Optimal Processing Time Research Articles

Parameters Tailoring on the Deposition of Hydroxyapatite by Pulsed Electrical Discharge.

The creation of strong adhesive layers of hydroxyapatite-based bioceramics (with or without bioinert metals, such as Ta, Ag, and Ti) on biocompatible metallic supports enhances the local biofunctionalization of surfaces. The processing of electroconductive materials using electrical impulse discharges is versatile, enabling precise coating of selected areas with perfectly adherent layers of varying thicknesses. This study aims to quantify the effects of varying the electrical power from the source generating the impulse discharge and the specific processing time per unit area of the cathode (made of titanium alloy) on the relative mass increase of the cathode. The anode comprised a mixture of hydroxyapatite powder and a self-polymerizing electroconductive acrylic resin in a tantalum sheath. The effects of the parameter adjustments on single-layer deposition adherence were quantified using a central composite design to build a second-order orthogonal model. The most significant difference in relative mass was observed with a low-power source (5 W) ensuring the electrical discharge impulse, combined with the longest specified surface treatment time (17.5 s/cm2 on a 4 cm2 surface) for a single layer presenting the largest mass increase of 0.153% of the original mass. This study aimed to enhance the performance of medical implants by optimizing surface biofunctionalization through robust hydroxyapatite-based bioceramic adhesive layers on metallic supports, determining the optimal electrical power and processing time for cathode mass increase during deposition processes, and analyzing parameter adjustments using second-order statistical orthogonal central composite programming, with a focus on single-layer deposition to identify significant differences in relative mass under specific conditions.

Organic municipal solid waste derived hydrogen production through supercritical water gasification process configured with K2CO3/SiO2: Performance study

Cities worldwide face a significant public health and environmental challenge in handling municipal solid waste (MSW). This research exposed an effective utilization of MSW as the source for hydrogen production via a supercritical water gasification process under 450–650 °C at 15–45 min processing time. The impacts of gasification temperature and processing time on the functional properties of hydrogen production are studied. Its results are compared to identify the optimum processing temperature and processing time to adopt the system. Integrating 3 wt% silicon dioxide (SiO2) nanoparticles/3 wt% of potassium carbonate (K2CO3) enhances hydrogen production by increasing the catalyst's surface area and improving the stability of active sites, leading to more efficient gasification reactions. Increasing the gasification temperature from 450 to 650 °C significantly raises the hydrogen molar fraction and gas yield with peak gasification efficiency (GE) and hydrogen efficiency (HE) values. The gasifier functioned with catalyst (3 wt% K2CO3/SiO2) under 650 °C gasification temperature and 45min gasification time influenced better output responses like improved hydrogen gas yield of 63.7 mol/kg, higher gasification efficiency of 59.8 %, better hydrogen efficiency (63.4 %) and increased carbon conversion efficiency of 63.4 and 42.5 % respectively.

Revealing the optimal traditional processing methods and its protective effects against febrile seizures of Arisaema cum bile.

Arisaema cum bile (known as Dan Nanxing in Chinese, DNX) is a herbal medicine used for treating febrile seizure (FS), which commonly prepared by using Arisaematis Rhizoma and animal bile. This study was designed to explore the optimal processing time of DNX and its potential mechanism on the anti-FS effect. A total of 17 volatile organic compounds (VOCs) were the characteristic ones to distinguish different fermentation stages of DNX by using gas chromatography-ion mobility spectrometry (GC-IMS), such as 2-heptanone monomer, and heptanal monomer. DNX with fermentation for 3 months had an obvious pattern of VOCs with others, which could be regarded as the optimal fermentation time. The Enterococcus and Staphylococcus might be the core bacteria on the production of VOCs. Additionally, DNX (2.8 g/kg, p.o.) reversed hot water bath-induced FSs of rats, as indicated by increased seizure latency and decreased seizure duration time. It also prevented hippocampal neuronal loss, increased GABAAR, and decreased GRIA1 expression. At the genus level, relative abundance of Enterococcus and Akkermansia were enriched after DNX treatment. These findings suggested that fermentation for 3 months might be the optimal process time for DNX, and DNX possess an anti-FS effect through regulating neurotransmitter disorder and gut microbiota.

CNN-LSTM for MFCC-based Speech Recognition on Smart Mirrors for Edge Computing Command

Smart mirrors are conventional mirrors that are augmented with embedded system capabilities to provide comfort and sophistication for users, including introducing the speech command function. However, existing research still applies the Google Speech API, which utilizes the cloud and provides sub-optimal processing time. Our research aim is to design speech recognition using Mel-frequency cepstral coefficients (MFCC) and convolutional neural network–long short-term memory (CNN-LSTM) to be applied to smart mirror edge devices for optimum processing time. Our first step was to download a synthetic speech recognition dataset consisting of waveform audio files (WAVs) from Kaggle, which included the utterances “left,” “right,” “yes,” “no,” “on,” and “off. ” We then designed speech recognition by involving Fourier transformation and low-pass filtering. We benchmark MFCC with linear predictive coding (LPC) because both are feature extraction methods on speech datasets. Then, we benchmarked CNN-LSTM with LSTM, simple recurrent neural network (RNN), and gated recurrent unit (GRU). Finally, we designed a smart mirror system complete with GUI and functions. The test results show that CNN-LSTM performs better than the three other methods with accuracy, precision, recall, and an f1-score of 0.92. The speech command with the best precision is "no," with a value of 0.940. Meanwhile, the command with the best recall is "off," with a value of 0.963. On the other hand, the speech command with the worst precision and recall is "other," with a value of 0.839. The contribution of this research is a smart mirror whose speech commands are carried out on the edge device with CNN-LSTM.

Atmospheric-pressure plasma jet texturing of C/C composites for improved joint strength

This study explores the use of air-fed atmospheric pressure plasma jets (APPJs) as a pre-joining treatment for 3D carbon fiber-reinforced carbon matrix composites (C/C) with the aim of both creating a textured surface that resembles a brush structure and improving the joint strength.The effects of various treatment time lengths on the mass loss, etching depth, and surface texture were investigated using SEM and confocal microscopy. An optimal process time of 30 s was selected, while keeping the other process parameters fixed (air flow of 1750 l/h and nozzle-sample distance of 5 mm). Wetting tests were conducted at 1000 °C, on both untreated and pre-treated C/C surfaces by means of liquid TiCuNi brazing alloy, and low contact angles of about 20° were measured. C/C–TiCuNi–C/C and C/C–TiCuNi–Cu joints were then produced, and their interfacial reactivity was evaluated. The apparent shear strength measured for the APPJ-treated C/C–Cu joints was 140 % higher than the value recorded for the untreated joints, thus confirming the effectiveness of the treatment.Even though a further investigation is needed in which an optimization of the process parameters should be included, this preliminary study has revealed the viability of APPJ as a promising technique to enhance the bonding of C/C composites in dissimilar assemblies and to improve the joint quality.

Reduction of Methylene Blue Using Silica Nanoparticles Obtained from Waste ZrC

AbstractThe study conducted an extraction of pure amorphous nano‐silica (SiO2 NP) from waste product at the ZrC factory. Various techniques such as TEM, SEM‐EDX, ICP, XRD, FTIR, BET, and DLS were utilized to synthesize and characterize the silica nanoparticle. The results showed successful production of pure amorphous silica, with no discernible difference in purity percentage between samples prepared with or without acidic pre‐treatment. It was found that the leaching temperature, process time, and reactant ratio all played a role in the production of nano‐silica. The ideal leaching temperature was determined to be 368 K, with an optimal process time of 2 h. The weight ratio of WPZF/NaOH that yielded the highest percentage of silica extraction was 9 : 10. Additionally, at pH 7, the nano‐silica exhibited the best specific surface area (BET) of 472.51 m2/g. The average size of the spherical nano‐silica, as determined by DLS, was approximately 38 nm. Furthermore, the produced nano‐silica was found to be an effective catalyst for the treatment of methylene blue (MB). MB could be degraded by more than 99 % of the initial concertation (10 mg/L) in the presence of NaBH4 within 16 min and rate constant of the catalytic reduction achieved as 0.134 min−1. These findings demonstrate the potential of amorphous nano‐silica as a valuable resource in various applications.

Development of a Parturition Detection System for Korean Native Black Goats.

Korean Native Black Goats deliver mainly during the cold season. However, in winter, there is a high risk of stunted growth and mortality for their newborns. Therefore, we conducted this study to develop a KNBG parturition detection system that detects and provides managers with early notification of the signs of parturition. The KNBG parturition detection system consists of triaxial accelerometers, gateways, a server, and parturition detection alarm terminals. Then, two different data, the labor and non-labor data, were acquired and a Decision Tree algorithm was used to classify them. After classifying the labor and non-labor states, the sum of the labor status data was multiplied by the activity count value to enhance the classification accuracy. Finally, the Labor Pain Index (LPI) was derived. Based on the LPI, the optimal processing time window was determined to be 10 min, and the threshold value for labor classification was determined to be 14 240.92. The parturition detection rate was 82.4%, with 14 out of 17 parturitions successfully detected, and the average parturition detection time was 90.6 min before the actual parturition time of the first kid. The KNBG parturition detection system is expected to reduce the risk of stunted growth and mortality due to hypothermia in KNBG kids by detecting parturition 90.6 min before the parturition of the first kid, with a success rate of 82.4%, enabling parturition nursing.

Efficient model predictive control of boiler coal combustion based on NARX neutral network

During coal-fired power generation, uniform combustion temperature in the boiler is desired which will benefit both economical efficiency and pollution reduction. To this end, a model predictive control (MPC) algorithm based on the Nonlinear Auto-Regressive Exogenous Inputs (NARX) neural network and KS-function is proposed, and the uniform combustion in the boiler is realized by controlling the opening travel of secondary windgates. In the modeling process, a multi-input and multi-output(MIMO) NARX neural network is developed using the historical data of the real system The NARX neural network is then used to predict the state variables, and the optimal control input is achieved by applying sequential quadratic programming (SQP), comparing with linear MPC the mean temperature difference is reduced by 64.2%. In addition, this paper proposes a new method to reduce the computational time of the online optimization process based on KS-function, which greatly accelerates the searching speed of SQP by 67.3%. The proposed MPC algorithm is applied to a 660 MW power generating unit. The results show that by applying the proposed algorithm, the temperature difference in the boiler is kept within 100 °C, the average coal consumption of the power plant is reduced by 5.71 g/kWh, and the NOx emission is reduced to 23.84 mg/m3. It can be concluded that the proposed algorithm greatly improves the economical efficiency of the power plant and reduces the emission of pollutants.

Improved dry sliding wear behavior of TA1titanium by low-temperature plasma nitriding by CCPN method

Cathodic cage plasma nitriding (CCPN) has been proven a promising technique to improving titanium’s poor wear resistance at a relatively lower temperature. Nonetheless, less attention has been paid to the performance of the treated sample at the cathodic potential by CCPN process, mostly on the sample at the floating potential. It has been demonstrated that a nitrogen diffusion layer is formed other than compound layer at the cathodic potential, which is beneficial to improve the bearing-load capacity and adhesion strength between the modified layer and the substrate. In this study, a cathodic cage in combination with pulsed-biased system has been used to realize nitriding of TA1 titanium at the cathodic potential below 660 °C. The influence of pulsed current and treatment time on the resulting surface microstructure and wear performance when sliding against Si3N4 balls were studied. Results showed that with the increasing pulsed current and prolonged processing time, the nitride layer thickness, hardness and roughness also increase. Additionally, although the anti-wear resistance is considerably improved through nitriding treatment compared to untreated TA1 titanium, and there are still differences between the samples prepared under different nitriding parameters. Lastly, the optimum pulsed current and processing time of the CCPN process that provide the best tribological characteristics are determined.

Revolutionizing the Developmental Processing of Short-Bodied Mackerel Fish (Rastrelliger Brachysoma) Through Advanced Thermal Techniques: Unveiling A Pathway to Unprecedented Quality Enhancement

This study focuses on the thermal processing of short-bodied mackerel fish (Rastrelliger brachysoma) through a bottling method, exploring its quality attributes such as appearance, taste, aroma, and texture. The conceptual framework involves input (materials, tools, and equipment), process (descriptive-quantitative research method with different sample treatments), and output (bottled short-bodied mackerel in three treatments). The study aims to determine the optimal processing time and assess the product's acceptability among food technology students and experts. The input phase details the materials used, including short-bodied mackerel, various ingredients, tools, and equipment. The process involves three treatments with different cooking durations. The output is the bottled short-bodied mackerel, pasteurized for extended shelf life and stable flavor. The study's significance lies in benefiting local fishermen, vendors, consumers, and future researchers. The research objectives include evaluating whether short-bodied mackerel can be effectively processed using thermal application and assessing its acceptability based on aroma, taste, texture, and color. The hypothesis suggests no significant differences in assessment between food experts and technology students. The study's significance extends to supporting local fishermen, vendors, and consumers while providing insights for future research. The methodology encompasses a quantitative research design, utilizing a checklist questionnaire and taste testing with third-year food technology students and experts. The study is conducted at Aurora State College of Technology, with thirty respondents. The experimental design involves three treatments with varying cooking durations, analyzed using ANOVA for statistical significance. Results from each treatment indicate that the processed short-bodied mackerel is generally acceptable, with variations in attributes across treatments. The study contributes valuable insights for the optimal processing of short-bodied mackerel, offering potential benefits to the fisheries industry and culinary preferences.

Optimal Computation Resource Allocation in Energy-Efficient Edge IoT Systems With Deep Reinforcement Learning

This paper investigates a computation resource optimization problem of mobile edge computing (MEC)-aided Internet-of-Things (IoT) devices with a reinforcement learning (RL) solution. Specifically, we leverage the stochastic optimization method and formulate the Lyapunov optimization technique to maximize the long-term energy efficiency, taking into account the transmission power, network stability, and transmission latency. Based on the Markov decision process and model-free deep RL (DRL) approach, we propose a double DRL-based online computation offloading method to implement a deep neural network that learns from interactions to solve the computation offloading and transmission latency problem in the dynamic MEC-aided IoT environments. Furthermore, we design an adaptive method for continuous action-state spaces to minimize the completion time and total energy consumption of the IoT devices for stochastic computation offloading tasks. The proposed real-time Lyapunov optimization and DRL algorithms achieve low computational complexity and optimal processing time. Simulation results demonstrate that the proposed algorithm can achieve near-optimal control performance with enhanced energy efficiency performance compared to the baseline policy control algorithms.

Multi‐layer task scheduling and resource allocation schemes considering idle resource and task priority in IoT networks

AbstractWith more and more interconnected smart devices (ISDs) accessing the Internet of Things (IoT), massive and diverse tasks need to be transformed and computed. Mobile edge computing enables the offloading of tasks to nearby servers to enhance processing efficiency, which makes ISDs idle, causing resource waste and failing to satisfy the high real‐time requirements of tasks. Besides, when tasks with different priorities are processed in the order they are generated, it will be difficult for IoT to guarantee a timely response to high‐priority tasks. To address the aforementioned issues, we establish an edge‐terminal‐local architecture by software‐defined networking to centrally manage idle ISD resource (2ISDR). Then the proposed two‐step scheduling mechanism with preemptive priority queue ensures the real‐time responses to high‐priority tasks, and the minimum resource allocation coefficients make offloading effective. Finally, we also propose a modified NSGA‐III algorithm named MNSGA‐III, which is designed to make decisions about offloading and solve resource allocation for tasks, and we correct infeasible solutions by a two‐step correction function to ensure the feasibility of MNSGA‐III. Experimental results show that the method can ensure a timely response to high‐priority tasks and optimize processing time, energy consumption, and economic cost through the utilization of 2ISDR.

An intelligent IoT intrusion detection system using HeInit-WGAN and SSO-BNMCNN based multivariate feature analysis

Devices connected to the Internet of Things (IoT) are growing in popularity across multiple industries. IoT links intelligent homes, buildings, businesses, and communities, and also links computers and mobile devices. Cybersecurity in IoT networks remains challenging, although many intrusion detection services for assault avoidance systems have been developed. Because of enormous growth in computing resources, attack surfaces, communications infrastructure, and attack rates, IoT services encounter substantial security issues. Innovative intrusion-detection systems ensuring data security, availability, and integrity have been developed to mitigate security problems; these systems are recommended for preventing common internal and external assaults and managing IoT environments. To clearly understand any impending attacks, the data are first preprocessed. Missing values are categorized with the concordance connection coefficient, and preprocessing is applied before handling of the missing values. The unevenly distributed and overlapping data are then handled through maximum likelihood estimation-based robust scalar (MLE-RS) scaling followed by random oversampling-based cluster-initialized divisive clustering (ROS-CInitDC). This study conceptualizes a Squirrel search optimization-based Bengio Nesterov momentum convolutional neural network (SSO-BNMCNN)-based approach, which indicates the relationships among information by considering causation. It keeps an optimal processing time and correctness to get data understanding. The selected features are then tested against the categorization of a He initialization-based Wasserstein gradient penalty loss generative adversarial network (HeInit-WGAN). The HeInit-WGAN technique identifies attacks more reliably and accurately than existing methods, reducing false alarms. The proposed strategy had an F-measure of 0.91, and scores of 0.96 for precision, 0.91 for awareness, and 0.98 for explicitness. Moreover, it decreased the false acceptance rate, achieving a 0.02 false positive rate and 0.09 false negative rate.

Discrimination of different processing degrees and quantitative study of processing end point of vinegar-processing Cyperi Rhizoma pieces based on electronic sensory technology

In this study, CM-5 spectrophotometer and Heracles NEO ultra-fast gas-phase electronic nose were used to analyze the changes in color and odor of vinegar-processed Cyperi Rhizoma(VPCR) pieces. Various analysis methods such as DFA and partial least squares discriminant analysis(PLS-DA) were combined to identify different processing degrees and quantify the end point of processing. The results showed that with the increase in vinegar processing, the brightness parameter L~* of VPCR pieces decreased gradua-lly, while the red-green value a~* and yellow-blue value b~* initially increased and reached their maximum at 8 min of processing, followed by a gradual decrease. A discriminant model based on the color parameters L~*, a~*, and b~* was established(with a discrimination accuracy of 98.5%), which effectively differentiated different degrees of VPCR pieces. Using the electronic nose, 26 odor components were identified from VPCR samples at different degrees of vinegar processing. DFA and PLS-DA models were established for different degrees of VPCR pieces. The results showed that the 8-min processed samples were significantly distinct from other samples. Based on variable importance in projection(VIP) value greater than 1, 10 odor components, including 3-methylfuran, 2-methylbuty-raldehyde, 2-methylpropionic acid, furfural, and α-pinene, were selected as odor markers for differentiating the degrees of vinegar processing in VPCR. By combining the changes in color and the characteristic odor components, the optimal processing time for VPCR was determined to be 8 min. This study provided a scientific basis for the standardization of vinegar processing techniques for VPCR and the improvement of its quality standards and also offered new methods and ideas for the rapid identification and quality control of the end point of processing for other traditional Chinese medicine.

Nonlinear plasma surface modification of polylactide to promote interaction with fibroblasts

AbstractSurface modification of polylactide films was performed using a dielectric barrier discharge (DBD) with the aim of increasing proliferative activity of human fibroblasts on these films. It has been shown that during the plasma treatment of the polylactide film, nonlinear processes occur depending on the processing time. The effect of the dielectric barrier discharge on the modification of polylactide films was evaluated using IR spectroscopy, AFM, XPS, TSDC, and the wetting angle of the surface. The optimal processing time in DBD of polylactide films is 3 min for this installation, the proliferative activity increases by 10% compared to the original film. This treatment time provides an increased concentration of oxygen‐containing groups, optimal relief, and free surface energy of 55 mJ/m2 on the surface.Highlights The biocompatibility of the polylactide film was improved by 10% used DBD. The optimal processing time of PLA films in DBD is 3 min. The functionalization of the polylactide surface occurs non‐linearly.

Evaluation of the effectiveness of allogeneic tendon graft sterilization with supercritical carbon dioxide

Structural and functional properties of the human tendon tissue complicate process of tendon-based grafts preserving. In the process of preservation, it is necessary to maintain mechanical and functional parameters of the tendon tissue as well as to provide sterility and biological safety of the graft. One could conclude effectiveness of techniques, combining tendon conservation at low temperatures and sterilization with the supercritical carbon dioxide.Aim of work: to find optimal conditions for allogeneic tendon grafts sterilization with supercritical carbon dioxide.Materials and methods. Allogeneic tendons were prepared from the tissue donors, following the rules of asepsis and antisepsis. After quarantine and confirmation of the absence of blood-borne infections the tendon grafts were divided into 3 groups: in the control group the tendons were not subjected to cryopreservation and sterilization procedures; in 2 experimental groups tendons were treated with a cryoprotector 10 % dimethyl sulfoxide (DMSO) solution and sterilized with supercritical carbon dioxide with slow gas discharge (group 2) or with fast gas discharge (group 3); the duration of sterilization in both groups varied from 1 to 12 hours. The toxicity of the grafts was assessed in human mesenchymal multipotent stromal cells (MMSC) culture on the 3rd and 7th days. The sterility of the grafts was confirmed on the 7th and 14th day by bacteriological culture on thioglycol medium and Saburo broth. Mechanical tests were performed on testing machine LLOYD Instruments LR5K Plus with the tensile speed 5 mm/min.Results. Histological analysis showed, that in the group with slow gas discharge collagen fibers retained their integrity and topography and contained only local minor tears; in all terms of treatment, the tendon grafts were sterile and nontoxic. On the contrary, in the group with fast gas discharge there was marked damage of the collagen fibers and growth of bacterial and fungal flora was observed in the culture. The grafts of the control group and the group, where sterilization with supercritical carbon dioxide was performed with slow gas discharge for 1-12 hours, were used to evaluate mechanical characteristics. In the preserved tendons the stiffness and ultimate strain did not significantly differ from the similar values in the control (p > 0.05), on the contrary, the level of ultimate strain in all experimental specimens was significantly reduced by 1.5-2.1 times comparing to the control. Young's modulus and load at rupture in the control grafts and grafts, sterilized for 1 hour, had similar values, whereas in grafts, sterilized from 3 to 12 hours, these parameters were 1.4-2.1 times lower (p < 0.05).Conclusions. The suggested technique of tendon preservation, using cryoprotector DMSO and sterilization with the supercritical carbon dioxide, allows to obtain sterile and non-toxic grafts. The structure of cells and fibers of the preserved tendons did not significantly disturbed. For supercritical carbon dioxide sterilization of tendon grafts the most optimal processing time is 1 hour.

Optimization of Deuteron Irradiation of 176Yb for Producing 177Lu of High Specific Activity Exceeding 3000 GBq/mg.

The irradiation of 176Yb with deuterons offers a promising pathway for the production of the theranostic radionuclide 177Lu. To optimize this process, calculations integrating deuteron transport, isotope production, and decay have been performed. In pure 176Yb, the undesired production of 174g+mLu occurs at higher deuteron energies, corresponding to a distribution slightly shallower than that of 177Lu. Hence, 174g+mLu can be effectively filtered out by employing either a low-energy deuteron beam or stacked foils. The utilization of stacked foils enables the production of 177Lu using a high-energy linear accelerator. Another unwanted isotope, 176mLu, is produced roughly at the same depth as 177Lu, but its concentration can be significantly reduced by selecting an appropriate post-irradiation processing time, owing to its relatively short half-life. The modeling approach extended to the mapping of yields as a function of irradiation time and post-irradiation processing time. An optimized processing time window was identified. The study demonstrates that a high-energy deuteron beam can be employed to produce 177Lu with high specific activity exceeding 3000 GBq/mg. The effect of different purity levels (ranging from 98% to 100%) was also discussed. The impurity levels have a slight impact. The modeling demonstrates the feasibility of obtaining 177Lu with a specific activity > 3000 GBq/mg and radionuclidic purity > 99.5% when using a commercially available 176Yb target of 99.6% purity.

A committee machine-based estimation of shear velocity log by combining intelligent systems and rock-physics model using metaheuristic algorithms

Estimation of reservoir parameters such as porosity, lithology and determination of elastic moduli is based on well-logging data and seismic velocity information. However, the lack of shear velocity log in many wells, and the high costs of its acquisition have led to developing different approaches for shear velocity estimation. Currently, shear velocity estimation is accomplished by common industrial methods such as empirical equations, regression analysis, intelligent methods and rock-physics models (RPMs). The current study proposes that robust, accurate and cost-effective intelligent methods coupled with suitable RPM provide reasonable estimations of the shear velocity in an optimal processing time. Hybridizing intelligent models with RPMs in the framework of a committee machine is an optimal solution for shear velocity estimation of carbonate reservoirs. The intelligent methods used in this study include neural network (NN), fuzzy logic (FL) and an adaptive-neuro fuzzy inference system (ANFIS). In this research, for each individual intelligent model and a developed RPM, the optimal weights were allocated by Metaheuristic optimization algorithms including genetic algorithm (GA), ant colony optimization routing (ACOR) and simulated annealing (SA)). To obtain the best results with the lowest mean squared error (MSE), a total of 9408, 10801 and 12288 models were created and tested in MATLAB to optimally parametrize the GA, ACOR and SA, respectively. The results showed that the combination of the applied intelligent models with the developed RPMs leads to a higher correlation coefficient with reference to the measured Shear velocity in test dataset. The use of a combination of intelligent methods in the form of committee-machine instead of individual methods has led to a reduction in error and improved the results by up to 2% Considering the high sensitivity of shear wave velocity in geomechanical and reservoir characterization studies, even small improvements in its estimation can significantly reduce error in the characterization of hydrocarbon reservoirs.

QuantLaneNet: A 640-FPS and 34-GOPS/W FPGA-Based CNN Accelerator for Lane Detection.

Lane detection is one of the most fundamental problems in the rapidly developing field of autonomous vehicles. With the dramatic growth of deep learning in recent years, many models have achieved a high accuracy for this task. However, most existing deep-learning methods for lane detection face two main problems. First, most early studies usually follow a segmentation approach, which requires much post-processing to extract the necessary geometric information about the lane lines. Second, many models fail to reach real-time speed due to the high complexity of model architecture. To offer a solution to these problems, this paper proposes a lightweight convolutional neural network that requires only two small arrays for minimum post-processing, instead of segmentation maps for the task of lane detection. This proposed network utilizes a simple lane representation format for its output. The proposed model can achieve 93.53% accuracy on the TuSimple dataset. A hardware accelerator is proposed and implemented on the Virtex-7 VC707 FPGA platform to optimize processing time and power consumption. Several techniques, including data quantization to reduce data width down to 8-bit, exploring various loop-unrolling strategies for different convolution layers, and pipelined computation across layers, are optimized in the proposed hardware accelerator architecture. This implementation can process at 640 FPS while consuming only 10.309 W, equating to a computation throughput of 345.6 GOPS and energy efficiency of 33.52 GOPS/W.

Enhancing Object Detection in Self-Driving Cars Using a Hybrid Approach

Recent advancements in artificial intelligence (AI) have greatly improved the object detection capabilities of autonomous vehicles, especially using convolutional neural networks (CNNs). However, achieving high levels of accuracy and speed simultaneously in vehicular environments remains a challenge. Therefore, this paper proposes a hybrid approach that incorporates the features of two state-of-the-art object detection models: You Only Look Once (YOLO) and Faster Region CNN (Faster R-CNN). The proposed hybrid approach combines the detection and boundary box selection capabilities of YOLO with the region of interest (RoI) pooling from Faster R-CNN, resulting in improved segmentation and classification accuracy. Furthermore, we skip the Region Proposal Network (RPN) from the Faster R-CNN architecture to optimize processing time. The hybrid model is trained on a local dataset of 10,000 labeled traffic images collected during driving scenarios, further enhancing its accuracy. The results demonstrate that our proposed hybrid approach outperforms existing state-of-the-art models, providing both high accuracy and practical real-time object detection for autonomous vehicles. It is observed that the proposed hybrid model achieves a significant increase in accuracy, with improvements ranging from 5 to 7 percent compared to the standalone YOLO models. The findings of this research have practical implications for the integration of AI technologies in autonomous driving systems.