Low FPR Research Articles

Finite State GUI Testing with Test Case Prioritization Using Z-BES and GK-GRU

To deliver user-friendly experiences, modern software applications rely heavily on graphical user interfaces (GUIs). However, it is paramount to ensure the quality of these GUIs through effective testing. This paper proposes a novel “Finite state testing for GUI with test case prioritization using ZScore-Bald Eagle Search (Z-BES) and Gini Kernel-Gated recurrent unit (GK-GRU)” approach to enhance GUI testing accuracy and efficiency. First, historical project data is collected. Subsequently, by utilizing the Z-BES algorithm, test cases are prioritized, aiding in improving GUI testing. Attributes are then extracted from prioritized test cases, which contain crucial details. Additionally, a state transition diagram (STD) is generated to visualize system behavior. The state activity score (SAS) is then computed to quantify state importance using reinforcement learning (RL). Next, GUI components are identified, and their text values are extracted. Similarity scores between GUI text values and test case attributes are computed. Grounded on similarity scores and SAS, a fuzzy algorithm labels the test cases. Data representation is enhanced by word embedding using GS-BERT. Finally, the test case outcomes are predicted by the GK-GRU, validating the GUI performance. The proposed work attains 98% accuracy, precision, recall, f-measure, and sensitivity, and low FPR and FNR error rates of 14.2 and 7.5, demonstrating the reliability of the model. The proposed Z-BES requires only 5587 ms to prioritize the test cases, retaining less time complexity. Meanwhile, the GK-GRU technique requires 38945 ms to train the neurons, thus enhancing the computational efficiency of the system. In conclusion, experimental outcomes demonstrate that, compared with the prevailing approaches, the proposed technique attains superior performance.

An Intrusion Detection Method Based on Hybrid Machine Learning and Neural Network in the Industrial Control Field

Aiming at the imbalance of industrial control system data and the poor detection effect of industrial control intrusion detection systems on network attack traffic problems, we propose an ETM-TBD model based on hybrid machine learning and neural network models. Aiming at the problem of high dimensionality and imbalance in the amount of sample data in the massive data of industrial control systems, this paper proposes an IG-based feature selection method and an oversampling method for SMOTE. In the ETM-TBD model, we propose a hyperparameter optimization method based on Bayesian optimization used to optimize the parameters of the four basic machine learners in the model. By introducing a multi-head-attention mechanism, the Transformer module increases the attention between local features and global features, enabling the discovery of the internal relationship between features. Additionally, the BiGRU is used to preserve the temporal features of the dataset, while the DNN is used to extract deeper features. Finally, the SoftMax classifier is used to classify the output. By analyzing the results of the comparison and ablation experiments, it can be concluded that the F1-score of the ETM-TBD model on a robotic arm dataset is 0.9665 and the model has very low FNR and FPR scores of 0.0263 and 0.0081, respectively. It can be seen that the model in this paper is better than the traditional single machine learning algorithm as well as the algorithm lacking any of the modules.

Detection of Paroxysmal Atrial Fibrillation from Dynamic ECG Recordings Based on a Deep Learning Model.

Atrial fibrillation (AF) is one of the most common arrhythmias clinically. Aging tends to increase the risk of AF, which also increases the burden of other comorbidities, including coronary artery disease (CAD), and even heart failure (HF). The precise detection of AF is a challenge due to its intermittence and unpredictability. A method for the accurate detection of AF is still needed. A deep learning model was used to detect atrial fibrillation. Here, a distinction was not made between AF and atrial flutter (AFL), both of which manifest as a similar pattern on an electrocardiogram (ECG). This method not only discriminated AF from normal rhythm of the heart, but also detected its onset and offset. The proposed model involved residual blocks and a Transformer encoder. The data used for training were obtained from the CPSC2021 Challenge, and were collected using dynamic ECG devices. Tests on four public datasets validated the availability of the proposed method. The best performance for AF rhythm testing attained an accuracy of 98.67%, a sensitivity of 87.69%, and a specificity of 98.56%. In onset and offset detection, it obtained a sensitivity of 95.90% and 87.70%, respectively. The algorithm with a low FPR of 0.46% was able to reduce troubling false alarms. The model had a great capability to discriminate AF from normal rhythm and to detect its onset and offset. Noise stress tests were conducted after mixing three types of noise. We visualized the model's features using a heatmap and illustrated its interpretability. The model focused directly on the crucial ECG waveform where showed obvious characteristics of AF.

An efficacy analysis of data encryption architecture for cloud platform

In recent times, cloud computing is being utilized largely for storage and information sharing purposes in several established commercial segments, particularly those where online businesses are prevalent, such as Google, Amazon, etc. Cloud system presents several benefits to users in terms of easy operations, low implementation, and maintenance expenses. However, significant risks are encountered in the data security procedures of cloud systems. Although the area is frequently being analyzed and reformed, the concern of cloud data protection and user reliability remains under uncertainty due to growing cyber-attack schemes as well as cloud storage system errors. To deal with this risk and contribute to the endeavor of providing optimal data security solutions in cloud data storage and retrieval system, this paper proposes a Symmetric Searchable Encryption influenced Machine Learning based cloud data encryption and retrieval model. The proposed model enhances data security and employs an effective keyword ranking approach by using an Artificial Neural Network. The comparative assessment of the proposed model against multiclass SVM and Naïve Bayes has established the better operational potentiality of the model. The effectiveness of the proposed work is justified by the association between high TPR and low FPR. Further, a low CCR of 0.6973 adds up to the success of the proposed work.

Assessment of groundwater arsenic contamination using machine learning in Varanasi, Uttar Pradesh, India.

This paper presents a machine learning approach for classification of arsenic (As) levels as safe and unsafe in groundwater samples collected from the Indo-Gangetic region. As water is essential for sustaining life, heavy metals like arsenic pose a public health concern. In this study, various tree-based machine learning models namely Random Forest, Optimized Forest, CS Forest, SPAARC, and REP Tree algorithms have been applied to classify water samples. As per the guidelines of the World Health Organization (WHO), the arsenic concentration in water should not exceed 10 μg/L. The groundwater quality parameter was ranked using a classifier attribute evaluator for training and testing the models. Parameters obtained from the confusion matrix, such as accuracy, precision, recall, and FPR, were used to analyze the performance of models. Among all models, Optimized Forest outperforms other classifier as it has a high accuracy of 80.64%, a precision of 80.70%, recall of 97.87%, and a low FPR of 73.33%. The Optimized Forest model can be used to test new water samples for classification of arsenic in groundwater samples.

Hybrid Representation to Locate Vulnerable Lines of Code

Locating vulnerable lines of code in large software systems needs huge efforts from human experts. This explains the high costs in terms of budget and time needed to correct vulnerabilities. To minimize these costs, automatic solutions of vulnerabilities prediction have been proposed. Existing machine learning (ML)-based solutions face difficulties in predicting vulnerabilities in coarse granularity and in defining suitable code features that limit their effectiveness. To addressee these limitations, in the present work, the authors propose an improved ML-based approach using slice-based code representation and the technique of TF-IDF to automatically extract effective features. The obtained results showed that combining these two techniques with ML techniques allows building effective vulnerability prediction models (VPMs) that locate vulnerabilities in a finer granularity and with excellent performances (high precision (>98%), low FNR (<2%) and low FPR (<3%) which outperforms software metrics and are equivalent to the best performing recent deep learning-based approaches.

Detecting Android Malware and Classifying Its Families in Large-scale Datasets

To relieve the burden of security analysts, Android malware detection and its family classification need to be automated. There are many previous works focusing on using machine (or deep) learning technology to tackle these two important issues, but as the number of mobile applications has increased in recent years, developing a scalable and precise solution is a new challenge that needs to be addressed in the security field. Accordingly, in this article, we propose a novel approach that not only enhances the performance of both Android malware and its family classification, but also reduces the running time of the analysis process. Using large-scale datasets obtained from different sources, we demonstrate that our method is able to output a high F-measure of 99.71% with a low FPR of 0.37%. Meanwhile, the computation time for processing a 300K dataset is reduced to nearly 3.3 hours. In addition, in classification evaluation, we demonstrate that the F-measure, precision, and recall are 97.5%, 96.55%, 98.64%, respectively, when classifying 28 malware families. Finally, we compare our method with previous studies in both detection and classification evaluation. We observe that our method produces better performance in terms of its effectiveness and efficiency.

Brain Tumor Detection and Classification on MR Images by a Deep Wavelet Auto-Encoder Model.

The process of diagnosing brain tumors is very complicated for many reasons, including the brain’s synaptic structure, size, and shape. Machine learning techniques are employed to help doctors to detect brain tumor and support their decisions. In recent years, deep learning techniques have made a great achievement in medical image analysis. This paper proposed a deep wavelet autoencoder model named “DWAE model”, employed to divide input data slice as a tumor (abnormal) or no tumor (normal). This article used a high pass filter to show the heterogeneity of the MRI images and their integration with the input images. A high median filter was utilized to merge slices. We improved the output slices’ quality through highlight edges and smoothened input MR brain images. Then, we applied the seed growing method based on 4-connected since the thresholding cluster equal pixels with input MR data. The segmented MR image slices provide two two-layer using the proposed deep wavelet auto-encoder model. We then used 200 hidden units in the first layer and 400 hidden units in the second layer. The softmax layer testing and training are performed for the identification of the MR image normal and abnormal. The contribution of the deep wavelet auto-encoder model is in the analysis of pixel pattern of MR brain image and the ability to detect and classify the tumor with high accuracy, short time, and low loss validation. To train and test the overall performance of the proposed model, we utilized 2500 MR brain images from BRATS2012, BRATS2013, BRATS2014, BRATS2015, 2015 challenge, and ISLES, which consists of normal and abnormal images. The experiments results show that the proposed model achieved an accuracy of 99.3%, loss validation of 0.1, low FPR and FNR values. This result demonstrates that the proposed DWAE model can facilitate the automatic detection of brain tumors.

Ultrasound guided needle biopsy of axilla to evaluate nodal metastasis after preoperative systemic therapy in cohort of 106 breast cancers enriched with BRCA1/2 pathogenic variant carriers

BackgroundAim of the study is to evaluate the role of ultrasound guided fine needle aspiration cytology (FNAC) in the restaging of node positive breast cancer after preoperative systemic therapy (PST).MethodsFrom January 2016 – October 2020 106 node positive stage IIA-IIIC breast cancer cases undergoing PST were included in the study. 18 (17 %) were carriers of pathogenic variant in BRCA1/2. After PST restaging of axilla was performed with ultrasound and FNAC of the marked and/or the most suspicious axillary node. In 72/106 cases axilla conserving surgery and in 34/106 cases axillary lymph node dissection (ALND) was performed.ResultsFalse Positive Rate (FPR) of FNAC after PST in whole cohort and BRCA1/2 positive subgroup is 8 and 0 % and False Negative Rate (FNR) – 43 and 18 % respectively. Overall Sensitivity − 55 %, specificity- 93 %, accuracy 70 %.ConclusionFNAC after PST has low FPR and is useful to predict residual axillary disease and to streamline surgical decision making regarding ALND both in BRCA1/2 positive and negative subgroups. FNR is high in overall cohort and FNAC alone are not able to predict ypCR and omission of further axillary surgery. However, FNAC performance in BRCA1/2 positive subgroup is more promising and further research with larger number of cases is necessary to confirm the results.

Synthesis, biological evaluation, molecular modeling, and structural analysis of new pyrazole and pyrazolone derivatives as N-formyl peptide receptors agonists.

N‐formyl peptide receptors (FPR1, FPR2, and FPR3) play key roles in the regulation of inflammatory processes, and recently, it was demonstrated that FPR1 and FPR2 have a dual role in the progression/suppression of some cancers. Therefore, FPRs represent an important therapeutic target for the treatment of both cancer and inflammatory diseases. Previously, we identified selective or mixed FPR agonists with pyridazinone or pyridinone scaffolds showing a common 4‐(bromophenyl)acetamide fragment, which was essential for activity. We report here new pyrazole and pyrazolone derivatives as restricted analogues of the above 6‐membered compounds, all exhibiting the same 4‐bromophenylacetamide side chain. Most new products had low or absent FPR agonist activity, suggesting that the pyrazole nucleus was not appropriate for FPR agonists. This hypothesis was confirmed by molecular modeling studies, which highlighted that the five‐membered scaffold was responsible for a worse arrangement of the molecules in the receptor binding site.

Deep Learning-Based Stroke Disease Prediction System Using Real-Time Bio Signals.

The emergence of an aging society is inevitable due to the continued increases in life expectancy and decreases in birth rate. These social changes require new smart healthcare services for use in daily life, and COVID-19 has also led to a contactless trend necessitating more non-face-to-face health services. Due to the improvements that have been achieved in healthcare technologies, an increasing number of studies have attempted to predict and analyze certain diseases in advance. Research on stroke diseases is actively underway, particularly with the aging population. Stroke, which is fatal to the elderly, is a disease that requires continuous medical observation and monitoring, as its recurrence rate and mortality rate are very high. Most studies examining stroke disease to date have used MRI or CT images for simple classification. This clinical approach (imaging) is expensive and time-consuming while requiring bulky equipment. Recently, there has been increasing interest in using non-invasive measurable EEGs to compensate for these shortcomings. However, the prediction algorithms and processing procedures are both time-consuming because the raw data needs to be separated before the specific attributes can be obtained. Therefore, in this paper, we propose a new methodology that allows for the immediate application of deep learning models on raw EEG data without using the frequency properties of EEG. This proposed deep learning-based stroke disease prediction model was developed and trained with data collected from real-time EEG sensors. We implemented and compared different deep-learning models (LSTM, Bidirectional LSTM, CNN-LSTM, and CNN-Bidirectional LSTM) that are specialized in time series data classification and prediction. The experimental results confirmed that the raw EEG data, when wielded by the CNN-bidirectional LSTM model, can predict stroke with 94.0% accuracy with low FPR (6.0%) and FNR (5.7%), thus showing high confidence in our system. These experimental results demonstrate the feasibility of non-invasive methods that can easily measure brain waves alone to predict and monitor stroke diseases in real time during daily life. These findings are expected to lead to significant improvements for early stroke detection with reduced cost and discomfort compared to other measuring techniques.

Mid-trimester prediction of spontaneous preterm birth with automated cervical quantitative ultrasound texture analysis and cervical length: a prospective study

The objective of this study was to evaluate a novel automated test based on ultrasound cervical texture analysis to predict spontaneous Preterm Birth (sPTB) alone and in combination with Cervical Length (CL). General population singleton pregnancies between 18 + 0 and 24 + 6 weeks’ gestation were assessed prospectively at two centers. Cervical ultrasound images were evaluated and the occurrence of sPTB before weeks 37 + 0 and 34 + 0 were recorded. CL was measured on-site. The automated texture analysis test was applied offline to all images. Their performance to predict the occurrence of sPTB before 37 + 0 and 34 + 0 weeks was evaluated separately and in combination on 633 recruited patients. AUC for sPTB prediction before weeks 37 and 34 respectively were as follows: 55.5% and 65.3% for CL, 63.4% and 66.3% for texture analysis, 67.5% and 76.7% when combined. The new test improved detection rates of CL at similar low FPR. Combining the two increased detection rate compared to CL alone from 13.0 to 30.4% for sPTB < 37 and from 14.3 to 42.9% sPTB < 34. Texture analysis of cervical ultrasound improved sPTB detection rate compared to cervical length for similar FPR, and the two combined together increased significantly prediction performance. This results should be confirmed in larger cohorts.

ВЗАИМОСВЯЗЬ ХИМИЧЕСКОГО СОСТАВА МОЛОКА С ВЕЛИЧИНАМИ ДИАГНОСТИЧЕСКИХ ПОКАЗАТЕЛЕЙ ИНТЕНСИВНОСТИ ОБМЕНА ВЕЩЕСТВ

It was found that, in accordance with the selected analysis criteria, in the studied animal population in 17.05 % of cows, FPR corresponded to the optimal values, and in 82.95 % it deviated to the lower side and amounted to 1.10 or less. FPR tended to decrease as the milk productivity of animals increased, and increased as soon as the milk productivity of animals began to decrease in the dynamics of milk days. In the group of animals with FPR 1.10 or less, the content of BHBA in milk significantly (by 80.0 %, p &lt;0.01) exceeded the content of BHBA in animals with normal FPR val-ues. In cows with a normal FPR value, the level of acetone in milk was higher than the threshold by 28.57 %, while in animals with low FPR values, the established significant excess was 141.43 % (p &lt;0.05). With the deviation of the FPR downward, an average negative reliable relationship of this indicator with the level of acetone was revealed (r = -0.572, p &lt;0.01). Between the content of BHBA and acetone, an average positive significant relationship was established with FPR less than 1.10 and with FPR from 1.11-1.50, and in the first case, the relationship is stronger.

A Review of Malware Classification Methods using Machine Learning

This paper talks about methods, problems and solutions to Malware Classification using Machine Learning. It is believed that the amount of malicious software being released might surpass the release of authoritative software. Since malware gets more sophisticated every year, this results in a need to shift from traditional methods and make the system automatically learn. The main focus here is studying machine learning methods along with their problems for detection and classification. Feature selection and high false-positive problems are explained and solutions to them are presented. Opcode, n-gram opcode, image-based classification techniques and are then compared. These methods will help cleaning malware and to classify them into their families. The results based on accuracy are better when using n-gram opcode classification as compared to normal opcode and image-based classifiers but using an ensemble method combines the benefits of both methods like less overfitting and low FPR, eventually the results display increased classification accuracy and provide overall better classification of malware.

Design and Development of an Efficient Network Intrusion Detection System Using Machine Learning Techniques

Today’s internets are made up of nearly half a million different networks. In any network connection, identifying the attacks by their types is a difficult task as different attacks may have various connections, and their number may vary from a few to hundreds of network connections. To solve this problem, a novel hybrid network IDS called NID‐Shield is proposed in the manuscript that classifies the dataset according to different attack types. Furthermore, the attack names found in attack types are classified individually helping considerably in predicting the vulnerability of individual attacks in various networks. The hybrid NID‐Shield NIDS applies the efficient feature subset selection technique called CAPPER and distinct machine learning methods. The UNSW‐NB15 and NSL‐KDD datasets are utilized for the evaluation of metrics. Machine learning algorithms are applied for training the reduced accurate and highly merit feature subsets obtained from CAPPER and then assessed by the cross‐validation method for the reduced attributes. Various performance metrics show that the hybrid NID‐Shield NIDS applied with the CAPPER approach achieves a good accuracy rate and low FPR on the UNSW‐NB15 and NSL‐KDD datasets and shows good performance results when analyzed with various approaches found in existing literature studies.

Leveraging Machine Learning Techniques to Identify Deceptive Decoy Documents Associated With Targeted Email Attacks

Detecting and preventing targeted email attacks is a long-standing challenge in cybersecurity research and practice. A typical targeted email attack capitalizes on a sophisticated email message to persuade a victim to run a specific, seemingly innocuous, action such as opening a link or an attachment and downloading and installing a software program. To successfully perform such an attack without being noticed afterwards, the attached exploit documents (hereafter referred to as decoy documents ), must contain content that is highly relevant to the target. An analysis of such decoy documents can provide crucial information for inferring and identifying the targeted or potentially harmed victims. In this paper, we propose an automatic approach that leverages natural language processing and machine learning to identify decoy documents that have a high chance of deceiving the targeted users. The experimental results show that the proposed method provides good prediction accuracy: the best result obtained on a collection of 200 Chinese decoy documents yielded an accuracy of 97.5%, an F-measure of 97.9% and a low FPR of 3.1%. The proposed scheme can be deployed at various access points to fortify the defense against targeted email attacks that threaten various targets.

Composite attacks‐based copy‐move image forgery detection using AKAZE and FAST with automatic contrast thresholding

Copy-move image forgery is one of the most popular image tampering technique which can be performed for vicious purposes. In this forgery technique, selected region is copied and pasted at different locations on the same image to produce a manipulated image. Such forgery is denigratory as it can alter the image content by hiding or appending visual information. In this study, the authors propose a novel keypoint-based technique to detect forged images sustaining composite attacks consisting of various combinations of geometrical and post-processing operations. In the authors' method, AKAZE and FAST techniques are used to extract keypoints from the image. Non-maximal value suppression with automatic contrast thresholding is performed during FAST keypoint extraction. SIFT and DAISY descriptors are computed corresponding to extracted keypoints. PCA is applied over SIFT and DAISY descriptors to discard lower components which are sensitive to distortions occurred in images. They apply a correlation-based nearest neighbour search technique to detect similarity among keypoint descriptors. HDBSCAN algorithm is applied to obtain matched keypoint clusters. Further, RANSAC algorithm is utilised for removal of keypoint outliers. In comparison to state-of-the-art techniques, their approach achieve high F-measure (%) and low FPR (%) for image-level as well as pixel-level copy-move forgery detection.

Improving the learning of self-driving vehicles based on real driving behavior using deep neural network techniques

Considering the significant advancements in autonomous vehicle technology, research in this field is of interest to researchers. To drive vehicles autonomously, controlling steer angle, gas hatch, and brakes needs to be learned. The behavioral cloning method is used to imitate humans’ driving behavior. We created a dataset of driving in different routes and conditions, and using the designed model, the output used for controlling the vehicle is obtained. In this paper, the learning of self-driving vehicles based on real driving behavior using deep neural network techniques (LSV-DNN) is proposed. We designed a convolutional network which uses the real driving data obtained through the vehicle’s camera and computer. The response of the driver during driving is recorded in different situations, and by converting the real driver’s driving video to images and transferring the data to an Excel file, obstacle detection is carried out with the best accuracy and speed using the Yolo algorithm version 3. This way, the network learns the response of the driver to obstacles in different locations and the network is trained with the Yolo algorithm version 3 and the output of obstacle detection. Then, it outputs the steer angle and amount of brake, gas, and vehicle acceleration. This study focuses on designing a convolutional network using behavioral cloning and motion planning of autonomous vehicle using a deep learning framework. Neural networks are effective systems for finding relationships between data, modeling, and predict new data or classify data. As a result Neural networks with input real data predict steer angle and speed for autonomous driving. The LSV-DNN is evaluated here via extensive simulations carried out in Python and TensorFlow environment. We evaluated the network error using the loss function. The results confirmed that our scheme is capable of exhibiting high prediction accuracy (exceeding 92.93%). In addition, our proposed scheme has high speed (more than 64.41%), low FPR (less than 6.89%), and low FNR (less than 3.95%), in comparison with the other approaches currently being employed. By comparing other methods which were conducted on the simulator’s data, we obtained good performance results for the designed network on the data from KITTI benchmark, the data collected using a private vehicle, and the data we collected.

Disease structure of milk cows and the effect of the mass fractions ratio of fat and protein in milk on the level of the metabolites

The analysis of diseases occurring is given in animals in the first 100 DIM. Determined milk content: MF, MP, pH, Ur, BHBA, Ac, calculated FPR. INCD in milk cows in the first 100 DIM is the second most widespread – 30.72 %. Among INCD, DSD and RSD predominate in the former – 38.8 % each, DMEO accounts for 20.4 % of disease cases. In 17.05 % of the examined animals, the FPR corresponded to optimal values, and in 82.95 % it was 1.10 or less, which may indicate the spread of subacute subclinical rumen acidosis in the animals of the studied population. Exceeding the upper limit of FPR, indicating the presence of ketosis in animals, has not been established. Studies revealed a double excess of Ur content in milk, and in animals with normal FPR values, the Ur content was 11.15 % (p &lt; 0.001) higher than in animals with reduced FPR. The pH of milk generally corresponded to the values of the physiological norm. The level of BHBA in milk was below the threshold values, but in the animal’s group with FPR 1.10 or less, the BHBA content in milk significantly (by 80.0 %, p &lt; 0.01) exceeded the BHBA content in animals with normal FPR values. Cows with a normal FPR value, the Ac level in milk was found to exceed the threshold value by 28.57 %, and in animals with low FPR values, the established excess was 141.43 % (p &lt;0.05).

Three-way partial VUS

The AUC and VUS for the ROC curve and surface are well known measures in various statistical fields. Since the partial AUC has only conditions on the FPR, this overlapped condition under the constraints of the TPR may reduce the efficiency and accuracy of the performance evaluation. For obtaining better performance measurement for high TPR and low FPR, the two-way partial AUC was proposed. In this work, the partial and two-way partial AUC are defined using the probability concept, and these are expressed with integration equations. Moreover, the partial VUS and three-way partial VUS for ROC surface are also derived.