Academic literature on the topic 'Embedding a vector of bits'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Embedding a vector of bits.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Journal articles on the topic "Embedding a vector of bits"
1
Yang, Zekun, and Juan Feng. "A Causal Inference Method for Reducing Gender Bias in Word Embedding Relations." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 05 (April 3, 2020): 9434–41. http://dx.doi.org/10.1609/aaai.v34i05.6486.
Full textAbstract:
Word embedding has become essential for natural language processing as it boosts empirical performances of various tasks. However, recent research discovers that gender bias is incorporated in neural word embeddings, and downstream tasks that rely on these biased word vectors also produce gender-biased results. While some word-embedding gender-debiasing methods have been developed, these methods mainly focus on reducing gender bias associated with gender direction and fail to reduce the gender bias presented in word embedding relations. In this paper, we design a causal and simple approach for mitigating gender bias in word vector relation by utilizing the statistical dependency between gender-definition word embeddings and gender-biased word embeddings. Our method attains state-of-the-art results on gender-debiasing tasks, lexical- and sentence-level evaluation tasks, and downstream coreference resolution tasks.
2
Lee, Jiann-Der, Yaw-Hwang Chiou, and Jing-Ming Guo. "Reversible Data Hiding Scheme with High Embedding Capacity Using Semi-Indicator-Free Strategy." Mathematical Problems in Engineering 2013 (2013): 1–11. http://dx.doi.org/10.1155/2013/476181.
Full textAbstract:
A novel reversible data-hiding scheme is proposed to embed secret data into a side-matched-vector-quantization- (SMVQ-) compressed image and achieve lossless reconstruction of a vector-quantization- (VQ-) compressed image. The rather random distributed histogram of a VQ-compressed image can be relocated to locations close to zero by SMVQ prediction. With this strategy, fewer bits can be utilized to encode SMVQ indices with very small values. Moreover, no indicator is required to encode these indices, which yields extrahiding space to hide secret data. Hence, high embedding capacity and low bit rate scenarios are deposited. More specifically, in terms of the embedding rate, the bit rate, and the embedding capacity, experimental results show that the performance of the proposed scheme is superior to those of the former data hiding schemes for VQ-based, VQ/SMVQ-based, and search-order-coding- (SOC-) based compressed images.
3
D R, Vinay, and Ananda Babu J. "A Novel Secure Data Hiding Technique into Video Sequences Using RVIHS." International Journal of Computer Network and Information Security 13, no. 2 (April 8, 2021): 53–65. http://dx.doi.org/10.5815/ijcnis.2021.02.05.
Full textAbstract:
Most of the present hiding techniques on video are considered over plaintext domain and plain video sequences are used to embed information bits. The work presented here reveals the novelty for information embedding in a video sequence over the ciphered domain. The carrier video signal is encrypted using chaos technique which uses multiple chaotic maps for encryption. The proposed reversible video information hiding scheme (RVIHS) exhibits an innovative property that, at the decoding side we can perfectly extract the information along with carrier video without any distortion. The public key modulation is a mechanism used to achieve data embedding, where as in secret key encryption is not required. The proposed approach is used to differentiate encoded and non-encoded picture patches at decoder end by implementing 2 class Support Vector Machine grouping. This helps for us to retrieve the original visual sequence with embedded message and to scale up embedding capacity. The experiment is conducted using real time videos for embedding the information. The outcome of proposed work bring about best embedding capacity, compared to existing techniques.
4
Lauscher, Anne, Goran Glavaš, Simone Paolo Ponzetto, and Ivan Vulić. "A General Framework for Implicit and Explicit Debiasing of Distributional Word Vector Spaces." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 05 (April 3, 2020): 8131–38. http://dx.doi.org/10.1609/aaai.v34i05.6325.
Full textAbstract:
Distributional word vectors have recently been shown to encode many of the human biases, most notably gender and racial biases, and models for attenuating such biases have consequently been proposed. However, existing models and studies (1) operate on under-specified and mutually differing bias definitions, (2) are tailored for a particular bias (e.g., gender bias) and (3) have been evaluated inconsistently and non-rigorously. In this work, we introduce a general framework for debiasing word embeddings. We operationalize the definition of a bias by discerning two types of bias specification: explicit and implicit. We then propose three debiasing models that operate on explicit or implicit bias specifications and that can be composed towards more robust debiasing. Finally, we devise a full-fledged evaluation framework in which we couple existing bias metrics with newly proposed ones. Experimental findings across three embedding methods suggest that the proposed debiasing models are robust and widely applicable: they often completely remove the bias both implicitly and explicitly without degradation of semantic information encoded in any of the input distributional spaces. Moreover, we successfully transfer debiasing models, by means of cross-lingual embedding spaces, and remove or attenuate biases in distributional word vector spaces of languages that lack readily available bias specifications.
5
Tissier, Julien, Christophe Gravier, and Amaury Habrard. "Near-Lossless Binarization of Word Embeddings." Proceedings of the AAAI Conference on Artificial Intelligence 33 (July 17, 2019): 7104–11. http://dx.doi.org/10.1609/aaai.v33i01.33017104.
Full textAbstract:
Word embeddings are commonly used as a starting point in many NLP models to achieve state-of-the-art performances. However, with a large vocabulary and many dimensions, these floating-point representations are expensive both in terms of memory and calculations which makes them unsuitable for use on low-resource devices. The method proposed in this paper transforms real-valued embeddings into binary embeddings while preserving semantic information, requiring only 128 or 256 bits for each vector. This leads to a small memory footprint and fast vector operations. The model is based on an autoencoder architecture, which also allows to reconstruct original vectors from the binary ones. Experimental results on semantic similarity, text classification and sentiment analysis tasks show that the binarization of word embeddings only leads to a loss of ∼2% in accuracy while vector size is reduced by 97%. Furthermore, a top-k benchmark demonstrates that using these binary vectors is 30 times faster than using real-valued vectors.
6
K., Akubuilo, and Rix Torimiro. "LARGE DATA EMBEDDING; PROBLEM & SOLUTION." Engineering Science & Technology Journal 1, no. 2 (December 29, 2019): 18–22. http://dx.doi.org/10.51594/estj.v1i2.114.
Full textAbstract:
The objective of the study was to propose a high capacity data embedding system from DCT domain. The default quantization table is used for fixed mask projection quantization steps. Accordingly, DCT coefficient of the host image from low to higher frequency bands and embed bits from band to band with specially designed base vectors called Hadamard vectors. The embedding scheme procedure is described step wise. The proposed system can be used for data embedding and can be associated with another encryption method to make it safer. The proposed system is reported to be highly robust and secure
7
Cao, Fang, Yujie Fu, Heng Yao, Mian Zou, Jian Li, and Chuan Qin. "Separable Reversible Data Hiding in Encrypted VQ-Encoded Images." Security and Communication Networks 2022 (April 23, 2022): 1–16. http://dx.doi.org/10.1155/2022/1227926.
Full textAbstract:
In this paper, a reversible data-hiding scheme in encrypted, vector quantization (VQ) encoded images is proposed. During image encryption, VQ-encoded image, including codebook and index table, is encrypted by content owner with stream-cipher and permutation to protect the privacy of image contents. As for additional-data embedding, a baseline method is first proposed and its corresponding optimized method is then given. By grouping one high-occurrence index with one or multiple low-occurrence indices, a series of index groups are constructed. Thus, by modifying the high-occurrence index to the corresponding index within the same group according to the current to-be-embedded bits, data embedding can be realized. The optimal hiding capacity is obtained by optimizing the coefficient vector for different types of index groups. Separable operations of data extraction, image decryption, and recovery can be achieved on the receiver side based on the availability of the encryption and data-hiding keys. Experimental results show that our scheme can achieve high hiding capacity and satisfactory directly decrypted image quality and guarantee security and reversibility simultaneously.
8
Subramanian, Maheswari, and Reeba Korah. "A Framework of Secured Embedding Scheme Using Vector Discrete Wavelet Transformation and Lagrange Interpolation." Journal of Computer Networks and Communications 2018 (2018): 1–9. http://dx.doi.org/10.1155/2018/8695103.
Full textAbstract:
Information hiding techniques have a significant role in recent application areas. Steganography is the embedding of information within an innocent cover work in a way which cannot be detected by any person without accessing the steganographic key. The proposed work uses a steganographic scheme for useful information with the help of human skin tone regions as cover image. The proposed algorithm has undergone Lagrange interpolation encryption for enhancement of the security of the hidden information. First, the skin tone regions are identified by using YCbCr color space which can be used as a cover image. Image pixels which belong to the skin regions are used to carry more secret bits, and the secret information is hidden in both horizontal and vertical sequences of the skin areas of the cover image. The secret information will hide behind the human skin regions rather than other objects in the same image because the skin pixels have high intensity value. The performance of embedding is done and is quite invisible by the vector discrete wavelet transformation (VDWT) technique. A new Lagrange interpolation-based encryption method is introduced to achieve high security of the hidden information with higher payload and better visual quality.
9
Tang, Chun Ge, Tie Sheng Fan, Lei Liu, and Zhi Hui Li. "Blind Digital Image Watermarking Algorithm Based on the Chain Code." Advanced Materials Research 546-547 (July 2012): 410–15. http://dx.doi.org/10.4028/www.scientific.net/amr.546-547.410.
Full textAbstract:
A new blind digital watermarking algorithm based on the chain code is proposed. The chain code is obtained by the characteristics of the original image -the edge contour. The feather can reflect the overall correlation of the vector image, and chain code expression can significantly reduce the boundary representation of the amount of data required. For the watermarking embedding, the original vector image is divided into sub-block images, and two bits of the watermarking information are embedded into sub-block images repeatedly by quantization. For watermarking extracting, the majority decision method is employed to determine the size of the extracted watermark. Experimental results show that the image quality is not significantly lowered after watermarking. The algorithm can resist the basic conventional attacks and has good robustness on the shear attacks.
10
Voyiatzis, Ioannis. "A Low-Cost BIST Scheme for Test Vector Embedding in Accumulator-Generated Sequences." VLSI Design 2008 (March 17, 2008): 1–8. http://dx.doi.org/10.1155/2008/680157.
Full textAbstract:
Test set embedding built-in self test (BIST) schemes are a class of pseudorandom BIST techniques where the test set is embedded into the sequence generated by the BIST pattern generator, and they displace common pseudorandom schemes in cases where reverse-order simulation cannot be applied. Single-seed embedding schemes embed the test set into a single sequence and demand extremely small hardware overhead since no additional control or memory to reconfigure the test pattern generator is required. The challenge in this class of schemes is to choose the best pattern generator among various candidate configurations. This, in turn, calls for a need to evaluate the location of each test pattern in the sequence as fast as possible, in order to try as many candidate configurations as possible for the test pattern generator. This problem is known as the test vector-embedding problem. In this paper we present a novel solution to the test vector-embedding problem for sequences generated by accumulators. The time overhead of the solution is of the order O(1). The applicability of the presented method for embedding test sets for the testing of real-world circuits is investigated through experimental results in some well-known benchmarks; comparisons with previously proposed schemes indicate that comparable test lengths are achieved, while the time required for the calculations is accelerated by more than 30 times.
Dissertations / Theses on the topic "Embedding a vector of bits"
1
Талмач, Дмитро Павлович. "Детерміновані методи відображення повідомлення в точку еліптичної кривої, заданої у різних формах." Bachelor's thesis, КПІ ім. Ігоря Сікорського, 2021. https://ela.kpi.ua/handle/123456789/44276.
Full textAbstract:
Данна робота присвячена розробцi детермiнованих полiномiальних
алгоритмiв кодування бiтових векторiв в точки елiптичних кривих
представлених у рiзних формах. У роботi приводяться основнi необхiднi
для розумiння викладок вiдомостi про елiптичнi кривi, особливо кривi в
формi Едвардса. Далi детально розглядається проблема кодування
елементiв поля, над яким визначена крива, у множину точок кривої для
використання у криптографiчних протоколах, в основi яких лежить
хешування або задача iнкапсуляцiї ключа. У останньому роздiлi
презентуються новi алгоритми, наводиться їх порiвняльний аналiз.The work is devoted to constructing deterministic polynomial algorithm for encoding sequences of bits into points of Elliptic Curves represented in different forms. The work presents basic information related to the topic of Elliptic Curves, especially in the Edwards form, that is necessary for understanding further mathematical calculations. Next, the problem of encoding underlying field elements, over which the curve is defined, into points of the curve for using this encoding in cryptographic protocols, which are based on hashing or key encapsulation schemes, is considered in more detail. In the last section new algorithms are presented and compared.
2
Gibert, Domingo Jaume. "Vector Space Embedding of Graphs via Statistics of Labelling Information." Doctoral thesis, Universitat Autònoma de Barcelona, 2012. http://hdl.handle.net/10803/96240.
Full textAbstract:
El reconeixement de patrons és la tasca que pretén distingir objectes entre diferents classes. Quan aquesta tasca es vol solucionar de forma automàtica un pas crucial és el com representar formalment els patrons a l'ordinador. En funció d'aquests formalismes, podem distingir entre el reconeixement estadístic i l'estructural. El primer descriu objectes com un conjunt de mesures col·locats en forma del que s'anomena un vector de característiques. El segon assumeix que hi ha relacions entre parts dels objectes que han de quedar explícitament representades i per tant fa servir estructures relacionals com els grafs per codificar la seva informació inherent. Els espais vectorials són una estructura matemàtica molt flexible que ha permès definir diverses maneres eficients d'analitzar patrons sota la forma de vectors de característiques. De totes maneres, la representació vectorial no és capaç d'expressar explícitament relacions binàries entre parts dels objectes i està restrigida a mesurar sempre, independentment de la complexitat dels patrons, el mateix nombre de característiques per cadascun d'ells. Les representacions en forma de graf presenten la situació contrària. Poden adaptar-se fàcilment a la complexitat inherent dels patrons però introdueixen un problema d'alta complexitat computational, dificultant el disseny d'eines eficients per al procés i l'anàlisis de patrons.
Resoldre aquesta paradoxa és el principal objectiu d'aquesta tesi. La situació ideal per resoldre problemes de reconeixement de patrons seria el representar-los fent servir estructures relacionals com els grafs, i a l'hora, poder fer ús del ric repositori d'eines pel processament de dades del reconeixement estadístic. Una solució elegant a aquest problema és la de transformar el domini dels grafs en el domini dels vectors, on podem aplicar qualsevol algorisme de processament de dades. En altres paraules, assignant a cada graf un punt en un espai vectorial, automàticament tenim accés al conjunt d'algorismes del món estadístic per aplicar-los al domini dels grafs. Aquesta metodologia s'anomena graph embedding.
En aquesta tesi proposem de fer una associació de grafs a vectors de característiques de forma simple i eficient fixant l'atenció en la informació d'etiquetatge dels grafs. En particular, comptem les freqüències de les etiquetes dels nodes així com de les aretes entre etiquetes determinades. Tot i la seva localitat, aquestes característiques donen una representació prou robusta de les propietats globals dels grafs. Primer tractem el cas de grafs amb etiquetes discretes, on les característiques són sencilles de calcular. El cas continu és abordat com una generalització del cas discret, on enlloc de comptar freqüències d'etiquetes, ho fem de representants d'aquestes. Ens trobem que les representacions vectorials que proposem pateixen d'alta dimensionalitat i correlació entre components, i tractem aquests problems mitjançant algorismes de selecció de característiques. També estudiem com la diversitat de diferents representacions pot ser explotada per tal de millorar el rendiment de classificadors base en el marc d'un sistema de múltiples classificadors. Finalment, amb una extensa evaluació experimental mostrem com la metodologia proposada pot ser calculada de forma eficient i com aquesta pot competir amb altres metodologies per a la comparació de grafs.Pattern recognition is the task that aims at distinguishing objects among different classes. When such a task wants to be solved in an automatic way a crucial step is how to formally represent such patterns to the computer. Based on the different representational formalisms, we may distinguish between statistical and structural pattern recognition. The former describes objects as a set of measurements arranged in the form of what is called a feature vector. The latter assumes that relations between parts of the underlying objects need to be explicitly represented and thus it uses relational structures such as graphs for encoding their inherent information. Vector spaces are a very flexible mathematical structure that has allowed to come up with several efficient ways for the analysis of patterns under the form of feature vectors. Nevertheless, such a representation cannot explicitly cope with binary relations between parts of the objects and it is restricted to measure the exact same number of features for each pattern under study regardless of their complexity. Graph-based representations present the contrary situation. They can easily adapt to the inherent complexity of the patterns but introduce a problem of high computational complexity, hindering the design of efficient tools to process and analyze patterns. Solving this paradox is the main goal of this thesis. The ideal situation for solving pattern recognition problems would be to represent the patterns using relational structures such as graphs, and to be able to use the wealthy repository of data processing tools from the statistical pattern recognition domain. An elegant solution to this problem is to transform the graph domain into a vector domain where any processing algorithm can be applied. In other words, by mapping each graph to a point in a vector space we automatically get access to the rich set of algorithms from the statistical domain to be applied in the graph domain. Such methodology is called graph embedding. In this thesis we propose to associate feature vectors to graphs in a simple and very efficient way by just putting attention on the labelling information that graphs store. In particular, we count frequencies of node labels and of edges between labels. Although their locality, these features are able to robustly represent structurally global properties of graphs, when considered together in the form of a vector. We initially deal with the case of discrete attributed graphs, where features are easy to compute. The continuous case is tackled as a natural generalization of the discrete one, where rather than counting node and edge labelling instances, we count statistics of some representatives of them. We encounter how the proposed vectorial representations of graphs suffer from high dimensionality and correlation among components and we face these problems by feature selection algorithms. We also explore how the diversity of different embedding representations can be exploited in order to boost the performance of base classifiers in a multiple classifier systems framework. An extensive experimental evaluation finally shows how the methodology we propose can be efficiently computed and compete with other graph matching and embedding methodologies.
3
Kim, Joo-Kyung. "Linguistic Knowledge Transfer for Enriching Vector Representations." The Ohio State University, 2017. http://rave.ohiolink.edu/etdc/view?acc_num=osu1500571436042414.
Full text
4
Ghazi, Kaoutar. "Heuristiques et conjectures à propos de la 2-dimension des ordres partiels." Thesis, Université Clermont Auvergne (2017-2020), 2017. http://www.theses.fr/2017CLFAC084/document.
Full textAbstract:
Dès qu’on manipule des ordres partiels (des hiérarchies), il est naturel de se demander comment les représenter dans un système informatique. Parmi les solutions proposées dans la littérature, on retrouve le codage par vecteur de bits. Dans cette thèse, nous nous intéressons au problème de calcul d’un codage des ordres par vecteur de bits de taille minimale, aussi connu par le problème de calcul de la 2-dimension des ordres, qui est NP-complet. Nous proposons des solutions du problème de nature heuristique, pour le cas général et pour des classes d’ordres particulières.Cette thèse présente également des résultats sur des conjectures autour de la 2-dimension des arbres. Notamment celle de Habib et al. à propos de la 2-approximabilité de la 2-dimension des arbres. Nous proposons quelques pistes de preuve de cette conjecture puis une reformulation, permettant d’apporter un nouveau regard sur le problème en question et d’espérer trouver des codages des ordres par vecteur de bits efficaces et de taille inférieure à leur 2-dimension. Nous apportons une réponse négative à deux autres conjecturesThe main question asked when manipulating partial orders (hierarchies), is how to represent them in computer. Among solutions proposed in literature, there is the bit-vector encoding. In this thesis, we consider the problem of computing a bit-vector encoding of orders with minimal size, which is also known as the problem of computing the2-dimension of orders that is NP-complete. We propose heuristics solutions of the problem for the general case and for some particular order classes. In addition, this thesis presents some results about conjectures on the 2-dimension of trees. Especially, the conjecture of Habib et al. about the 2-approximability of the 2-dimension of trees. We propose some ideas of a proof of this conjecture then give a reformulation of it that brings new perspectives on the problem that are finding efficient bits-vector encodings of orders of size less than their 2-dimension. We disprove two other conjectures
5
Bahceci, Oktay. "Deep Neural Networks for Context Aware Personalized Music Recommendation : A Vector of Curation." Thesis, KTH, Skolan för datavetenskap och kommunikation (CSC), 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-210252.
Full textAbstract:
Information Filtering and Recommender Systems have been used and has been implemented in various ways from various entities since the dawn of the Internet, and state-of-the-art approaches rely on Machine Learning and Deep Learning in order to create accurate and personalized recommendations for users in a given context. These models require big amounts of data with a variety of features such as time, location and user data in order to find correlations and patterns that other classical models such as matrix factorization and collaborative filtering cannot. This thesis researches, implements and compares a variety of models with the primary focus of Machine Learning and Deep Learning for the task of music recommendation and do so successfully by representing the task of recommendation as a multi-class extreme classification task with 100 000 distinct labels. By comparing fourteen different experiments, all implemented models successfully learn features such as time, location, user features and previous listening history in order to create context-aware personalized music predictions, and solves the cold start problem by using user demographic information, where the best model being capable of capturing the intended label in its top 100 list of recommended items for more than 1/3 of the unseen data in an offine evaluation, when evaluating on randomly selected examples from the unseen following week.Informationsfiltrering och rekommendationssystem har använts och implementeratspå flera olika sätt från olika enheter sedan gryningen avInternet, och moderna tillvägagångssätt beror påMaskininlärrning samtDjupinlärningför att kunna skapa precisa och personliga rekommendationerför användare i en given kontext. Dessa modeller kräver data i storamängder med en varians av kännetecken såsom tid, plats och användardataför att kunna hitta korrelationer samt mönster som klassiska modellersåsom matris faktorisering samt samverkande filtrering inte kan. Dettaexamensarbete forskar, implementerar och jämför en mängd av modellermed fokus påMaskininlärning samt Djupinlärning för musikrekommendationoch gör det med succé genom att representera rekommendationsproblemetsom ett extremt multi-klass klassifikationsproblem med 100000 unika klasser att välja utav. Genom att jämföra fjorton olika experiment,så lär alla modeller sig kännetäcken såsomtid, plats, användarkänneteckenoch lyssningshistorik för att kunna skapa kontextberoendepersonaliserade musikprediktioner, och löser kallstartsproblemet genomanvändning av användares demografiska kännetäcken, där den bästa modellenklarar av att fånga målklassen i sin rekommendationslista medlängd 100 för mer än 1/3 av det osedda datat under en offline evaluering,när slumpmässigt valda exempel från den osedda kommande veckanevalueras.
6
Malik, Muhammad Hamza. "Information extraction and mapping for KG construction with learned concepts from scientic documents : Experimentation with relations data for development of concept learner." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-285572.
Full textAbstract:
Systematic review of research manuscripts is a common procedure in which research studies pertaining a particular field or domain are classified and structured in a methodological way. This process involves, between other steps, an extensive review and consolidation of scientific metrics and attributes of the manuscripts, such as citations, type or venue of publication. The extraction and mapping of relevant publication data, evidently, is a very laborious task if performed manually. Automation of such systematic mapping steps intend to reduce the human effort required and therefore can potentially reduce the time required for this process.The objective of this thesis is to automate the data extraction and mapping steps when systematically reviewing studies. The manual process is replaced by novel graph modelling techniques for effective knowledge representation, as well as novel machine learning techniques that aim to learn these representations. This eventually automates this process by characterising the publications on the basis of certain sub-properties and qualities that give the reviewer a quick high-level overview of each research study. The final model is a concept learner that predicts these sub-properties which in addition addresses the inherent concept-drift of novel manuscripts over time. Different models were developed and explored in this research study for the development of concept learner.Results show that: (1) Graph reasoning techniques which leverage the expressive power in modern graph databases are very effective in capturing the extracted knowledge in a so-called knowledge graph, which allows us to form concepts that can be learned using standard machine learning techniques like logistic regression, decision trees and neural networks etc. (2) Neural network models and ensemble models outperformed other standard machine learning techniques like logistic regression and decision trees based on the evaluation metrics. (3) The concept learner is able to detect and avoid concept drift by retraining the model.Systematisk granskning av forskningsmanuskript är en vanlig procedur där forskningsstudier inom ett visst område klassificeras och struktureras på ett metodologiskt sätt. Denna process innefattar en omfattande granskning och sammanförande av vetenskapliga mätvärden och attribut för manuskriptet, såsom citat, typ av manuskript eller publiceringsplats. Framställning och kartläggning av relevant publikationsdata är uppenbarligen en mycket mödosam uppgift om den utförs manuellt. Avsikten med automatiseringen av processen för denna typ av systematisk kartläggning är att minska den mänskliga ansträngningen, och den tid som krävs kan på så sätt minskas. Syftet med denna avhandling är att automatisera datautvinning och stegen för kartläggning vid systematisk granskning av studier. Den manuella processen ersätts av avancerade grafmodelleringstekniker för effektiv kunskapsrepresentation, liksom avancerade maskininlärningstekniker som syftar till att lära maskinen dessa representationer. Detta automatiserar så småningom denna process genom att karakterisera publikationerna beserat på vissa subjektiva egenskaper och kvaliter som ger granskaren en snabb god översikt över varje forskningsstudie. Den slutliga modellen är ett inlärningskoncept som förutsäger dessa subjektiva egenskaper och dessutom behandlar den inneboende konceptuella driften i manuskriptet över tiden. Olika modeller utvecklades och undersöktes i denna forskningsstudie för utvecklingen av inlärningskonceptet. Resultaten visar att: (1) Diagrammatiskt resonerande som uttnytjar moderna grafdatabaser är mycket effektiva för att fånga den framställda kunskapen i en så kallad kunskapsgraf, och gör det möjligt att vidareutveckla koncept som kan läras med hjälp av standard tekniker för maskininlärning. (2) Neurala nätverksmodeller och ensemblemodeller överträffade andra standard maskininlärningstekniker baserat på utvärderingsvärdena. (3) Inlärningskonceptet kan detektera och undvika konceptuell drift baserat på F1-poäng och omlärning av algoritmen.
7
Dall'Olio, Lorenzo. "Estimation of biological vascular ageing via photoplethysmography: a comparison between statistical learning and deep learning." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2020. http://amslaurea.unibo.it/21687/.
Full textAbstract:
This work aims to exploit the biological ageing phenomena which affects human blood vessels. The analysis is performed starting from a database of photoplethysmographic signals acquired through smartphones. The further step involves a preprocessing phase, where the signals are detrended using a central moving average filter, demoduled using the envelope of the analytic signal obtained from the Hilbert transform, denoised using the central moving average filter over the envelope. After the preprocessing we compared two different approaches. The first one regards Statistical Learning, which involves feature extraction and selection through the usage of statistics and machine learning algorithms. This in order to perform a classification supervised task over the chronological age of the individual, which is used as a proxy for healthy/non healthy vascular ageing. The second one regards Deep Learning, which involves the realisation of a convolutional neural network to perform the same task, but avoiding the feature extraction/selection step and so possible bias introduced by such phases. Doing so we obtained comparable outcomes in terms of area under the curve metrics from a 12 layers ResNet convolutional network and a support vector machine using just covariates together with a couple of extracted features, acquiring clues regarding the possible usage of such features as biomarkers for the vascular ageing process. The two mentioned features can be related with increasing arterial stiffness and increasing signal randomness due to ageing.
8
Lipecki, Johan, and Viggo Lundén. "The Effect of Data Quantity on Dialog System Input Classification Models." Thesis, KTH, Hälsoinformatik och logistik, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-237282.
Full textAbstract:
This paper researches how different amounts of data affect different word vector models for classification of dialog system user input. A hypothesis is tested that there is a data threshold for dense vector models to reach the state-of-the-art performance that have been shown with recent research, and that character-level n-gram word-vector classifiers are especially suited for Swedish classifiers–because of compounding and the character-level n-gram model ability to vectorize out-of-vocabulary words. Also, a second hypothesis is put forward that models trained with single statements are more suitable for chat user input classification than models trained with full conversations. The results are not able to support neither of our hypotheses but show that sparse vector models perform very well on the binary classification tasks used. Further, the results show that 799,544 words of data is insufficient for training dense vector models but that training the models with full conversations is sufficient for single statement classification as the single-statement- trained models do not show any improvement in classifying single statements.Detta arbete undersöker hur olika datamängder påverkar olika slags ordvektormodeller för klassificering av indata till dialogsystem. Hypotesen att det finns ett tröskelvärde för träningsdatamängden där täta ordvektormodeller när den högsta moderna utvecklingsnivån samt att n-gram-ordvektor-klassificerare med bokstavs-noggrannhet lämpar sig särskilt väl för svenska klassificerare söks bevisas med stöd i att sammansättningar är särskilt produktiva i svenskan och att bokstavs-noggrannhet i modellerna gör att tidigare osedda ord kan klassificeras. Dessutom utvärderas hypotesen att klassificerare som tränas med enkla påståenden är bättre lämpade att klassificera indata i chattkonversationer än klassificerare som tränats med hela chattkonversationer. Resultaten stödjer ingendera hypotes utan visar istället att glesa vektormodeller presterar väldigt väl i de genomförda klassificeringstesterna. Utöver detta visar resultaten att datamängden 799 544 ord inte räcker till för att träna täta ordvektormodeller väl men att konversationer räcker gott och väl för att träna modeller för klassificering av frågor och påståenden i chattkonversationer, detta eftersom de modeller som tränats med användarindata, påstående för påstående, snarare än hela chattkonversationer, inte resulterar i bättre klassificerare för chattpåståenden.
9
Chen, Fu-Mei, and 陳富美. "Metadata Embedding for Vector Maps by Using Reversible Steganographic Algorithms." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/17764355267847349951.
Full textAbstract:
博士國立東華大學
企業管理學系
97
A vector map consists of a sequence of two-dimensional coordinates to represent points, lines, and polygons in a digital map. They are data widely used in economic, social and environmental decision support and planning applications and are also the fuel of many applications based on Geographic Information Systems (GIS). Nowadays, more and more vector maps have been compiled and made available for dissemination via internet. Accordingly, there is need for providing the details of the downloaded vector maps to be available on demand. Metadata which is the “data about data” are introduced to provide the details of vector maps. In this thesis, we have explored an important issue on metadata embedding for vector maps by using reversible steganographic algorithms. The basic idea of this research comes from utilizing the characteristics of steganographic technologies to develop metadata embedding methods for vector maps. Thus, the major objective of this research is to propose and compare methods of using reversible steganographic algorithms to embed metadata in vector maps and to provide a better metadata storing mechanism than current used. Experiments are implemented to evaluate the feasibility of the proposed methods. In this thesis, we have successfully explored and proposed three reversible steganographic algorithms to embed metadata in vector maps. The first algorithm, which is named as the original algorithm, is used to embed 2(n-2) bits of metadata in a vector map, where n represents the total vertices in a vector map. To the best of our knowledge, the algorithm has achieved the highest bit per vertex (BPV) in th literature of steganograhy for vector maps. The second algorithm, which is named as the extended algorithm, is improved from the original algorithm for the purpose of decreasing the distortion of stego vector maps and increasing the accuracy of recovery vector maps. The experimental results, compare with the results from the original algorithm, show that the extended algorithm has reduced 50%-60% of distortion rate in stego vector maps and improved 40%-60% of accuracy in recovery vector maps. The third algorithm, which is named as the extensive algorithm, is proposed to have better data embedding capacity. The algorithm can be used to embed 2(n-2)s bits of metadata in a vector map. The n in the third algorithm also represents the total vertices of vector maps and the s here represents the segmentation values that create sub-intervals between the intervals designed for metadata embedding. Results show that we have successfully implementing a cover vector map with 65,828 vertices by using the extensive reversible steganographic algorithm to embed and extract metadata with insignificant distortion in stego vector maps and high accuracy of recovery vector maps. Although our approaches have already delivered good results, the main limitations of the proposed algorithms are coming from map precision and machine precision errors when considering cover vector map with small amount of vertices. Since the definitive capacity limit is reached when map precision and machine precision errors occur. Thus, the first suggested future work is to use other approaches to divide intervals or even use different approaches and rules to decide intervals for increased capacity or to avoid map precision and machine precision errors. The second future work which is worth to be investigated is to survey the effects of cover vector maps’ features to the algorithms proposed in this thesis, such as the complexity, the smoothness of boundary, and the included angle between vertices of cover maps. Finally, it is also worth to survey how to apply these algorithms in online mapping systems for providing better spatial vector data services.
10
Guo, Ji, and 郭驥. "Algal Recognition Based on Locally Linear Embedding and Support Vector Machine." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/85622915091259655246.
Full textAbstract:
碩士國立臺灣大學
環境工程學研究所
103
This article is aimed to construct an effective system to implement algae recognition by using CUDA(compute unified device architecture)-based locally linear embedding(LLE) and support vector machine (SVMs approaches). In general, the previous pattern accuracy of algae recognition system is about 90% but it was lower for the recognition of some algae with irregular shapes in the natural water samples. Continuing Yang’s year study, I wanted to achieve a higher accuracy for the identification of the irregularly shaped algae. We used the images of algae captured from charge-coupled device (CCD) and only considered the algorithmic scheme. The algorithm of algal recognition system was constructed on Matlab. Features of algae were extracted by LLE, a manifold learning method, and then algae was classified by SVM, a classifier. Although the recognition accuracy for the unidentified objects is low, the accuracy for all the other algae is satisfactory. By deleting the unidentified objects first, the recognition rates for Chlorella, unidentified separatedCyanobacteria,Monoraphidium, Pediastrum,Cylindrospermum, Staurastrum are more than 80%. The recognition rates for unidentified agglomerated Cyanobacteria, Merismopedia, Microcystis are obviously lower, but they are still higher than the rates in Yang’s research. Besides, the k coefficient of the accuracy of recognition is 0.8099, which means that our recognition system is a method with high accuracy. Thirdly, LLE based on CUDA does accelerate the calculation. According to the results, this algal recognition system rlied on CUDA-based LLE and SVMs is proved to be more efficient and less time-consuming than the traditional method. Also, LLE with SVMs is better to recognize irregularly-shaped algae than explicit feature extraction method with ANN in natural water body. This system can be improved. First, removal of unidentified objects before classification of algae helps to achieve a higher accuracy rate, probably because the corresponding points of these objects do not lie in a manifold. We may also improve accuracy by modifying the existing LLE. In addition we might be able to adjust the depth of field and visual field of microscope and CCD to obtain clear enough images of appointed algae. Also, we need to dilute the samples to avoid the overlapping of several algae. Besides, it is time-consuming to compute the features if the size of sample set of test set is very large. Hence using CUDA to accelerate the process is essential and effective.
Books on the topic "Embedding a vector of bits"
1
Riesen, Kaspar. Graph classification and clustering based on vector space embedding. New Jersey: World Scientific, 2010.
Find full text
2
Hrushovski, Ehud, and François Loeser. The space of stably dominated types. Princeton University Press, 2017. http://dx.doi.org/10.23943/princeton/9780691161686.003.0003.
Full textAbstract:
This chapter introduces the space unit vector V of stably dominated types on a definable set V. It first endows unit vector V with a canonical structure of a (strict) pro-definable set before providing some examples of stably dominated types. It then endows unit vector V with the structure of a definable topological space, and the properties of this definable topology are discussed. It also examines the canonical embedding of V in unit vector V as the set of simple points. An essential feature in the approach used in this chapter is the existence of a canonical extension for a definable function on V to unit vector V. This is considered in the next section where continuity criteria are given. The chapter concludes by describing basic notions of (generalized) paths and homotopies, along with good metrics, Zariski topology, and schematic distance.
3
Hrushovski, Ehud, and François Loeser. A closer look at the stable completion. Princeton University Press, 2017. http://dx.doi.org/10.23943/princeton/9780691161686.003.0005.
Full textAbstract:
This chapter introduces the concept of stable completion and provides a concrete representation of unit vector Mathematical Double-Struck Capital A superscript n in terms of spaces of semi-lattices, with particular emphasis on the frontier between the definable and the topological categories. It begins by constructing a topological embedding of unit vector Mathematical Double-Struck Capital A superscript n into the inverse limit of a system of spaces of semi-lattices L(Hsubscript d) endowed with the linear topology, where Hsubscript d are finite-dimensional vector spaces. The description is extended to the projective setting. The linear topology is then related to the one induced by the finite level morphism L(Hsubscript d). The chapter also considers the condition that if a definable set in L(Hsubscript d) is an intersection of relatively compact sets, then it is itself relatively compact.
Book chapters on the topic "Embedding a vector of bits"
1
Sherkat, Ehsan, and Evangelos E. Milios. "Vector Embedding of Wikipedia Concepts and Entities." In Natural Language Processing and Information Systems, 418–28. Cham: Springer International Publishing, 2017. http://dx.doi.org/10.1007/978-3-319-59569-6_50.
Full text
2
Ferrer, Miquel, Itziar Bardají, Ernest Valveny, Dimosthenis Karatzas, and Horst Bunke. "Median Graph Computation by Means of Graph Embedding into Vector Spaces." In Graph Embedding for Pattern Analysis, 45–71. New York, NY: Springer New York, 2012. http://dx.doi.org/10.1007/978-1-4614-4457-2_3.
Full text
3
Gallier, Jean. "Embedding an Affine Space in a Vector Space." In Texts in Applied Mathematics, 85–101. New York, NY: Springer New York, 2011. http://dx.doi.org/10.1007/978-1-4419-9961-0_4.
Full text
4
Gallier, Jean. "Embedding an Affine Space in a Vector Space." In Texts in Applied Mathematics, 70–86. New York, NY: Springer New York, 2001. http://dx.doi.org/10.1007/978-1-4613-0137-0_4.
Full text
5
Fuchs, Mathias, and Kaspar Riesen. "Graph Embedding in Vector Spaces Using Matching-Graphs." In Similarity Search and Applications, 352–63. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-89657-7_26.
Full text
6
Luqman, Muhammad Muzzamil, Jean-Yves Ramel, and Josep Lladós. "Multilevel Analysis of Attributed Graphs for Explicit Graph Embedding in Vector Spaces." In Graph Embedding for Pattern Analysis, 1–26. New York, NY: Springer New York, 2012. http://dx.doi.org/10.1007/978-1-4614-4457-2_1.
Full text
7
Yao, Jinkui, and Yulong Zhao. "Knowledge Graph Embedding Bi-vector Models for Symmetric Relation." In Lecture Notes in Electrical Engineering, 27–36. Singapore: Springer Singapore, 2019. http://dx.doi.org/10.1007/978-981-32-9698-5_4.
Full text
8
Lima, Clodoaldo A. M., André L. V. Coelho, and Fernando J. Zuben. "Embedding Support Vector Machines into Localised Mixtures of Experts." In Applications and Science in Soft Computing, 155–62. Berlin, Heidelberg: Springer Berlin Heidelberg, 2004. http://dx.doi.org/10.1007/978-3-540-45240-9_22.
Full text
9
Amani, Arash, Mohammad Mohammadamini, and Hadi Veisi. "Kurdish Spoken Dialect Recognition Using X-Vector Speaker Embedding." In Speech and Computer, 50–57. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-87802-3_5.
Full text
10
Ludwig, Günther. "Embedding of Ensembles and Effect Sets in Topological Vector Spaces." In An Axiomatic Basis for Quantum Mechanics, 101–25. Berlin, Heidelberg: Springer Berlin Heidelberg, 1985. http://dx.doi.org/10.1007/978-3-642-70029-3_4.
Full textConference papers on the topic "Embedding a vector of bits"
1
Zhao, Juan, and Zhitang Li. "Lossless Steganography on Orthogonal Vector for 3D H.264 with Limited Distortion Diffusion." In 10th International Conference on Software Engineering and Applications (SEAS 2021). AIRCC Publishing Corporation, 2021. http://dx.doi.org/10.5121/csit.2021.110203.
Full textAbstract:
In order to improve the undetectability, a lossless algorithm based on orthogonal vectors with limited distortion diffusion for 3D H.264 video is proposed in this paper. Inter-view distortion drift is avoided by embedding data into frames, which do not predict other views. Three conditions and pairs of coefficients are proposed to prevent intra-frame distortion diffusion. Several quantized discrete cosine transform coefficients are chosen from an embeddable luminance 4×4 block to construct a carrier vector, which is modified by an offset vector. When the carrier vector and the offset vector are orthogonal or near to be orthogonal, a data bit can be hidden. Experimental results indicate that the method is effective by enhancing peak signal-to-noise ratio with 7.5dB and reducing the Kullback-Leibler divergence with 0.07 at least. More than 1.7×1015 ways could be utilized for constructing the vectors, so it is more difficult for others to steal data.
2
Ding, Minjie, Weiqin Tong, Xuehai Ding, Xiaoli Zhi, Xiao Wang, and Guoqing Zhang. "Knowledge Graph Embedding by Bias Vectors." In 2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI). IEEE, 2019. http://dx.doi.org/10.1109/ictai.2019.00180.
Full text
3
Zhuang, Dongye, Dongming Zhang, Jintao Li, Ke Lv, and Qi Tian. "Hamming embedding with fragile bits for image search." In 2014 IEEE International Conference on Image Processing (ICIP). IEEE, 2014. http://dx.doi.org/10.1109/icip.2014.7026157.
Full text
4
Yang, Hong, Shirui Pan, Ling Chen, Chuan Zhou, and Peng Zhang. "Low-Bit Quantization for Attributed Network Representation Learning." In Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}. California: International Joint Conferences on Artificial Intelligence Organization, 2019. http://dx.doi.org/10.24963/ijcai.2019/562.
Full textAbstract:
Attributed network embedding plays an important role in transferring network data into compact vectors for effective network analysis. Existing attributed network embedding models are designed either in continuous Euclidean spaces which introduce data redundancy or in binary coding spaces which incur significant loss of representation accuracy. To this end, we present a new Low-Bit Quantization for Attributed Network Representation Learning model (LQANR for short) that can learn compact node representations with low bitwidth values while preserving high representation accuracy. Specifically, we formulate a new representation learning function based on matrix factorization that can jointly learn the low-bit node representations and the layer aggregation weights under the low-bit quantization constraint. Because the new learning function falls into the category of mixed integer optimization, we propose an efficient mixed-integer based alternating direction method of multipliers (ADMM) algorithm as the solution. Experiments on real-world node classification and link prediction tasks validate the promising results of the proposed LQANR model.
5
Yang, Shihui, Jidong Tian, Honglun Zhang, Junchi Yan, Hao He, and Yaohui Jin. "TransMS: Knowledge Graph Embedding for Complex Relations by Multidirectional Semantics." In Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}. California: International Joint Conferences on Artificial Intelligence Organization, 2019. http://dx.doi.org/10.24963/ijcai.2019/268.
Full textAbstract:
Knowledge graph embedding, which projects the symbolic relations and entities onto low-dimension continuous spaces, is essential to knowledge graph completion. Recently, translation-based embedding models (e.g. TransE) have aroused increasing attention for their simplicity and effectiveness. These models attempt to translate semantics from head entities to tail entities with the relations and infer richer facts outside the knowledge graph. In this paper, we propose a novel knowledge graph embedding method named TransMS, which translates and transmits multidirectional semantics: i) the semantics of head/tail entities and relations to tail/head entities with nonlinear functions and ii) the semantics from entities to relations with linear bias vectors. Our model has merely one additional parameter α than TransE for each triplet, which results in its better scalability in large-scale knowledge graph. Experiments show that TransMS achieves substantial improvements against state-of-the-art baselines, especially the Hit@10s of head entity prediction for N-1 relations and tail entity prediction for 1-N relations improved by about 27.1% and 24.8% on FB15K database respectively.
6
Assanovich, B. A. "Embedding bits in compressed data for selective encryption and watermarking." In 2008 IEEE Region 8 International Conference on Computational Technologies in Electrical and Electronics Engineering (SIBIRCON). IEEE, 2008. http://dx.doi.org/10.1109/sibircon.2008.4602590.
Full text
7
Mihaljevic, Miodrag J., and Hideki Imai. "A stream cipher design based on embedding of random bits." In 2008 International Symposium on Information Theory and Its Applications (ISITA). IEEE, 2008. http://dx.doi.org/10.1109/isita.2008.4895641.
Full text
8
Vandierendonck, Hans, and Koen De Bosschere. "Implicit hints: Embedding hint bits in programs without ISA changes." In 2010 IEEE International Conference on Computer Design (ICCD 2010). IEEE, 2010. http://dx.doi.org/10.1109/iccd.2010.5647699.
Full text
9
Liao, Xin, and Qiao-yan Wen. "Embedding in Two Least Significant Bits with Wet Paper Coding." In 2008 International Conference on Computer Science and Software Engineering. IEEE, 2008. http://dx.doi.org/10.1109/csse.2008.970.
Full text
10
Georges, Munir, Jonathan Huang, and Tobias Bocklet. "Compact Speaker Embedding: lrx-Vector." In Interspeech 2020. ISCA: ISCA, 2020. http://dx.doi.org/10.21437/interspeech.2020-2106.
Full textReports on the topic "Embedding a vector of bits"
1
Antignus, Yehezkiel, Ernest Hiebert, Shlomo Cohen, and Susan Webb. Approaches for Studying the Interaction of Geminiviruses with Their Whitefly Vector Bemisia tabaci. United States Department of Agriculture, July 1995. http://dx.doi.org/10.32747/1995.7604928.bard.
Full textAbstract:
The DNA of tomato yellow leaf curl virus (TYLCB) was detected in its whitefly vector, Bemisia tabaci, by dot spot hybridization as early as 1 h after acquisition access. The retention of the virus nucleic acid in the vector was at least 23 days after a 48 h acquisition access. However, the retention of TYLCV coat protein did not exceed 10 days. No replicative forms of TYLCV could be detected in B. tabaci, indicating a non-propagative relationship with the vector. Whiteflies were not able to accumulate naked virion ssDNA, virus cloned dsDNA, or virions with impaired coat protein. Deletion, frameshift, and single amino acid mutations were inserted into open reading frames (ORFs) V1 and V2 (Coat protein) of TYLCV. The ability of these mutants to replicate, to spread and to induce symptoms was tested both in leaf disks and in intact plants. No replication was found in tissues that were infected with a deletion mutant that lacked the carboxy half of the coat protein gene. Residual amounts of ssDNA and dsDNA were detected i tissues infected with a frameshift mutant in which an early termination at the extreme part of the protein. Two other mutants in which a single amino acid was changed in the overlapping part of V1 and V2 were able to spread systemically but infections remained symptomless and the production of ssDNA and dsDNA were significantly lower. These mutants were acquired and transmitted by Bemisia tabaci. Procedures for the the dissection, fixation and embedding of whiteflies were developed. The anatomy and ultrastructure of the salivary gland and the midgut of Bemisia tabaci and Trialeurodes vaporariorum (a vector and non-vector of geminiviruses respectively) was studied and described. Monoclonal antibodies against bean golden mosaic virus (BGMV) with narrow and broad spectrum were prepared. Transmission studies of tomato mottle geminivirus (TMoV) by B. tabaci were carried out. These studies were essential for a further work aimed to understand the interaction of geminiviruses with the insect and their localization in its tissues. To enable the production of transgenic plants procedures were developed for tomato transformation with both Agrobacterium and microparticle bombardment.