Search

Background: Lung cancer, also known as lung carcinoma, has a high mortality rate; however, an early prediction helps to reduce the risk. In the current literature, various approaches have been developed for the prediction of lung carcinoma (at an early stage), but these still have various issues, such as low accuracy, high noise, low contrast, poor recognition rates, and a high false-positive rate, etc. Thus, in this research effort, we have proposed an advanced algorithm and combined two different types of deep neural networks to make it easier to spot lung melanoma in the early phases. Methods: We have used WDSI (weakly supervised dense instance-level lung segmentation) for laborious pixel-level annotations. In addition, we suggested an SS-CL (deep continuous learning-based deep neural network) that can be applied to the labeled and unlabeled data to improve efficiency. This work intends to evaluate potential lightweight, low-memory deep neural net (DNN) designs for image processing. Results: Our experimental results show that, by combining WDSI and LSO segmentation, we can achieve super-sensitive, specific, and accurate early detection of lung cancer. For experiments, we used the lung nodule (LUNA16) dataset, which consists of the patients' 3D CT scan images. We confirmed that our proposed model is lightweight because it uses less memory. We have compared them with state-of-the-art models named PSNR and SSIM. The efficiency is 32.8% and 0.97, respectively. The proposed lightweight deep neural network (DNN) model archives a high accuracy of 98.2% and also removes noise more effectively. Conclusions: Our proposed approach has a lot of potential to help medical image analysis to help improve the accuracy of test results, and it may also prove helpful in saving patients' lives. [ABSTRACT FROM AUTHOR]

The Internet of Things (IoT) is a sophisticated network of objects embedded with electronic systems that enable devices to collect and exchange data. IoT is a recent trending leading technology and changing the way we live. However, it has several challenges especially efficiency, architecture, complexity, and network topology. The traditional technologies are not enough to provide support. It is evident from the literature that complex networks are used to study the topology and the structure of a network and are applied to modern technologies. Thus, the capability of powerful computational tools and the existence of theoretical frameworks enable complex networks to derive new approaches in analyzing IoT-based technologies in terms of improving efficiency, architecture, complexity, and topology. In this direction, limited research has been carried out. The integration aspect remains a key challenge. Therefore, in order to fill this gap. Herein, we design a comprehensive literature review. In this research effort, we explore a newly leading emerging technology named the Social Internet of Things (SIoT). It is developed to overcome the challenges in IoT. We discuss the importance and the key applications of SIoT. We first presented a conceptual view along with a recent technological roadmap. The big data play an important role in the modern world. We discuss big data and the 5 Vs along with suitable applications and examples. Then, we highlighted the key concepts in complex networks, scale-free, random networks, and small-world networks. We explored and presented various graph models and metrics aligned with social networks and the most recent trends. The novelty of this research is to propose a synergy of complex networks to the IoT, SIoT, and big data together. We discuss the advantages of integration in detail. We present a detailed discussion on complex networks emerging technologies and cyber-physical systems (CPS). Briefly, our literature review covers the most recent advancements and developments in 10 years. In addition, our critical analysis is based on up-to-date surveys and case studies. Finally, we outline the impact of recent emerging technologies on challenges applications, and solutions for the future. This paper provides a good reference for researchers and readers in the IoT domain. [ABSTRACT FROM AUTHOR]

Predicting court rulings has gained attention over the past years. The court rulings are among the most important documents in all legal systems, profoundly impacting the lives of the children in case of divorce or separation. It is evident from literature that Natural language processing (NLP) and machine learning (ML) are widely used in the prediction of court rulings. In general, the court decisions comprise several pages and require a lot of space. In addition, extracting valuable information and predicting legal decisions task is difficult. Moreover, the legal system's complexity and massive litigation make this problem more serious. Thus to solve this issue, we propose a new neural network-based model for predicting court decisions on child custody. Our proposed model efficiently performs an efficient search from a massive court decisions database and accurately identifies specific ones that especially deal with copyright claims. More specially, our proposed model performs a careful analysis of court decisions, especially on child custody, and pinpoints the plaintiff's custody request, the court's ruling, and the pivotal arguments. The working mechanism of our proposed model is performed in two phases. In the first phase, the isolation of pertinent sentences within the court ruling encapsulates the essence of the proceedings performed. In the second phase, these documents were annotated independently by using two legal professionals. In this phase, NLP and transformer-based models were employed and thus processed 3,000 annotated court rulings. We have used a massive dataset for the training and refining of our proposed model. The novelty of the proposed model is the integration of bidirectional encoder representations from transformers (BERT) and bidirectional long short-term memory (Bi_LSTM). The traditional methods are primarily based on support vector machines (SVM), and logistic regression. We have performed a comparison with the state-of-the-art model. The efficient results indicate that our proposed model efficiently navigates the complex terrain of legal language and court decision structures. The efficiency of the proposed model is measured in terms of the F1 score. The achieved results show that scores range from 0.66 to 0.93 and Kappa indices from 0.57 to 0.80 across the board. The performance is achieved at times surpassing the inter-annotator agreement, underscoring the model's adeptness at extracting and understanding nuanced legal concepts. The efficient results proved the potential of the proposed neural network model, particularly those based on transformers, to effectively discern and categorize key elements within legal texts, even amidst the intricacies of judicial language and the layered complexity of appellate rulings. [ABSTRACT FROM AUTHOR]

Mobile networks possess significant information and thus are considered a gold mine for the researcher's community. The call detail records (CDR) of a mobile network are used to identify the network's efficacy and the mobile user's behavior. It is evident from the recent literature that cyber-physical systems (CPS) were used in the analytics and modeling of telecom data. In addition, CPS is used to provide valuable services in smart cities. In general, a typical telecom company has millions of subscribers and thus generates massive amounts of data. From this aspect, data storage, analysis, and processing are the key concerns. To solve these issues, herein we propose a multilevel cyber-physical social system (CPSS) for the analysis and modeling of large internet data. Our proposed multilevel system has three levels and each level has a specific functionality. Initially, raw Call Detail Data (CDR) was collected at the first level. Herein, the data preprocessing, cleaning, and error removal operations were performed. In the second level, data processing, cleaning, reduction, integration, processing, and storage were performed. Herein, suggested internet activity record measures were applied. Our proposed system initially constructs a graph and then performs network analysis. Thus proposed CPSS system accurately identifies different areas of internet peak usage in a city (Milan city). Our research is helpful for the network operators to plan effective network configuration, management, and optimization of resources. [ABSTRACT FROM AUTHOR]

In recent years, the Internet of Things (IoT) has become one of the most familiar names creating a benchmark and scaling new heights. IoT an indeed future of the communication that has transformed the objects (things) of the real world into smarter devices. With the advent of IoT technology, this decade is witnessing a transformation from traditional agriculture approaches to the most advanced ones. Limited research has been carried out in this direction. Thus, herein we present various technological aspects involved in IoT-based cultivation. The role and the key components of smart farming using IoT were examined, with a focus on network technologies, including layers, protocols, topologies, network architecture, etc. We also delve into the integration of relevant technologies such as cloud computing, big data analytics, and the integration of IoT-based cultivation. We explored various security issues in modern IoT cultivation and also emphasized the importance of safeguarding sensitive agricultural data. Additionally, a comprehensive list of applications based on sensors and mobile devices is provided, offering refined solutions for greenhouse management. The principles and regulations established by different countries for IoT-based cultivation systems are presented, demonstrating the global recognition of these technologies. Furthermore, a selection of successful use cases and real-world scenarios and applications were presented. Finally, the open research challenges and solutions in modern IoT-based cultivation were discussed. [ABSTRACT FROM AUTHOR]

The provision of Wireless Fidelity (Wi-Fi) service in an indoor environment is a crucial task and the decay in signal strength issues arises especially in indoor environments. The Line-of-Sight (LOS) is a path for signal propagation that commonly impedes innumerable indoor objects damage signals and also causes signal fading. In addition, the Signal decay (signal penetration), signal reflection, and long transmission distance between transceivers are the key concerns. The signals lose their power due to the existence of obstacles (path of signals) and hence destroy received signal strength (RSS) between different communicating nodes and ultimately cause loss of the packet. Thus, to solve this issue, herein we propose an advanced model to maximize the LOS in communicating nodes using a modern indoor environment. Our proposal comprised various components for instance signal enhancers, repeaters, reflectors,. these components are connected. The signal attenuation and calculation model comprises of power algorithm and hence it can quickly and efficiently find the walls and corridors as obstacles in an indoor environment. We compared our proposed model with state of the art model using Received Signal Strength (RSS) and Packet Delivery Ratio (PDR) (different scenario) and found that our proposed model is efficient. Our proposed model achieved high network throughput as compared to the state-of-the-art models. [ABSTRACT FROM AUTHOR]

Background: Cancer remains one of the leading causes of mortality globally, with conventional chemotherapy often resulting in severe side effects and limited effectiveness. Recent advancements in bioinformatics and machine learning, particularly deep learning, offer promising new avenues for cancer treatment through the prediction and identification of anticancer peptides. Objective: This study aimed to develop and evaluate a deep learning model utilizing a two-dimensional convolutional neural network (2D CNN) to enhance the prediction accuracy of anticancer peptides, addressing the complexities and limitations of current prediction methods. Methods: A diverse dataset of peptide sequences with annotated anticancer activity labels was compiled from various public databases and experimental studies. The sequences were preprocessed and encoded using one-hot encoding and additional physicochemical properties. The 2D CNN model was trained and optimized using this dataset, with performance evaluated through metrics such as accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC-ROC). Results: The proposed 2D CNN model achieved superior performance compared to existing methods, with an accuracy of 0.87, precision of 0.85, recall of 0.89, F1-score of 0.87, and an AUC-ROC value of 0.91. These results indicate the model's effectiveness in accurately predicting anticancer peptides and capturing intricate spatial patterns within peptide sequences. Conclusion: The findings demonstrate the potential of deep learning, specifically 2D CNNs, in advancing the prediction of anticancer peptides. The proposed model significantly improves prediction accuracy, offering a valuable tool for identifying effective peptide candidates for cancer treatment. Future Work: Further research should focus on expanding the dataset, exploring alternative deep learning architectures, and validating the model's predictions through experimental studies. Efforts should also aim at optimizing computational efficiency and translating these predictions into clinical applications. [ABSTRACT FROM AUTHOR]

Lung cancer, also known as lung carcinoma, has a high death rate, but an early diagnosis can substantially reduce this risk. In the current era, prediction models face challenges such as low accuracy, excessive noise, and low contrast. To resolve these problems, an advanced lung carcinoma prediction and risk screening model using transfer learning is proposed. Our proposed model initially preprocesses lung computed tomography images for noise removal, contrast stretching, convex hull lung region extraction, and edge enhancement. The next phase segments the preprocessed images using the modified Bates distribution coati optimization (B-RGS) algorithm to extract key features. The PResNet classifier then categorizes the cancer as normal or abnormal. For abnormal cases, further risk screening determines whether the risk is low or high. Experimental results depict that our proposed model performs at levels similar to other state-of-the-art models, achieving enhanced accuracy, precision, and recall rates of 98.21%, 98.71%, and 97.46%, respectively. These results validate the efficiency and effectiveness of our suggested methodology in early lung carcinoma prediction and risk assessment. [ABSTRACT FROM AUTHOR]

The main objective of the current work was to fabricate calcium phosphate (CaP) coating on 99.9% purity magnesium, Mg substrate through simple chemical conversion method and evaluated the surface properties and corrosion performance of the coated substrates. The chemical conversion method was done by immersing the samples inside primary phosphating bath and followed by secondary treatment in alkaline solutions. The coated samples from the primary (PRI) and secondary (SEC) coating treatment were analyzed from morphological, topographical, and phase analysis aspects. The corrosion behaviour of the coatings inside simulated body fluid was assessed by potentiodynamic polarization (PDP) and electrochemical impedance spectroscopy (EIS). The PRI and SEC coated were composed of dicalcium phosphate dehydrate (DCPD) and hydroxyapatite (HA), respectively. Both of the coatings improved the corrosion resistance of the Mg substrate. The corrosion potentials, Ecorr of the coated samples becomes nobler compared to the bare substrates. EIS shows that the polarization resistance, Rp is improved about 40 and 2 times fold for PRI and SEC compared to the uncoated samples. Furthermore, PRI shows better corrosion resistance compared to SEC due to lower porosity along with thicker and better coating coverage. Keywords: Magnesium, Calcium phosphate coating, Chemical conversion coating

In recent years, the Internet of Things (IoT) has played a vital role in providing various services to users in a smart city. However, searching for services, objects, data, and frameworks remains a concern. The technological advancements in Cyber-Physical Systems (CPSs) and the Social Internet of Things (SIoT) open a new era of research. Thus, we propose a Cyber-Physical-Social Systems (CPSs) for service search. Herein, service search and object discovery operation carries with the suitable selection of friends in the network. Our proposed model constructs a graph and performs social network analysis (SNA). We suggest degree centrality, clustering, and scalefree emergence and show that a rational selection of friends per service exploration increases the overall network navigability. The efficiency of our proposed system is verified using real-world datasets based on service processing time, path length, giant component, and network diameter. The simulation results proved that our proposed system is efficient, robust, and scalable. [ABSTRACT FROM AUTHOR]

Underwater Wireless Sensor Networks (UWSNs) obtains more attention due to their wide range of applications such as underwater oil field discovery, Tsunami monitoring systems, surveillance systems, and many more. In such a resource-constrained environment, sensors are more vulnerable to malicious attacks. Node authentication and secure communication is one of the vital issues in UWSNs. In this study, a secure and lightweight key management framework for UWSNs is proposed. The proposed framework includes key generation, key distribution, revocation, and authentication mechanisms along with lightweight implementation, and scalability. We use an elliptic curve-based algorithm for key distribution, and certificate revocation list (CRL) for key revocation. We also examine the performance of the proposed framework taking into account the amount of communication overhead as well as the level of security. The simulation results show that the proposed framework provides better security with less communication overhead compared to existing frameworks. This framework can be used for secure data communication in UWSNs, which has various applications in oceanography, environmental monitoring, and military operations. [ABSTRACT FROM AUTHOR]

In the current era of ubiquitous computing and mobile technology, almost all human beings use various self-monitoring applications. Mobile applications could be the best health assistant for safety and adopting a healthy lifestyle. Therefore, persuasive designing is a compulsory element for designing such apps. A popular model for persuasive design named the Persuasive System Design (PSD) model is a generalized model for whole persuasive technologies. Any type of persuasive application could be designed using this model. Designing any special type of application using the PSD model could be difficult because of its generalized behavior which fails to provide moral support for users of health applications. There is a strong need to propose a customized and improved persuasive system design model for each category to overcome the issue. This study evaluates the PSD model and finds persuasive gaps in users of the Mobile Health Monitoring application, developed by following the PSD model. Furthermore, this study finds that users misunderstand health-related problems when using such apps. A misunderstanding of this nature can have serious consequences for the user's life in some cases. [ABSTRACT FROM AUTHOR]

Early detection of brain tumors is critical to ensure successful treatment, and medical imaging is essential in this process. However, analyzing the large amount of medical data generated from various sources such as magnetic resonance imaging (MRI) has been a challenging task. In this research, we propose a method for early brain tumor segmentation using big data analysis and patch-based convolutional neural networks (PBCNNs). We utilize BraTS 2012–2018 datasets. The data is preprocessed through various steps such as profiling, cleansing, transformation, and enrichment to enhance the quality of the data. The proposed CNN model utilizes a patch-based architecture with global and local layers that allows the model to analyze different parts of the image with varying resolutions. The architecture takes multiple input modalities, such as T1, T2, T2-c, and FLAIR, to improve the accuracy of the segmentation. The performance of the proposed model is evaluated using various metrics, such as accuracy, sensitivity, specificity, Dice similarity coefficient, precision, false positive rate, and true positive rate. Our results indicate that the proposed method outperforms the existing methods and is effective in early brain tumor segmentation. The proposed method can also assist medical professionals in making accurate and timely diagnoses, and thus improve patient outcomes, which is especially critical in the case of brain tumors. This research also emphasizes the importance of big data analysis in medical imaging research and highlights the potential of PBCNN models in this field. [ABSTRACT FROM AUTHOR]