Please login first

List of accepted submissions

Show results per page
Find papers
  • Open access
  • 67 Reads
An Automated Image Based System for Colour Assessment of Prints and Textiles in Light Booth

Colour is a subjective perception, and in an industrial environment using colour, objectivity is of great significance. In pursuit of improvising the measurement approaches inheriting the scientific progressions, this research emphasis on the development of an automated system with image processing and machine learning techniques for non-contact colour assessment of both prints and textiles under user-defined daylight conditions in the light booth. The system consists of a light booth with tunable LED daylight luminaire to set the day-lighting conditions of D50, D65 and D75 with adjustable illuminance as per colour assessment standards of ISO/ASTM. The feature vectors of the sample images are extracted using colour histograms through histogram quantization. Colour classification is performed using K-Nearest Neighbor (KNN) algorithm trained with 140 shades of Macbeth colour checker chart SG. The proposed system is compared with visual and instrumental measurement methods for experimental validation. The results demonstrate an accuracy rate of 86% in colour classification of prints. Correlating to the lightness of textile samples an accuracy rate of 86% (very dark colour), 83% (medium light colour), 100% (very light colour) found

  • Open access
  • 58 Reads
Multi-commodity Contraflow Problem on Lossy Network with Asymmetric Transit times

During transmission of commodities from one place to another, there may be loss due to death, leakage, damage, or evaporation. To address the problem, each arc of the network contains a gain factor. The network is a lossy network with a gain factor at most one on each arc. The generalized multi-commodity flow problem deals with routing several distinct goods from specific supply points to the corresponding demand points on an underlying network with minimum loss. The sum of all commodities on each arc does not exceed its capacity. Motivated by the uneven road condition of transportation network topology, we incorporate a contraflow approach with orientation-dependent transit times on arcs and introduce the generalized multi-commodity contraflow problem on a lossy network with orientation-dependent transit times.

In general, the generalized dynamic multi-commodity contraflow problem is $\mathcal{NP}$-hard. For a lossy network with symmetric transit time on anti-parallel arcs, the problem is solved in pseudo-polynomial-time. We extend the analytical solution with symmetric transit time on anti-parallel arcs to asymmetric transit times and present algorithms which solve it within the same time complexity.

  • Open access
  • 106 Reads
Quickest transshipment in an integrated network topology

The quickest transshipment of the evacuees in an integrated evacuation network topology depends upon the evacuee arrival pattern in the collection network and their better assignment in the assignment network with appropriate traffic route guidance, destination
optimization, and optimal route.

In this work, the quickest transshipment aspect in an integrated evacuation network topology is revisited concerning a transit-based evacuation system. Appropriate collection approaches for the evacuees and their better assignment to transit vehicles for their quickest transshipment in such an embedded evacuation network are presented with their solution strategies.

  • Open access
  • 99 Reads
Detection of misogyny from Arabic Levantine Twitter tweets using machine learning techniques
Published: 19 September 2021 by MDPI in The 1st Online Conference on Algorithms session Artificial Intelligence Algorithms

Due to the increased abundance of user comments on the internet, such as Twitter, Arabic Text Detection (ATD) is one of the most difficult computational tasks for the machine learning field. Misogyny in Arabic text detection has become a touchy issue, especially among Arab women. Online misogyny has become a major threat to women in many countries, and online misogynistic harassment has grown in recent years In this article, we use misogynistic women in Levantine as a case study to build a new approach for detecting Arabic text. The suggested study's goal is to discover a novel Arabic text recognition algorithm for misogyny of women in Arabic countries. Our approach has been evaluated on the Arabic Levantine Twitter Dataset for Misogynistic, and we achieved an excellent accuracy of 90% using the BERTv2n in binary classification and 89 in multi classification .

  • Open access
  • 156 Reads
Avoiding Temporal Confounding in Timeseries Forecasting using Machine Learning

Timeseries forecasting plays an important role in many applications where knowledge of the future behaviour of a given quantity of interest is required.

Traditionally, this task is approached using methods such as exponential smoothing, ARIMA and, more recently, recurrent neural networs such as LSTM architectures or transformers. These approaches intrinsically rely on the auto-correlation or partial auto-correlation between subsequent events to forecast the future values. Essentially, the past values of the timeseries are used to model its future behaviour. Implicitly, this assumes that the auto-correlation and partial auto-correlation is genuine and not spurious. In the latter case, the methods exploit the (partial) auto-correlation in the prediction even though they are not grounded in the causal data generation process of the timeseries. This can happen if some external event or intervention affects the value of the timeseries at multiple times. In terms of causal analysis, this is equivalent to introducing a confounder into the timeseries where the variable of interest at different times takes over the role of multiple variables in standard causal analysis. This effectively opens a backdoor path between different times that in turn leads to a spurious auto-correlation. If a forecasting model is built including such spurious correlations, the generalizeability and forecasting power of the model is reduced and future predictions many consequently be wrong.

Using a supervised learning approach, we show how machine learning can be used to avoid temporal confounding in timeseries forecasting, thereby limiting or avoiding the influence of spurious auto-correlations or partial auto-correlations.

  • Open access
  • 185 Reads
A novel strategy for tall building optimization via combination of asymmetric genetic algorithm and machine learning methods

The optimum design of tall buildings, which have a proportionately huge quantity of structural elements and a variety of design code constraints, is a very computationally expensive process. In this paper, a novel strategy, with a combination of evolutionary algorithms and machine learning methods, is developed for achieving the optimal design of steel high-rise buildings. The most time-consuming part of the procedure is the analysis of tall buildings and the control of design code constraints, requiring frequent re-analyses. The main idea here proposed is to use machine learning methods for this purpose. The optimization process will be performed by a novel evolutionary algorithm, named asymmetric genetic algorithm (AGA), and in each iteration that requires checking the constraints for a large number of different structural states, machine learning methods, including MLP, GMDH and ANFIS-PSO are facilitators. By coupling ETABS and MATLAB software, various combinations of sections for structural elements are assigned and analyzed automatically, thus creating a database for training the neural networks. Accordingly, a practical methodology for the optimal design of steel tall buildings, allowing for the constraints imposed by typical building codes, is introduced. The applicability of the suggested procedure is described through the determination of the optimal seismic design for some case studies. Results testify that the present method not only supports the precision of the results but also remarkably diminishes the computational time and memory needed, in comparison with the existing classical methods; the optimization process time is also significantly decreased.

  • Open access
  • 67 Reads
Flows on Network with Intermediate Storage Capability: Evacuation Planning Perspective

Optimization models for evacuation with capability of holding evacuees at intermediate places are of particular interest when all the evacuees cannot be sent to the safe destination. We study the maximum flow evacuation planning problem that aims to lexicographically maximize the evacuees entering a set of capacitated terminals, sink and intermediate vertices, with respect to a given prioritization.

We propose a polynomial time algorithm for the problem modeled on uniform path length (UPL) network. We also apply this algorithm to solve quickest flow evacuation planning problem that lexicographically minimizes the time required to fulfill the demand of evacuees at such terminals. Moreover, we show that the algorithm solves an earliest arrival version of the problem with sufficient vertex capacities for uniform path length two terminal series parallel (UPL-TTSP) network.

  • Open access
  • 52 Reads
Algorithmization of transport analyzes for urbanized areas - concept and case studies.

The article presents the concept of algorithmization of the process of creating transport analyzes for urbanized areas. The need to develop the algorithmization process results from the formation of key elements of transport analyzes as well as new possibilities of obtaining data, in particular Big Data describing both transport processes and urbanization processes. Algorithmization covers the various stages of creating a transport analysis in a systemic perspective. The presented concept uses systems engineering methods adapted to the specifics of the description of transport systems and processes in urbanized areas. The article presents examples of case studies for the transport systems of urbanized areas in the following scales: city, agglomeration and metropolitan area. Cases related to intelligent transport systems, mobility management and the creation of new transport systems with a metropolitan range were included.

  • Open access
  • 108 Reads
A Generative Adversarial Network based autoencoder for Structural Health Monitoring

Civil structures and infrastructures such as buildings, bridges, tunnels and dams play a crucial role in our society. Their safety and health are threatened by different factors: aging, progressive accumulation of damage and alteration of working and environmental conditions with respect to the design ones, are just a few examples. Rebuilding these systems when damage has grown too large, would not be economically feasible; therefore, various approaches for damage detection have been recently developed. In this context, Structural Health Monitoring (SHM) has become an active field of research, aiming to detect, locate and quantify the damage, namely the degradation of the strength and stiffness properties of the structural system. Compared to the widespread visual inspections and non-destructive testing, a global monitoring approach based on continuous vibrational measurements provides numerous advantages: first, it does not require any a-priori knowledge on the position of the damage; second, it can provide a quantitative estimate of the structural health that is seldom furnished by traditional methods. In this work we propose a new SHM approach leveraging on a Generative Adversarial Network (GAN) based autoencoder. The characteristic feature of the offered neural network architecture is the capability to reconstruct the sensor recordings, leading to an informative and disentangled latent space associated to the damage class. The main novelty of the approach is represented by the capability to generate plausible signals for different damage states, based only on undamaged recorded or simulated structural responses, thus without the need to rely upon real recordings linked to damaged conditions.

  • Open access
  • 76 Reads
Two-scale deep learning model for polysilicon MEMS sensors

Micro Electro-Mechanical Systems (MEMS) are often affected in their operational environment by different physical phenomena, each one possibly occurring at different length and time scales. Data-driven formulations can then be helpful to deal with such complexity in their modeling. By referring to a single-axis Lorentz force micro-magnetometer, characterized by a current flowing inside slender mechanical parts so that the system can be driven into resonance, it has been shown that the sensitivity to the magnetic field may get largely enhanced through proper (topology) optimization strategies. In our previous work, a reduced-order physical model for the movable structure was developed; such model-based approach did not account for all the stochastic effects leading to the measured scattering in the experimental data. A new formulation is here proposed resting on a two-scale deep learning model designed as follows: at the material level, a deep neural network is used a-priori to learn the scattering in the mechanical properties of polysilicon induced by its morphology; at the device level, a further deep neural network is used to account for the effects on the response induced by etch defects, learning on-the-fly relevant geometric features of the movable parts. Some preliminary results are here reported, and the capabilities of the learning models at the two length scales are discussed.

1 2 3 4