Abstract: This paper aims to provide an interpretation of artificial neural networks (ANNs) and explore some of its implications. The interpretation views ANNs as a memory which encodes instances of experience. An experiment explores the behavior of encoding and retrieval of instances from memory. A localised representation ANN is created that allows control over encoding and retrieved memory sample size and is experimented with using the MNIST digits dataset. The relationship between input familiarity, conflict within retrieved samples, and error rates is described and demonstrated to be an effective driver for memory encoding. Results indicate that selective encoding and retrieval samples that allow detection of memory conflicts produce optimal performance, and that error rates are normally distributed with input familiarity and conflict. By using input familiarity and sample consistency to guide memory encoding, the number of encoding trials on the dataset were reduced to 18.33% of the training data while maintaining good recognition performance on the test data.
Abstract: Early detection of anomalies in data centers is important to reduce downtimes and the costs of periodic maintenance. However, there is little research on this topic and even fewer on the fusion of sensor data for the detection of abnormal events. The goal of this paper is to propose a method for anomaly detection in data centers by combining sensor data (temperature, humidity, power) and deep learning models. The model described in the paper uses one autoencoder per sensor to reconstruct the inputs. The auto-encoders contain Long-Short Term Memory (LSTM) layers and are trained using the normal samples of the relevant sensors selected by correlation analysis. The difference signal between the input and its reconstruction is then used to classify the samples using feature extraction and a random forest classifier. The data measured by the sensors of a data center between January 2019 and May 2020 are used to train the model, while the data between June 2020 and May 2021 are used to assess it. Performances of the model are assessed a posteriori through F1-score by comparing detected anomalies with the data center’s history. The proposed model outperforms the state-of-the-art reconstruction method, which uses only one autoencoder taking multivariate sequences and detects an anomaly with a threshold on the reconstruction error, with an F1-score of 83.60% compared to 24.16%.
Abstract: In this paper, we predict the likelihood of a player making a shot in basketball from multiagent trajectories. To approach this problem, we present a convolutional neural network (CNN) approach where we initially represent the multiagent behavior as an image. To encode the adversarial nature of basketball, we use a multichannel image which we then feed into a CNN. Additionally, to capture the temporal aspect of the trajectories we use “fading.” We find that this approach is superior to a traditional FFN model. By using gradient ascent, we were able to discover what the CNN filters look for during training. Last, we find that a combined FFN+CNN is the best performing network with an error rate of 39%.
Abstract: Detecting subjectively biased statements is a vital task. This is because this kind of bias, when present in the text or other forms of information dissemination media such as news, social media, scientific texts, and encyclopedias, can weaken trust in the information and stir conflicts amongst consumers. Subjective bias detection is also critical for many Natural Language Processing (NLP) tasks like sentiment analysis, opinion identification, and bias neutralization. Having a system that can adequately detect subjectivity in text will boost research in the above-mentioned areas significantly. It can also come in handy for platforms like Wikipedia, where the use of neutral language is of importance. The goal of this work is to identify the subjectively biased language in text on a sentence level. With machine learning, we can solve complex AI problems, making it a good fit for the problem of subjective bias detection. A key step in this approach is to train a classifier based on BERT (Bidirectional Encoder Representations from Transformers) as upstream model. BERT by itself can be used as a classifier; however, in this study, we use BERT as data preprocessor as well as an embedding generator for a Bi-LSTM (Bidirectional Long Short-Term Memory) network incorporated with attention mechanism. This approach produces a deeper and better classifier. We evaluate the effectiveness of our model using the Wiki Neutrality Corpus (WNC), which was compiled from Wikipedia edits that removed various biased instances from sentences as a benchmark dataset, with which we also compare our model to existing approaches. Experimental analysis indicates an improved performance, as our model achieved state-of-the-art accuracy in detecting subjective bias. This study focuses on the English language, but the model can be fine-tuned to accommodate other languages.
Abstract: Essential genes play an important role in the survival of an organism. It has been shown that cancer-associated essential genes are genes necessary for cancer cell proliferation, where these genes are potential therapeutic targets. Also, it was demonstrated that mutations of the cancer-associated essential genes give rise to the resistance of immunotherapy for patients with tumors. In the present study, we focus on studying the biological effects of the essential genes from a network perspective. We hypothesize that one can analyze a biological molecular network by decomposing it into both three-node and four-node digraphs (subgraphs). These network subgraphs encode the regulatory interaction information among the network’s genetic elements. In this study, the frequency of occurrence of the subgraph-associated essential genes in a molecular network was quantified by using the statistical parameter, odds ratio. Biological effects of subgraph-associated essential genes are discussed. In summary, the subgraph approach provides a systematic method for analyzing molecular networks and it can capture useful biological information for biomedical research.
Abstract: The low availability of well-trained, unlimited, dynamic-access models for specific languages makes it hard for corporate users to adopt quick translation techniques and incorporate them into product solutions. As translation tasks increasingly require a dynamic sequence learning curve; stable, cost-free opensource models are scarce. We survey and compare current translation techniques and propose a modified sequence to sequence model repurposed with attention techniques. Sequence learning using an encoder-decoder model is now paving the path for higher precision levels in translation. Using a Convolutional Neural Network (CNN) encoder and a Recurrent Neural Network (RNN) decoder background, we use Fairseq tools to produce an end-to-end bilingually trained Spanish-English machine translation model including source language detection. We acquire competitive results using a duo-lingo-corpus trained model to provide for prospective, ready-made plug-in use for compound sentences and document translations. Our model serves a decent system for large, organizational data translation needs. While acknowledging its shortcomings and future scope, it also identifies itself as a well-optimized deep neural network model and solution.
Abstract: This paper presents the results of a mechatronic design based on a 4-wheel omnidirectional mobile robot that can be used in indoor logistic applications. The low-level control has been selected using two open-source hardware (Raspberry Pi 3 Model B+ and Arduino Mega 2560) that control four industrial motors, four ultrasound sensors, four optical encoders, a vision system of two cameras, and a Hokuyo URG-04LX-UG01 laser scanner. Moreover, the system is powered with a lithium battery that can supply 24 V DC and a maximum current-hour of 20Ah.The Robot Operating System (ROS) has been implemented in the Raspberry Pi and the performance is evaluated with the selection of the sensors and hardware selected. The mechatronic system is evaluated and proposed safe modes of power distribution for controlling all the electronic devices based on different tests. Therefore, based on different performance results, some recommendations are indicated for using the Raspberry Pi and Arduino in terms of power, communication, and distribution of control for different devices. According to these recommendations, the selection of sensors is distributed in both real-time controllers (Arduino and Raspberry Pi). On the other hand, the drivers of the cameras have been implemented in Linux and a python program has been implemented to access the cameras. These cameras will be used for implementing a deep learning algorithm to recognize people and objects. In this way, the level of intelligence can be increased in combination with the maps that can be obtained from the laser scanner.
Abstract: Women for centuries have undergone gender discrimination under the pretext of patriarchy which is engraved in the culture and tradition of some societies. It is important to highlight that this condition has been encoded by the male gender to dominate and manipulate women. It is therefore necessary to draw attention to this important obstacle that stands in the way of women’s achievement of their full potential and humanity in the face of these cultural traditions. The appropriate style that was chosen for this literary analysis is a qualitative research method that relies on the feminist technique using Freud’s psychological theories. This article explores patriarchy and gender discrimination as portrayed in Ahdaf Soueif’s In The Eye of the Sun (1992) and Pramoedya Ananta Toer’s The Girl from the Coast (2002). It could be argued that those two novels describe a society that is feminist, patriarchal, and gender discriminatory. Moreover, it is important to assert that patriarchy and gender discrimination are part of the system’s social order which compels the female characters to adjust to society’s norms and conventions. This social order is supported by traditional and cultural masculine attitudes and results in sustaining gender inequality, female stereo typing and patriarchy which suppress women’s beliefs and dreams.
Abstract: The linguistic and conceptual systems exhibit a tight relationship considering that words are access sites to conceptual structure. However, linguistic and conceptual structures seem to combine into a sort of homogeneous system which makes the distinction between them fuzzy. The article explores the possibility of positing a type of schematic linguistic content that is unique to the linguistic system. This linguistic content comes in the form of lexical concepts and linguistic parameters. These notions will shed some light on the parametric linguistic knowledge that might be encoded in and externalized via language. This in turn, could be the feature about language that differentiates it from the closely related conceptual system.
Abstract: The large pose discrepancy is one of the critical
challenges in face recognition during video surveillance. Due to
the entanglement of pose attributes with identity information, the
conventional approaches for pose-independent representation lack
in providing quality results in recognizing largely posed faces. In
this paper, we propose a practical approach to disentangle the pose
attribute from the identity information followed by synthesis of a face
using a classifier network in latent space. The proposed approach
employs a modified generative adversarial network framework
consisting of an encoder-decoder structure embedded with a classifier
in manifold space for carrying out factorization on the latent
encoding. It can be further generalized to other face and non-face
attributes for real-life video frames containing faces with significant
attribute variations. Experimental results and comparison with state
of the art in the field prove that the learned representation of the
proposed approach synthesizes more compelling perceptual images
through a combination of adversarial and classification losses.
Abstract: Yi is an ethnic group mainly living in mainland China, with its own spoken and written language systems, after development of thousands of years. Ancient Yi is one of the six ancient languages in the world, which keeps a record of the history of the Yi people and offers documents valuable for research into human civilization. Recognition of the characters in ancient Yi helps to transform the documents into an electronic form, making their storage and spreading convenient. Due to historical and regional limitations, research on recognition of ancient characters is still inadequate. Thus, deep learning technology was applied to the recognition of such characters. Five models were developed on the basis of the four-layer convolutional neural network (CNN). Alpha-Beta divergence was taken as a penalty term to re-encode output neurons of the five models. Two fully connected layers fulfilled the compression of the features. Finally, at the softmax layer, the orthographic features of ancient Yi characters were re-evaluated, their probability distributions were obtained, and characters with features of the highest probability were recognized. Tests conducted show that the method has achieved higher precision compared with the traditional CNN model for handwriting recognition of the ancient Yi.
Abstract: In this paper, a simple method is presented for measurement of power frequency deviations. A phase locked loop (PLL) is used to multiply the signal under test by a factor of 100. The number of pulses in this pulse train signal is counted over a stable known period, using decade driving assemblies (DDAs) and flip-flops. These signals are combined using logic gates and then passed through decade counters to give a unique combination of pulses or levels, which are further encoded. These pulses are equally suitable for both control applications and display units. The experimental circuit developed gives a resolution of 1 Hz within the measurement period of 20 ms. The proposed circuit is also simulated in Verilog Hardware Description Language (VHDL) and implemented using Field Programing Gate Arrays (FPGAs). A Mixed signal Oscilloscope (MSO) is used to observe the results of FPGA implementation. These results are compared with the results of the proposed circuit of discrete components. The proposed system is useful for frequency deviation measurement and control in power systems.
Abstract: One of the main challenges in MIMO-OFDM system
to achieve the expected performances in terms of data rate
and robustness against multi-path fading channels is the channel
estimation. Several methods were proposed in the literature based on
either least square (LS) or minimum mean squared error (MMSE)
estimators. These methods present high implementation complexity
as they require the inversion of large matrices. In order to overcome
this problem and to reduce the complexity, this paper presents
a solution that benefits from the use of the STBC encoder and
transforms the channel estimation process into a set of simple
linear operations. The proposed method is evaluated via simulation
in AWGN-Rayleigh fading channel. Simulation results show a
maximum reduction of 6.85% of the bit error rate (BER) compared to
the one obtained with the ideal case where the receiver has a perfect
knowledge of the channel.
Abstract: Autonomous vehicles offer the possibility of significant benefits to social welfare. However, fully automated cars might not be going to happen in the near further. To speed the adoption of the self-driving technologies, many governments worldwide are passing laws requiring data recorders for the testing of autonomous vehicles. Currently, the self-driving vehicle, (e.g., shuttle bus) has to be monitored from a remote control center. When an autonomous vehicle encounters an unexpected driving environment, such as road construction or an obstruction, it should request assistance from a remote operator. Nevertheless, large amounts of data, including images, radar and lidar data, etc., have to be transmitted from the vehicle to the remote center. Therefore, this paper proposes a data compression method of in-vehicle networks for remote monitoring of autonomous vehicles. Firstly, the time-series data are rearranged into a multi-dimensional signal space. Upon the arrival, for controller area networks (CAN), the new data are mapped onto a time-data two-dimensional space associated with the specific CAN identity. Secondly, the data are sampled based on differential sampling. Finally, the whole set of data are encoded using existing algorithms such as Huffman, arithmetic and codebook encoding methods. To evaluate system performance, the proposed method was deployed on an in-house built autonomous vehicle. The testing results show that the amount of data can be reduced as much as 1/7 compared to the raw data.
Abstract: Today, the mankind is in the stage of development, every day comes with new proposal of technology, in order to secure these types of technology, we also prepare high yielding security modules to conserve these resources. The capacity of human brain to recognize anything is far more than any species; this is all due to our developing cycle of curiosity. In this paper, we proposed a scheme based on graphical password using QR Code which provides more security to the recent online system. It also contains a supportive sound signature. In this system, authentication is done using sequence of images in QR code form. Users select one click-point per image with the help of QR scanner or recognizer. The encoded phrase in a QR code emphasizes the minimum probability of attacking via shoulder surfing or other attacks.
Abstract: Rv3873 is a relatively large size protein (371 amino acids in length) and its gene is located in the immunodominant genomic region of difference (RD)1 that is present in the genome of Mycobacterium tuberculosis but deleted from the genomes of all the vaccine strains of Bacillus Calmette Guerin (BCG) and most other mycobacteria. However, when tested for cellular immune responses using peripheral blood mononuclear cells from tuberculosis patients and BCG-vaccinated healthy subjects, this protein was found to be a major stimulator of cell mediated immune responses in both groups of subjects. In order to further identify the sequence of immunodominant epitopes and explore their Human Leukocyte Antigen (HLA)-restriction for epitope recognition, 24 peptides (25-mers overlapping with the neighboring peptides by 10 residues) covering the sequence of Rv3873 were synthesized chemically using fluorenylmethyloxycarbonyl chemistry and tested in cell mediated immune responses. The results of these experiments helped in the identification of an immunodominant peptide P9 that was recognized by people expressing varying HLA-DR types. Furthermore, it was also predicted to be a promiscuous binder with multiple epitopes for binding to HLA-DR, HLA-DP and HLA-DQ alleles of HLA-class II molecules that present antigens to T helper cells, and to HLA-class I molecules that present antigens to T cytotoxic cells. In addition, the evaluation of peptide P9 using an immunogenicity predictor server yielded a high score (0.94), which indicated a greater probability of this peptide to elicit a protective cellular immune response. In conclusion, P9, a peptide with multiple epitopes and ability to bind several HLA class I and class II molecules for presentation to cells of the cellular immune response, may be useful as a peptide-based vaccine against tuberculosis.
Abstract: The comparisons of mycobacterial genomes have identified several Mycobacterium tuberculosis-specific genomic regions that are absent in other mycobacteria and are known as regions of differences. Due to M. tuberculosis-specificity, the peptides encoded by these regions could be useful in the specific diagnosis of tuberculosis. To explore this possibility, overlapping synthetic peptides corresponding to 39 proteins predicted to be encoded by genes present in regions of differences were tested for antibody-reactivity with sera from tuberculosis patients and healthy subjects. The results identified four immunodominant peptides corresponding to four different proteins, with three of the peptides showing significantly stronger antibody reactivity and rate of positivity with sera from tuberculosis patients than healthy subjects. The fourth peptide was recognized equally well by the sera of tuberculosis patients as well as healthy subjects. Predication of antibody epitopes by bioinformatics analyses using ABCpred server predicted multiple linear epitopes in each peptide. Furthermore, peptide sequence analysis for sequence identity using BLAST suggested M. tuberculosis-specificity for the three peptides that had preferential reactivity with sera from tuberculosis patients, but the peptide with equal reactivity with sera of TB patients and healthy subjects showed significant identity with sequences present in nob-tuberculous mycobacteria. The three identified M. tuberculosis-specific immunodominant peptides may be useful in the serological diagnosis of tuberculosis.
Abstract: In this paper, an improved motion estimation (ME) approach based on weighted constrained one-bit transform is proposed for block-based ME employed in video encoders. Binary ME approaches utilize low bit-depth representation of the original image frames with a Boolean exclusive-OR based hardware efficient matching criterion to decrease computational burden of the ME stage. Weighted constrained one-bit transform (WC‑1BT) based approach improves the performance of conventional C-1BT based ME employing 2-bit depth constraint mask instead of a 1-bit depth mask. In this work, the range of constraint mask is further extended to increase ME performance of WC-1BT approach. Experiments reveal that the proposed method provides better ME accuracy compared existing similar ME methods in the literature.
Abstract: In this paper, we present a wavelet coefficients masking
based on Local Binary Patterns (WLBP) approach to enhance the
temporal spectra of the wavelet coefficients for speech enhancement.
This technique exploits the wavelet denoising scheme, which splits
the degraded speech into pyramidal subband components and extracts
frequency information without losing temporal information. Speech
enhancement in each high-frequency subband is performed by binary
labels through the local binary pattern masking that encodes the ratio
between the original value of each coefficient and the values of the
neighbour coefficients. This approach enhances the high-frequency
spectra of the wavelet transform instead of eliminating them through
a threshold. A comparative analysis is carried out with conventional
speech enhancement algorithms, demonstrating that the proposed
technique achieves significant improvements in terms of PESQ, an
international recommendation of objective measure for estimating
subjective speech quality. Informal listening tests also show that
the proposed method in an acoustic context improves the quality
of speech, avoiding the annoying musical noise present in other
speech enhancement techniques. Experimental results obtained with a
DNN based speech recognizer in noisy environments corroborate the
superiority of the proposed scheme in the robust speech recognition
scenario.
Abstract: This paper focuses on how the government-led language policies and the political changes in Taiwan manipulate the languages choice in translations and what translation strategies are employed by the translator to show his or her language ideology behind the power struggles and decision-making. Therefore, framed by Lefevere’s theoretical concept of translating as rewriting, and carried out a diachronic and chronological study, this paper specifically sets out to investigate the language ideology and translator’s idiolect of Chinese language translations of Anglo-American novels. The examples drawn to explore these issues were taken from different versions of Chinese renditions of Mark Twain’s English-language novel The Adventures of Huckleberry Finn in which there are several different dialogues originally written in the colloquial language and dialect used in the American state of Mississippi and reproduced in Mark Twain’s works. Also, adapted corpus methodology, many examples are extracted as instances from the translated texts and source text, to illuminate how the translators in Taiwan deal with the dialectal features encoded in Twain’s works, and how different versions of Chinese translations are employed by Taiwanese translators to confirm the language polices and to express their language identity textually in different periods of the past five decades, from the 1960s onward. The finding of this study suggests that the use of Taiwanese dialect and language patterns in translations does relate to the movement of the mother-tongue language and language ideology of the translator as well as to the issue of language identity raised in the island of Taiwan. Furthermore, this study confirms that the change of political power in Taiwan does bring significantly impact in language policy-- assimilationism, pluralism or multiculturalism, which also makes Taiwan from a monolingual to multilingual society, where the language ideology and identity can be revealed not only in people’s daily communication but also in written translations.