Execution Time Efficiency Research Articles

Performance Comparison of Bio-Inspired Algorithms for Optimizing an ANN-Based MPPT Forecast for PV Systems.

This study compares bio-inspired optimization algorithms for enhancing an ANN-based Maximum Power Point Tracking (MPPT) forecast system under partial shading conditions in photovoltaic systems. Four algorithms-grey wolf optimizer (GWO), particle swarm optimization (PSO), squirrel search algorithm (SSA), and cuckoo search (CS)-were evaluated, with the dataset augmented by perturbations to simulate shading. The standard ANN performed poorly, with 64 neurons in Layer 1 and 32 in Layer 2 (MSE of 159.9437, MAE of 8.0781). Among the optimized approaches, GWO, with 66 neurons in Layer 1 and 100 in Layer 2, achieved the best prediction accuracy (MSE of 11.9487, MAE of 2.4552) and was computationally efficient (execution time of 1198.99 s). PSO, using 98 neurons in Layer 1 and 100 in Layer 2, minimized MAE (2.1679) but had a slightly longer execution time (1417.80 s). SSA, with the same neuron count as GWO, also performed well (MSE 12.1500, MAE 2.7003) and was the fastest (987.45 s). CS, with 84 neurons in Layer 1 and 74 in Layer 2, was less reliable (MSE 33.7767, MAE 3.8547) and slower (1904.01 s). GWO proved to be the best overall, balancing accuracy and speed. Future real-world applications of this methodology include improving energy efficiency in solar farms under variable weather conditions and optimizing the performance of residential solar panels to reduce energy costs. Further optimization developments could address more complex and larger-scale datasets in real-time, such as integrating renewable energy sources into smart grid systems for better energy distribution.

Virtualized network functions resource allocation in network functions virtualization using mathematical programming

Network Functions Virtualization (NFV) revolutionizes network services by eliminating the need for dedicated hardware. This virtualization enables flexible and efficient deployment of various network functions like proxies, firewalls, and load balancers. Providing the service requested by the user in the network is done by a sequence of virtual network functions, which are known as service functions chain. One of the main challenges in the development of network functions virtualization architecture is the allocation of resources to the requested network services in network infrastructures, this challenge is called network function virtualization resource allocation problem. Therefore, this paper addresses the resource allocation problem in Network Functions Virtualization (NFV) architectures using mathematical programming techniques. A multi-objective mixed-integer linear programming (MILP) model is proposed to optimize resource allocation for virtual network functions (VNFs). The model incorporates constraints related to node and link resource capacities, as well as delay requirements. The objective functions focus on maximizing network throughput, minimizing node resource costs (CPU cores and memory), reducing capital and operational expenses, and ensuring efficient execution time. These constraints and objective functions are formally defined by mathematical functions. The proposed mathematical model is implemented and solved using the Cplex solver. To evaluate the effectiveness of the proposed mathematical model, various network topologies were evaluated under different parameters. These parameters included the length of Service Function Chains (SFCs), the number and length of flows, node resource capacities, the number of nodes and VNFs. The experimental results demonstrated the model’s ability to efficiently allocate resources to VNFs across these different scenarios.

An efficient key tag missing identification protocol for multiple regions in the Industrial Internet of Things

Radio Frequency Identification (RFID) is a special wireless network technology that uses radio frequency communication to achieve non-contact automatic identification through tags affixed to items. As one of the core technologies for physical layer communication in the Industrial Internet of Things(IIoT), RFID technology has been widely used in inventory management, supply chain management, access control identification, and many other areas. In practical application scenarios, the value and importance of some special tags far exceeds that of other tags. Therefore, in many cases, managers only need to pay attention to the status of these special tags, i.e., key tags, and not the status of all tags. However, the response of ordinary tags to reader commands will seriously interfere with identifying key missing tags. Therefore, we propose a novel protocol, Random Grouped Missing Key Tag Identification (RGKMTI), designed for multi-region key tag identification. RGKMTI employs a region-based sequential tag identification method to identify each group of tags individually, which effectively reduces collision slots and utilizes the duality property of slots containing only two key tags during the missing key tag verification phase, where the reader can verify two tags by transmitting at most a single tag ID, which significantly reduces the transmission load and shortens the total execution time. The experimental results show that the RGKMTI is significantly better than the existing schemes in terms of execution time and time efficiency, even though it reduces the identification time by 19.83% and improves the time efficiency by 6.82% compared with the best existing schemes.

A New Optimized Hybridization Approach for in silico High Throughput Molecular Docking on FPGA Platform.

The development process of a new drug should be a subject of continuous evolution and rapid improvement as drugs are essential to treat a wide range of diseases of which many are life-threatening. The advances in technology resulted in a novel track in drug discovery and development known as in silico drug design. The molecular docking phase plays a vital role in in silico drug development process. In this phase, thousands of 3D conformations of both the ligand and receptor are generated and the best conformations that create the most stable drug-receptor complex are determined. The speed in finding accurate and high-quality complexes depends on the efficiency of the search function in the molecular docking procedure. The objective of this research is to propose and implement a novel hybrid approach called hABCDE to replace the EMC searching part inside the BUDE docking algorithm. This helps in reaching the best solution in a much accelerated time and higher solution quality compared to using the ABC and DE algorithms separately. In this work, we have employed a new approach of hybridization between the Artificial Bee Colony (ABC) algorithm and the Differential Evolution (DE) algorithm as an alternative searching part of the Bristol University Docking Engine (BUDE) in order to accelerate the search for higher quality solutions. Moreover, the proposed docking approach was implemented on Field Programmable Gate Array (FPGA) parallel platform using Vivado High-Level Synthesis Tool (HLST) in order to optimize and enhance the execution time and overall efficiency. The NDM-1 protein was used as a model receptor in our experiments to demonstrate the efficiency of our approach. The NDM-1 protein was used as a model receptor in our experiments to demonstrate the efficiency of our approach. The results showed that the execution time for the BUDE with the new proposed hybridization approach was improved by 9,236 times. Our novel approach was significantly effective to improve the functionality of docking algorithms (Bristol University Docking Engine (BUDE)).

Enhancing data privacy in wireless sensor network using homomorphic encryption

From environmental monitoring to healthcare, WSN are essential. The extensive use of these networks to gather sensitive data requires strong data privacy mechanisms. Cryptographic homomorphic encryption may solve this problem. This study uses CKKS encryption and ciphertext packing to improve Wireless Sensor Network data privacy. CKKS is a fully homomorphic encryption scheme that allows complex data operations. This makes it ideal for data analytics and computations. Ciphertext packing improves computational efficiency, making this combination a good choice for data protection in WSN environments with limited resources. Performance efficiency is crucial to evaluation. This parameter evaluates CKKS encryption with ciphertext packing’s computational resource and execution time efficiency. This study examines how this approach affects WSN node and network performance, revealing its feasibility and practicality in real-world situations. The Data Security parameter highlights CKKS encryption with ciphertext packing’s data security. This comprehensive assessment determines data confidentiality and integrity in the Wireless Sensor Network. The system’s ability to withstand data breaches and unauthorized access is crucial for protecting sensitive data. Any WSN solution must consider energy consumption. This parameter evaluates data encryption and processing energy usage, taking sensor node energy constraints into account. The assessment of CKKS encryption with ciphertext packing in WSN sheds light on its potential to improve data confidentiality while addressing WSN challenges. This research strengthens WSN data protection efforts and lays the groundwork for future advances in this vital field.

Enhancing architectural image processing: A novel 2D to 3D algorithm using improved convolutional neural networks

In light of the escalating advancements in architectural intelligence and information technology, the construction of smart cities increasingly necessitates a higher degree of precision in architectural measurements. Conventional approaches to architectural measurement, characterized by their low efficiency and protracted execution time, need to be revised to meet these burgeoning demands. To address this gap, we introduce a novel architectural image processing model that synergistically integrates Restricted Boltzmann Machines (RBMs) with Convolutional Neural Networks (CNNs) to facilitate the conversion of 2D architectural images into 3D. In the implementation phase of the model, an initial preprocessing of the architectural images is performed, followed by depth map conversion via bilateral filtering. Subsequently, minor voids in the images are rectified through a neighborhood interpolation algorithm. Finally, the preprocessed 2D images are input into the integrated model of RBMs and CNNs, realizing the 2D to 3D conversion. Experimental outcomes substantiate that this novel model attains a precision rate of 97%, and significantly outperforms comparative algorithms in terms of both runtime and efficiency. These results compellingly corroborate our model?s superiority in architectural image processing, enhancing measurement accuracy and drastically reducing execution time.

Optimizing Loop Tiling in Computing Systems through Ensemble Machine Learning Techniques

This work investigates the use of ensemble machine-learning algorithms to optimize loop-tiling in computing systems, with the goal of improving performance by predicting optimal tile sizes. It compares two approaches: independent training and averaging (soft voting) and an ensemble technique (hard voting) that employs models such as linear regression, ridge regression, and random forests. Experiments on an Intel Core i7-8565U CPU with several benchmark programs revealed that the hard voting Ensemble Approach beat the soft voting technique, providing more dependable and accurate predictions across a range of computing environments. The hard voting technique reduced execution time by around 87.5% for dynamic features and 89.89% for static features, whereas the soft voting approach showed an average drop of 75.45% for dynamic features and 78.13% for static characteristics. This work demonstrates the effectiveness of hard voting ensemble machine learning approaches in improving cache efficiency and total execution time, opening the way for future advances in high-performance computing settings.

Anomaly Detection Using an Ensemble of Multi-Point LSTMs.

As technologies for storing time-series data such as smartwatches and smart factories become common, we are collectively accumulating a great deal of time-series data. With the accumulation of time-series data, the importance of time-series abnormality detection technology that detects abnormal patterns such as Cyber-Intrusion Detection, Fraud Detection, Social Networks Anomaly Detection, and Industrial Anomaly Detection is emerging. In the past, time-series anomaly detection algorithms have mainly focused on processing univariate data. However, with the development of technology, time-series data has become complicated, and corresponding deep learning-based time-series anomaly detection technology has been actively developed. Currently, most industries rely on deep learning algorithms to detect time-series anomalies. In this paper, we propose an anomaly detection algorithm with an ensemble of multi-point LSTMs that can be used in three cases of time-series domains. We propose our anomaly detection model that uses three steps. The first step is a model selection step, in which a model is learned within a user-specified range, and among them, models that are most suitable are automatically selected. In the next step, a collected output vector from M LSTMs is completed by stacking ensemble techniques of the previously selected models. In the final step, anomalies are finally detected using the output vector of the second step. We conducted experiments comparing the performance of the proposed model with other state-of-the-art time-series detection deep learning models using three real-world datasets. Our method shows excellent accuracy, efficient execution time, and a good F1 score for the three datasets, though training the LSTM ensemble naturally requires more time.

Neural Network Mapping of Industrial Robots’ Task Times for Real-Time Process Optimization

The ability to predict the maximal performance of an industrial robot executing non-deterministic tasks can improve process productivity through time-based planning and scheduling strategies. These strategies require the configuration and the comparison of a large number of tasks in real time for making a decision; therefore, an efficient task execution time estimation method is required. In this work, we propose the use of neural network models to approximate the task time function of a generic multi-DOF robot; the models are trained using data obtained from sophisticated motion planning algorithms that optimize the shape of the trajectory and the executed motion law, taking into account the kinematic and dynamic model of the robot. For scheduling purposes, we propose to evaluate only the neural network models, thus confining the online use of the motion planning software to the full definition of the actually scheduled task. The proposed neural network model presents a uniform interface and an implementation procedure that is easily adaptable to generic robots and tasks. The paper’s results show that the models are accurate and more efficient than the full planning pipeline, having evaluation times compatible with real-time process optimization.

Binary search of the optimal cut-point value in ROC analysis using the F1 score

This paper introduces a binary search algorithm for determining the optimal probability cut-point value (C) of binary classifiers. Cut-points are operating points on the receiver operating characteristic curve that divide positive and negative predictions. Compared to the traditional exhaustive search for optimal C value, the proposed method offers execution time efficiency (O(log2(k))) and a small cut-point error of 1/2 n after k steps of binary search. Traditionally, the optimal C value is determined by stepping through all possible C values. This search is uninformed because there is no indication of the search direction. To address this issue, we derive the expectation of the F-Measure (aka F1 score); and use it to guide the search process. Specifically, by comparing the F-Measure at the current cut-point with the F-Measure at expected cut-point, we can use the information to adjust C dynamically towards the optimal cut-point, resulting in optimal model performance. Our results on two classifiers trained from disease classification datasets suggest that the algorithm is robust and efficient, as compared to the traditional methods.

Hybrid COOT-Reverse Cognitive Fruit Fly Optimization-Based Big Data Services and Virtual Machine Allocation for Cloud Storage System

In recent years, cloud computing technologies have been developed rapidly in this computing world to provide suitable on-demand network access all over the world. A cloud service provider offers numerous types of cloud services to the user. But the most significant issue is how to attain optimal virtual machine (VM) allocation for the user and design an efficient big data storage platform thereby satisfying the requirement of both the cloud service provider and the user. Therefore, this paper presents two novel strategies for optimizing VM resource allocation and cloud storage. An optimized cloud cluster storage service is introduced in this paper using a binarization based on modified fuzzy c-means clustering (BMFCM) algorithm to overcome the negative issues caused by the repetitive nature of the big data traffic. The BMFCM algorithm utilized can be implemented transparently and can also address problems associated with massive data storage. The VM selection is optimized in the proposed work using a hybrid COOT-reverse cognitive fruit fly (RCFF) optimization algorithm. The main aim of this algorithm is to improve the massive big data traffic and storage locality. The CPU utilization, VM power, memory dimension and network bandwidth are taken as the fitness function of the hybrid COOT-RCFF algorithm. When implemented in CloudSim and Hadoop, the proposed methodology offers improvements in terms of completion time, overall energy consumption, makespan, user provider satisfaction and load ratio. The results show that the proposed methodology improves the execution time and data retrieval efficiency by up to 32% and 6.3% more than the existing techniques.

An investigation of performance and power efficiency for parallax background scrolling hardware written in high-level synthesis

We are developing a game programming software library so that high-level synthesis, HLS, can automatically generate high-performance and low-power hardware modules. A mobile terminal with a user-available reconfigurable device like Field programmable gate array, FPGA, we have proposed will efficiently perform game application built in HLS-oriented game library instead of power-hungry software execution. The dynamic hardware reconfiguration on a single FPGA can execute many kinds of game applications. Our previous research has developed software description methods for two-background scrolling in HLS-oriented game programming library by using two methods. They are (1) Full-parallel equips plural physical ports loading background images individually making HLS hardware execute the entire process parallelly increasing the amount of hardware: (2) Semi-parallel shares the single port loading background images serially, suppressing the hardware growth while achieving moderate performance by overlapping operation phases. We investigate two methods about execution time and power efficiency on the parallax scrolling with 2 to 4 backgrounds. The execution times of full-parallel hardware at 100MHz clock frequency are constantly about 9.65 [ms] while those of semi-parallel are 28, 38 and 47 [ms]. The PC at 3.2 GHz shows 78, 98 and 105 [ms] respectively as well. The power efficiencies about the full-parallel estimated considering hardware enlargement are 167, 208 and 112 times compared to the software execution in the PC, while those of semi-parallel are 94, 88 and 75 times. This fact indicates that the full-parallel is better strategy for parallax background scrolling in this case although more hardware resource are invested.

Guiding the optimization of membraneless microfluidic fuel cells via explainable artificial intelligence: Comparative analyses of multiple machine learning models and investigation of key operating parameters

Membraneless microfluidic fuel cells (MMFCs) offer great potential for clean energy production, but their expense and tedious optimization process have limited their wider use. Machine learning (ML) algorithms have shown promise in improving the optimization of MMFCs, but the “black box” nature of these models has caused uncertainty and limited their adoption. To address this, we conducted the first study that implements the explainable artificial intelligence (XAI) approach to gain in-depth insights into multiple ML optimization models' predictions and the impacts of operating parameters on MMFCs' performance. Among 27 investigated models that are generated based on nine ML and three bio-inspired evolutionary algorithms, the combination of a decision tree and the particle swarm optimization algorithm is the most effective model that satisfied all criteria of high time efficiency (execution time = 3.194 s), accuracy (squared correlation coefficient = 0.999), and optimum power density identification (0.278 mWcm−2). The ML-optimized power density is 239.024% increased, which is 3.4 times higher than the average power density obtained without optimization. We further utilized the XAI model to comprehensively examine the impacts of operating parameters, providing valuable decision aids for the researchers, technicians, and engineers in manufacturing optimal power MMFCs at a significantly lower cost and faster rate.

Curriculum Learning for Goal-Oriented Semantic Communications With a Common Language

Goal-oriented semantic communication will be a pillar of next-generation wireless networks. Despite significant recent efforts in this area, most prior works are focused on specific data types (e.g., image or audio), and they ignore the goal and effectiveness aspects of semantic transmissions. In contrast, in this paper, a holistic goal-oriented semantic communication framework is proposed to enable a speaker and a listener to cooperatively execute a set of sequential tasks in a dynamic environment. A common language based on a hierarchical belief set is proposed to enable semantic communications between speaker and listener. The speaker, acting as an observer of the environment, utilizes the beliefs to transmit an initial description of its observation (called event) to the listener. The listener is then able to infer on the transmitted description and complete it by adding related beliefs to the transmitted beliefs of the speaker. As such, the listener reconstructs the observed event based on the completed description, and it then takes appropriate action in the environment based on the reconstructed event. An optimization problem is defined to determine the perfect and abstract description of the events while minimizing the various communication costs with constraints on the task execution time and belief efficiency. Then, a novel bottom-up curriculum learning (CL) framework based on reinforcement learning is proposed to solve the optimization problem and enable the speaker and listener to gradually identify the structure of the belief set and the perfect and abstract description of the events. Simulation results show that the proposed CL method outperforms classical RL and CL without inference scheme in terms of convergence time, task execution cost and time, reliability, and belief efficiency.

A security services for internet of thing smart health care solutions based blockchain technology

Pervasive and ubiquitous computing has enabled people better integrate physical things into the digital world. The internet of things (IoT) has been considerably more widely used in business and everyday life in the last decade. Innovative healthcare information and communication technologies are a vast field of research and applications that need IoT benefits, including speed, security, and low cost. The proposed modified advanced encryption standard (AES)-cipher block chaining (CBC)-based blockchain technology offers a shared key to devices that need to communicate directly with or with entities outside the smart healthcare network to give users greater control over transactions. The experiments are carried out using a Raspberry Pi 3, whereas two different sensors are ‎employed in this case. Blockchain technology encrypts data between doctor and patient with varied user numbers. The results from experiments revealed that the proposed modified AES-CBC based blockchain technology could provide the IoT application with security services (confidentiality, integrity, and access control) with efficient execution time.

Attention-Gate-Based Model with Inception-like Block for Single-Image Dehazing

In recent decades, haze has become an environmental issue due to its effects on human health. It also reduces visibility and degrades the performance of computer vision algorithms in autonomous driving applications, which may jeopardize car driving safety. Therefore, it is extremely important to instantly remove the haze effect on an image. The purpose of this study is to leverage useful modules to achieve a lightweight and real-time image-dehazing model. Based on the U-Net architecture, this study integrates four modules, including an image pre-processing block, inception-like blocks, spatial pyramid pooling blocks, and attention gates. The original attention gate was revised to fit the field of image dehazing and consider different color spaces to retain the advantages of each color space. Furthermore, using an ablation study and a quantitative evaluation, the advantages of using these modules were illustrated. Through existing indoor and outdoor test datasets, the proposed method shows outstanding dehazing quality and an efficient execution time compared to other state-of-the-art methods. This study demonstrates that the proposed model can improve dehazing quality, keep the model lightweight, and obtain pleasing dehazing results. A comparison to existing methods using the RESIDE SOTS dataset revealed that the proposed model improves the SSIM and PSNR metrics by at least 5–10%.

A comparative analysis of matrix reordering algorithms regarding canonical data patterns

Matrix reordering is an Information Visualization topic that aims to study how to reveal information hidden within matrix-based visualizations, through appropriate reordering of its rows and columns. Considering the plethora of algorithms currently available to perform this task, and the set of matrix patterns presented in the visualization literature, we noted a lack of a comprehensive comparative analysis related to a subset of these patterns, known as canonical data patterns. Thus, this work aimed to perform a broad comparison of 37 state-of-the-art reordering algorithms by measuring the efficiency (execution time) and effectiveness (which combines objective functions as Moore Neighborhood, Minimal Span Loss Function and Circular Correlation, and a qualitative approach by visually assessing the output matrices) of the algorithms. We used as input a large synthetic matrix data set with different canonical data patterns. As a result, it was possible to indicate the most appropriate reordering algorithms for each pattern considered.

Energy-Efficient Robot Configuration and Motion Planning Using Genetic Algorithm and Particle Swarm Optimization

The implementation of Industry 5.0 necessitates a decrease in the energy consumption of industrial robots. This research investigates energy optimization for optimal motion planning for a dual-arm industrial robot. The objective function for the energy minimization problem is stated based on the execution time and total energy consumption of the robot arm configurations in its workspace for pick-and-place operation. Firstly, the PID controller is being used to achieve the optimal parameters. The parameters of PID are then fine-tuned using metaheuristic algorithms such as Genetic Algorithms and Particle Swarm Optimization methods to create a more precise robot motion trajectory, resulting in an energy-efficient robot configuration. The results for different robot configurations were compared with both motion planning algorithms, which shows better compatibility in terms of both execution time and energy efficiency. The feasibility of the algorithms is demonstrated by conducting experiments on a dual-arm robot, named as duAro. In terms of energy efficiency, the results show that dual-arm motions can save more energy than single-arm motions for an industrial robot. Furthermore, combining the robot configuration problem with metaheuristic approaches saves energy consumption and robot execution time when compared to motion planning with PID controllers alone.

An Effective Conversion of Visemes to Words for High-Performance Automatic Lipreading.

As an alternative approach, viseme-based lipreading systems have demonstrated promising performance results in decoding videos of people uttering entire sentences. However, the overall performance of such systems has been significantly affected by the efficiency of the conversion of visemes to words during the lipreading process. As shown in the literature, the issue has become a bottleneck of such systems where the system’s performance can decrease dramatically from a high classification accuracy of visemes (e.g., over 90%) to a comparatively very low classification accuracy of words (e.g., only just over 60%). The underlying cause of this phenomenon is that roughly half of the words in the English language are homophemes, i.e., a set of visemes can map to multiple words, e.g., “time” and “some”. In this paper, aiming to tackle this issue, a deep learning network model with an Attention based Gated Recurrent Unit is proposed for efficient viseme-to-word conversion and compared against three other approaches. The proposed approach features strong robustness, high efficiency, and short execution time. The approach has been verified with analysis and practical experiments of predicting sentences from benchmark LRS2 and LRS3 datasets. The main contributions of the paper are as follows: (1) A model is developed, which is effective in converting visemes to words, discriminating between homopheme words, and is robust to incorrectly classified visemes; (2) the model proposed uses a few parameters and, therefore, little overhead and time are required to train and execute; and (3) an improved performance in predicting spoken sentences from the LRS2 dataset with an attained word accuracy rate of 79.6%—an improvement of 15.0% compared with the state-of-the-art approaches.

A* Based Routing and Scheduling Modules for Multiple AGVs in an Industrial Scenario

A multi-AGV based logistic system is typically associated with two fundamental problems, critical for its overall performance: the AGV’s route planning for collision and deadlock avoidance; and the task scheduling to determine which vehicle should transport which load. Several heuristic functions can be used according to the application. This paper proposes a time-based algorithm to dynamically control a fleet of Autonomous Guided Vehicles (AGVs) in an automatic warehouse scenario. Our approach includes a routing algorithm based on the A* heuristic search (TEA*—Time Enhanced A*) to generate free-collisions paths and a scheduling module to improve the results of the routing algorithm. These modules work cooperatively to provide an efficient task execution time considering as basis the routing algorithm information. Simulation experiments are presented using a typical industrial layout for 10 and 20 AGVs. Moreover, a comparison with an alternative approach from the state-of-the-art is also presented.