From Sparse to Structured: A Diffusion-Enhanced and Feature-Aligned Framework for Coincidental Correctness Detection

Fault localization seeks to locate the suspicious statements possible for causing a program failure. Experimental evidence shows that fault localization effectiveness is affected adversely by the existence of coincidental correctness (CC) test cases, where a CC test case denotes the test case which executes a fault but no failure occurs. Even worse, CC test cases are prevailing in realistic testing and debugging, leading to a severe issue on fault localization effectiveness. Thus, it is indispensable to accurately detect CC test cases and alleviate their harmful effect on fault localization effectiveness.To address this problem, we propose NeuralCCD: a neural coincidental correctness detection approach by integrating multiple features. Specifically, NeuralCCD first leverages suspiciousness score, coverage ratio and similarity to define three CC detection features. Based on these CC detection features and CC labels, NeuralCCD utilizes multi-layer perceptron to learn a different feature-based model for a program, and finally combine the trained models of different programs as an ensemble system to detect CC test cases. To evaluate the effectiveness of NeuralCCD, we conduct large-scale experiments on 247 faulty version of five representative benchmarks and compare NeuralCCD with four state-of-the-art CC detection approaches. The experimental results show that NeuralCCD significantly improves the effectiveness of CC detection, e.g., NeuralCCD yields by at most 109.5%, 93% and 81.3% improvement of Top-1, Top-3 and Top-5 over Tech-I when utilized in Dstar formular.

Coincidental correctness (CC) is a situation during the execution of a test case, the buggy entity is executed, but the program behaves correctly as expected. Many automated fault localization (FL) techniques use runtime information to discover the underlying connection between the executed buggy entity and the failing test result. The existence of CC will weaken such connection, mislead the FL algorithms to build inaccurate models, and consequently, decrease the localization accuracy. To alleviate the adverse effect of CC on FL, CC detection techniques have been proposed to identify the possible CC tests via heuristic or machine learning algorithms. However, their performance on precision is not satisfactory since they overestimate the possible CC tests and are insufficient in learning the deep semantic features. In this work, we propose a novel <u>Tri</u>plet network-based <u>Co</u>incidental <u>Co</u>rrectness detection technique (<i>i.e.,</i> <b>TriCoCo</b>) to overcome the limitations of the prior works. <b>TriCoCo</b> narrows the possible CC tests by designing three features to identify genuine passing tests. Instead of using all tests as inputs by existing techniques, <b>TriCoCo</b> takes the identified genuine passing tests and failing ones to train a triplet model that can evaluate their relative distance. Finally, <b>TriCoCo</b> infers the probability of being a CC test of the test in the rest of the passing tests by using the trained triplet model. We conduct large-scale experiments to evaluate <b>TriCoCo</b> based on the widely-used Defects4J benchmark. The results demonstrate that <b>TriCoCo</b> can improve not only the precision of CC detection but also the effectiveness of FL techniques, <i>e.g.,</i> the precision of <b>TriCoCo</b> is 80.33<inline-formula><tex-math notation="LaTeX">$\%$</tex-math></inline-formula> on average, and <b>TriCoCo</b> boosts the efficacy of DStar by 18<inline-formula><tex-math notation="LaTeX">$\%$</tex-math></inline-formula>–74<inline-formula><tex-math notation="LaTeX">$\%$</tex-math></inline-formula> in terms of MFR metric when compared to seven state-of-the-art CC detection baselines.

Coincidental Correctness (CC) arises when a test case executes faulty entity in a program without causing a failure. This phenomenon injects noise into coverage information, as CC tests weaken the connection between faulty entities and test failures. Since many fault localization (FL) approaches relies on analyzing test execution traces to locate faulty entities, the compromised reliability of test results directly undermines FL accuracy. Furthermore, the detrimental effects of CC extend beyond fault localization to subsequent software maintenance tasks like automatic program repair. Therefore, identifying and mitigating CC tests becomes critical not only for enhancing FL but also for ensuring robust software quality assurance. Thus, we propose FusionCC: an approach that applies multiscale coverage features and handcrafted features to fuse complementary feature representations for CC test case detection. Specifically, FusionCC first refines original coverage data by filtering out noisy irrelevant elements, then extracts multiscale features from the refined matrix, and finally fuses the coverage and handcrafted features to generate highly informative feature representations for CC detection. FusionCC realizes a comprehensive fusion of complementary features across different scales and from diverse sources, which significantly enhances the accuracy of CC detection. To evaluate the effectiveness of FusionCC, we conduct large-scale experiments on 277 faulty versions of six representative benchmarks. The experimental results show that FusionCC significantly improves CC detection (e.g., average improvements of 50.93% precision and 82.03% in <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$F_{1}$</tex-math></inline-formula> value compared to state-of-the-art CC detection approaches) and fault localization effectiveness (e.g., 10.33, 19.33, 25.67 average faults can be found in terms of Top-1, Top-3, Top-5 metrics at relabel strategy compared with state-of-the-art FL approaches).

Compared with single emotion recognition, the emotional change detection of speech has greater practical values. However, there are only few researches on this subject at present. This paper presented a basic framework for emotional change detection. Firstly, the smoothing strategy was adopted and the effect of smoothing width was also investigated to improve the correct detection rate. Then four different smoothing functions were compared and that utilizing the mean value smoothing was considered as the elementary detection method. Finally, how window width and shift step affect the correct detection rate was analyzed and time precision of elementary method was evaluated. Experimental results demonstrated that the proposed framework is feasible and effective.

With the significant growth in medical imaging techniques and the demand for better processing of medical information, the mandate of automation in disease detection is also increasing. In the modern time, the nature of the diseases has also changed. The highly mortal diseases are becoming difficult to detect due to the high involvements of medical individual and high dependency of human knowledges. The human knowledge is prone to error and often criticized for longer time delay for processing information in disease detections. Thus, the demand from the modern computing and implementation based computational algorithms are to automate the medical disease detection processes with greater accuracy. One such disease with superior mortal rate is brain tumours or cancerous growth in the brain tissues. The regular medical practice approaches have demonstrated the challenges in detection of the tumours and more so the nature of the tumours. Ill detection of the tumour type or the shape of the tumour or the size of the tumours can lead to life threats. Thus, the need for automation in detection is the most expected form of replacements in place of manual diagnosis. Another challenge is the available data formats for such disease reports. The available reports for brain tumour are only in the form of magnetic resonance images or MR Images. The MR Images can cause higher obstacles for further processing as due to the capture process of the patient data. Often, it is observed that the noise present in the MR images makes the processing vulnerable in accuracy. A number of parallel research outcomes have demonstrated significant outcomes of detection of available tumours in the human brain using segmentation methods. Nonetheless, all parallel attempts are criticized for not able to model the growth or the nature of the tumours presents in the human brain. Thus, this work proposes a novel automated framework for detection of tumour types by deploying progressive segmentation and model the growth stages based on features. The parallel outcomes have outrun on detection accuracy due to the use of standard segmentation methods, which is designed for generic image processing and bound not to match the specificity of medical image processing. Thus, this work introduces a novel segmentation method, which is progressive in nature for higher accuracy. This work also outcomes into an automated feature extraction model for brain tumours. The major contribution of the work is to determine the nature of tumour and a sustainable prediction model for tumour stages inside the human brain. The work demonstrates high accuracy for correct detection and prediction of the patient’s life threats in in real time order to take timely medication for making the precious human life more precious.

Autonomous navigation systems depend on robust perception models to guarantee safe and effective operation regardless of the environment in which they find themselves. Therefore, heavy rain, fog or snow affecting the operation of traditional modes will negatively impact the performance of object sensing systems, with the outcome that correct detection becomes difficult. In this paper, we present an adaptive 4D Radar and LiDAR fusion framework for all-weather 3D object detection in autonomous driving. The proposed model uses 4D Radar's high-resolution spatial data and LiDAR's superior penetration ability synergistically, creating a complementary fusion that raises detection accuracy in hard environments. Conditional dynamic sensor fusion is adopted. According to the environmental conditions and the confidence levels of the sensors, sensor weights are adjusted adaptively. To improve occlusions and the performance of sensors in ways not formerly imagined, the framework integrates deep learning-based feature extraction, temporal consistency refinement and attention-driven fusion mechanism. In the resistant capacity of LiDAR and Radar-based object recognition, benchmark results from standard datasets and actual driving experiments show that the proposed method significantly outperforms both single modality approaches. This method lays a solid foundation for the development of resilient multi-sensor fusion methods which will increase the trustworthiness of autonomous perception systems in actual application scenarios.

We consider the problem of detect pedestrian under from images collected under various viewpoints. This paper utilizes a novel framework called locality-constrained affine subspace coding (LASC). Firstly, the positive training samples are clustered into similar entities which represent similar viewpoint. Then Principal Component Analysis (PCA) is used to obtain the shared feature of each viewpoint. Finally, the samples that can be reconstructed by linear approximation using their top- k nearest shared feature with a small error are regarded as a correct detection. No negative samples are required for our method. Histograms of orientated gradient (HOG) features are used as the feature descriptors, and the sliding window scheme is adopted to detect humans in images. The proposed method exploits the sparse property of intrinsic information and the correlations among the multiple-views samples. Experimental results on the INRIA and SDL human datasets show that the proposed method achieves a higher performance than the state-of-the-art methods in form of effect and efficiency.

Detection of bad smells refers to any indication in the program code of a execution that perhaps designate a issue, maintain the software and software evolution. Code Smell detection is a main challenging for software developers and their informal classification direct to the designing of various smell detection methods and software tools. It appraises 4 code smell detection tool in software like as a in Fusion, JDeodorant, PMD and Jspirit. In this research proposes a method for detection the bad code smells in software is called as code smell. Bad smell detection in software, OOSMs are used to identify the Source Code whereby Plug-in were implemented for code detection in which position of program initial code the bad smell appeared so that software refactoring can then acquire position. Classified the code smell, as a type of codes: long method, PIH, LPL, LC, SS and GOD class etc. Detection of the code smell and as a result applying the correct detection phases when require is significant to enhance the Quality of the code or program. The various tool has been proposed for detection of the code smell each one featured by particular properties. The main objective of this research work described our proposed method on using various tools for code smell detection. We find the major differences between them and dissimilar consequences we attained. The major drawback of current research work is that it focuses on one particular language which makes them restricted to one kind of programs only. These tools fail to detect the smelly code if any kind of change in environment is encountered. The base paper compares the most popular code smell detection tools on basis of various factors like accuracy, False Positive Rate etc. which gives a clear picture of functionality these tools possess. In this paper, a unique technique is designed to identify CSs. For this purpose, various object-oriented programming (OOPs)-based-metrics with their maintainability index are used. Further, code refactoring and optimization technique are applied to obtain low maintainability Index. Finally, the proposed scheme is evaluated to achieve satisfactory results. The results of the BFOA test defined that the lazy class caused framework defects in DLS, DR, and SE. However, the LPL caused no framework defects what so ever. The consequences of the connection rules test searched that the LCCS (Lazy Class Code Smell) caused structured defects in DE and DLS, which corresponded to the consequences of the BFOA test. In this research work, a proposed method is designed to verify the code smell. For this purpose, different OOPs based Software Metrics with their MI (Maintainability Index) are utilized. Further Code refactoring and optimization method id applied to attained the less maintainability index and evaluated to achieved satisfactory results.

The growing integration of smart technologies into residential environments has heightened their exposure to cybersecurity threats, thereby necessitating robust and intelligent intrusion detection systems (IDS). This study proposes a hybrid AI-driven intrusion detection framework tailored for smart home networks, leveraging the Extreme Gradient Boosting Classifier (XGBoost or XGBC) enhanced by three metaheuristic optimization techniques: the Arithmetic Optimization Algorithm (AOA), Horse Herd Optimization (HHO), and Wild Geese Algorithm (WGA). The performance of these hybrid schemes XGAO, XGHH, and XGWG was rigorously evaluated using a comprehensive dataset containing 148,518 labeled network traffic instances, compiled through data mining methods. The dataset includes diverse attributes such as source and destination bytes, service types, protocols, and various connection-related flags. Performance evaluation was conducted using four standard classification metrics: accuracy, precision, recall, and F1-score. Among all models, the hybrid XGAO scheme demonstrated superior performance, achieving a training accuracy of 0.991, outperforming the baseline XGBC model, which scored 0.946 under the same conditions. In the testing phase, XGAO maintained high generalizability with an accuracy of 0.987, compared to 0.953 for XGBC. The XGAO model also excelled in recall (0.989), precision (0.991), and F1-score (0.990) for correct detections. These findings affirm that integrating XGBoost with AOA significantly enhances the classification accuracy and reliability of intrusion detection systems in smart home environments. The study contributes to the development of resilient, adaptive IDS architectures capable of mitigating evolving cyber threats in the domain of intelligent residential technologies.

We propose a framework for automatic modeling, detection, and tracking of 3D objects with a Kinect. The detection part is mainly based on the recent template-based LINEMOD approach [1] for object detection. We show how to build the templates automatically from 3D models, and how to estimate the 6 degrees-of-freedom pose accurately and in real-time. The pose estimation and the color information allow us to check the detection hypotheses and improves the correct detection rate by 13% with respect to the original LINEMOD. These many improvements make our framework suitable for object manipulation in Robotics applications. Moreover we propose a new dataset made of 15 registered, 1100+ frame video sequences of 15 various objects for the evaluation of future competing methods.

In domain classification for spoken language understanding, correct detection of out-of-domain (OOD) utterances is crucial because it reduces confusion and unnecessary interaction costs between users and the systems. In the situation where both in-domain (ID) and OOD samples are available, our goal is to take advantage of OOD samples under the GAN-based framework for OOD detection. We propose a GAN-based OOD detector with OOD prior distribution and weighted loss (WOODP-GAN). The model consists of a GAN-based detector with OOD prior distribution for generating effective pseudo OOD samples, and a weighted loss function for balancing the loss of fake OOD samples against real OOD samples in the discriminator. Extensive experiments show our proposed WOODP-GAN model outperforms the existing methods in the benchmark dataset CLINC150.

In this paper, we apply the existing framework of anomaly-based intrusion detection (ABID) to the problem of detecting protocol-aware jammers. These types of jammers target MAC or NET layer control messages in an attempt to increase jamming effectiveness and remain harder to detect. ABID systems detect activities that deviate significantly from the normal profile. Signature recognition is based on storing signatures of known intrusion scenarios, and detecting the presence of these signatures in real-time. By choosing a suitable set of features, a high probability of correct detection can be achieved. Our proposed detection strategy involves tracking the statistics of signal-to-noise ratio (SNR) and packet type (critical or non-critical). An alternative strategy that only requires information about packet loss is also provided. Through simulation, we show that these types of jammers can be detected in a large portion of scenarios.

Gold-standard and improved framework for sperm head segmentation

The emergence of IoT devices has complicated the landscape of cybersecurity in ways that had never been experienced before, thereby, giving raise to the need for more developed methods that can assist in threat evaluation and deterrent. The work in the international scope analyses the particulars of the artificial intelligence-based anomaly detection in the IoT technology implementation including the perspectives of recent period between 2020 and 2024 of the various architectures’ effectiveness and their use in low-resource IoT environments. In this review, as well as in many other recent works carried out by other authors, it is observed that deep learning methods, such us Long Short-Term Memory (LSTM) networks and GRU-LSTM hybrid models, achieved the most accurate performance, ranging from 96% up to 99.9% correct detection. Our examination focuses on several aspects of IoT security, such as challenges at the device level, issues related to security at the network level, data security, and facets related to artificial intelligence concepts and architectures capable of addressing the challenges. The results of the study state that the AI techniques tend to be more efficient and have a high performance than the conventional methods before but have drawbacks for realistic application owing to lack of adequate resources, absence of standard practices and sophistication of new threats. The study also highlights the gaps that exist in addressing the current approaches and makes suggestions on what is to be done, such as the importance of developing

The COVID-19 pandemic, which affected over 400 million people worldwide and caused nearly 6 million deaths, has become a nightmare. Along with vaccination, self-testing, and physical distancing, wearing a well-fitted mask can help protect people by reducing the chance of spreading the virus. Unfortunately, researchers indicate that most people do not wear masks correctly, with their nose, mouth, or chin uncovered. This issue makes masks a useless tool against the virus. Recent studies have attempted to use deep learning technology to recognize wrong mask usage behavior. However, current solutions either tackle the mask/non-mask classification problem or require heavy computational resources that are infeasible for a computational-limited system. We focus on constructing a deep learning model that achieves high-performance results with low processing time to fill the gap in recent research. As a result, we propose a framework to identify mask behaviors in real-time benchmarked on a low-cost, credit-card-sized embedded system, Raspberry Pi 4. By leveraging transfer learning, with only 4–6 h of the training session on approximately 5,000 images, we achieve a model with accuracy ranging from 98 to 99% accuracy with the minimum of 0.1 s needed to process an image frame. Our proposed framework enables organizations and schools to implement cost-effective correct face mask usage detection on constrained devices.KeywordsFace mask detectionConvolution neural networkAIoT