General Purpose Optimization Library (GPOL): A Flexible and Efficient Multi-Purpose Optimization Library in Python

Several interesting libraries for optimization have been proposed. Some focus on individual optimization algorithms, or limited sets of them, and others focus on limited sets of problems. Frequently, the implementation of one of them does not precisely follow the formal definition, and they are difficult to personalize and compare. This makes it difficult to perform comparative studies and propose novel approaches. In this paper, we propose to solve these issues with the General Purpose Optimization Library (GPOL): a flexible and efficient multipurpose optimization library that covers a wide range of stochastic iterative search algorithms, through which flexible and modular implementation can allow for solving many different problem types from the fields of continuous and combinatorial optimization and supervised machine learning problem solving. Moreover, the library supports full-batch and mini-batch learning and allows carrying out computations on a CPU or GPU. The package is distributed under an MIT license. Source code, installation instructions, demos and tutorials are publicly available in our code hosting platform (the reference is provided in the Introduction).

Download Full-text

A Generalization Performance Study Using Deep Learning Networks in Embedded Systems

Sensors ◽

10.3390/s21041031 ◽

2021 ◽

Vol 21 (4) ◽

pp. 1031

Author(s):

Joseba Gorospe ◽

Rubén Mulero ◽

Olatz Arbelaitz ◽

Javier Muguerza ◽

Miguel Ángel Antón

Keyword(s):

Deep Learning ◽

Embedded Systems ◽

Embedded System ◽

General Purpose ◽

Learning Networks ◽

Performance Study ◽

Learning Techniques ◽

Wide Range ◽

Learning Architectures

Deep learning techniques are being increasingly used in the scientific community as a consequence of the high computational capacity of current systems and the increase in the amount of data available as a result of the digitalisation of society in general and the industrial world in particular. In addition, the immersion of the field of edge computing, which focuses on integrating artificial intelligence as close as possible to the client, makes it possible to implement systems that act in real time without the need to transfer all of the data to centralised servers. The combination of these two concepts can lead to systems with the capacity to make correct decisions and act based on them immediately and in situ. Despite this, the low capacity of embedded systems greatly hinders this integration, so the possibility of being able to integrate them into a wide range of micro-controllers can be a great advantage. This paper contributes with the generation of an environment based on Mbed OS and TensorFlow Lite to be embedded in any general purpose embedded system, allowing the introduction of deep learning architectures. The experiments herein prove that the proposed system is competitive if compared to other commercial systems.

Download Full-text

Early Dropout Prediction in MOOCs through Supervised Learning and Hyperparameter Optimization

Electronics ◽

10.3390/electronics10141701 ◽

2021 ◽

Vol 10 (14) ◽

pp. 1701

Author(s):

Theodor Panagiotakopoulos ◽

Sotiris Kotsiantis ◽

Georgios Kostopoulos ◽

Omiros Iatrellis ◽

Achilles Kameas

Keyword(s):

Online Education ◽

Online Courses ◽

Early Stage ◽

Activity Patterns ◽

Daily Basis ◽

Machine Learning Algorithms ◽

Supervised Machine Learning ◽

Educational Institutions ◽

Student Dropout ◽

Wide Range

Over recent years, massive open online courses (MOOCs) have gained increasing popularity in the field of online education. Students with different needs and learning specificities are able to attend a wide range of specialized online courses offered by universities and educational institutions. As a result, large amounts of data regarding students’ demographic characteristics, activity patterns, and learning performances are generated and stored in institutional repositories on a daily basis. Unfortunately, a key issue in MOOCs is low completion rates, which directly affect student success. Therefore, it is of utmost importance for educational institutions and faculty members to find more effective practices and reduce non-completer ratios. In this context, the main purpose of the present study is to employ a plethora of state-of-the-art supervised machine learning algorithms for predicting student dropout in a MOOC for smart city professionals at an early stage. The experimental results show that accuracy exceeds 96% based on data collected during the first week of the course, thus enabling effective intervention strategies and support actions.

Download Full-text

An information theoretic approach to link prediction in multiplex networks

Scientific Reports ◽

10.1038/s41598-021-92427-1 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Seyed Hossein Jafari ◽

Amir Mahdi Abdolhosseini-Qomi ◽

Masoud Asadpour ◽

Maseud Rahgozar ◽

Naser Yazdani

Keyword(s):

Real World ◽

Link Prediction ◽

Large Scale ◽

Similarity Measures ◽

Prediction Method ◽

General Purpose ◽

Fast Method ◽

Theoretic Approach ◽

Multiplex Networks ◽

Wide Range

AbstractThe entities of real-world networks are connected via different types of connections (i.e., layers). The task of link prediction in multiplex networks is about finding missing connections based on both intra-layer and inter-layer correlations. Our observations confirm that in a wide range of real-world multiplex networks, from social to biological and technological, a positive correlation exists between connection probability in one layer and similarity in other layers. Accordingly, a similarity-based automatic general-purpose multiplex link prediction method—SimBins—is devised that quantifies the amount of connection uncertainty based on observed inter-layer correlations in a multiplex network. Moreover, SimBins enhances the prediction quality in the target layer by incorporating the effect of link overlap across layers. Applying SimBins to various datasets from diverse domains, our findings indicate that SimBins outperforms the compared methods (both baseline and state-of-the-art methods) in most instances when predicting links. Furthermore, it is discussed that SimBins imposes minor computational overhead to the base similarity measures making it a potentially fast method, suitable for large-scale multiplex networks.

Download Full-text

Towards an accurate description of perovskite ferroelectrics: exchange and correlation effects

Scientific Reports ◽

10.1038/srep43482 ◽

2017 ◽

Vol 7 (1) ◽

Cited By ~ 21

Author(s):

Simuck F. Yuk ◽

Krishna Chaitanya Pitike ◽

Serge M. Nakhmanson ◽

Markus Eisenbach ◽

Ying Wai Li ◽

...

Keyword(s):

Density Functional ◽

General Purpose ◽

Correlation Effects ◽

Lattice Constants ◽

Bulk Solids ◽

Wide Range ◽

Exchange Enhancement ◽

Experimental Values ◽

Similar Accuracy ◽

Ferroelectric Oxides

Abstract Using the van der Waals density functional with C09 exchange (vdW-DF-C09), which has been applied to describing a wide range of dispersion-bound systems, we explore the physical properties of prototypical ABO 3 bulk ferroelectric oxides. Surprisingly, vdW-DF-C09 provides a superior description of experimental values for lattice constants, polarization and bulk moduli, exhibiting similar accuracy to the modified Perdew-Burke-Erzenhoff functional which was designed specifically for bulk solids (PBEsol). The relative performance of vdW-DF-C09 is strongly linked to the form of the exchange enhancement factor which, like PBEsol, tends to behave like the gradient expansion approximation for small reduced gradients. These results suggest the general-purpose nature of the class of vdW-DF functionals, with particular consequences for predicting material functionality across dense and sparse matter regimes.

Download Full-text

SYSTEMC IMPLEMENTATION AND PERFORMANCE EVALUATION OF A DECOUPLED GENERAL-PURPOSE MATRIX PROCESSOR

Parallel Processing Letters ◽

10.1142/s0129626410000090 ◽

2010 ◽

Vol 20 (02) ◽

pp. 103-121 ◽

Cited By ~ 1

Author(s):

MOSTAFA I. SOLIMAN ◽

ABDULMAJID F. Al-JUNAID

Keyword(s):

Performance Evaluation ◽

Matrix Multiplication ◽

General Purpose ◽

System Level ◽

Memory Latency ◽

Single Chip ◽

Wide Range ◽

Matrix Unit ◽

And Performance ◽

Vector Matrix

Technological advances in IC manufacturing provide us with the capability to integrate more and more functionality into a single chip. Today's modern processors have nearly one billion transistors on a single chip. With the increasing complexity of today's system, the designs have to be modeled at a high-level of abstraction before partitioning into hardware and software components for final implementation. This paper explains in detail the implementation and performance evaluation of a matrix processor called Mat-Core with SystemC (system level modeling language). Mat-Core is a research processor aiming at exploiting the increasingly number of transistors per IC to improve the performance of a wide range of applications. It extends a general-purpose scalar processor with a matrix unit. To hide memory latency, the extended matrix unit is decoupled into two components: address generation and data computation, which communicate through data queues. Like vector architectures, the data computation unit is organized in parallel lanes. However, on parallel lanes, Mat-Core can execute matrix-scalar, matrix-vector, and matrix-matrix instructions in addition to vector-scalar and vector-vector instructions. For controlling the execution of vector/matrix instructions on the matrix core, this paper extends the well known scoreboard technique. Furthermore, the performance of Mat-Core is evaluated on vector and matrix kernels. Our results show that the performance of four lanes Mat-Core with matrix registers of size 4 × 4 or 16 elements each, queues size of 10, start up time of 6 clock cycles, and memory latency of 10 clock cycles is about 0.94, 1.3, 2.3, 1.6, 2.3, and 5.5 FLOPs per clock cycle; achieved on scalar-vector multiplication, SAXPY, Givens, rank-1 update, vector-matrix multiplication, and matrix-matrix multiplication, respectively.

Download Full-text

Evaluation of Composted Sewage Sludge/Straw Mixture for Horticultural Utilization

Water Science & Technology ◽

10.2166/wst.1989.0291 ◽

1989 ◽

Vol 21 (8-9) ◽

pp. 889-897 ◽

Cited By ~ 6

Author(s):

J. M. Lopez-Real ◽

E. Witter ◽

F. N. Midmer ◽

B. A. O. Hewett

Keyword(s):

Collaborative Research ◽

Slow Release ◽

General Purpose ◽

Exchange Capacity ◽

Soluble Salts ◽

Slow Release Fertilizer ◽

Wide Range ◽

Sludge Cake ◽

Bulk Volume ◽

Composted Sewage Sludge

Collaborative research between Southern Water and Wye College, University of London, has led to the development of a static aerated pile composting process for the treatment of dewatered activated sludge cake/straw mixtures. The process reduces bulk volume of the sludge producing an environmentally acceptable, stabilised, odour and pathogen-free product. Characteristics of the compost make it a suitable general purpose medium for container grown plants, providing the salt concentration is reduced by washing the compost prior to planting. Compared with peat the compost has a higher bulk density, a lower waterholding capacity, a lower cation exchange capacity, a high content of soluble salts, and a higher content of plant nutrients. A compost mixture was successfully developed in the growing trials containing equal quantities of compost, Sphagnum peat, and horticultural vermiculite. The compost has been used successfully to grow a wide range of plants. Plants grown in mixtures based on the compost were in general similar to those grown in peat-based growing media. The compost is a valuable soil conditioner and slow release fertilizer.

Download Full-text

Familiarity of Iranian M.A. Translation Students with ICT Tools

International Journal of Linguistics and Translation Studies ◽

10.36892/ijlts.v2i1.118 ◽

2021 ◽

Vol 2 (1) ◽

pp. 17-26

Author(s):

Hamidreza Abdi

Keyword(s):

Information Search ◽

Search Engines ◽

Instant Messaging ◽

General Purpose ◽

Internet Search ◽

Chi Square ◽

Software Application ◽

Wide Range ◽

Chi Square Test ◽

Ict Tools

Familiarity with information and communication technology (ICT) is of great importance to the translation students because it allows the students to make use of a wide range of ICT tools. The present study investigated the degree of students’ familiarity with ICT tools employed to support ICT related activities included in the translator’s workstation. To do this, a questionnaire encompassing 24 questions was designed on the basis of translation activities proposed by Fulford and Granell-Zafar (2005), including information search and retrieval, communications, and marketing and work procurement. The results indicated the high familiarity of the M.A. translation students with general-purpose software application, namely online dictionaries and internet search engines, and the lower than the average familiarity of them with specific-purpose software, such as FTP and MUDs. Furthermore, chi-square test (X²) was run to see whether there is a significant relationship between each type of ICT tools and the participants. The results illustrated that the relationships between the M.A. translation students and some ICT applications, including internet search engines, web browsers, online dictionaries and encyclopedia, IRC, and MUDs, were significant; whereas, it was not significant between the other types of ICT software and students. This includes online translation marketplaces, internet forums, email, instant messaging, video chat, discussion mailing lists, talkers, and FTP.

Download Full-text

Multi-Softcore Architecture on FPGA

International Journal of Reconfigurable Computing ◽

10.1155/2014/979327 ◽

2014 ◽

Vol 2014 ◽

pp. 1-13 ◽

Cited By ~ 4

Author(s):

Mouna Baklouti ◽

Mohamed Abid

Keyword(s):

High Performance ◽

Design Methodology ◽

Matrix Multiplication ◽

Rapid Prototype ◽

General Purpose ◽

Parallel Applications ◽

Multicore Systems ◽

Processor Core ◽

Nios Ii ◽

Wide Range

To meet the high performance demands of embedded multimedia applications, embedded systems are integrating multiple processing units. However, they are mostly based on custom-logic design methodology. Designing parallel multicore systems using available standards intellectual properties yet maintaining high performance is also a challenging issue. Softcore processors and field programmable gate arrays (FPGAs) are a cheap and fast option to develop and test such systems. This paper describes a FPGA-based design methodology to implement a rapid prototype of parametric multicore systems. A study of the viability of making the SoC using the NIOS II soft-processor core from Altera is also presented. The NIOS II features a general-purpose RISC CPU architecture designed to address a wide range of applications. The performance of the implemented architecture is discussed, and also some parallel applications are used for testing speedup and efficiency of the system. Experimental results demonstrate the performance of the proposed multicore system, which achieves better speedup than the GPU (29.5% faster for the FIR filter and 23.6% faster for the matrix-matrix multiplication).

Download Full-text

SHEMAT-Suite: a parallel open source simulator for flow, heat and mass transport in porous media

10.5194/egusphere-egu21-15084 ◽

2021 ◽

Author(s):

Johannes Keller ◽

Johanna Fink ◽

Norbert Klitzsch

Keyword(s):

Porous Media ◽

Mass Transport ◽

Open Source ◽

Source Code ◽

Modular Structure ◽

Numerical Code ◽

Heat And Mass Transport ◽

Transport In Porous Media ◽

Wide Range ◽

Flow Heat

We present SHEMAT-Suite, a numerical code for simulating flow, heat, and mass transport in porous media that has been published as an open source code recently. The functionality of SHEMAT-Suite comprises pure forward computation, deterministic Bayesian inversion, and stochastic Monte Carlo simulation and data assimilation. Additionally, SHEMAT-Suite features a multi-level OpenMP parallelization. Along with the source code of the software, extensive documentation and a suite of test models is provided.SHEMAT-Suite has a modular structure that makes it easy for users to adapt the code to their needs. Most importantly, there is an interface for defining the functional relationship between dynamic variables and subsurface parameters. Additionally, user-defined input and output can be implemented without interfering with the core of the code. Finally, at a deeper level, linear solvers and preconditioners can be added to the code.We present studies that have made use of the code's HPC capabilities. SHEMAT-Suite has been applied to large-scale groundwater models for a wide range of purposes, including studying the formation of convection cells, assessing geothermal potential below an office building, or modeling submarine groundwater discharge since the last ice age. The modular structure of SHEMAT-Suite has also led to diverse applications, such as glacier modeling, simulation of borehole heat exchangers, or Optimal Experimental Design applied to the placing of geothermal boreholes.Further, we present ongoing developments for improving the performance of SHEMAT-Suite, both by refactoring the source code and by interfacing SHEMAT-Suite with up-to-date HPC software. Examples of this include interfacing SHEMAT-Suite with the Portable Data Interface (PDI) for improved data management, interfacing SHEMAT-Suite with PetSC for MPI-parallel solvers, and interfacing SHEMAT-Suite with PDAF for parallel EnKF algorithms.The goal for the open source SHEMAT-Suite is to provide a rigorously tested core code for flow, heat and transport simulation, Bayesian and stochastic inversion, while at the same time enabling a wide range of scientific research through straightforward user interaction.

Download Full-text

Development of innovative monitoring technologies in the framework of InnovaMare Project

10.5194/egusphere-egu21-10131 ◽

2021 ◽

Author(s):

Angelo Odetti ◽

Federica Braga ◽

Fabio Brunetti ◽

Massimo Caccia ◽

Simone Marini ◽

...

Keyword(s):

Environmental Monitoring ◽

Shallow Water ◽

Adriatic Sea ◽

Temporal Dynamics ◽

Supervised Machine Learning ◽

Detection Techniques ◽

Cross Border ◽

Wide Range ◽

Air Cushion ◽

The Cross

The IT-HR InnovaMare project, led by the Croatian Chamber of Economy, puts together policy instruments and key players for development of innovative technologies for the sustainable development of the Adriatic Sea (https://www.italy-croatia.eu/web/innovamare). The project aims at enhancing the cross-border cooperation among research, public and private stakeholders through creation of a Digital Innovation Hub (DIH). The goal is to increase effectiveness of innovation in underwater robotics and sensors to achieve and maintain a healthy and productive Adriatic Sea, as one of the crucial and strategic societal challenges existing at the cross-border level. Within InnovaMare, CNR ISMAR and INM institutes and OGS, in cooperation with the University of Zagreb and other project partners, contribute to developing a solution to access and monitor extremely shallow water by means of portable, modular, reconfigurable and highly maneuverable robotic vehicles. The identified vehicle is SWAMP, an innovative highly modular catamaran ASV recently developed by CNR-INM. SWAMP is characterised by small size, low draft, new materials, azimuth propulsion system for shallow waters and modular WiFi-based hardware&software architecture. Two SWAMP vehicles will be enhanced with a series of kits, tools and sensors to perform a series of strategic actions in the environmental monitoring of the Venice Lagoon: i) An air-cushion-system-kit will be designed and developed. The vehicle will become a side-wall air-cushion-vehicle with reduction of drag and increase in speed. This will also increase the payload with a reduction of draft. ii) An intelligent winch kit with a communication cable for the management of underwater sensors and tools. iii) A GPS-RTK kit for highly accurate positioning in the range of centimeters. iv) An Autonomous programmable device for image acquisition and processing based on the Guard1 camera. This camera acquires images content and, by means of a supervised machine learning approach, recognises/classifies features such as fish, zooplankton, seabed, infrastructures. The system is conceived for autonomous monitoring activities extended in time in fixed or mobile platforms. v) A Multibeam Echo-sounder (MBES) coupled with an IMU (for pitch-roll compensation). MBES data can be used, also coupled with Cameras Imagery, through image-detection techniques for reconstruction and comprehensive knowledge of underwater environment and infrastructures. Possible analyses in coastal areas are: seabed mapping also for cultural heritage, offshore structures and resources and monitoring of biodiversity, hydrocarbon, marine litter, pollution. vi) An underwater Radiometer for multiple analysis: temporal dynamics of optical properties of water; temporal dynamics of water turbidity from water reflectance; submerged vegetation and water depth mapping in optically shallow water; produce reference data for validation of satellite data. vii) Automatic Nutrient Analyzer for real-time nutrient monitoring. This sensor measures nitrate with high accuracy over a wide range of environmental conditions (including extremely turbid and high CDOM conditions), from blue-ocean nitraclines to storm runoff in rivers and streams.&#160; The final result of this pilot action is the creation of an innovative prototype platform for sea environmental monitoring. This will be validated through the analysis of results and draw up of guidelines for the improvement of underwater conditions.

Download Full-text