High Level Of Precision Research Articles

Efficient Eye State Detection for Driver Fatigue Monitoring Using Optimized YOLOv7-Tiny

This study refines the YOLOv7-tiny model through structured pruning and architectural fine-tuning, specifically for real-time eye state detection. By focusing on enhancing the model’s efficiency, particularly in environments with limited computational resources, this research contributes significantly to advancing driver monitoring systems, where timely and accurate detection of eye states such as openness or closure can prevent accidents caused by drowsiness or inattention. Structured pruning was utilized to simplify the YOLOv7-tiny model, reducing complexity and storage requirements. Subsequent fine-tuning involved adjustments to the model’s width and depth to further enhance processing speed and efficiency. The experimental outcomes reveal a pronounced reduction in storage size, of approximately 97%, accompanied by a sixfold increase in frames per second (FPS). Despite these substantial modifications, the model sustains high levels of precision, recall, and mean average precision (mAP). These improvements indicate a significant enhancement in both the speed and efficiency of the model, rendering it highly suitable for real-time applications where computational resources are limited.

Integrated approach to assessing strength in slag-based geopolymer mortars: experimental study and modeling with advanced techniques

The study consists of two main parts. In the initial phase, a variety of slag-based geopolymer mortars with different activator concentrations were prepared. These mortars underwent curing in both water and air environments for periods of 3, 7, 28, and 90 days, after which their compressive strength was evaluated at the conclusion of each curing interval. The second phase of the study is dedicated to the development of innovative models for estimating the compressive strength based on the data gathered. To achieve this, a range of techniques including multi-gene genetic programming (MGGP), artificial neural networks (ANN), XGBoost, SVM-Gauss, long short-term memory (LSTM), and convolutional neural networks (CNN) were employed to formulate a model capable of estimating compressive strength accurately. The study made use of various performance evaluation metrics such as mean squared error (MSE), root mean squared error (RMSE), R-squared, mean absolute error (MAE), and scatter index (SI) to assess the precision of the MGGP method in evaluating slag-based geopolymer mortars under both water and air curing conditions. The findings indicate that the equations generated by the MGGP method exhibit a high level of precision when juxtaposed with experimental outcomes. This research endeavors to enhance the prediction of compressive strength in geopolymer mortars, a subject that has garnered significant interest in scholarly literature.

Machine learning-based anomaly detection in Android network flows for ransomware identification

Ransomware continues to pose a significant challenge as it infiltrates networks and employs advanced techniques to encrypt data. To counteract such adversarial endeavors and mitigate any harm, prompt identification of ransomware operations is imperative. The primary objective of this research was to examine the viability of utilizing machine learning techniques for the identification of irregularities in network flows, specifically focusing on the identification of ransomware within Android ecosystems. The fundamental basis of this study was a comprehensive dataset comprising both benign and malicious instances of network traffic originating from several ransomware families. A neural network model was meticulously constructed and trained using a portion of the dataset, followed by thorough testing on novel data to assess its predictive performance. The model has exceptional performance across all classes, as seen by its high levels of accuracy, precision, recall, and F1 Score. Significantly, the model demonstrates a robust ability to extrapolate findings to several categories of ransomware and benign network activity, indicating its potential as a reliable solution for practical implementation. This study establishes the foundation for future endeavors aimed at enhancing the model, exploring real-time detection alternatives, and integrating with comprehensive security solutions. Keywords: Android Security; anomaly detection; cybersecurity; ransomware identification; machine learning

Development of an Innovative Biosensor Based on Graphene/PEDOT/Tyrosinase for the Detection of Phenolic Compounds in River Waters.

Phenolic compounds, originating from industrial, agricultural, and urban sources, can leach into flowing waters, adversely affecting aquatic life, biodiversity, and compromising the quality of drinking water, posing potential health hazards to humans. Thus, monitoring and mitigating the presence of phenolic compounds in flowing waters are essential for preserving ecosystem integrity and safeguarding public health. This study explores the development and performance of an innovative sensor based on screen-printed electrode (SPE) modified with graphene (GPH), poly(3,4-ethylenedioxythiophene) (PEDOT), and tyrosinase (Ty), designed for water analysis, focusing on the manufacturing process and the obtained electroanalytical results. The proposed biosensor (SPE/GPH/PEDOT/Ty) was designed to achieve a high level of precision and sensitivity, as well as to allow efficient analytical recoveries. Special attention was given to the manufacturing process and optimization of the modifying elements' composition. This study highlights the potential of the biosensor as an efficient and reliable solution for water analysis. Modification with graphene, the synthesis and electropolymerization deposition of the PEDOT polymer, and tyrosinase immobilization contributed to obtaining a high-performance and robust biosensor, presenting promising perspectives in monitoring the quality of the aquatic environment. Regarding the electroanalytical experimental results, the detection limits (LODs) obtained with this biosensor are extremely low for all phenolic compounds (8.63 × 10-10 M for catechol, 7.72 × 10-10 M for 3-methoxycatechol, and 9.56 × 10-10 M for 4-methylcatechol), emphasizing its ability to accurately measure even subtle variations in the trace compound parameters. The enhanced sensitivity of the biosensor facilitates detection and quantification in river water samples. Analytical recovery is also an essential aspect, and the biosensor presents consistent and reproducible results. This feature significantly improves the reliability and usefulness of the biosensor in practical applications, making it suitable for monitoring industrial or river water.

Evaluation of the performance characteristics of aerostatic bearing with porous alumina (Al2O3) membrane using theoretical and experimental methods

Instruments with high levels of precision commonly use aerostatic bearings. Moreover, the use of porous (Al2O3 membrane) material validates that the pressure is spread uniformly throughout the air film region. The impression of applied load on the thickness of the air film of the aerostatic bearings was evaluated using a certain experimental technique. As the applied load rises, the thickness of the air film expands, and as the compressive stress rises, it contracts. The theoretical model parameters were set using the experimental stipulations. It was discovered that the theoretical model and the experimental data were consistent. The pressure gradient induced in the air film and the air bearings’ capacity for carrying loads were calculated using a theoretical simulation. The results of theoretical modeling and experimental comparison of the different characteristics of porous (Al2O3 membrane) aerostatic bearings based on stiffness and load-carrying capacity are graphically illustrated in this study. Porous aerostatic bearings with Al2O3 membranes have a number of potential applications, including high-speed spindles, precision instruments, microelectromechanical systems, vacuum pumps, cryogenic applications, etc.

Heart rate monitoring system based on piezoelectric poly(vinylidene fluoride-co-trifluoroethylene) composites with barium strontium titanate ceramic particles

A heart rate sensor device has been designed and developed based on a composite material based on poly(vinylidene fluoride – co – trifluoroethylene), P(VDF-TrFE) as polymer matrix and barium strontium titanate (BST) particles as ceramic fillers. The composite films were prepared by solvent casting varying the ceramic particles content between up to 40 wt%, allowing to tailor the dielectric and piezoelectric response. The morphology, polymer phase and thermal properties are independent of the ceramic filler content, whereas the dielectric constant increases significantly with increasing filler content, the largest dielectric constant, ε’ = 38 at 1 kHz, being obtained for the composite with 40 wt% of ceramic particles. Further, the highest piezoelectric response, also dependent on ceramic filler content, is |d33|= 29 pC/N, being obtained for the 10 wt% ceramic particle content film. It is also shown by piezoresponse force microscopy that higher ceramic particles are characterized by more stable ferroelectric domains. The composite has been successfully proved for its potential in heart rate monitoring applications, exhibiting high levels of precision as well as reliability. This work on heart rate sensing presents a material suitable for its incorporation into wearable gadgets, medical devices, and sports equipment, compatible with integration by printing technologies, enabling consumers to access immediate data relevant to their cardiovascular health.

Deep transfer learning with gravitational search algorithm for enhanced plant disease classification

Plant diseases annually cause damage and loss of much of the crop, if not its complete destruction, and this constitutes a significant challenge for farm owners, governments, and consumers alike. Therefore, identifying and classifying diseases at an early stage is very important in order to sustain local and global food security. In this research, we designed a new method to identify plant diseases by combining transfer learning and Gravitational Search Algorithm (GSA). Two state-of-the-art pretrained models have been adopted for extracting features in this study, which are MobileNetV2 and ResNe50V2. Multilayer feature extraction is applied in this study to ensure representations of plant leaves from different levels of abstraction for precise classification. These features are then concatenated and passed to GSA for optimizing them. Finally, optimized features are passed to Multinomial Logistic Regression (MLR) for final classification. This integration is essential for categorizing 18 different types of infected and healthy leaf samples. The performance of our approach is strengthened by a comparative analysis that incorporates features optimized by the Genetic Algorithm (GA). Additionally, the MLR algorithm is contrasted with K-Nearest Neighbors (KNN). The empirical findings indicate that our model, which has been refined using GSA, achieves very high levels of precision. Specifically, the average precision for MLR is 99.2%, while for KNN it is 98.6%. The resulting results significantly exceed those achieved with GA-optimized features, thereby highlighting the superiority of our suggested strategy. One important result of our study is that we were able to decrease the number of features by more than 50%. This reduction greatly reduces the processing requirements without sacrificing the quality of the diagnosis. This work presents a robust and efficient approach to the early detection of plant diseases. The work demonstrates the utilization of sophisticated computational methods in agriculture, enabling the development of novel data-driven strategies for plant health management, therefore enhancing worldwide food security.

25 років Яворівському НГП – структура, використання, значення досліджень, перспективи

This paper presents detailed information about the stages of creation and directions of use of a special multifunctional standard scientific geodetic polygon (SGP) in Yavoriv district of Lviv region. The main purpose of the SGP is the metrological control of modern geodetic instruments and the testing of new technologies. The features of constructing geodetic networks, creating a local reference gravimetric network to refine the parameters of the global Earth gravimetric model, and constructing a quasi-geoid model with centimeter accuracy within the local polygon are described. The determination of high-precision astronomical coordinates and reference azimuths with an accuracy of 0.5–1.0, the creation of metrological objects of the NGP are outlined: the standard linear baseline (SLB) of original design and the fundamental geodetic network (FGN) for conducting special research and metrological verification of electronic theodolites, rangefinders, GNSS receivers, the development of a high-precision leveling network for studying accuracy and GNSS-leveling, etc. It provides information about multi-year experimental calibrations of the SLB using various methods and devices, and the first international intercomparisons on the SLB (working standard) in Ukraine, as well as multi-day GNSS observation campaigns at FGN points, the results of processing, and the achieved high accuracy. New experimental studies are related to improving the accuracy of FGN and GNSS leveling, new calibrations of SLB, including international intercomparisons, establishment of fundamental gravimetric points, optimization of the use of reference directions for metrological control and calibration of navigation equipment.

Analisis Kinerja Mesin CNC Milling 3 Axis pada Pembuatan Pipa Jet Oil

The study evaluated the performance of a 3-axis CNC milling machine in the production of jet oil pipes with a focus on achieving a high level of precision. Through variation of cutting parameters and feeding speed, the machine succeeded in reaching the industry standard for jet oil pipe production. Optimization of parameters improved production efficiency, demonstrated by results that achieved the desired precision tolerance. Cutting tool wear analysis provides insight into machine performance and possible repair actions. This research confirms the potential of 3 axis CNC milling machines in addressing the challenge of high-precision jet oil pipe production, contributing to the development of CNC Milling technology in the context of the oil and gas industry.

An Entity Extraction Pipeline for Medical Text Records Using Large Language Models: Analytical Study.

The study of disease progression relies on clinical data, including text data, and extracting valuable features from text data has been a research hot spot. With the rise of large language models (LLMs), semantic-based extraction pipelines are gaining acceptance in clinical research. However, the security and feature hallucination issues of LLMs require further attention. This study aimed to introduce a novel modular LLM pipeline, which could semantically extract features from textual patient admission records. The pipeline was designed to process a systematic succession of concept extraction, aggregation, question generation, corpus extraction, and question-and-answer scale extraction, which was tested via 2 low-parameter LLMs: Qwen-14B-Chat (QWEN) and Baichuan2-13B-Chat (BAICHUAN). A data set of 25,709 pregnancy cases from the People's Hospital of Guangxi Zhuang Autonomous Region, China, was used for evaluation with the help of a local expert's annotation. The pipeline was evaluated with the metrics of accuracy and precision, null ratio, and time consumption. Additionally, we evaluated its performance via a quantified version of Qwen-14B-Chat on a consumer-grade GPU. The pipeline demonstrates a high level of precision in feature extraction, as evidenced by the accuracy and precision results of Qwen-14B-Chat (95.52% and 92.93%, respectively) and Baichuan2-13B-Chat (95.86% and 90.08%, respectively). Furthermore, the pipeline exhibited low null ratios and variable time consumption. The INT4-quantified version of QWEN delivered an enhanced performance with 97.28% accuracy and a 0% null ratio. The pipeline exhibited consistent performance across different LLMs and efficiently extracted clinical features from textual data. It also showed reliable performance on consumer-grade hardware. This approach offers a viable and effective solution for mining clinical research data from textual records.

A machine learning-based assessment model for defect diagnosis in XLPE power cables

Cross-linked polyethylene (XLPE) power cables are commonly used in flexible DC transmission applications. The diagnosis of the defects of XLPE power cable has consistently been a focal point of research as it is an essential equipment for power delivery. Previous research works have seldom employed machine learning methods to deal with this problem. Therefore, this work presents a machine learning-based assessment model that combines the Categorical Boosting (CatBoost) algorithm and Aquila optimizer. The CatBoost model is developed to examine the stages of the cable defect. The load condition, corrosion condition, operating life, and partial discharge are the inputs into the CatBoost model. The Aquila optimizer is employed to optimize parameters in an automated manner during the training of the CatBoost model. The performance comparison is made between the proposed model and the existing models. The proposed model demonstrates a high level of accuracy, precision, recall, and F1-score, all higher than 99 %. The model exhibits at least 1 % more achievement in accuracy, precision, recall, and F1-score when compared to the next best model, XGBoost. These results suggest that the proposed model is capable of effectively assessing the stages of cable defects. In addition to this, these experimental results of the proposed model are superior to those of the existing models, which demonstrate that the proposed model is superior to the existing models in terms of its ability to assess the defect stages of cables.

An efficient protocol for quantifying catalase activity in biological samples

BackgroundCatalase is an important enzyme that helps protect cells against oxidative stress. The current protocol presents a reliable method for measuring catalase (CAT) enzyme activity in biological systems using the CUPRAC-CAT method.MethodsIn the CUPRAC-CAT method, the component of the enzymatic reaction was incubated before adding the Cu(Nc)22+ reagent. The unreacted substrates reduced the Cu(II)-the neocuproine complex, resulting in the highly colored Cu(I)-neocuproine product, which could be detected spectrophotometrically at 450 nm. The negative correlation between catalase activity and the absorbance of the Cu(I)-neocuproine complex was examined. To assess the optimization of Cu(I)-neocuproine complex production, response surface methodology (RSM) was employed, specifically utilizing the Box–Behnken design (BBD). Additionally, the reliability of the newly developed protocol was confirmed through Bland–Altman analysis of catalase activity in paired samples, employing the peroxovanadate method.ResultsThe novel method is just as accurate as the established standard; the correlation between the two methods was 0.99. The CUPRAC-CAT method is stable, sensitive, linear, reproducible, accurate, and selective and can be used for quantifying oxidative stress while measuring catalase activity in liver tissue homogenates.ConclusionsThis study has demonstrated a straightforward and dependable protocol for evaluating catalase activity. The protocol is free from interference and can be easily employed in scientific research, ensuring a high level of accuracy and precision. The CUPRAC-CAT method is an effective technique to monitor bacterial contamination. This method provides quick and reliable results that can help ensure food safety and prevent or address bacterial contamination.Graphical abstract

Advancements in γδT cell engineering: paving the way for enhanced cancer immunotherapy.

Comprising only 1-10% of the circulating T cell population, γδT cells play a pivotal role in cancer immunotherapy due to their unique amalgamation of innate and adaptive immune features. These cells can secrete cytokines, including interferon-γ (IFN-γ) and tumor necrosis factor-α (TNF-α), and can directly eliminate tumor cells through mechanisms like Fas/FasL and antibody-dependent cell-mediated cytotoxicity (ADCC). Unlike conventional αβT cells, γδT cells can target a wide variety of cancer cells independently of major histocompatibility complex (MHC) presentation and function as antigen-presenting cells (APCs). Their ability of recognizing antigens in a non-MHC restricted manner makes them an ideal candidate for allogeneic immunotherapy. Additionally, γδT cells exhibit specific tissue tropism, and rapid responsiveness upon reaching cellular targets, indicating a high level of cellular precision and adaptability. Despite these capabilities, the therapeutic potential of γδT cells has been hindered by some limitations, including their restricted abundance, unsatisfactory expansion, limited persistence, and complex biology and plasticity. To address these issues, gene-engineering strategies like the use of chimeric antigen receptor (CAR) T therapy, T cell receptor (TCR) gene transfer, and the combination with γδT cell engagers are being explored. This review will outline the progress in various engineering strategies, discuss their implications and challenges that lie ahead, and the future directions for engineered γδT cells in both monotherapy and combination immunotherapy.

Tuning the Probe-Bilayer Architecture of Silver Nanoneedle-based Ion Channel Probes.

Ion channel probes, as one of the ion channel platforms, provide an appealing opportunity to perform localized detection with a high precision level. These probes come basically in two classes: glass and metal. While the glass-based probes showed the potential to be employed for molecular sensing and chemical imaging, these probes still suffer from limited resolution and lack of control over protein insertion. On the other hand, metal-based nanoneedle probes (gold and silver) have been recently developed to allow reducing probe dimensions to the nanoscale geometry. More specifically, silver probes are preferable owing to their ability to mitigate the channel current decay observed with gold probes and provide a stable DC channel current. However, there are still some challenges related to the probe design and bilayer curvature that render such probes insensitive to small changes in the tip-substrate distance. Herein, we introduce two main pathways to control the probe-bilayer architecture; the first is by altering the probe shape and geometry during the fabrication process of silver probes. The second pathway is by altering the surface characteristics of the silver probe via an electrophoretic deposition process. Our findings reveal that varying the electrochemical etching parameters results in different probe geometries and producing sharper tips with a 2-fold diameter reduction. In addition, the electrophoretic deposition of a cathodic paint on the silver nanoneedle surface led to a miniaturized exposed silver tip that enables the formation of a confined bilayer. We further investigated the characteristics of bilayers supported on both the sharper nanoneedles and the HSR-coated silver probes produced by controlling the etching conditions and electrodeposition process, respectively. We believe this work paves the way to rationally design silver nanoneedle ion channel probes, which are well suited for localized molecular sensing and chemical imaging.

Action research of lean 4.0 application to the maintenance of hydraulic systems in steel industry

PurposeMaintenance represents an indispensable role in the productive sector of the steel industry. The increasing use of operating with a high level of precision makes hydraulic systems one of the issues that require a high level of attention. This study aims to explore an empirical investigation for decreasing the occurrences of corrective maintenance of hydraulic systems in the context of Lean 4.0.Design/methodology/approachThe maintenance model is developed based on action-research methodology through an empirical investigation, with nine stages. This approach aims to build a scenario to analyze and interpret the occurrences, seeking to implement and evaluate the actions to be performed. The undertaken initiatives demonstrate that this approach can be applied to optimize the maintenance of an organization.FindingsThe main contribution of this paper is to demonstrate that the applied method allows the overviewing results, with a qualitative approach concerning the maintenance actions and management processes to be considered, allowing a holistic understanding and contributing to the current literature. The results also indicated that Lean 4.0 has direct and mediating effects on maintenance performance.Originality/valueThis research intends to propose an evaluation framework with an interdimensional linkage between action research methodology and Lean 4.0, to explore an empirical investigation and contributing to understanding the actions to reduce the occurrences of hydraulic systems corrective maintenance in a production line in the steel industry.

IoT-based implementation of rickshaws for real-time monitoring and measuring the weight of cattle

In the era of modern agriculture that is increasingly dependent on technology, livestock management has become crucial to increasing efficiency and productivity. An important aspect in livestock management is providing appropriate feed to fattening cattle. Manual monitoring of feed weight is often complex and prone to errors, which can have a significant impact on operational efficiency and result in losses. Accuracy in monitoring feed weight is the key to maintaining optimal health and growth of cattle. Internet of Things (IoT) technology is emerging as an innovative solution to overcome these challenges. The use of Angkong load cells, a tool connected to IoT, allows automatic monitoring of feed weight with a high level of precision. The test results show an error rate close to zero, with a Mean Absolute Percentage Error (MAPE) of around 0.158%, making the Angkong load cell a reliable tool. With this capability, farmers can monitor cow feed weight in real-time with minimal error rates. This not only increases the operational efficiency of the farm but also optimizes the health and growth of livestock more efficiently, having a positive impact on overall farm productivity. The aim of this research is to monitor the amount of feed given to cows with an adequate level of accuracy. Rickshaw load cells can be well suited for this use due to their ability to handle relatively large weights with fairly good accuracy, but do not necessarily have the level of precision required in laboratory measurements or the pharmaceutical industry.

Assistance Device Based on SSVEP-BCI Online to Control a 6-DOF Robotic Arm.

This paper explores the potential benefits of integrating a brain-computer interface (BCI) utilizing the visual-evoked potential paradigm (SSVEP) with a six-degrees-of-freedom (6-DOF) robotic arm to enhance rehabilitation tools. The SSVEP-BCI employs electroencephalography (EEG) as a method of measuring neural responses inside the occipital lobe in reaction to pre-established visual stimulus frequencies. The BCI offline and online studies yielded accuracy rates of 75% and 83%, respectively, indicating the efficacy of the system in accurately detecting and capturing user intent. The robotic arm achieves planar motion by utilizing a total of five control frequencies. The results of this experiment exhibited a high level of precision and consistency, as indicated by the recorded values of ±0.85 and ±1.49 cm for accuracy and repeatability, respectively. Moreover, during the performance tests conducted with the task of constructing a square within each plane, the system demonstrated accuracy of 79% and 83%. The use of SSVEP-BCI and a robotic arm together shows promise and sets a solid foundation for the development of assistive technologies that aim to improve the health of people with amyotrophic lateral sclerosis, spina bifida, and other related diseases.

The Vagueness of Religion

Abstract A concept is vague if it admits of borderline cases—cases in which it is not clear whether the concept applies. Thus vague concepts are concepts without sharp boundaries. I argue that religion is vague, and I draw conclusions from this claim for both framing up conceptions of religion and studying it. One result will be to undermine arguments to the effect that any account of religion that does not sharply demarcate the religious from the nonreligious is somehow defective. Another will be that admitting the existence of borderline cases relieves us of the obligation to seek high levels of precision in our various usages of the term. And a third will be that is it not at all clear that any periods of human history can be characterized as times “before religion” on any but the narrowest of definitions.

Parametric Study of Die Sinking EDM of H13 Steel using Taguchi Techniques

As for H13 die steel, it is distinguished by a high hardness and a unique surface characteristics that must be created during machining using non-standard methods. One of such non conventional manufacturing techniques involving the use of Electrical Discharge Machining (EDM) for machining complex or hard material parts. It indicates that EDM has progressed from a series of a tool and die process to an alternative micro-scale application machining process. The paper is aimed at elaborating mathematical models defining the link between the MRR and SR to measured input parameters (current, pulse-on time, pulse-off time, and Reference voltage) in hot work steel EDM. With a L9 orthogonal involving four variables at three levels were used. The values of the model quality factors analyzed by the ANOVA procedure show that the selected mathematical models describe the process performance within successfully studied range with high level of precision. To determine the optimal condition, Taguchi method was used to measure the performance impact of different process parameters and find out best mixing. Minitab V 21 software has been used for the analysis and explanations. A good agreement between experimental value and the predicted one was found.

Machine learning-based prediction of proteins’ architecture using sequences of amino acids and structural alphabets

In addition to the growth of protein structures generated through wet laboratory experiments and deposited in the PDB repository, AlphaFold predictions have significantly contributed to the creation of a much larger database of protein structures. Annotating such a vast number of structures has become an increasingly challenging task. CATH is widely recognized as one the most common platforms for addressing this challenge, as it classifies proteins based on their structural and evolutionary relationships, offering the scientific community an invaluable resource for uncovering various properties, including functional annotations. While CATH annotation involves – to some extent – human intervention, keeping up with the classification of the rapidly expanding repositories of protein structures has become exceedingly difficult. Therefore, there is a pressing need for a fully automated approach. On the other hand, the abundance of protein sequences stemming from next generation sequencing technologies, lacking structural annotations, presents an additional challenge to the scientific community. Consequently, 'pre-annotating’ protein sequences with structural features, ensuring a high level of precision, could prove highly advantageous. In this paper, after a thorough investigation, we introduce a novel machine-learning model capable of classifying any protein domain, whether it has a known structure or not, into one of the 40 main CATH Architectures. We achieve an F1 Score of 0.92 using only the amino acid sequence and a score of 0.94 using both the sequence of amino acids and the sequence of structural alphabets. Communicated by Ramaswamy H. Sarma