# Hilal Nuha's research while affiliated with Telkom University and other places

**What is this page?**

This page lists the scientific contributions of an author, who either does not have a ResearchGate profile, or has not yet added these contributions to their profile.

It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.

If you're a ResearchGate member, you can follow this page to keep up with this author's work.

If you are this author, and you don't want us to display this page anymore, please let us know.

It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.

If you're a ResearchGate member, you can follow this page to keep up with this author's work.

If you are this author, and you don't want us to display this page anymore, please let us know.

## Publications (30)

Multipath transmission control protocol (MPTCP) has been proposed for devices with multiple network interfaces. This idea seems to be impossible for user implementation at the beginning of its proposal. However, the emergence of smartphones with multiple network access allows this idea to be implemented. This paper provides both theoretical and emp...

Investigating the potential for deploying a wind farm requires accurate knowledge of the vertical profile of wind speed (WS), both temporal and with height. Commonly, WS estimations at different heights involves calculating site‐dependent parameters such as roughness length, atmospheric conditions, and wind shear coefficient. This study proposes a...

This paper provides a data visualization and analysis of the COVID-19 vaccination program. Important information such as which countries have the highest vaccination rates and numbers. In addition to the types of vaccines used and used by countries in the world, an infographic on the geographic distribution of vaccine use is also shown. To model th...

With the advent of robust computing power, any sophisticated algorithm for data compression is becoming a trivial task. With more than petabytes of seismic data produced every day and the trend toward 4D survey, it is becoming essential to develop robust algorithms for the seismic data compression. This led to significant research efforts in data c...

Seismic data may undergo many types of distortions. However, the effect of distortion on raw data may not be apparent until the end of the standard processing of seismic reflection data. This paper presents a semi-blind metric for seismic data quality assessment, namely weighted normalized mean squared error (wNMSE). A weighting scheme is utilized...

This paper presents an investigation of the long short-term memory (LSTM) neural networks for seismogram time series prediction. LSTM has been widely used for time series prediction problems and achieved excellent results therefore it is interesting to utilize this technique for seismology. A seismogram from Albuquerque, New Mexico (Anmo), USA prov...

In this work, we present a weighted l1 norm-based Extreme Learning Machine (ELM), namely, enhanced Regularized ELM (eRELM) for regression problems with outliers contaminated data. The enhancement includes the introduction of a weighting scheme based on l1 norm to a regularization term in the optimization problem. Seismogram is typically recorded wi...

The modern seismic acquisition produces a large data volume that significantly increases the cost of storage and transmission. Therefore, it is desirable to reduce the cost by compressing the seismic data. In this work, we propose a model-based compression scheme to deal with the large data volume. First, each seismic trace is modeled as a superpos...

This work develops a model-based compression scheme for seismic data. First, seismic traces are modeled as multitone sinusoidal waves superposition. Each sinusoidal wave is regarded as a model component and is represented by a set of distinct parameters. Second, a parameter estimation algorithm for this model is proposed accordingly. In this algori...

Text images are used in many types of conventional data communication where texts are not directly represented by digital character such as ASCII but represented by an image, for instance facsimile file or scanned documents. We propose a combination of Run Length Encoding (RLE) and Huffman coding for two dimensional binary image compression namely...

This paper develops a new framework for data compression in seismic sensor networks by using the distributed principal component analysis (DPCA). The proposed DPCA scheme compresses all seismic traces in the network at the sensor level. First of all, the statistics of the seismic traces acquired at all sensors are represented by a mixture model of...

This work considers the data compression of sequential seismic sensor arrays. First, the statistics of the seismic traces collected by all the sensors are modeled by using the mixture model. Hence, a distributed Principle Component Analysis (PCA) compression scheme for sequential sensor arrays is designed. The proposed scheme does not require trans...

## Citations

... Abedinia et al. [16] put forward a comprehensive prediction method, based on the improved wavelet transform. Al-Shaikhi et al. [17] proposed a hybrid model to estimate the wind speed at different heights, based on the measurements at lower heights using the particle swarm optimization (PSO) and long short-term memory (LSTM). Mohandes et al. [18] analyzed the predictability of wind speed with heights and employed the recurrent neural network (RNN) model for predicting the wind speed 12 h ahead of time, using 48 previous hourly values. ...

... Al-Shaikhi et al. [17] proposed a hybrid model to estimate the wind speed at different heights, based on the measurements at lower heights using the particle swarm optimization (PSO) and long short-term memory (LSTM). Mohandes et al. [18] analyzed the predictability of wind speed with heights and employed the recurrent neural network (RNN) model for predicting the wind speed 12 h ahead of time, using 48 previous hourly values. Salman et al. [19] put forward a short-term, multi-dimensional prediction of the wind speed, based on LSTM. ...

... Each particle that represents a single individual in the swarm, records the best solution found by itself and by the whole swarm along the search space. 17 Each individual updates its position in the search trajectory and exchanges ...

... Simple linear regression techniques can be used to predict the number of vaccinations. Linear prediction coding (LPC) [10], [11] differs from linear regression by the use of single dimensionality. LPC is usually applied to one dimension time series without taking other values as inputs. ...

... It is intended to broken down the gray image into the bit planes, and individual bit planes are individually compressed. One of the variants of run time coding is an efficient runlength coding mechanism [16]. ...

... Bilateral filtering with Gaussian kernels has outperformed wavelet transform-based denoising, dictionary learning-based denoising and standard Bilateral filter with noise thresholding for seismic image denoising [18]. Motivated by this and its effectiveness in improving event detection for time-series non-intrusive load monitoring [19], we adopt and adapt a graph-based bilateral filter (GraphBF) with Gaussian kernel [20], which has never been tested for denoising of timeseries raw seismic signal recordings. ...

... Deep learning methods are widely used to solve the seismic compression problem. Restricted Boltzmann machine (RBM) [14] with single layer neural network is proposed in Nuha et al. [15]. Although being computationally efficient, a single layer cannot capture all data features and the reconstruction error is high. ...

Reference: Seismic Data Compression Using Deep Learning

... The experiment was then carried out as follows. First, the Kalman filtering as shown in (10)- (16) was applied to the system (2)-(3) without considering the effect of the potential change v t . This step output the innovation ε t and its covariance S t . ...

... They all rely on the observation that the covariance matrix can be computed exactly at the global server by adding up the local covariance matrices. This basic version is, for instance, used in Liu et al. (2018). In this version, the covariance matrices of the local datasets are computed and sent to the aggregator. ...

... The results showed that the proposed scheme can extract the information from both seismic reflection layers and neighboring traces. More recently, a distributed principal component analysis (DPCA) compression was proposed for smart seismic acquisition networks in [32] and [33], wherein the overall statistics of the seismic traces recorded by all sensors in the acquisition network are used for global PC estimation. In [34], the nonlinearities of seismic traces were investigated and extended by using a five-layer autoassociative neural network model to improve seismic interpretation. ...