arXiv subjects

Jun Feng

Publications and source records attributed to Jun Feng.

At least 55 records · Page 3Linked to original sources

arXiv2022

A Deep CNN Architecture with Novel Pooling Layer Applied to Two Sudanese Arabic Sentiment Datasets

Arabic sentiment analysis has become an important research field in recent years. Initially, work focused on Modern Standard Arabic (MSA), which is the most widely-used form. Since then, work has been carried out on several different dialects, including Egyptian, Levantine and Moroccan. Moreover, a number of datasets have been created to support such work. However, up until now, less work has been carried out on Sudanese Arabic, a dialect which has 32 million speakers. In this paper, two new publicly available datasets are introduced, the 2-Class Sudanese Sentiment Dataset (SudSenti2) and the 3-Class Sudanese Sentiment Dataset (SudSenti3). Furthermore, a CNN architecture, SCM, is proposed, comprising five CNN layers together with a novel pooling layer, MMA, to extract the best features. This SCM+MMA model is applied to SudSenti2 and SudSenti3 with accuracies of 92.75% and 84.39%. Next, the model is compared to other deep learning classifiers and shown to be superior on these new datasets. Finally, the proposed model is applied to the existing Saudi Sentiment Dataset and to the MSA Hotel Arabic Review Dataset with accuracies 85.55% and 90.01%.

cs.CL↗

arXiv2022

Kinit Classification in Ethiopian Chants, Azmaris and Modern Music: A New Dataset and CNN Benchmark

In this paper, we create EMIR, the first-ever Music Information Retrieval dataset for Ethiopian music. EMIR is freely available for research purposes and contains 600 sample recordings of Orthodox Tewahedo chants, traditional Azmari songs and contemporary Ethiopian secular music. Each sample is classified by five expert judges into one of four well-known Ethiopian Kinits, Tizita, Bati, Ambassel and Anchihoye. Each Kinit uses its own pentatonic scale and also has its own stylistic characteristics. Thus, Kinit classification needs to combine scale identification with genre recognition. After describing the dataset, we present the Ethio Kinits Model (EKM), based on VGG, for classifying the EMIR clips. In Experiment 1, we investigated whether Filterbank, Mel-spectrogram, Chroma, or Mel-frequency Cepstral coefficient (MFCC) features work best for Kinit classification using EKM. MFCC was found to be superior and was therefore adopted for Experiment 2, where the performance of EKM models using MFCC was compared using three different audio sample lengths. 3s length gave the best results. In Experiment 3, EKM and four existing models were compared on the EMIR dataset: AlexNet, ResNet50, VGG16 and LSTM. EKM was found to have the best accuracy (95.00%) as well as the fastest training time. We hope this work will encourage others to explore Ethiopian music and to experiment with other models for Kinit classification.

cs.SD↗

arXiv2022

A New Amharic Speech Emotion Dataset and Classification Benchmark

In this paper we present the Amharic Speech Emotion Dataset (ASED), which covers four dialects (Gojjam, Wollo, Shewa and Gonder) and five different emotions (neutral, fearful, happy, sad and angry). We believe it is the first Speech Emotion Recognition (SER) dataset for the Amharic language. 65 volunteer participants, all native speakers, recorded 2,474 sound samples, two to four seconds in length. Eight judges assigned emotions to the samples with high agreement level (Fleiss kappa = 0.8). The resulting dataset is freely available for download. Next, we developed a four-layer variant of the well-known VGG model which we call VGGb. Three experiments were then carried out using VGGb for SER, using ASED. First, we investigated whether Mel-spectrogram features or Mel-frequency Cepstral coefficient (MFCC) features work best for Amharic. This was done by training two VGGb SER models on ASED, one using Mel-spectrograms and the other using MFCC. Four forms of training were tried, standard cross-validation, and three variants based on sentences, dialects and speaker groups. Thus, a sentence used for training would not be used for testing, and the same for a dialect and speaker group. The conclusion was that MFCC features are superior under all four training schemes. MFCC was therefore adopted for Experiment 2, where VGGb and three other existing models were compared on ASED: RESNet50, Alex-Net and LSTM. VGGb was found to have very good accuracy (90.73%) as well as the fastest training time. In Experiment 3, the performance of VGGb was compared when trained on two existing SER datasets, RAVDESS (English) and EMO-DB (German) as well as on ASED (Amharic). Results are comparable across these languages, with ASED being the highest. This suggests that VGGb can be successfully applied to other languages. We hope that ASED will encourage researchers to experiment with other models for Amharic SER.

cs.CL↗

arXiv2021

ScalingNet: extracting features from raw EEG data for emotion recognition

Convolutional Neural Networks(CNNs) has achieved remarkable performance breakthrough in a variety of tasks. Recently, CNNs based methods that are fed with hand-extracted EEG features gradually produce a powerful performance on the EEG data based emotion recognition task. In this paper, we propose a novel convolutional layer allowing to adaptively extract effective data-driven spectrogram-like features from raw EEG signals, which we reference as scaling layer. Further, it leverages convolutional kernels scaled from one data-driven pattern to exposed a frequency-like dimension to address the shortcomings of prior methods requiring hand-extracted features or their approximations. The proposed neural network architecture based on the scaling layer, references as ScalingNet, has achieved the state-of-the-art result across the established DEAP benchmark dataset.

eess.SP↗

arXiv2021

Lookup subnet based Spatial Graph Convolutional neural Network

Convolutional Neural Networks(CNNs) has achieved remarkable performance breakthrough in Euclidean structure data. Recently, aggregation-transformation based Graph Neural networks(GNNs) gradually produce a powerful performance on non-Euclidean data. In this paper, we propose a cross-correlation based graph convolution method allowing to naturally generalize CNNs to non-Euclidean domains and inherit the excellent natures of CNNs, such as local filters, parameter sharing, flexible receptive field, etc. Meanwhile, it leverages dynamically generated convolution kernel and cross-correlation operators to address the shortcomings of prior methods based on aggregation-transformation or their approximations. Our method has achieved or matched popular state-of-the-art results across three established graph benchmarks: the Cora, Citeseer, and Pubmed citation network datasets.

cs.LG↗

arXiv2020

The interplay between spatial and heliconical bond order in twist-bend nematic materials

The nanostructure of two novel sulfur containing dimer materials has been investigated experimentally by hard and by resonant tender X-ray scattering techniques. On cooling the dimers through the nematic to twist-bend nematic (N-NTB) phase transition, the correlation length associated with short-range positional order drops, while the heliconical orientational order becomes more correlated. The heliconical pitch shows a stronger temperature dependence near the N-NTB transition than observed in previously studied dimers, such as the CBnCB series of compounds. We explain both this strong variation and the dependence of the heliconical pitch on the length of the spacer connecting the monomer units by taking into account a temperature dependent molecular bend and intermolecular overlap. and. The heliconical structure is observed even in the upper 3-4°C range of the smectic phase that forms just below the NTB state. The coexistence of smectic layering and the heliconical order indicates a SmCTB -type phase where the rigid units of the dimers are tilted with respect to the layer normal in order to accommodate the bent conformation of the dimers, but the tilt direction rotates along the heliconical axis. This is potentially similar to the SmCTB phase reported by Abberley et al (Nat. Commun. 2018, 9, 228) below a SmA phase.

cond-mat.soft↗

arXiv2020

Identification of New Assembly Mode in the Heliconical Nematic Phase via Tender Resonant X-ray Scattering

Helical structures are exciting and are utilized in numerous applications ranging from biotechnology to displays to medicine. Accurate description and understanding of resonance effects in helical structures provides crucial knowledge on molecular packing beyond positional ordering. We exam-ined the manifestation of resonance effects in a nematic phase with heliconical structure, the so called twist bend nematic (NTB) via tender resonant X-ray scattering (TReXS) at the sulfur K-edge. We demonstrate for the first time quantitatively that the energy dependence of the scattering peak in the NTB phase follows the energy dependence of the complex refractive indices measured by X-ray absorption. This allows us to identify a new self-assembly mode for specific sets of liquid crystal dimers in the NTB phase. We anticipate that new avenues in the exploration of complex orientational structures both in static as well as in dynamic modes induced by external stimuli will be pursued.

cond-mat.soft↗

arXiv2020

Design of optimal illumination patterns in single-pixel imaging using image dictionaries

Single-pixel imaging (SPI) has a major drawback that many sequential illuminations are required for capturing one single image with long acquisition time. Basis illumination patterns such as Fourier patterns and Hadamard patterns can achieve much better imaging efficiency than random patterns. But the performance is still sub-optimal since the basis patterns are fixed and non-adaptive for varying object images. This Letter proposes a novel scheme for designing and optimizing the illumination patterns adaptively from an image dictionary by extracting the common image features using principal component analysis (PCA). Simulation and experimental results reveal that our proposed scheme outperforms conventional Fourier SPI in terms of imaging efficiency.

eess.IV↗

arXiv2020

Does deep learning always outperform simple linear regression in optical imaging?

Deep learning has been extensively applied in many optical imaging applications in recent years. Despite the success, the limitations and drawbacks of deep learning in optical imaging have been seldom investigated. In this work, we show that conventional linear-regression-based methods can outperform the previously proposed deep learning approaches for two black-box optical imaging problems in some extent. Deep learning demonstrates its weakness especially when the number of training samples is small. The advantages and disadvantages of linear-regression-based methods and deep learning are analyzed and compared. Since many optical systems are essentially linear, a deep learning network containing many nonlinearity functions sometimes may not be the most suitable option.

cs.CV↗

arXiv2020

Stream-Flow Forecasting of Small Rivers Based on LSTM

Stream-flow forecasting for small rivers has always been of great importance, yet comparatively challenging due to the special features of rivers with smaller volume. Artificial Intelligence (AI) methods have been employed in this area for long, but improvement of forecast quality is still on the way. In this paper, we tried to provide a new method to do the forecast using the Long-Short Term Memory (LSTM) deep learning model, which aims in the field of time-series data. Utilizing LSTM, we collected the stream flow data from one hydrologic station in Tunxi, China, and precipitation data from 11 rainfall stations around to forecast the stream flow data from that hydrologic station 6 hours in the future. We evaluated the prediction results using three criteria: root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R^2). By comparing LSTM's prediction with predictions of Support Vector Regression (SVR) and Multilayer Perceptions (MLP) models, we showed that LSTM has better performance, achieving RMSE of 82.007, MAE of 27.752, and R^2 of 0.970. We also did extended experiments on LSTM model, discussing influence factors of its performance.

cs.LG↗

arXiv2019

Multi-Kernel Filtering for Nonstationary Noise: An Extension of Bilateral Filtering Using Image Context

Bilateral filtering (BF) is one of the most classical denoising filters, however, the manually initialized filtering kernel hampers its adaptivity across images with various characteristics. To deal with image variation (i.e., non-stationary noise), in this paper, we propose multi-kernel filter (MKF) which adapts filtering kernels to specific image characteristics automatically. The design of MKF takes inspiration from adaptive mechanisms of human vision that make full use of information in a visual context. More specifically, for simulating the visual context and its adaptive function, we construct the image context based on which we simulate the contextual impact on filtering kernels. We first design a hierarchically clustering algorithm to generate a hierarchy of large to small coherent image patches, organized as a cluster tree, so that obtain multi-scale image representation. The leaf cluster and corresponding predecessor clusters are used to generate one of multiple range kernels that are capable of catering to image variation. At first, we design a hierarchically clustering framework to generate a hierarchy of large to small coherent image patches that organized as a cluster tree, so that obtain multi-scale image representation, i.e., the image context. Next, a leaf cluster is used to generate one of the multiple kernels, and two corresponding predecessor clusters are used to fine-tune the adopted kernel. Ultimately, the single spatially-invariant kernel in BF becomes multiple spatially-varying ones. We evaluate MKF on two public datasets, BSD300 and BrainWeb which are added integrally-varying noise and spatially-varying noise, respectively. Extensive experiments show that MKF outperforms state-of-the-art filters w.r.t. both mean absolute error and structural similarity.

cs.CV↗

arXiv2019

DeepBundle: Fiber Bundle Parcellation with Graph Convolution Neural Networks

Parcellation of whole-brain tractography streamlines is an important step for tract-based analysis of brain white matter microstructure. Existing fiber parcellation approaches rely on accurate registration between an atlas and the tractograms of an individual, however, due to large individual differences, accurate registration is hard to guarantee in practice. To resolve this issue, we propose a novel deep learning method, called DeepBundle, for registration-free fiber parcellation. Our method utilizes graph convolution neural networks (GCNNs) to predict the parcellation label of each fiber tract. GCNNs are capable of extracting the geometric features of each fiber tract and harnessing the resulting features for accurate fiber parcellation and ultimately avoiding the use of atlases and any registration method. We evaluate DeepBundle using data from the Human Connectome Project. Experimental results demonstrate the advantages of DeepBundle and suggest that the geometric features extracted from each fiber tract can be used to effectively parcellate the fiber tracts.

eess.IV↗

arXiv2019

Optical machine learning with incoherent light and a single-pixel detector

An optical diffractive neural network (DNN) can be implemented with a cascaded phase mask architecture. Like an optical computer, the system can perform machine learning tasks such as number digit recognition in an all-optical manner. However, the system can only work under coherent light illumination and the precision requirement in practical experiments is quite high. This paper proposes an optical machine learning framework based on single-pixel imaging (MLSPI). The MLSPI system can perform the same linear pattern recognition task as DNN. Furthermore, it can work under incoherent lighting conditions, has lower experimental complexity and can be easily programmable.

cs.CV↗

arXiv2019

Visual cryptography in single-pixel imaging

Two novel visual cryptography (VC) schemes are proposed by combining VC with single-pixel imaging (SPI) for the first time. It is pointed out that the overlapping of visual key images in VC is similar to the superposition of pixel intensities by a single-pixel detector in SPI. In the first scheme, QR-code VC is designed by using opaque sheets instead of transparent sheets. The secret image can be recovered when identical illumination patterns are projected onto multiple visual key images and a single detector is used to record the total light intensities. In the second scheme, the secret image is shared by multiple illumination pattern sequences and it can be recovered when the visual key patterns are projected onto identical items. The application of VC can be extended to more diversified scenarios by our proposed schemes.

eess.IV↗

arXiv2019

Aggregating E-commerce Search Results from Heterogeneous Sources via Hierarchical Reinforcement Learning

In this paper, we investigate the task of aggregating search results from heterogeneous sources in an E-commerce environment. First, unlike traditional aggregated web search that merely presents multi-sourced results in the first page, this new task may present aggregated results in all pages and has to dynamically decide which source should be presented in the current page. Second, as pointed out by many existing studies, it is not trivial to rank items from heterogeneous sources because the relevance scores from different source systems are not directly comparable. To address these two issues, we decompose the task into two subtasks in a hierarchical structure: a high-level task for source selection where we model the sequential patterns of user behaviors onto aggregated results in different pages so as to understand user intents and select the relevant sources properly; and a low-level task for item presentation where we formulate a slot filling process to sequentially present the items instead of giving each item a relevance score when deciding the presentation order of heterogeneous items. Since both subtasks can be naturally formulated as sequential decision problems and learn from the future user feedback on search results, we build our model with hierarchical reinforcement learning. Extensive experiments demonstrate that our model obtains remarkable improvements in search performance metrics, and achieves a higher user satisfaction.

cs.IR↗

arXiv2019

A Quantum-Inspired Method for Three-Dimensional Ligand-Based Virtual Screening

Measuring similarity between molecules is an important part of virtual screening (VS) experiments deployed during the early stages of drug discovery. Most widely used methods for evaluating the similarity of molecules use molecular fingerprints to encode structural information. While similarity methods using fingerprint encodings are efficient, they do not consider all the relevant aspects of molecular structure. In this paper, we describe a quantum-inspired graph-based molecular similarity (GMS) method for ligand-based VS. The GMS method is formulated as a quadratic unconstrained binary optimization problem that can be solved using a quantum annealer, providing the opportunity to take advantage of this nascent and potentially groundbreaking technology. In this study, we consider various features relevant to ligand-based VS, such as pharmacophore features and three-dimensional atomic coordinates, and include them in the GMS method. We evaluate this approach on various datasets from the DUD_LIB_VS_1.0 library. Our results show that using three-dimensional atomic coordinates as features for comparison yields higher early enrichment values. In addition, we evaluate the performance of the GMS method against conventional fingerprint approaches. The results demonstrate that the GMS method outperforms fingerprint methods for most of the datasets, presenting a new alternative in ligand-based VS with the potential for future enhancement.

q-bio.QM↗

arXiv2018

Relation Mention Extraction from Noisy Data with Hierarchical Reinforcement Learning

In this paper we address a task of relation mention extraction from noisy data: extracting representative phrases for a particular relation from noisy sentences that are collected via distant supervision. Despite its significance and value in many downstream applications, this task is less studied on noisy data. The major challenges exists in 1) the lack of annotation on mention phrases, and more severely, 2) handling noisy sentences which do not express a relation at all. To address the two challenges, we formulate the task as a semi-Markov decision process and propose a novel hierarchical reinforcement learning model. Our model consists of a top-level sentence selector to remove noisy sentences, a low-level mention extractor to extract relation mentions, and a reward estimator to provide signals to guide data denoising and mention extraction without explicit annotations. Experimental results show that our model is effective to extract relation mentions from noisy data.

cs.CL↗

arXiv2018

Bell inequalities violation within non-Bunch-Davies states

We study the quantum nature of non-Bunch-Davies states in de Sitter space by evaluating CHSH inequality on a localized two-atom system. We show that quantum nonlocality can be generated through the Markovian evolution of two-atom, witnessed by a violation of CHSH inequality on its final equilibrium state. We find that the upper bound of inequality violation is determined by different choices of de Sitter-invariant vacua sectors. In particular, with growing Gibbons-Hawking temperature, the CHSH bound degrades monotonously for Bunch-Davies vacuum sector. Due to the intrinsic correlation of non-Bunch-Davies vacua, we find that the related violation of inequality can however drastically increase after certain turning point, and may persist for arbitrarily large environment decoherence. This implies that the CHSH inequality is useful to classify the initial quantum state of the Universe. Finally, we clarify that the witnessed intrinsic correlation of non-Bunch-Davies vacua can be utilized for quantum information applications, e.g., surpassing the Heisenberg uncertainty bound of quantum measurement in de Sitter space.

hep-th↗