• Title/Summary/Keyword: and Pre-Processing

Search Result 1,936, Processing Time 0.03 seconds

The Noise Robust Algorithm to Detect the Starting Point of Music for Content Based Music Retrieval System (노이즈에 강인한 음악 시작점 검출 알고리즘)

  • Kim, Jung-Soo;Sung, Bo-Kyung;Koo, Kwang-Hyo;Ko, Il-Ju
    • Journal of the Korea Society of Computer and Information
    • /
    • v.14 no.9
    • /
    • pp.95-104
    • /
    • 2009
  • This paper proposes the noise robust algorithm to detect the starting point of music. Detection of starting point of music is necessary to solve computational-waste problem and retrieval-comparison problem with inconsistent input data in music content based retrieval system. In particular, such detection is even more necessary in time sequential retrieval method that compares data in the sequential order of time in contents based music retrieval system. Whereas it has the long point that the retrieval is fast since it executes simple comparison in the order of time, time sequential retrieval method has the short point that data starting time to be compared should be the same. However, digitalized music cannot guarantee the equity of starting time by bit rate conversion. Therefore, this paper ensured that recognition rate shall not decrease even while executing high speed retrieval by applying time sequential retrieval method through detection of music starting point in the pre-processing stage of retrieval. Starting point detection used minimum wave model that can detect effective sound, and for strength against noise, the noises existing in mute sound were swapped. The proposed algorithm was confirmed to produce about 38% more excellent performance than the results to which starting point detection was not applied, and was verified for the strength against noise.

Improving Naïve Bayes Text Classifiers with Incremental Feature Weighting (점진적 특징 가중치 기법을 이용한 나이브 베이즈 문서분류기의 성능 개선)

  • Kim, Han-Joon;Chang, Jae-Young
    • The KIPS Transactions:PartB
    • /
    • v.15B no.5
    • /
    • pp.457-464
    • /
    • 2008
  • In the real-world operational environment, most of text classification systems have the problems of insufficient training documents and no prior knowledge of feature space. In this regard, $Na{\ddot{i}ve$ Bayes is known to be an appropriate algorithm of operational text classification since the classification model can be evolved easily by incrementally updating its pre-learned classification model and feature space. This paper proposes the improving technique of $Na{\ddot{i}ve$ Bayes classifier through feature weighting strategy. The basic idea is that parameter estimation of $Na{\ddot{i}ve$ Bayes considers the degree of feature importance as well as feature distribution. We can develop a more accurate classification model by incorporating feature weights into Naive Bayes learning algorithm, not performing a learning process with a reduced feature set. In addition, we have extended a conventional feature update algorithm for incremental feature weighting in a dynamic operational environment. To evaluate the proposed method, we perform the experiments using the various document collections, and show that the traditional $Na{\ddot{i}ve$ Bayes classifier can be significantly improved by the proposed technique.

Improvements of an English Pronunciation Dictionary Generator Using DP-based Lexicon Pre-processing and Context-dependent Grapheme-to-phoneme MLP (DP 알고리즘에 의한 발음사전 전처리와 문맥종속 자소별 MLP를 이용한 영어 발음사전 생성기의 개선)

  • 김회린;문광식;이영직;정재호
    • The Journal of the Acoustical Society of Korea
    • /
    • v.18 no.5
    • /
    • pp.21-27
    • /
    • 1999
  • In this paper, we propose an improved MLP-based English pronunciation dictionary generator to apply to the variable vocabulary word recognizer. The variable vocabulary word recognizer can process any words specified in Korean word lexicon dynamically determined according to the current recognition task. To extend the ability of the system to task for English words, it is necessary to build a pronunciation dictionary generator to be able to process words not included in a predefined lexicon, such as proper nouns. In order to build the English pronunciation dictionary generator, we use context-dependent grapheme-to-phoneme multi-layer perceptron(MLP) architecture for each grapheme. To train each MLP, it is necessary to obtain grapheme-to-phoneme training data from general pronunciation dictionary. To automate the process, we use dynamic programming(DP) algorithm with some distance metrics. For training and testing the grapheme-to-phoneme MLPs, we use general English pronunciation dictionary with about 110 thousand words. With 26 MLPs each having 30 to 50 hidden nodes and the exception grapheme lexicon, we obtained the word accuracy of 72.8% for the 110 thousand words superior to rule-based method showing the word accuracy of 24.0%.

  • PDF

Development of Win32 API Message Authorization System for Windows based Application Provision Service (윈도우 기반 응용프로그램 제공 서비스를 위한 Win32 API 메시지 인가 시스템의 개발)

  • Kim, Young-Ho;Jung, Mi-Na;Won, Yong-Gwan
    • The KIPS Transactions:PartC
    • /
    • v.11C no.1
    • /
    • pp.47-54
    • /
    • 2004
  • The growth of computer resource and network speed has increased requests for the use of remotely located computer systems by connecting through computer networks. This phenomenon has hoisted research activities for application service provision that uses server-based remote computing paradigm. The server-based remote computing paradigm has been developed as the ASP (Application Service Provision) model, which provides remote users through application sharing protocol to application programs. Security requirement such as confidentiality, availability, integrity should be satisfied to provide ASP service using centralized computing system. Existing Telnet or FTP service for a remote computing systems have satisfied security requirement by a simple access control to files and/or data. But windows-based centralized computing system is vulnerable to confidentiality, availability, integrity where many users use the same application program installed in the same computer. In other words, the computing system needs detailed security level for each user different from others, such that only authorized user or group of users can run some specific functional commands for the program. In this paper, we propose windows based centralized computing system that sets security policies for each user for the use of instructions of the application programs, and performs access control to the instructions based on the security policies. The system monitors all user messages which are executed through graphical user interface by the users connecting to the system. Ail Instructions, i.e. messages, for the application program are now passed to authorization process that decides if an Instruction is delivered to the application program based on the pre-defined security polices. This system can be used as security clearance for each user for the shared computing resource as well as shared application programs.

Efficient Processing using Static Validity Circle for Continuous Skyline Queries (연속적인 스카이라인 질의의 정적 유효 영역을 이용한 효율적인 처리)

  • Li, Zhong-He;Park, Young-Bae
    • Journal of KIISE:Databases
    • /
    • v.33 no.6
    • /
    • pp.631-643
    • /
    • 2006
  • Moving objects in a mobile environment to change their position based on the change of time require a query with their position as a basis. Efficient Regional Decision for Continuous Skyline Queries requires objectively pre-calculating the OSR(Optimal Skyline Region) regardless of the speed and direction of the moving objects. It proposes techniques to reduce the frequency of continuous queries by choosing a VCircle(Validity Circle) as safe location which has radius of the distance to the closest region with position on the moving object at center. But, a VCircle's area varies based on the Moving object's position from first marked time of continuous query. Therefore, the frequency of its continuous query is variable and also when the object moves inside of OSR, query can re-occur frequently In this paper, we suggest a technique of selecting an IVCircle(Interior Validity Circle) in a Skyline Region as the static Safe Region using the characteristics of the OSR. An Interior IVCircle can be calculated in advance when the OSR is decided. Our experiment shows that the frequency of using IVcircle as safe region reduced than that of using VCircle as safe region by 52.55%.

Comparative Analysis of Pre-processing Method for Standardization of Multi-spectral Drone Images (다중분광 드론영상의 표준화를 위한 전처리 기법 비교·분석)

  • Ahn, Ho-Yong;Ryu, Jae-Hyun;Na, Sang-il;Lee, Byung-mo;Kim, Min-ji;Lee, Kyung-do
    • Korean Journal of Remote Sensing
    • /
    • v.38 no.6_1
    • /
    • pp.1219-1230
    • /
    • 2022
  • Multi-spectral drones in agricultural observation require quantitative and reliable data based on physical quantities such as radiance or reflectance in crop yield analysis. In the case of remote sensing data for crop monitoring, images taken in the same area over time-series are required. In particular, biophysical data such as leaf area index or chlorophyll are analyzed through time-series data under the same reference, it can be directly analyzed. So, comparable reflectance data are required. Orthoimagery using drone images, the entire image pixel values are distorted or there is a difference in pixel values at the junction boundary, which limits accurate physical quantity estimation. In this study, reflectance and vegetation index based on drone images were calculated according to the correction method of drone images for time-series crop monitoring. comparing the drone reflectance and ground measured data for spectral characteristics analysis.

Extending StarGAN-VC to Unseen Speakers Using RawNet3 Speaker Representation (RawNet3 화자 표현을 활용한 임의의 화자 간 음성 변환을 위한 StarGAN의 확장)

  • Bogyung Park;Somin Park;Hyunki Hong
    • KIPS Transactions on Software and Data Engineering
    • /
    • v.12 no.7
    • /
    • pp.303-314
    • /
    • 2023
  • Voice conversion, a technology that allows an individual's speech data to be regenerated with the acoustic properties(tone, cadence, gender) of another, has countless applications in education, communication, and entertainment. This paper proposes an approach based on the StarGAN-VC model that generates realistic-sounding speech without requiring parallel utterances. To overcome the constraints of the existing StarGAN-VC model that utilizes one-hot vectors of original and target speaker information, this paper extracts feature vectors of target speakers using a pre-trained version of Rawnet3. This results in a latent space where voice conversion can be performed without direct speaker-to-speaker mappings, enabling an any-to-any structure. In addition to the loss terms used in the original StarGAN-VC model, Wasserstein distance is used as a loss term to ensure that generated voice segments match the acoustic properties of the target voice. Two Time-Scale Update Rule (TTUR) is also used to facilitate stable training. Experimental results show that the proposed method outperforms previous methods, including the StarGAN-VC network on which it was based.

유청단백질로 만들어진 식품포장재에 관한 연구

  • Kim, Seong-Ju
    • 한국유가공학회:학술대회논문집
    • /
    • 2002.04a
    • /
    • pp.59-60
    • /
    • 2002
  • Edible films such as wax coatings, sugar and chocolate covers, and sausage casings, have been used in food applications for years$^{(1)}$ However, interest in edible films and biodegradable polymers has been renewed due to concerns about the environment, a need to reduce the quantity of disposable packaging, and demand by the consumer for higher quality food products. Edible films can function as secondary packaging materials to enhance food quality and reduce the amount of traditional packaging needed. For example, edible films can serve to enhance food quality by acting as moisture and gas barriers, thus, providing protection to a food product after the primary packaging is opened. Edible films are not meant to replace synthetic packaging materials; instead, they provide the potential as food packagings where traditional synthetic or biodegradable plastics cannot function. For instance, edible films can be used as convenient soluble pouches containing single-servings for products such as instant noodles and soup/seasoning combination. In the food industry, they can be used as ingredient delivery systems for delivering pre-measured ingredients during processing. Edible films also can provide the food processors with a variety of new opportunities for product development and processing. Depends on materials of edible films, they also can be sources of nutritional supplements. Especially, whey proteins have excellent amino acid balance while some edible films resources lack adequate amount of certain amino acids, for example, soy protein is low in methionine and wheat flour is low in lysine$^{(2)}$. Whey proteins have a surplus of the essential amino acid lysine, threonine, methionine and isoleucine. Thus, the idea of using whey protein-based films to individually pack cereal products, which often deficient in these amino acids, become very attractive$^{(3)}$. Whey is a by-product of cheese manufacturing and much of annual production is not utilized$^{(4)}$. Development of edible films from whey protein is one of the ways to recover whey from dairy industry waste. Whey proteins as raw materials of film production can be obtained at inexpensive cost. I hypothesize that it is possible to make whey protein-based edible films with improved moisture barrier properties without significantly altering other properties by producing whey protein/lipid emulsion films and these films will be suitable far food applications. The fellowing are the specific otjectives of this research: 1. Develop whey protein/lipid emulsion edible films and determine their microstructures, barrier (moisture and oxygen) and mechanical (tensile strength and elongation) properties. 2. Study the nature of interactions involved in the formation and stability of the films. 3. Investigate thermal properties, heat sealability, and sealing properties of the films. 4. Demonstrate suitability of their application in foods as packaging materials. Methodologies were developed to produce edible films from whey protein isolate (WPI) and concentrate (WPC), and film-forming procedure was optimized. Lipids, butter fat (BF) and candelilla wax (CW), were added into film-forming solutions to produce whey protein/lipid emulsion edible films. Significant reduction in water vapor and oxygen permeabilities of the films could be achieved upon addition of BF and CW. Mechanical properties were also influenced by the lipid type. Microstructures of the films accounted for the differences in their barrier and mechanical properties. Studies with bond-dissociating agents indicated that disulfide and hydrogen bonds, cooperatively, were the primary forces involved in the formation and stability of whey protein/lipid emulsion films. Contribution of hydrophobic interactions was secondary. Thermal properties of the films were studied using differential scanning calorimetry, and the results were used to optimize heat-sealing conditions for the films. Electron spectroscopy for chemical analysis (ESCA) was used to study the nature of the interfacial interaction of sealed films. All films were heat sealable and showed good seal strengths while the plasticizer type influenced optimum heat-sealing temperatures of the films, 130$^{\circ}$C for sorbitol-plasticized WPI films and 110$^{\circ}$C for glycerol-plasticized WPI films. ESCA spectra showed that the main interactions responsible for the heat-sealed joint of whey protein-based edible films were hydrogen bonds and covalent bonds involving C-0-H and N-C components. Finally, solubility in water, moisture contents, moisture sorption isotherms and sensory attributes (using a trained sensory panel) of the films were determined. Solubility was influenced primarily by the plasticizer in the films, and the higher the plasticizer content, the greater was the solubility of the films in water. Moisture contents of the films showed a strong relationship with moisture sorption isotherm properties of the films. Lower moisture content of the films resulted in lower equilibrium moisture contents at all aw levels. Sensory evaluation of the films revealed that no distinctive odor existed in WPI films. All films tested showed slight sweetness and adhesiveness. Films with lipids were scored as being opaque while films without lipids were scored to be clear. Whey protein/lipid emulsion edible films may be suitable for packaging of powder mix and should be suitable for packaging of non-hygroscopic foods$^{(5,6,7,8,)}$.

  • PDF

A Study on Information Exchange Scheme for Reliability in the Wireless Multicasting (무선 멀티캐스팅에서 신뢰성을 위한 정보 교환 기법에 관한 연구)

  • Im, Ji-Yeong;Jeong, Tae-Myeong
    • The KIPS Transactions:PartC
    • /
    • v.9C no.2
    • /
    • pp.247-256
    • /
    • 2002
  • In a wireless multicasting when a mobile host moves to the new bate station being in the same multicast group it needs to exchange information about data delivery between base stations to receive data from the new base station at once. However it is inefficient to use the existence schemes because it takes too much time to exchange information and many overheads. The next, a mobile host moving to the base station not being in the same multicast group, the old base station will pre-forward data to neighboring base stations to avoid transmission delay. However, if other mobile hosts move at short interval, the old base station may retransmit the same data to the same neighboring base stations. In this paper we proposed called Information Exchange Scheme (IES). In IES in the same multicast grope the base stations exchange information locally so it takes the minimum time and overheads to use IES. Also in IES the neighboring base stations delay to delete data for continuous moving of other MHs. We also present how our scheme is efficient by producing cost ad simulating.

A study of SCM strategic plan: Focusing on the case of LG electronics (공급사슬 관리 구축전략에 관한 연구: LG전자 사례 중심으로)

  • Lee, Gi-Wan;Lee, Sang-Youn
    • Journal of Distribution Science
    • /
    • v.9 no.3
    • /
    • pp.83-94
    • /
    • 2011
  • Most domestic companies, with the exclusion of major firms, are reluctant to implement a supply chain management (SCM) network into their operations. Most small- and medium-sized enterprises are not even aware of SCM. Due to the inherent total-systems efficiency of SCM, it coordinates domestic manufacturers, subcontractors, distributors, and physical distributors and cuts down on cost of inventory control, as well as demand management. Furthermore, a lack of SCM causes a decrease in competitiveness for domestic companies. The reason lies in the fundamentality of SCM, which is the characteristic of information sharing, process innovation throughout SCM, and the vast range of problems the SCM management tool is able to address. This study suggests the contemplation and reformation of the current SCM situation by analyzing the SCM strategic plan, discourses and logical discussions on the topic, and a successful case for adapting SCM; hence, the study plans to productively "process" SCM. First, it is necessary to contemplate the theoretical background of SCM before discussing how to successfully process SCM. I will describe the concept and background of SCM in Chapter 2, with a definition of SCM, types of SCM promotional activities, fields of SCM, necessity of applying SCM, and the effects of SCM. All of the defects in currently processing SCM will be introduced in Chapter 3. Discussion items include the following: the Bullwhip Effect; the breakdown in supply chain and sales networks due to e-business; the issue that even though the key to a successful SCM is cooperation between the production and distribution company, during the process of SCM, the companies, many times, put their profits first, resulting in a possible defect in demands estimation. Furthermore, the problems of processing SCM in a domestic distribution-production company concern Information Technology; for example, the new system introduced to the company is not compatible with the pre-existing document architecture. Second, for effective management, distribution and production companies should cooperate and enhance their partnership in the aspect of the corporation; however, in reality, this seldom occurs. Third, in the aspect of the work process, introducing SCM could provoke corporations during the integration of the distribution-production process. Fourth, to increase the achievement of the SCM strategy process, they need to set up a cross-functional team; however, many times, business partners lack the cooperation and business-information sharing tools necessary to effect the transition to SCM. Chapter 4 will address an SCM strategic plan and a case study of LG Electronics. The purpose of the strategic plan, strategic plans for types of business, adopting SCM in a distribution company, and the global supply chain process of LG Electronics will be introduced. The conclusion of the study is located in Chapter 5, which addresses the issue of the fierce competition that companies currently face in the global market environment and their increased investment in SCM, in order to better cope with short product life cycle and high customer expectations. The SCM management system has evolved through the adaptation of improved information, communication, and transportation technologies; now, it demands the utilization of various strategic resources. The introduction of SCM provides benefits to the management of a network of interconnected businesses by securing customer loyalty with cost and time savings, derived through the consolidation of many distribution systems; additionally, SCM helps enterprises form a wide range of marketing strategies. Thus, we could conclude that not only the distributors but all types of businesses should adopt the systems approach to supply chain strategies. SCM deals with the basic stream of distribution and increases the value of a company by replacing physical distribution with information. By the company obtaining and sharing ready information, it is able to create customer satisfaction at the end point of delivery to the consumer.

  • PDF