Fault detection is a process of quality assurance which aims to identify where a fault has occurred and pinpoint the type of fault. However, in the field of software engineering, researchers mainly focus on statically or dynamically analyzing faults or vulnerabilities after the program is completed, and there are few works proposed to detect hidden faults that can only be discovered during program execution during the programming process. In this paper, we propose an automatic fault detection technology called Program Segment Testing (PST) based on the idea of Human-Machine Pair Programming (HMPP), which can automatically detect program segments during the programming process and give prompts when there are vulnerabilities or faults that trigger runtime exceptions. First, we introduce some preliminary definitions and notations that are used in our technology. Then, we use the array index overflow exception as a case to introduce the PST in detail, point out the issues that need to be resolved in order to complete this technology and the corresponding solutions.

Cervical cancer may be avoided by having frequent tests to detect and cure precancers. The Pap analysis evaluates the cells of the cervix for any unusual or precancerous alterations. Therefore, manual Pap smear testing in the microscope is arbitrary, with criteria that is difficult to repeat. In the cervical cancer diagnostic method, image processing of Pap smears is critical. Our cervical cancer diagnostic system has four main components. Nuclei were recognized through a shape-based adaptive approach and redundant cytoplasm was segregated utilizing a marker-control watershed technique in cell division. Three essential characteristics were recovered from the areas of fragmented cytoplasm and nuclei during the characteristics extraction process. As a component extraction technique, the RF algorithm was applied. A bagging clustering algorithm was used in the classification step, which integrated the findings of five different classifiers: support vector machine, bagged trees, linear discriminant, boosted trees, and k-nearest neighbor. The efficacy of our suggested method was demonstrated using the Herlev datasets and SIPaKMeD. According to the observational data, the two-class accuracy rate of 95.12 percent and five-class accuracy rate of 96.12 percent was considerably better in 2 and 5 class tasks.

In the present work we propose a novel heterogeneous deep ensemble based multi-feature learning environment for diabetic mellitus prediction. The overall proposed model was designed in such manner that it addresses the key at hand problems like data or the class imbalance, low accuracy and lack of consensus. To achieve it, a multi-level enhancement approach where to address the problem of class-imbalance was performed, data sampling with 95% of confidence interval is performed. Different sampling approaches were applied such as random-sampling, down-sampling and synthetic minority oversampling technique (SMOTE). Once sample data is retrieved, we performed feature selection using different algorithms like Wilcoxon Significant Test, also called significant predictor test (SPR), Univariate Logistic Regression based feature selection (ULOGR), Cross-Correlation Analysis (CRA), Principle Component Analysis (PCA), Gini Score based significant feature selection (GSFR) and Information Gain based features (IGFR). The key purpose of applying different feature selection methods was to retain most suitable features for high accuracy with low computation. In the subsequent phase, we designed a first-of-its kind heterogenous deep ensemble model using Decision Tree (DT), Artificial Neural Network (ANN) with Radial Basis Function (RBF) and Levenberg Marquardt (LM) learning methods, Probabilistic Neural Network (PNN) and Support Vector Machine (SVM) algorithms as the base classifier. For the ensemble decision, Maximum Voting Ensemble (MVE) and Best Trained Ensemble (BTE) were applied for two-class classification, which predicts each sample of the Pima Indian dataset as diabetic or non-diabetic. The simulation-based performance comparison in terms of accuracy (91.56%), F-measure (0.91) and AUC (0.91) confirmed superiority of the proposed system over major existing approaches.

Internet of Things is drawing the attention of researchers due to its wide range of applications in emerging areas. To support interoperability in IoT, IETF has proposed 6LoWPAN. Due to the hardware limitations of IoT devices, it is presenting a lot of challenges mainly related to the routing. To address the issues in routing, IETF has proposed the Routing Protocol for Low-power and Lossy Networks (RPL). In the RPL protocol, an acyclic graph is constructed to exchange the data in between nodes. The RPL protocol is widely used in different applications. Even though the RPL protocol is used in various applications, there are several drawbacks and limitations that have been exposed by recent studies. Researchers have proposed several new solutions to address these issues. This paper discusses the limitations of the RPL protocol in routing the data and solutions proposed by different researchers as well as drawbacks of the proposed methodologies by various researchers.

The Internet of Things (IoT) is rapidly approaching its capability as the next Digital uprising. It enables smart objects to interact and collaborate, allowing us to share information that helps us to maintain a healthy lifestyle. Cloud computing, on the other hand, delivers on-demand, flexible, and adaptable network access, permitting devices to access computational resources which facilitates the integration of unstructured information from multiple data sources. Cloud and IoT services have profound influences that can have a significant effect on today's ever-growing digital life, as well as the need to address a myriad of challenges for each system, namely scalability, security, and reliability with real-world objects in a more versatile and decentralized manner. Therefore, IoT requires more data storage and computation power. Cloud computing delivers on-demand accessibility of network assets especially for data storage and computing power to share the resources. Several architectures have been undergone with the literature to integrate these two technologies by using current computing paradigms, namely FOG and EDGE computing. This platform can use Cloud resources and services to gather, transmit, analyze, process, and store data created by a variety of sources. With this integration, we can resolve storage and computation issues. Moreover, in many applications, the integration plays a vital role in producing automated services and solutions without any delay.

The sensory system of human upper limbs is controlled by the brachial plexus nerves. Upper limb surgical anesthesia is based on accurately segmenting this nerve system using ultrasound scans. The incorporation of images can include many types of noise. Speckle noise is one of the common noises introduced during the capturing of ultrasound images, and denoising of this is one of the major challenges as it causes a lot of trouble for clinicians during the diagnosis process. Cellular Automata is a computational model that uses simple rules to represent a complex system. It has been used extensively in image processing operations. Because of the ease with which a digital image may be mapped to a cellular automaton and the ability to perform different image processing procedures in real time, it appears to be a natural tool for image processing. In this paper a novel cellular automaton based despeckling filter for ultrasound images of brachial plexus nerves is suggested and its effect is compared with the various existing noise filters such as Kuan, Lee, Lee diffusion, frost diffusion and wavelet filter. Results are compared and analyzed both qualitatively and quantitatively. Various parameters such as mean square error, signal to noise ratio, square root mean square error, peak signal to noise ratio, structured similarity index are used for quantitative comparison. The effect of all filters under consideration have been analyzed at low, medium, and high levels of noise in ultrasound images. It has been observed that the proposed filter performs well both in terms of noise filtering as well as retaining the structure of the original image in most cases. For qualitative analysis, expert opinion of scientific officer grade D at ACTREC, Mumbai has been considered.

The present scenario has seen a sharp increase in the use of composites in the field of manufacturing due to their esteemed strength. In this paper, research has been done on Al Metal Matrix Composite. Aluminium alloy of Al 2024 has been chosen as the matrix and Ni-Ti powder is used as the reinforcement. The stir casting process has been adopted for the preparation of the metal matrix composite, where the reinforcement is mixed in definite proportions of 2%, 4%, 6% and 8% with the matrix. Different tests have been conducted to study the mechanical and tribological properties of the composite. The flexural stress of ASTM standard E 290-14 is at 0% and 6% inclusion of Ni-Ti Powder in Al 2024 while the specimen with 2%, 4% and 8% inclusion of Ni-Ti Powder in Al 2024 exhibited Lower Flexure Modulus. The Vickers hardness test of ASTM E384-17 standard revealed that with an increase in the weight percentage of the reinforcement, there has been an increase in the hardness of the composite. Topography test images indicated that the sum of peak values obtained determines the crystallinity of the given specimen.