Classification Algorithm Research Articles

Near-Term Quantum Classification Algorithms Applied to Antimalarial Drug Discovery.

Computational approaches are widely applied in drug discovery to explore properties related to bioactivity, physiochemistry, and toxicology. Over at least the last 20 years, the exploitation of machine learning on molecular data sets has been used to understand the structure-activity relationships that exist between biomolecules and druggable targets. More recently, these methods have also seen application for phenotypic screening data for neglected diseases such as tuberculosis and malaria. Herein, we apply machine learning to build quantum Quantitative Structure Activity Relationship models from antimalarial data sets. There is a continual need for new antimalarials to address drug resistance, and the readily available in vitro data sets could be utilized with newer machine learning approaches as these develop. Furthermore, quantum machine learning is a relatively new method that uses a quantum computer to perform the calculations. First, we present a classical-quantum hybrid computational approach by building a Latent Bernoulli Autoencoder machine learning model for compressing bit-vector descriptors to a size that can be adapted to quantum computers for classification tasks with limited loss of embedded information. Second, we apply our method for feature map compression to quantum classification algorithms, including a completely novel machine learning algorithm with no analogy in classical computers: the Quantum Fourier Transform Classifier. We apply both these approaches to build quantum machine learning models for small-molecule antimalarials with quantum simulation software and then benchmark these quantum models against classical machine learning approaches. While there are many challenges currently facing the development of reliable quantum computers, our results demonstrate that there is potential for the use of this technology in the field of drug discovery.

Spectral sensor‐based device for real‐time detection and severity estimation of groundnut bud necrosis virus in tomato

AbstractA machine learning‐based approach was utilized to develop a device for groundnut bud necrosis virus (GBNV) disease severity detection and estimation in tomato plants (Solanum lycopersicum L.). The study involved inoculating tomato plants with GBNV, monitoring changes in morphological and spectral characteristics, evaluating machine learning algorithms (decision tree [DT] classifier) for analysis and classification of disease severity, and developing and validating a device for disease detection and severity estimation. Spectral data analysis revealed distinct patterns in reflectance, with notable peaks observed in the 680 and 760 nm bands, while reflectance remained low and constant beyond 900 nm. Machine learning techniques, specifically a DT model, were employed to classify disease severity based on spectral data with high accuracy (95.01% training accuracy and 93.65% testing accuracy). The model identified the near‐infrared band as highly correlated (correlation coefficient of 0.82) with disease severity. Furthermore, a compact handheld device integrating a spectral sensor, organic light‐emitting diode display, and Raspberry Pi 3B was developed for real‐time disease severity estimation. The device demonstrated robust performance, accurately predicting disease severity at different growth stages, even in the absence of visible symptoms. Additionally, disease severity percentages obtained via reverse transcription polymerase chain reaction were used to validate the accuracy of the device's estimations. Its responsive nature, with estimated response times ranging from milliseconds to seconds, facilitates timely interventions in agricultural settings. Overall, this interdisciplinary approach, combining spectral analysis, machine learning, and device development, presents a promising solution for efficient disease monitoring and management in agriculture, contributing to enhanced crop health and food security.

Optimizing Convolutional Neural Networks for Image Classification on Resource-Constrained Microcontroller Units

Running machine learning algorithms for image classification locally on small, cheap, and low-power microcontroller units (MCUs) has advantages in terms of bandwidth, inference time, energy, reliability, and privacy for different applications. Therefore, TinyML focuses on deploying neural networks on MCUs with random access memory sizes between 2 KB and 512 KB and read-only memory storage capacities between 32 KB and 2 MB. Models designed for high-end devices are usually ported to MCUs using model scaling factors provided by the model architecture’s designers. However, our analysis shows that this naive approach of substantially scaling down convolutional neural networks (CNNs) for image classification using such default scaling factors results in suboptimal performance. Consequently, in this paper we present a systematic strategy for efficiently scaling down CNN model architectures to run on MCUs. Moreover, we present our CNN Analyzer, a dashboard-based tool for determining optimal CNN model architecture scaling factors for the downscaling strategy by gaining layer-wise insights into the model architecture scaling factors that drive model size, peak memory, and inference time. Using our strategy, we were able to introduce additional new model architecture scaling factors for MobileNet v1, MobileNet v2, MobileNet v3, and ShuffleNet v2 and to optimize these model architectures. Our best model variation outperforms the MobileNet v1 version provided in the MLPerf Tiny Benchmark on the Visual Wake Words image classification task, reducing the model size by 20.5% while increasing the accuracy by 4.0%.

Using Nighttime Light Data to Explore the Extent of Power Outages in the Florida Panhandle after 2018 Hurricane Michael

The destructive forces of tropical cyclones can have significant impacts on the land, contributing to degradation through various mechanisms such as erosion, debris, loss of vegetation, and widespread damage to infrastructure. Storm surge and flooding can wash away buildings and other structures, deposit debris and sediments, and contaminate freshwater resources, making them unsuitable for both human use and agriculture. High winds and flooding often damage electrical disubstations and transformers, leading to disruptions in electricity supply. Restoration can take days or even weeks, depending on the extent of the damage and the resources available. In the meantime, communities affected by power outages may experience difficulties accessing essential services and maintaining communication. In this study, we used a weighted maximum likelihood classification algorithm to reclassify NOAA’s National Geodetic Survey Emergency Response Imagery scenes into debris, sand, water, trees, and roofs to assess the extent of the damage around Mexico Beach, Florida, following the 2018 Hurricane Michael. NASA’s Visible Infrared Imaging Radiometer Suite (VIIRS) Day/Night Band (DNB) was processed to estimate power outage duration and rate of restoration in the Florida Panhandle based on the 7-day moving averages. Percent loss of electrical service at a neighborhood level was estimated using the 2013–2017 American Community Survey block group data. Spatial lag models were employed to examine the association between restoration rates and socioeconomic factors. The analysis revealed notable differences in power-restoration rates between urbanized and rural areas and between disadvantaged and more affluent communities. The findings indicated that block groups with higher proportions of minorities, multi-family housing units, rural locations, and households receiving public assistance experienced slower restoration of power compared to urban and more affluent neighborhoods. These results underscore the importance of integrating socioeconomic factors into disaster preparedness and recovery-planning efforts, emphasizing the need for targeted interventions to mitigate disparities in recovery times following natural disasters.

Voice Recognition Based on Machine Learning Classification Algorithms: A Review

One essential component of biometric identity is voice recognition technology, which uses speech pattern analysis to authenticate people. With an emphasis on machine learning classification techniques, this review article thoroughly examines the field of speech recognition. We examine the effectiveness of random forest (RF), multilayer perceptrons (MLP), k-nearest neighbours (KNN), and support vector machine (SVM) classifiers via painstaking analysis and empirical evaluation. Utilizing a collection of Sepedi speech audio files, our results demonstrate the remarkable accuracy of 99.86% that RF is capable of producing. Aside from visual aids for better understanding, assessment indicators like as accuracy, precision, recall, F-measure, and root mean square error (RMSE) clarify the effectiveness of the model. The research highlights how machine learning algorithms, especially reinforcement learning (RF), have the capacity to revolutionize speech recognition technology in a variety of contexts.

An Analysis of Traditional Methods and Deep Learning Methods in SSVEP-Based BCI: A Survey

The brain–computer interface (BCI) is a direct communication channel between humans and machines that relies on the central nervous system. Neuroelectric signals are collected by placing electrodes, and after feature sampling and classification, they are converted into control signals to control external mechanical devices. BCIs based on steady-state visual evoked potential (SSVEP) have the advantages of high classification accuracy, fast information conduction rate, and relatively strong anti-interference ability, so they have been widely noticed and discussed. From k-nearest neighbor (KNN), multilayer perceptron (MLP), and support vector machine (SVM) classification algorithms to the current deep learning classification algorithms based on neural networks, a wide variety of discussions and analyses have been conducted by numerous researchers. This article summarizes more than 60 SSVEP- and BCI-related articles published between 2015 and 2023, and provides an in-depth research and analysis of SSVEP-BCI. The survey in this article can save a lot of time for scholars in understanding the progress of SSVEP-BCI research and deep learning, and it is an important guide for designing and selecting SSVEP-BCI classification algorithms.

Optimizing waste management strategies through artificial intelligence and machine learning - An economic and environmental impact study

Applying artificial intelligence (AI) and machine learning (ML) techniques to optimize waste management strategies, focusing on enhancing economic efficiency and reducing environmental impact, is vital. The study utilized ML models to analyze and forecast waste generation trends, assess the viability of various waste management methods, and develop optimization models for resource allocation and operational efficiency. The research employs the World Bank’s comprehensive waste management dataset. After rigorous data preprocessing, including cleaning and feature selection, a variety of ML techniques, such as regression models, classification algorithms like Support Vector Machines (SVM), Random Forest (RF), Extreme Gradient Boosting (XGBoost), and optimization algorithms, including linear programming, are applied. Unlike other research, this study achieved 85 % accuracy on predictive analytics models for forecasting waste generation trends, primarily attributed to integrating more diverse data sets, including socio-economic factors. Also, the optimization resource allocation achieved a 15 % increase in operational efficiency. These findings provide significant insights for policymakers and urban planners, suggesting that integrating ML in waste management can lead to more sustainable and cost-effective practices. This paper demonstrates the transformative potential of ML in optimizing waste management strategies, offering a pathway towards more sustainable and economically viable waste management solutions globally.

An experimental review of the ensemble-based data stream classification algorithms in non-stationary environments

Data streams are sequences of fast-growing and high-speed data points that typically suffer from the infinite length, large volume, and specifically unstable data distribution. Ensemble learning as a prevalent classification approach is widely used in data stream mining studies. Besides the impressive performance of ensemble learning algorithms in providing a collection of diverse and accurate classifiers, they are specifically efficient in handling non-stationary data streams. Due to the component-based nature and the chance of dynamic updates for the components of the ensemble, this category is appropriate for dynamically learning the changing concepts of the data. Several review research have been conducted on the challenges of non-stationary data streams so far. None of the available surveys are dedicated to examine the effect of ensemble learning models on concept drift handling. This paper aims to provide a thorough theoretical and experimental review of the most significant ensemble-based data stream classification approaches in confronting with various types of concept drifts. In this comprehensive experimental analysis, 21 state-of-the-art ensemble algorithms are tested on 30 synthetic datasets under various types and volumes of concept drifts. This experimental analysis involves analyzing the classification accuracy, kappa score and running time of the algorithms, along with performing various statistical tests. In addition to conducting experimental analysis, a comprehensive investigation is carried out on the most significant challenges posed by non-stationary data streams, which provides the reader with valuable insights.

Interatrial Communications: Prevalence and Subtypes in 12,385 Newborns-a Copenhagen Baby Heart Study.

The prevalence of interatrial communications in newborns, i.e., patent foramen ovale or atrial septal defect, was previously reported to be between 24 and 92%, but the area has been impeded by lack of a universal classification method. A recently published novel echocardiographic diagnostic algorithm for systematic classification of interatrial communications had inter-and intraobserver agreements superior to standard expert assessment. This study aimed to determine the prevalence of subtypes of interatrial communications on transthoracic echocardiography in newborns. Echocardiograms of newborns aged 0-30days were prospectively collected in the population-based cohort study Copenhagen Baby Heart Study in 2017-2018 and analyzed according to the new diagnostic algorithm, classifying interatrial communications into three subtypes of patent foramen ovale and three subtypes of atrial septal defects. Echocardiograms from 15,801 newborns were analyzed; 3416 (21.6%) were excluded due to suboptimal image quality or severe structural heart disease (n = 3), leaving 12,385 newborns (aged 12 [interquartile range 8; 15] days, 48.2% female) included in the study. An interatrial communication was detected in 9766 (78.9%) newborns. According to the algorithm, 9029 (72.9%) had a patent foramen ovale, while 737 (6.0%) fulfilled criteria for an atrial septal defect, further divided into subtypes. An interatrial communication was seen on echocardiography in almost 80% of newborns aged 0-30days. Patent foramen ovale was 12 times more frequent than atrial septal defects. The observed prevalence of atrial septal defects was higher than previously reported. Follow up studies could distinguish which interatrial communications require follow-up or intervention. ClinicalTrial.gov, NCT02753348, posted April 27, 2016, [ https://classic.clinicaltrials.gov/ct2/show/NCT02753348 ].

Fine-Grained Few-Shot Image Classification Based on Feature Dual Reconstruction

Fine-grained few-shot image classification is a popular research area in deep learning. The main goal is to identify subcategories within a broader category using a limited number of samples. The challenge stems from the high intra-class variability and low inter-class variability of fine-grained images, which often hamper classification performance. To overcome this, we propose a fine-grained few-shot image classification algorithm based on bidirectional feature reconstruction. This algorithm introduces a Mixed Residual Attention Block (MRA Block), combining channel attention and window-based self-attention to capture local details in images. Additionally, the Dual Reconstruction Feature Fusion (DRFF) module is designed to enhance the model’s adaptability to both inter-class and intra-class variations by integrating features of different scales across layers. Cosine similarity networks are employed for similarity measurement, enabling precise predictions. The experiments demonstrate that the proposed method achieves classification accuracies of 96.99%, 98.53%, and 89.78% on the CUB-200-2011, Stanford Cars, and Stanford Dogs datasets, respectively, confirming the method’s efficacy in fine-grained classification tasks.

Eigen-entropy based time series signatures to support multivariate time series classification

Most current algorithms for multivariate time series classification tend to overlook the correlations between time series of different variables. In this research, we propose a framework that leverages Eigen-entropy along with a cumulative moving window to derive time series signatures to support the classification task. These signatures are enumerations of correlations among different time series considering the temporal nature of the dataset. To manage dataset’s dynamic nature, we employ preprocessing with dense multi scale entropy. Consequently, the proposed framework, Eigen-entropy-based Time Series Signatures, captures correlations among multivariate time series without losing its temporal and dynamic aspects. The efficacy of our algorithm is assessed using six binary datasets sourced from the University of East Anglia, in addition to a publicly available gait dataset and an institutional sepsis dataset from the Mayo Clinic. We use recall as the evaluation metric to compare our approach against baseline algorithms, including dependent dynamic time warping with 1 nearest neighbor and multivariate multi-scale permutation entropy. Our method demonstrates superior performance in terms of recall for seven out of the eight datasets.

Novel mining conveyor monitoring system based on quasi-distributed optical fiber accelerometer array and self-supervised learning

Belt conveyors in mining are crucial, with downtime leading to significant losses and safety hazards. Unplanned shutdowns often result from idler failures. To address this, an online monitoring system for continuous idler health assessment is proposed. Considering the large number and dense spatial distribution of idlers over long distances, this work presents a system that utilizes a quasi-distributed optical fiber accelerometer array. This array incorporates phase-sensitive optical time domain reflectometry (Phase-OTDR) interrogation technology and ultra-weak fiber Bragg gratings (UWFBGs) to effectively capture idler vibrations. The designed array achieves high-sensitivity vibration sensing with a sensitivity of 2.4 rad/g and a resolution of 1.7 mg/Hz. After collecting the vibrations of idlers by the designed accelerometer array, an automatic fault classification algorithm based on self-supervised learning (SSL) is introduced, which requires only a small number of labeled samples. By leveraging large amount of unlabeled data in the pretext task, the algorithm efficiently extracts latent features from the quasi-distributed accelerometer array. A diagnosis accuracy of 95.37 % can be achieved on a seven-class classification task with only 3.6 % labeled data (16 samples/class). This system offers a promising solution for idler monitoring, combining high sensitivity, distributed measurement capabilities, enhanced security, and superior fault detection accuracy.

Towards electrophysiological measurement of presence in virtual reality through auditory oddball stimuli

Objective. Presence is an important aspect of user experience in virtual reality (VR). It corresponds to the illusion of being physically located in a virtual environment (VE). This feeling is usually measured through questionnaires that disrupt presence, are subjective and do not allow for real-time measurement. Electroencephalography (EEG), which measures brain activity, is increasingly used to monitor the state of users, especially while immersed in VR. Approach. In this paper, we present a way of evaluating presence, through the measure of the attention dedicated to the real environment via an EEG oddball paradigm. Using breaks in presence, this experimental protocol constitutes an ecological method for the study of presence, as different levels of presence are experienced in an identical VE. Main results. Through analysing the EEG data of 18 participants, a significant increase in the neurophysiological reaction to the oddball, i.e. the P300 amplitude, was found in low presence condition compared to high presence condition. This amplitude was significantly correlated with the self-reported measure of presence. Using Riemannian geometry to perform single-trial classification, we present a classification algorithm with 79% accuracy in detecting between two presence conditions. Significance. Taken together our results promote the use of EEG and oddball stimuli to monitor presence offline or in real-time without interrupting the user in the VE.

A comparative study of deep learning models and classification algorithms for chemical compound identification and Tox21 prediction

Chemical compound classification, toxicity prediction, and environmental risk assessments are critically important in various applications within the field of chemistry. Deep learning models provide highly effective tools for extracting features from complex large datasets and performing classification tasks. Four different deep learning models, namely ResNet50V2, VGG19, InceptionV3, and MobileNetV2, have been compared with the random forest (RF) and k-nearest neighbors (KNN) algorithms. The results obtained from experiments conducted using QRCODE images of the Tox21SMILES dataset demonstrate the effectiveness of deep learning models for classifying chemical compounds and showcase the performance of different classification algorithms. The findings of the study thoroughly evaluate the performance of deep learning models and classification algorithms in the task of chemical classification. While ResNet50V2 and VGG19 models achieve high accuracy and precision, InceptionV3 and MobileNetV2 models provide more balanced results. Additionally, in terms of classification algorithms, the k-nearest neighbors (KNN) algorithm generally outperforms the Random Forest (RF) algorithm. Although the RF algorithm achieves good accuracy, the KNN algorithm proves to be more effective in terms of sensitivity and F1 score. These results emphasize the factors to consider when choosing which deep learning model or classification algorithm to use in chemical classification tasks. In conclusion, this study presents a comprehensive analysis comparing the performance of deep learning models and classification algorithms in chemical classification tasks. The selection of the most suitable model and algorithm for a specific task supports achieving better results in the classification of chemical compounds and related applications.

The use of image classification to estimate flamingo abundance from aerial, drone and satellite imagery

The Lesser Flamingo Phoeniconaias minor is a Near Threatened species known to be highly gregarious and that can concentrate in large numbers at core foraging and breeding sites, yet is also known to disperse widely in search of suitable foraging habitat. The density of flamingos at occupied sites, together with frequent dispersal between foraging sites, poses significant challenges to obtaining reliable counts and associated population estimates. Our study tested the use of unmanned aerial vehicles (drones) imagery and high-resolution satellite imagery for producing density estimates of Lesser Flamingos at the only known breeding site in South Africa (Kamfers Dam, Northern Cape Province). We implemented a supervised classification approach using multiple supervised classification algorithms, including xgbTree, randomForest, nnet and GBM. The four supervised classification models performed very well at classifying flamingos from both drone and satellite imagery, with classification accuracies ranging between 0.98 and 0.99. The inclusion of an additional predictor (other than RGB bands) yielded the highest variable importance score and greatly increased model accuracy and predictive performance. Estimates of adult flamingos from drone imagery acquired across nesting mudflats on 5 February (n = 1 320) and 14 February (n = 330) 2019 suggested a 75% decline in incubating adults. Furthermore, a total of 16 134 (15 973–16 295) flamingos were estimated from drone imagery on 1 March 2019, and 17 291 (17 118–17 290) flamingos from satellite imagery on 19 March 2019. The modelled size of the creche across dates suggested a loss of 234 birds (4.5%) during the period of assessment, with the highest count estimating 5 218 juveniles. Our study successfully implemented machine learning classifiers that were able to detect and derive highly accurate counts of Lesser Flamingos from both drone and satellite imagery. This use of machine learning could greatly improve the efficiency of monitoring and associated conservation efforts underway for the Lesser Flamingo.

Compressed sensing: a discrete optimization approach

We study the Compressed Sensing (CS) problem, which is the problem of finding the most sparse vector that satisfies a set of linear measurements up to some numerical tolerance. CS is a central problem in Statistics, Operations Research and Machine Learning which arises in applications such as signal processing, data compression, image reconstruction, and multi-label learning. We introduce an ℓ2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\ell _2$$\\end{document} regularized formulation of CS which we reformulate as a mixed integer second order cone program. We derive a second order cone relaxation of this problem and show that under mild conditions on the regularization parameter, the resulting relaxation is equivalent to the well studied basis pursuit denoising problem. We present a semidefinite relaxation that strengthens the second order cone relaxation and develop a custom branch-and-bound algorithm that leverages our second order cone relaxation to solve small-scale instances of CS to certifiable optimality. When compared against solutions produced by three state of the art benchmark methods on synthetic data, our numerical results show that our approach produces solutions that are on average 6.22%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$6.22\\%$$\\end{document} more sparse. When compared only against the experiment-wise best performing benchmark method on synthetic data, our approach produces solutions that are on average 3.10%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$3.10\\%$$\\end{document} more sparse. On real world ECG data, for a given ℓ2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\ell _2$$\\end{document} reconstruction error our approach produces solutions that are on average 9.95%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$9.95\\%$$\\end{document} more sparse than benchmark methods (3.88%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$3.88\\%$$\\end{document} more sparse if only compared against the best performing benchmark), while for a given sparsity level our approach produces solutions that have on average 10.77%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$10.77\\%$$\\end{document} lower reconstruction error than benchmark methods (1.42%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$1.42\\%$$\\end{document} lower error if only compared against the best performing benchmark). When used as a component of a multi-label classification algorithm, our approach achieves greater classification accuracy than benchmark compressed sensing methods. This improved accuracy comes at the cost of an increase in computation time by several orders of magnitude. Thus, for applications where runtime is not of critical importance, leveraging integer optimization can yield sparser and lower error solutions to CS than existing benchmarks.

Research on high-speed classification and location algorithm for logistics parcels based on a monocular camera

The rapid development of the logistics industry has driven innovations in parcel sorting technology, among which the swift and precise positioning and classification of parcels have become key to enhancing the performance of logistics systems. This study aims to address the limitations of traditional light curtain positioning methods in logistics sorting workshops amidst high-speed upgrades. This paper proposes a high-speed classification and location algorithm for logistics parcels utilizing a monocular camera. The algorithm combines traditional visual processing methods with an enhanced version of the lightweight YOLOv5 object detection algorithm, achieving high-speed, high-precision parcel positioning. Through the adjustment of the network structure and the incorporation of new feature extraction modules and ECIOU loss functions, the model’s robustness and detection accuracy have been significantly improved. Experimental results demonstrate that this model exhibits outstanding performance on a customized logistics parcel dataset, notably enhancing the model's parameter efficiency and computational speed, thereby offering an effective solution for industrial applications in high-speed logistics supply.

Efficient Malware Detection in Android Devices to Improve Cyber Security

The project introduces a novel framework for detecting Android malware based on permissions, utilizing multiple linear regression methods. Permissions play a crucial role in the security of the Android operating system, serving as fundamental indicators of an application's behavior. Through static analysis, the framework extracts application permissions and employs machine learning techniques to conduct security analyses. Specifically, the framework employs multiple linear regression techniques to develop two classifiers for permission-based Android malware detection. These classifiers leverage the relationships between various permission attributes to accurately identify potentially malicious applications. Notably, the framework achieves notable performance levels using classification algorithms without the need for overly complex models. In the project, the existing system utilizes the Random Forest (RF) algorithm, while the proposed system adopts the Support Vector Machine (SVM) algorithm. Both algorithms are evaluated in terms of accuracy, with the results demonstrating that the proposed SVM approach outperforms the existing RF method. This highlights the effectiveness of SVM in accurately detecting Android malware based on permission analysis.

Fast Learning Network Algorithm for Voice Pathology Detection and Classification

Fast Learning Network Algorithm for Voice Pathology Detection and Classification

Clinical Pilot of Bacterial Transcriptional Profiling as a Combined Genotypic and Phenotypic Antimicrobial Susceptibility Test.

Antimicrobial resistance is a growing health threat, but standard methods for determining antibiotic susceptibility are slow and can delay optimal treatment, which is especially consequential in severe infections such as bacteremia. Novel approaches for rapid susceptibility profiling have emerged that characterize either bacterial response to antibiotics (phenotype) or detect specific resistance genes (genotype). GoPhAST-R is a novel assay, performed directly on positive blood cultures, that integrates rapid transcriptional response profiling with detection of key resistance gene transcripts, thereby providing simultaneous data on both phenotype and genotype. Here, we performed the first clinical pilot of GoPhAST-R on 42 positive blood cultures: 26 growing Escherichia coli, 15 growing Klebsiella pneumoniae, and 1 with both. An aliquot of each positive blood culture was exposed to 9 different antibiotics, lysed, then underwent rapid transcriptional profiling on the NanoString® platform; results were analyzed using an in-house susceptibility classification algorithm. GoPhAST-R achieved 95% overall agreement with standard antimicrobial susceptibility testing methods, with the highest agreement for beta-lactams (98%) and the lowest for fluoroquinolones (88%). Epidemic resistance genes including the extended spectrum beta-lactamase bla CTX-M-15 and the carbapenemase bla KPC were also detected within the population. This study demonstrates the clinical feasibility of using transcriptional response profiling for rapid resistance determination, although further validation with larger and more diverse bacterial populations will be essential in future work. GoPhAST-R represents a promising new approach for rapid and comprehensive antibiotic susceptibility testing in clinical settings.