract:

Spectrum underutilization has made cognitive radio a promising technology both for current and future telecommunications. This is due to the ability to exploit the unused spectrum in the bands dedicated to other wireless communication systems, and thus, increase their occupancy. The essential function, which allows the cognitive radio device to perceive the occupancy of the spectrum, is spectrum sensing. In this paper, the performance of modern adaptations of the four most widely used spectrum sensing techniques namely, energy detection (ED), cyclostationary feature detection (CSFD), matched filter (MF) and eigenvalues-based detection (EBD) is compared. The implementation has been accomplished through the PlutoSDR hardware platform and the GNU Radio software package in very low Signal-to-Noise Ratio (SNR) conditions. The optimal detection performance of the examined methods in a realistic implementation-oriented model is found for the common relevant parameters (number of observed samples, sensing time and required probability of false alarm).

Keywords: cognitive radio, dynamic spectrum access, GNU Radio, spectrum sensing

Procedia PDF Downloads 245

Authors: Feng Wang, Shencheng Ni, Shuying Han, Shanhong You

Abstract:

With the development of optical communication, optical performance monitoring (OPM) has received more and more attentions. Since optical signal-to-noise ratio (OSNR) is directly related to bit error rate (BER), it is one of the important parameters in optical networks. Recently, artificial neural network (ANN) has been greatly developed. ANN has strong learning and generalization ability. In this paper, a method of OSNR monitoring based on delay-tap sampling (DTS) and ANN has been proposed. DTS technique is used to extract the eigenvalues of the signal. Then, the eigenvalues are input into the ANN to realize the OSNR monitoring. The experiments of 10 Gb/s non-return-to-zero (NRZ) on–off keying (OOK), 20 Gb/s pulse amplitude modulation (PAM4) and 20 Gb/s return-to-zero (RZ) differential phase-shift keying (DPSK) systems are demonstrated for the OSNR monitoring based on the proposed method. The experimental results show that the range of OSNR monitoring is from 15 to 30 dB and the root-mean-square errors (RMSEs) for 10 Gb/s NRZ-OOK, 20 Gb/s PAM4 and 20 Gb/s RZ-DPSK systems are 0.36 dB, 0.45 dB and 0.48 dB respectively. The impact of chromatic dispersion (CD) on the accuracy of OSNR monitoring is also investigated in the three experimental systems mentioned above.

Keywords: artificial neural network (ANN), chromatic dispersion (CD), delay-tap sampling (DTS), optical signal-to-noise ratio (OSNR)

Procedia PDF Downloads 112

Authors: Yu Hung Chiang, Hei Chia Wang

Abstract:

Nowadays, tourism has become a part of life. Before reserving hotels, customers need some information, which the most important source is online reviews, about hotels to help them make decisions. Due to the dramatic growing of online reviews, it is impossible for tourists to read all reviews manually. Therefore, designing an automatic review analysis system, which summarizes reviews, is necessary for them. The main purpose of the system is to understand the opinion of reviews, which may be positive or negative. In other words, the system would analyze whether the customers who visited the hotel like it or not. Using sentiment analysis methods will help the system achieve the purpose. In sentiment analysis methods, the targets of opinion (here they are called the feature) should be recognized to clarify the polarity of the opinion because polarity of the opinion may be ambiguous. Hence, the study proposes an unsupervised method using Part-Of-Speech pattern and multi-lexicons sentiment analysis to summarize all reviews. We expect this method can help customers search what they want information as well as make decisions efficiently.

Keywords: text mining, sentiment analysis, product feature extraction, multi-lexicons

Procedia PDF Downloads 331

Authors: Umm-E-Hani, Faiza Babar, Hanif Durad

Abstract:

Malware-detecting approaches suffer many limitations, due to which all anti-malware solutions have failed to be reliable enough for detecting zero-day malware. Signature-based solutions depend upon the signatures that can be generated only when malware surfaces at least once in the cyber world. Another approach that works by detecting the anomalies caused in the environment can easily be defeated by diligently and intelligently written malware. Solutions that have been trained to observe the behavior for detecting malicious files have failed to cater to the malware capable of detecting the sandboxed or protected environment. Machine learning and deep learning-based approaches greatly suffer in training their models with either an imbalanced dataset or an inadequate number of samples. AI-based anti-malware solutions that have been trained with enough samples targeted a selected feature vector, thus ignoring the input of leftover features in the maliciousness of malware just to cope with the lack of underlying hardware processing power. Our research focuses on producing an anti-malware solution for detecting malicious PE files by circumventing the earlier-mentioned shortcomings. Our proposed framework, which is based on automated feature engineering through autoencoders, trains the model over a fairly large dataset. It focuses on the visual patterns of malware samples to automatically extract the meaningful part of the visual pattern. Our experiment has successfully produced a state-of-the-art accuracy of 99.54 % over test data.

Keywords: malware, auto encoders, automated feature engineering, classification

Procedia PDF Downloads 72

Authors: Tajinder Kaur, Anu Bala

Abstract:

An image retrieval system is a computer system for browsing, searching, and retrieving images from a large database of digital images a new algorithm meant for content-based image retrieval (CBIR) is presented in this paper. The proposed method combines the color and texture features which are extracted the global and local information of the image. The local texture feature is extracted by using local binary patterns (LBP), which are evaluated by taking into consideration of local difference between the center pixel and its neighbors. For the global color feature, the color histogram (CH) is used which is calculated by RGB (red, green, and blue) spaces separately. In this paper, the combination of color and texture features are proposed for content-based image retrieval. The performance of the proposed method is tested on Corel 1000 database which is the natural database. The results after being investigated show a significant improvement in terms of their evaluation measures as compared to LBP and CH.

Keywords: color, texture, feature extraction, local binary patterns, image retrieval

Procedia PDF Downloads 366

Authors: Konysbek Aksaule

Abstract:

The purpose of this work is to explore new and effective ways of teaching English to students who are studying a foreign language since the timeliness of the problem disclosed in this article is due to the high level of English proficiency that potential specialists must have due to high competition in the context of global globalization. The article presents an analysis of the feasibility and effectiveness of using an authentic feature film in teaching English to students. The methodological basis of the study includes an assessment of the level of students' proficiency in a foreign language, the stage of evaluating the film, and the method of selecting the film for certain categories of students. The study also contains a list of practical tasks that can be applied in the process of viewing and perception of an original feature film in a foreign language, and which are aimed at developing language skills such as speaking and listening. The results of this study proved that teaching English to students through watching an original film is one of the most effective methods because it improves speech perception, speech reproduction ability, and also expands the vocabulary of students and makes their speech fluent. In addition, learning English through watching foreign films has a huge impact on the cultural views and knowledge of students about the country of the language being studied and the world in general. Thus, this study demonstrates the high potential of using authentic feature film in English lessons for pedagogical science and methods of teaching English in general.

Keywords: university, education, students, foreign language, feature film

Procedia PDF Downloads 148

Authors: Othman Maklouf, Abdunnaser Tresh

Abstract:

GPS and inertial navigation system (INS) have complementary qualities that make them ideal use for sensor fusion. The limitations of GPS include occasional high noise content, outages when satellite signals are blocked, interference and low bandwidth. The strengths of GPS include its long-term stability and its capacity to function as a stand-alone navigation system. In contrast, INS is not subject to interference or outages, have high bandwidth and good short-term noise characteristics, but have long-term drift errors and require external information for initialization. A combined system of GPS and INS subsystems can exhibit the robustness, higher bandwidth and better noise characteristics of the inertial system with the long-term stability of GPS. The most common estimation algorithm used in integrated INS/GPS is the Kalman Filter (KF). KF is able to take advantages of these characteristics to provide a common integrated navigation implementation with performance superior to that of either subsystem (GPS or INS). This paper presents a simplified KF algorithm for land vehicle navigation application. In this integration scheme, the GPS derived positions and velocities are used as the update measurements for the INS derived PVA. The KF error state vector in this case includes the navigation parameters as well as the accelerometer and gyroscope error states.

Keywords: GPS, INS, Kalman filter, inertial navigation system

Procedia PDF Downloads 471

Authors: Bushra Zafar, Usman Qamar

Abstract:

Large data sample size and dimensions render the effectiveness of conventional data mining methodologies. A data mining technique are important tools for collection of knowledgeable information from variety of databases and provides supervised learning in the form of classification to design models to describe vital data classes while structure of the classifier is based on class attribute. Classification efficiency and accuracy are often influenced to great extent by noisy and undesirable features in real application data sets. The inherent natures of data set greatly masks its quality analysis and leave us with quite few practical approaches to use. To our knowledge first time, we present a new approach for investigation of structure and quality of datasets by providing a targeted analysis of localization of noisy and irrelevant features of data sets. Machine learning is based primarily on feature selection as pre-processing step which offers us to select few features from number of features as a subset by reducing the space according to certain evaluation criterion. The primary objective of this study is to trim down the scope of the given data sample by searching a small set of important features which may results into good classification performance. For this purpose, a heuristic for wrapper-based feature selection using genetic algorithm and for discriminative feature selection an external classifier are used. Selection of feature based on its number of occurrence in the chosen chromosomes. Sample dataset has been used to demonstrate proposed idea effectively. A proposed method has improved average accuracy of different datasets is about 95%. Experimental results illustrate that proposed algorithm increases the accuracy of prediction of different diseases.

Keywords: data mining, generic algorithm, KNN algorithms, wrapper based feature selection

Procedia PDF Downloads 316

Authors: Thomas Bryan, Veton Kepuska, Ivica Kostanic

Abstract:

A simple adaptive voice activity detector (VAD) is implemented using Gabor and gammatone atomic decomposition of speech for high Gaussian noise environments. Matching pursuit is used for atomic decomposition, and is shown to achieve optimal speech detection capability at high data compression rates for low signal to noise ratios. The most active dictionary elements found by matching pursuit are used for the signal reconstruction so that the algorithm adapts to the individual speakers dominant time-frequency characteristics. Speech has a high peak to average ratio enabling matching pursuit greedy heuristic of highest inner products to isolate high energy speech components in high noise environments. Gabor and gammatone atoms are both investigated with identical logarithmically spaced center frequencies, and similar bandwidths. The algorithm performs equally well for both Gabor and gammatone atoms with no significant statistical differences. The algorithm achieves 70% accuracy at a 0 dB SNR, 90% accuracy at a 5 dB SNR and 98% accuracy at a 20dB SNR using 30dB SNR as a reference for voice activity.

Keywords: atomic decomposition, gabor, gammatone, matching pursuit, voice activity detection

Procedia PDF Downloads 290

Authors: Pushpendra S. Bharti, S. Maheshwari

Abstract:

Electric discharge machining (EDM) is one of the most widely used non-conventional manufacturing process to shape difficult-to-cut materials. The process yield, in terms of material removal rate, surface roughness and tool wear rate, of EDM may considerably be improved by selecting the optimal combination(s) of process parameters. This paper employs Multi-response signal-to-noise (MRSN) ratio technique to find the optimal combination(s) of the process parameters during EDM of Inconel 718. Three cases v.i.z. high cutting efficiency, high surface finish, and normal machining have been taken and the optimal combinations of input parameters have been obtained for each case. Analysis of variance (ANOVA) has been employed to find the dominant parameter(s) in all three cases. The experimental verification of the obtained results has also been made. MRSN ratio technique found to be a simple and effective multi-objective optimization technique.

Keywords: electric discharge machining, material removal rate, surface roughness, too wear rate, multi-response signal-to-noise ratio, multi response signal-to-noise ratio, optimization

Procedia PDF Downloads 354

Authors: Dim En Nyaung, Thin Lai Lai Thein

Abstract:

Due to the rapid increase of Internet, web opinion sources dynamically emerge which is useful for both potential customers and product manufacturers for prediction and decision purposes. These are the user generated contents written in natural languages and are unstructured-free-texts scheme. Therefore, opinion mining techniques become popular to automatically process customer reviews for extracting product features and user opinions expressed over them. Since customer reviews may contain both opinionated and factual sentences, a supervised machine learning technique applies for subjectivity classification to improve the mining performance. In this paper, we dedicate our work is the task of opinion summarization. Therefore, product feature and opinion extraction is critical to opinion summarization, because its effectiveness significantly affects the identification of semantic relationships. The polarity and numeric score of all the features are determined by Senti-WordNet Lexicon. The problem of opinion summarization refers how to relate the opinion words with respect to a certain feature. Probabilistic based model of supervised learning will improve the result that is more flexible and effective.

Keywords: opinion mining, opinion summarization, sentiment analysis, text mining

Procedia PDF Downloads 332

Authors: A. Bortkiewcz, A. Dudarewicz, P. Małecki, M. Kłaczyński, T. Wszołek, Małgorzata Pawlaczyk-Łuszczyńska

Abstract:

Low-frequency noise (LFN) has been recognized as a special environmental pollutant. It is usually considered a broadband noise with the dominant content of low frequencies from 10 Hz to 250 Hz. A growing body of data shows that LFN differs in nature from other environmental noises, which are at comparable levels but not dominated by low-frequency components. The primary and most frequent adverse effect of LFN exposure is annoyance. Moreover, some recent investigations showed that LFN at relatively low A-weighted sound pressure levels (40−45 dB) occurring in office-like areas could adversely affect the mental performance, especially of high-sensitive subjects. It is well documented that high-frequency noise disturbs various types of human functions; however, there is very little data on the impact of LFN on well-being and health, including the cardiovascular system. Heart rate variability (HRV) is a sensitive marker of autonomic regulation of the circulatory system. Walker and co-workers found that LFN has a significantly more negative impact on cardiovascular response than exposure to high-frequency noise and that changes in HRV parameters resulting from LFN exposure tend to persist over time. The negative reactions of the cardiovascular system in response to LFN generated by wind turbines (20-200 Hz) were confirmed by Chiu. The scientific aim of the study is to assess the relationship between the spectral-temporal characteristics of LFN and the activity of the autonomic nervous system, considering the subjective assessment of annoyance, sensitivity to this type of noise, and cognitive and general health status. The study will be conducted in 20 male students in a special, acoustically prepared, constantly supervised room. Each person will be tested 4 times (4 sessions), under conditions of non-exposure (sham) and exposure to noise of wind turbines recorded at a distance of 250 meters from the turbine with different frequencies and frequency ranges: acoustic band 20 Hz-20 kHz, infrasound band 5-20 Hz, acoustic band + infrasound band. The order of sessions of the experiment will be randomly selected. Each session will last 1 h. There will be a 2-3 days break between sessions to exclude the possibility of the earlier session influencing the results of the next one. Before the first exposure, a questionnaire will be conducted on noise sensitivity, general health status using the GHQ questionnaire, hearing organ status and sociodemographic data. Before each of the 4 exposures, subjects will complete a brief questionnaire on their mood and sleep quality the night before the test. After the test, the subjects will be asked about any discomfort and subjective symptoms during the exposure. Before the test begins, Holter ECG monitoring equipment will be installed. HRV will be analyzed from the ECG recordings, including time and frequency domain parameters. The tests will always be performed in the morning (9-12) to avoid the influence of diurnal rhythm on HRV results. Students will perform psychological tests 15 minutes before the end of the test (Vienna Test System).

Keywords: neurovegetative control, heart rate variability (HRV), cognitive processes, low frequency noise

Procedia PDF Downloads 80

Authors: Meenal Badki

Abstract:

We address the issue of active feature determination, where the objective is to determine the set of examples on which additional data (such as lab tests) needs to be gathered, given a large number of examples with some features (such as demographics) and some examples with all the features (such as the complete Electronic Health Record). We note that certain features may be more costly, unique, or laborious to gather. Our proposal is a general active learning approach that is independent of classifiers and similarity metrics. It allows us to identify examples that differ from the full data set and obtain all the features for the examples that match. Our comprehensive evaluation shows the efficacy of this approach, which is driven by four authentic clinical tasks.

Keywords: feature determination, classification, active learning, sample-efficiency

Procedia PDF Downloads 75

Authors: Hyunchul Ahn, William X. S. Wong

Abstract:

Corporate credit rating prediction is one of the most important topics, which has been studied by researchers in the last decade. Over the last decade, researchers are pushing the limit to enhance the exactness of the corporate credit rating prediction model by applying several data-driven tools including statistical and artificial intelligence methods. Among them, multiclass support vector machine (MSVM) has been widely applied due to its good predictability. However, heuristics, for example, parameters of a kernel function, appropriate feature and instance subset, has become the main reason for the critics on MSVM, as they have dictate the MSVM architectural variables. This study presents a hybrid MSVM model that is intended to optimize all the parameter such as feature selection, instance selection, and kernel parameter. Our model adopts genetic algorithm (GA) to simultaneously optimize multiple heterogeneous design factors of MSVM.

Keywords: corporate credit rating prediction, Feature selection, genetic algorithms, instance selection, multiclass support vector machines

Procedia PDF Downloads 294

Authors: Usman Qamar, Younus Javed

Abstract:

Frequent pattern mining is the process of finding a pattern (a set of items, subsequences, substructures, etc.) that occurs frequently in a data set. It was proposed in the context of frequent itemsets and association rule mining. Frequent pattern mining is used to find inherent regularities in data. What products were often purchased together? Its applications include basket data analysis, cross-marketing, catalog design, sale campaign analysis, Web log (click stream) analysis, and DNA sequence analysis. However, one of the bottlenecks of frequent itemset mining is that as the data increase the amount of time and resources required to mining the data increases at an exponential rate. In this investigation a new algorithm is proposed which can be uses as a pre-processor for frequent itemset mining. FASTER (FeAture SelecTion using Entropy and Rough sets) is a hybrid pre-processor algorithm which utilizes entropy and rough-sets to carry out record reduction and feature (attribute) selection respectively. FASTER for frequent itemset mining can produce a speed up of 3.1 times when compared to original algorithm while maintaining an accuracy of 71%.

Keywords: rough-sets, classification, feature selection, entropy, outliers, frequent itemset mining

Procedia PDF Downloads 437

Authors: Abdulkerim Ilgun, Ahmad Javid Zia

Abstract:

In developing countries, the urban populations are increasing rapidly and with this increment the residential areas are experiencing major problems. Construction of high-rise buildings in confined spaces is one of the most practical solutions for this problem. However, by living in high-rise buildings and sharing common residential areas, residents will face many problems. Irritating sound problem which is known as noise is one of the major problems mentioned above. The second most important problem is the weight of the high-rise buildings which makes the structure more vulnerable to earthquakes. To decrease earthquake loads it’s very important to decrease the weight of the buildings. To solve the problem of noise and keep the building weight at minimum level, experimentally designed soundproof gypsum partition wall which has optimum thickness has been used in high-rise story building and the results have been compared with ordinary brick partition walls. In this compression the effect of weights of soundproof gypsum walls and ordinary brick walls in accordance to structural engineering have been investigated.

Keywords: cellubor, gypsum board, gypsum partition walls, light partition walls, noise, sound

Procedia PDF Downloads 307

Authors: Woei-Shyan Lee, Shuo-Ling Chang

Abstract:

The nanoindentation behaviour and phase transformation of annealed single-crystal silicon wafers are examined. The silicon specimens are annealed at temperatures of 250, 350 and 450ºC, respectively, for 15 minutes and are then indented to maximum loads of 30, 50 and 70 mN. The phase changes induced in the indented specimens are observed using transmission electron microscopy (TEM) and micro-Raman scattering spectroscopy (RSS). For all annealing temperatures, an elbow feature is observed in the unloading curve following indentation to a maximum load of 30 mN. Under higher loads of 50 mN and 70 mN, respectively, the elbow feature is replaced by a pop-out event. The elbow feature reveals a complete amorphous phase transformation within the indented zone, whereas the pop-out event indicates the formation of Si XII and Si III phases. The experimental results show that the formation of these crystalline silicon phases increases with an increasing annealing temperature and indentation load. The hardness and Young’s modulus both decrease as the annealing temperature and indentation load are increased.

Keywords: nanoindentation, silicon, phase transformation, amorphous, annealing

Procedia PDF Downloads 373

Authors: Jian Shi, Baoguo Yu, Haonan Jia, Meng Liu, Ping Huang

Abstract:

Adapting to the flexibility of war, a large number of guided weapons launch from aircraft. Therefore, the inertial navigation system loaded in the weapon needs to undergo an alignment process in the air. This article proposes the following methods to the problem of inaccurate modeling of the system under large misalignment angles, the accuracy reduction of filtering caused by outliers, and the noise changes in GPS signals: first, considering the large misalignment errors of Strapdown Inertial Navigation System (SINS)/GPS, a more accurate model is made rather than to make a small-angle approximation, and the Unscented Kalman Filter (UKF) algorithms are used to estimate the state; then, taking into account the impact of GPS noise changes on the fine alignment algorithm, the innovation adaptive filtering algorithm is introduced to estimate the GPS’s noise in real-time; at the same time, in order to improve the anti-interference ability of the air fine alignment algorithm, a robust filtering algorithm based on outlier detection is combined with the air fine alignment algorithm to improve the robustness of the algorithm. The algorithm can improve the alignment accuracy and robustness under interference conditions, which is verified by simulation.

Keywords: air alignment, fine alignment, inertial navigation system, integrated navigation system, UKF

Procedia PDF Downloads 166

Authors: Pengfei Meng, Shuangcheng Jia, Qian Li

Abstract:

We proposed a real-time high-precision semantic segmentation network based on a multi-resolution feature fusion module, the auxiliary feature extracting module, upsampling module, and atrous spatial pyramid pooling (ASPP) module. We designed a feature fusion structure, which is integrated with sufficient features of different resolutions. We also studied the effect of side-branch structure on the network and made discoveries. Based on the discoveries about the side-branch of the network structure, we used a side-branch auxiliary feature extraction layer in the network to improve the effectiveness of the network. We also designed upsampling module, which has better results than the original upsampling module. In addition, we also re-considered the locations and number of atrous spatial pyramid pooling (ASPP) modules and modified the network structure according to the experimental results to further improve the effectiveness of the network. The network presented in this paper takes the backbone network of Bisenetv2 as a basic network, based on which we constructed a network structure on which we made improvements. We named this network deep multiple-resolution bilateral networks for real-time, referred to as DMBR-Net. After experimental testing, our proposed DMBR-Net network achieved 81.2% mIoU at 119FPS on the Cityscapes validation dataset, 80.7% mIoU at 109FPS on the CamVid test dataset, 29.9% mIoU at 78FPS on the COCOStuff test dataset. Compared with all lightweight real-time semantic segmentation networks, our network achieves the highest accuracy at an appropriate speed.

Keywords: multi-resolution feature fusion, atrous convolutional, bilateral networks, pyramid pooling

Procedia PDF Downloads 149

Authors: Varun Agarwal

Abstract:

Introduction: With the advent of personalized medicine, histopathological review of whole slide images (WSIs) for cancer diagnosis presents an exceedingly time-consuming, complex task. Specifically, detecting metastatic regions in WSIs of sentinel lymph node biopsies necessitates a full-scanned, holistic evaluation of the image. Thus, digital pathology, low-level image manipulation algorithms, and machine learning provide significant advancements in improving the efficiency and accuracy of WSI analysis. Using Camelyon16 data, this paper proposes a deep learning pipeline to automate and ameliorate breast cancer metastasis localization and WSI classification. Methodology: The model broadly follows five stages -region of interest detection, WSI partitioning into image tiles, convolutional neural network (CNN) image-segment classifications, probabilistic mapping of tumor localizations, and further processing for whole WSI classification. Transfer learning is applied to the task, with the implementation of Inception-ResNetV2 - an effective CNN classifier that uses residual connections to enhance feature representation, adding convolved outputs in the inception unit to the proceeding input data. Moreover, in order to augment the performance of the transfer learning CNN, a stack of convolutional denoising autoencoders (CDAE) is applied to produce embeddings that enrich image representation. Through a saliency-detection algorithm, visual training segments are generated, which are then processed through a denoising autoencoder -primarily consisting of convolutional, leaky rectified linear unit, and batch normalization layers- and subsequently a contrast-normalization function. A spatial pyramid pooling algorithm extracts the key features from the processed image, creating a viable feature map for the CNN that minimizes spatial resolution and noise. Results and Conclusion: The simplified and effective architecture of the fine-tuned transfer learning Inception-ResNetV2 network enhanced with the CDAE stack yields state of the art performance in WSI classification and tumor localization, achieving AUC scores of 0.947 and 0.753, respectively. The convolutional feature retention and compilation with the residual connections to inception units synergized with the input denoising algorithm enable the pipeline to serve as an effective, efficient tool in the histopathological review of WSIs.

Keywords: breast cancer, convolutional neural networks, metastasis mapping, whole slide images

Procedia PDF Downloads 130

Authors: Zainab Mutlaq Ibrahim, Mohamed Bader-El-Den, Mihaela Cocea

Abstract:

Students' textual feedback can hold unique patterns and useful information about learning process, it can hold information about advantages and disadvantages of teaching methods, assessment components, facilities, and other aspects of teaching. The results of analysing such a feedback can form a key point for institutions’ decision makers to advance and update their systems accordingly. This paper proposes a data mining framework for analysing end of unit general textual feedback using part of speech feature (PoS) with four machine learning algorithms: support vector machines, decision tree, random forest, and naive bays. The proposed framework has two tasks: first, to use the above algorithms to build an optimal model that automatically classifies the whole data set into two subsets, one subset is tailored to assessment practices (assessment related), and the other one is the non-assessment related data. Second task to use the same algorithms to build an optimal model for whole data set, and the new data subsets to automatically detect their sentiment. The significance of this paper is to compare the performance of the above four algorithms using part of speech feature to the performance of the same algorithms using n-grams feature. The paper follows Knowledge Discovery and Data Mining (KDDM) framework to construct the classification and sentiment analysis models, which is understanding the assessment domain, cleaning and pre-processing the data set, selecting and running the data mining algorithm, interpreting mined patterns, and consolidating the discovered knowledge. The results of this paper experiments show that both models which used both features performed very well regarding first task. But regarding the second task, models that used part of speech feature has underperformed in comparison with models that used unigrams and bigrams.

Keywords: assessment, part of speech, sentiment analysis, student feedback

Procedia PDF Downloads 142

Authors: Jianghao Hu, Hongyu Wang

Abstract:

The effective and efficient human pose estimation algorithm is an important task for real-time human pose estimation on mobile devices. This paper proposes a light-weight human key points detection algorithm, Light-Weight Network for Real-Time Pose Estimation (LWPE). LWPE uses light-weight backbone network and depthwise separable convolutions to reduce parameters and lower latency. LWPE uses the feature pyramid network (FPN) to fuse the high-resolution, semantically weak features with the low-resolution, semantically strong features. In the meantime, with multi-scale prediction, the predicted result by the low-resolution feature map is stacked to the adjacent higher-resolution feature map to intermediately monitor the network and continuously refine the results. At the last step, the key point coordinates predicted in the highest-resolution are used as the final output of the network. For the key-points that are difficult to predict, LWPE adopts the online hard key points mining strategy to focus on the key points that hard predicting. The proposed algorithm achieves excellent performance in the single-person dataset selected in the AI (artificial intelligence) challenge dataset. The algorithm maintains high-precision performance even though the model only contains 3.9M parameters, and it can run at 225 frames per second (FPS) on the generic graphics processing unit (GPU).

Keywords: depthwise separable convolutions, feature pyramid network, human pose estimation, light-weight backbone

Procedia PDF Downloads 154