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: 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: 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: 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: 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: 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: This study investigates experimentally the effects
of hydrogen addition in the intake manifold of a diesel generator
operating with a 7% biodiesel-diesel oil blend (B7). An experimental
apparatus setup was used to conduct performance and emissions tests
in a single cylinder, air cooled diesel engine. This setup consisted
of a generator set connected to a wirewound resistor load bank that
was used to vary engine load. In addition, a flowmeter was used to
determine hydrogen volumetric flowrate and a digital anemometer
coupled with an air box to measure air flowrate. Furthermore, a
digital precision electronic scale was used to measure engine fuel
consumption and a gas analyzer was used to determine exhaust
gas composition and exhaust gas temperature. A thermopar was
installed near the exhaust collection to measure cylinder temperature.
In-cylinder pressure was measured using an AVL Indumicro data
acquisition system with a piezoelectric pressure sensor. An AVL
optical encoder was installed in the crankshaft and synchronized
with in-cylinder pressure in real time. The experimental procedure
consisted of injecting hydrogen into the engine intake manifold
at different mass concentrations of 2,6,8 and 10% of total fuel
mass (B7 + hydrogen), which represented energy fractions of 5,15,
20 and 24% of total fuel energy respectively. Due to hydrogen
addition, the total amount of fuel energy introduced increased
and the generators fuel injection governor prevented any increases
of engine speed. Several conclusions can be stated from the test
results. A reduction in specific fuel consumption as a function
of hydrogen concentration increase was noted. Likewise, carbon
dioxide emissions (CO2), carbon monoxide (CO) and unburned
hydrocarbons (HC) decreased as hydrogen concentration increased.
On the other hand, nitrogen oxides emissions (NOx) increased due
to average temperatures inside the cylinder being higher. There
was also an increase in peak cylinder pressure and heat release
rate inside the cylinder, since the fuel ignition delay was smaller
due to hydrogen content increase. All this indicates that hydrogen
promotes faster combustion and higher heat release rates and can
be an important additive to all kind of fuels used in diesel generators.
Abstract: The aim of this paper is to present the QoE (Quality of Experience) IPTV SDN-based media streaming server enhanced architecture for configuring, controlling, management and provisioning the improved delivery of IPTV service application with low cost, low bandwidth, and high security. Furthermore, it is given a virtual QoE IPTV SDN-based topology to provide an improved IPTV service based on QoE Control and Management of multimedia services functionalities. Inside OpenFlow SDN Controller there are enabled in high flexibility and efficiency Service Load-Balancing Systems; based on the Loading-Balance module and based on GeoIP Service. This two Load-balancing system improve IPTV end-users Quality of Experience (QoE) with optimal management of resources greatly. Through the key functionalities of OpenFlow SDN controller, this approach produced several important features, opportunities for overcoming the critical QoE metrics for IPTV Service like achieving incredible Fast Zapping time (Channel Switching time) < 0.1 seconds. This approach enabled Easy and Powerful Transcoding system via FFMPEG encoder. It has the ability to customize streaming dimensions bitrates, latency management and maximum transfer rates ensuring delivering of IPTV streaming services (Audio and Video) in high flexibility, low bandwidth and required performance. This QoE IPTV SDN-based media streaming architecture unlike other architectures provides the possibility of Channel Exchanging between several IPTV service providers all over the word. This new functionality brings many benefits as increasing the number of TV channels received by end –users with low cost, decreasing stream failure time (Channel Failure time < 0.1 seconds) and improving the quality of streaming services.
Abstract: Low-resolution digital encoder (LRDE) is commonly adopted as a position sensor in low-cost and resource-constraint applications. Traditionally, a digital encoder is modeled as a quantizer without considering the initial position of the LRDE. However, it cannot be applied to extreme LRDE for which stroke of angular motion is only a few times of resolution of the encoder. Besides, the actual angular motion is substantially distorted by this extreme LRDE so that the encoder reading does not faithfully represent the actual angular motion. This paper presents a modeling method for extreme LRDE by taking into account the initial position of the LRDE. For a control system with sinusoidal reference signal and extreme LRDE, this paper analyzes the characteristics of angular motion. Specifically, two descriptors of sinusoidal angular motion are studied, which essentially sheds light on the actual angular motion from extreme LRDE.
Abstract: In this paper, we have presented and analyzed three-dimensional (3-D) matrices of wavelength/time/space code for optical code division multiple access (OCDMA) networks with NAND subtraction detection technique. The 3-D codes are constructed by integrating a two-dimensional modified quadratic congruence (MQC) code with one-dimensional modified prime (MP) code. The respective encoders and decoders were designed using fiber Bragg gratings and optical delay lines to minimize the bit error rate (BER). The performance analysis of the 3D-OCDMA system is based on measurement of signal to noise ratio (SNR), BER and eye diagram for a different number of simultaneous users. Also, in the analysis, various types of noises and multiple access interference (MAI) effects were considered. The results obtained with NAND detection technique were compared with those obtained with OR and AND subtraction techniques. The comparison results proved that the NAND detection technique with 3-D MQC\MP code can accommodate more number of simultaneous users for longer distances of fiber with minimum BER as compared to OR and AND subtraction techniques. The received optical power is also measured at various levels of BER to analyze the effect of attenuation.
Abstract: In the presented technique, a simple method is given for accurate measurement and control of power frequency deviation. The sinusoidal signal for which the frequency deviation measurement is required is transformed to a low voltage level and passed through a zero crossing detector to convert it into a pulse train. Another stable square wave signal of 10 KHz is obtained using a crystal oscillator and decade dividing assemblies (DDA). These signals are combined digitally and then passed through decade counters to give a unique combination of pulses or levels, which are further encoded to make them equally suitable for both control applications and display units. The developed circuit using discrete components has a resolution of 0.5 Hz and completes measurement within 20 ms. The realized circuit is simulated and synthesized using Verilog HDL and subsequently implemented on FPGA. The results of measurement on FPGA are observed on a very high resolution logic analyzer. These results accurately match the simulation results as well as the results of same circuit implemented with discrete components. The proposed system is suitable for accurate measurement and control of power frequency deviation.
Abstract: Speaker recognition is performed in high Additive White Gaussian Noise (AWGN) environments using principals of Computational Auditory Scene Analysis (CASA). CASA methods often classify sounds from images in the time-frequency (T-F) plane using spectrograms or cochleargrams as the image. In this paper atomic decomposition implemented by matching pursuit performs a transform from time series speech signals to the T-F plane. The atomic decomposition creates a sparsely populated T-F vector in “weight space” where each populated T-F position contains an amplitude weight. The weight space vector along with the atomic dictionary represents a denoised, compressed version of the original signal. The arraignment or of the atomic indices in the T-F vector are used for classification. Unsupervised feature learning implemented by a sparse autoencoder learns a single dictionary of basis features from a collection of envelope samples from all speakers. The approach is demonstrated using pairs of speakers from the TIMIT data set. Pairs of speakers are selected randomly from a single district. Each speak has 10 sentences. Two are used for training and 8 for testing. Atomic index probabilities are created for each training sentence and also for each test sentence. Classification is performed by finding the lowest Euclidean distance between then probabilities from the training sentences and the test sentences. Training is done at a 30dB Signal-to-Noise Ratio (SNR). Testing is performed at SNR’s of 0 dB, 5 dB, 10 dB and 30dB. The algorithm has a baseline classification accuracy of ~93% averaged over 10 pairs of speakers from the TIMIT data set. The baseline accuracy is attributable to short sequences of training and test data as well as the overall simplicity of the classification algorithm. The accuracy is not affected by AWGN and produces ~93% accuracy at 0dB SNR.
Abstract: In this paper, a design of H.263 based wireless video
transceiver is presented for wireless camera system. It uses standard
WIFI transceiver and the covering area is up to 100m. Furthermore the
standard H.263 video encoding technique is used for video
compression since wireless video transmitter is unable to transmit high
capacity raw data in real time and the implemented system is capable
of streaming at speed of less than 1Mbps using NTSC 720x480 video.
Abstract: For the last decade, researchers have started to focus
their interest on Multicast Group Key Management Framework. The
central research challenge is secure and efficient group key
distribution. The present paper is based on the Bit model based
Secure Multicast Group key distribution scheme using the most
popular absolute encoder output type code named Gray Code. The
focus is of two folds. The first fold deals with the reduction of
computation complexity which is achieved in our scheme by
performing fewer multiplication operations during the key updating
process. To optimize the number of multiplication operations, an
O(1) time algorithm to multiply two N-bit binary numbers which
could be used in an N x N bit-model of reconfigurable mesh is used
in this proposed work. The second fold aims at reducing the amount
of information stored in the Group Center and group members while
performing the update operation in the key content. Comparative
analysis to illustrate the performance of various key distribution
schemes is shown in this paper and it has been observed that this
proposed algorithm reduces the computation and storage complexity
significantly. Our proposed algorithm is suitable for high
performance computing environment.
Abstract: This paper describes a cycle accurate simulation results of weight values learned by an auto-encoder behavior model in terms of pre-route simulation. Given the results we visualized the first layer representations with natural images. Many common deep learning threads have focused on learning high-level abstraction of unlabeled raw data by unsupervised feature learning. However, in the process of handling such a huge amount of data, the learning method’s computation complexity and time limited advanced research. These limitations came from the fact these algorithms were computed by using only single core CPUs. For this reason, parallel-based hardware, FPGAs, was seen as a possible solution to overcome these limitations. We adopted and simulated the ready-made auto-encoder to design a behavior model in VerilogHDL before designing hardware. With the auto-encoder behavior model pre-route simulation, we obtained the cycle accurate results of the parameter of each hidden layer by using MODELSIM. The cycle accurate results are very important factor in designing a parallel-based digital hardware. Finally this paper shows an appropriate operation of behavior model based pre-route simulation. Moreover, we visualized learning latent representations of the first hidden layer with Kyoto natural image dataset.
Abstract: When using modern Code Division Multiple Access (CDMA) in mobile communications, the user must be able to vary the transmission rate of users to allocate bandwidth efficiently. In this work, Orthogonal Variable Spreading Factor (OVSF) codes are used with the same principles applied in a low-rate superorthogonal turbo code due to their variable-length properties. The introduced system is the Variable Rate Superorthogonal Turbo Code (VRSTC) where puncturing is not performed on the encoder’s final output but rather before selecting the output to achieve higher rates. Due to bandwidth expansion, the codes outperform an ordinary turbo code in the AWGN channel. Simulations results show decreased performance compared to those obtained with the employment of Walsh-Hadamard codes. However, with OVSF codes, the VRSTC system keeps the orthogonality of codewords whilst producing variable rate codes contrary to Walsh-Hadamard codes where puncturing is usually performed on the final output.
Abstract: Error correcting codes are used for detection and correction of errors in digital communication system. Error correcting coding is based on appending of redundancy to the information message according to a prescribed algorithm. Reed Solomon codes are part of channel coding and withstand the effect of noise, interference and fading. Galois field arithmetic is used for encoding and decoding reed Solomon codes. Galois field multipliers and linear feedback shift registers are used for encoding the information data block. The design of Reed Solomon encoder is complex because of use of LFSR and Galois field arithmetic. The purpose of this paper is to design and implement Reed Solomon (255, 239) encoder with optimized and lesser number of Galois Field multipliers. Symmetric generator polynomial is used to reduce the number of GF multipliers. To increase the capability toward error correction, convolution interleaving will be used with RS encoder. The Design will be implemented on Xilinx FPGA Spartan II.
Abstract: Now a days video data embedding approach is a very challenging and interesting task towards keeping real time video data secure. We can implement and use this technique with high-level applications. As the rate-distortion of any image is not confirmed, because the gain provided by accurate image frame segmentation are balanced by the inefficiency of coding objects of arbitrary shape, with a lot factors like losses that depend on both the coding scheme and the object structure. By using rate controller in association with the encoder one can dynamically adjust the target bitrate. This paper discusses about to keep secure videos by mixing signature data with negligible distortion in the original video, and to keep steganographic video as closely as possible to the quality of the original video. In this discussion we propose the method for embedding the signature data into separate video frames by the use of block Discrete Cosine Transform. These frames are then encoded by real time encoding H.264 scheme concepts. After processing, at receiver end recovery of original video and the signature data is proposed.