The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Intrusion detection techniques have been extensively used as a protective measure against network attacks. Machine learning (ML) has been widely recognized as an effective method for data based intrusion detection analysis. Especially, semi-supervised ML approaches apply both labelled and unlabelled data to train the detection model, which can avoid the high cost of labelling data. In this paper,...
Stochastic sampling machines (SSM) utilize neural sampling from probabilistic spiking neurons to escape local minima and prevent overfitting of training datasets [1]. This enables improved error rates compared to deterministic implementations, and, in turn, enables lower bit precision, decreased chip area, and reduced energy consumption. In this work, we experimentally demonstrate: (i) Insulator-to-Metal...
In the practice applications of defect detecting, large amounts of data need to be analyzed. In this paper, a new analysis method is developed based on adaboost algorithm. By using neural networks with a fixed structure, a series of models are built which may be not accurate. Error rates of the models are computed to gain and adjust the weights of every model. A higher accurate model is built by the...
This paper introduces the development of ShefCE: a Cantonese-English bilingual speech corpus from L2 English speakers in Hong Kong. Bilingual parallel recording materials were chosen from TED online lectures. Script selection were carried out according to bilingual consistency (evaluated using a machine translation system) and the distribution balance of phonemes. 31 undergraduate to postgraduate...
Grapheme-to-phoneme (G2P) conversion is an important problem for many speech and language processing applications. G2P models are particularly useful for low-resource languages that do not have well-developed pronunciation lexicons. Prominent G2P paradigms are based on initial alignments between grapheme and phoneme sequences. In this work, we devise new alignment strategies that work effectively...
This paper reports on investigations using two techniques for language model text data augmentation for low-resourced automatic speech recognition and keyword search. Lowresourced languages are characterized by limited training materials, which typically results in high out-of-vocabulary (OOV) rates and poor language model estimates. One technique makes use of recurrent neural networks (RNNs) using...
DNN based acoustic models require a large amount of training data. Parametric data augmentation techniques such as adding noise, reverberation, or changing the speech rate, are often employed to boost the dataset size and the ASR performance. The choice of augmentation techniques and the associated parameters has been handled heuristically so far. In this work we propose an algorithm to automatically...
This paper proposes a new detection scheme for concealed micro-electronic devices by analyzing harmonic waves which are reflected from targets with classification restricted Boltzmann machine algorithm (Class/RBM). This new method exploits the characteristics of the second and the third harmonics waves to classify metal and electronic devices, as is done in all other Pdetection schemes. Moreover the...
At present, Spark is widely used in a number of enterprises. Although Spark is much faster than Hadoop for some applications, its configuration parameters can have a great impact on its performance due to the large number of the parameters, interaction between them, and various characteristics of applications as well. Unfortunately, there is not yet any research conducted to predict the performance...
Aphasia is a type of acquired language impairment caused by brain injury. This paper presents an automatic speech recognition (ASR) based approach to objective assessment of aphasia patients. A dedicated ASR system is developed to facilitate acoustical and linguistic analysis of Cantonese aphasia speech. The acoustic models and the language models are trained with domain- and style-matched speech...
It is certain that the individual learners should be different from each other in order for a committee machine to reach the better performance. However, differences alone among the individual learners are not enough for the committee machine to predict well on the unknown data. It would be essential for each individual learner to be able to decide whether to learn to be different or not to the other...
Negative correlation learning has been proposed to create a set of negatively correlated artificial neural networks (ANNs) in a committee machine. In negative correlation learning, the error signals for each ANN on a given data are not only decided by the error differences between the output of ANN and the targets. Two terms are optimized at the same time. The first one is to minimize the error between...
Aiming to that the different hierarchic feature has a different degree contribution on expert ranking, the thesis proposes an expert ranking method which is based on ListNet combined with feature hierarchy type information. Firstly, the method thoroughly analyses characteristics of experts ranking, and defines four feature types, correlative features between query and document, page content features,...
Since Krizhevsky won the ImageNet Large Scale Visual Recognition Challenge (ILSVRC) 2012 competition with the brilliant deep convolutional neural networks(D-CNNs), researchers have designed lots of D-CNNs. However, almost all the existing very deep convolutional neural networks are trained on the giant ImageNet datasets. Small datasets like CIFAR-10 has rarely taken advantage of the power of depth...
This paper presents a novel technique for modeling of photovoltaic (PV) array using random forests (RFs). Metrological variables such as solar radiation and ambient temperature as well as actual output current of a 3 kWp PV grid-connected system installed at Universiti Kebangsaan Malaysia have been utilized. These data are used to train and validate the proposed RFs model. Three statistical error...
Different to other re-sampling ensemble learning, negative correlation learning trains all individual models in an ensemble simultaneously and cooperatively. In negative correlation learning, each individual could see all training data, and adapt its target function based on what the rest of individuals in the ensemble have learned. In this paper, two error bounds are introduced in negative correlation...
The paper presents a system to accurately differentiate between unique individuals by utilizing the various eye-movement biometric features. Eye Movements are highly resistant to forgery as the generation of eye movements occur due to the involvement of complex neurological interactions and extra ocular muscle properties. We have employed Linear Multiclass SVM model to classify the numerous eye movement...
Grid systems have emerged as a means of sharing computational resources and information. Providing services for accessing, sharing and modifying large databases is a crucial task for grid management systems. This paper proposes an artificial neural network (ANN) prediction mechanism that provides an enhancement to data replication solutions within grid systems. Current replication services often exhibit...
The purpose of this paper is to investigate heterogeneous multi-column ConvNets (MCCNN) and fusion methods for them. We first construct heterogeneous MCCNN by combining ConvNets with different structures. We then use different fusion methods to check their performances to find out the effect of fusion methods for MCCNN. We also propose a novel sliding window based fusion framework which defines a...
Vote count (VC) is a fast search algorithm originally designed for similarity search on large scale data set. VC can be efficiently implemented using simple modification to the Random Access Memory (RAM) or other memory structures such as NOR or NAND Flash memory, such that the search complexity reduces to O(1) regardless of the dimensionality of data or the size of the data set. This paper proposes...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.