Due to its complexity and high diagnosis and treatment costs, heart attack (HA) is the top cause of death globally. Heart failure's widespread effect and high morbidity and death rates make accurate and fast prognosis and diagnosis crucial. Due to the complexity of medical data, early and accurate prediction of HA is difficult. Healthcare providers must evaluate data quickly and accurately to intervene. This novel hybrid approach predicts HA using Long Short-Term Memory (LSTM) networks, Deep belief networks (DBNs) with attention mechanism, and robust data mining to fill this essential gap. HA is predicted using Kaggle, PhysioNet, and UCI datasets. Wearable sensor data, ECG signals, and demographic and clinical data provide a solid analytical base. To maintain consistency, ECG signals are normalized and segmented after thorough cleaning to remove missing values and noise. Feature extraction employs complex approaches like Principal Component Analysis (PCA) and Autoencoders to pick time-domain (MNN, SDNN, RMSSD, PNN50) and frequency-domain (PSD at VLF, LF, HF bands) characteristics. The hybrid model architecture uses LSTM networks for sequence learning and DBNs for feature representation and selection to create a robust and comprehensive prediction model. Accuracy, precision, recall, F1-score, and ROC-AUC are measured after cross-entropy loss and SGD optimization. The LSTM-DBN model outperforms predictive methods in accuracy, sensitivity, and specificity. The findings show that several data sources and powerful algorithms can improve heart attack predictions. The proposed architecture performed well on many datasets, with an accuracy rate of 96.00%, sensitivity of 98%, AUC of 0.98, and F1-score of 0.97. High performance proves this system's dependability. Moreover, the proposed approach is outperformed compared to state-of-the-art systems.

Mobile phones have become immensely popular as intelligent terminals worldwide. The open-source nature of mobile platforms has facilitated the development of third-party mobile applications, but it has also created an environment for mobile malware to thrive. Unfortunately, the abundance of mobile applications and lax management of some app stores has led to potential risks for mobile users, including privacy breaches and malicious deductions of fees, among other adverse consequences. This research presents a mobile malware static detection method based on Gaussian Naïve Bayes. The approach aims to offer a solution to protect users from potential threats such as Banking Trojan malware. The objectives of this project are to study the requirement of the Naïve Bayes algorithm in Mobile Banking Trojan detection, and to evaluate the performance and accuracy of the Gaussian Naïve Bayes algorithm in the Mobile Banking Trojan detection. This study presents a mobile banking trojan detection system utilizing the Gaussian Naïve Bayes algorithm, achieving a high classification accuracy of 95.83% in distinguishing between benign and trojan APK files.

Currently, on social media, malicious comments have emerged as a serious issue. Existing artificial intelligence-based comment classification systems have limitations due to data bias and overfitting. To address this, this study proposed a novel comment classification system that combines crowdsourcing and federated learning. This system collects data from various users and utilizes a large language model like KoBERT through federated learning to classify comments accurately while protecting user privacy. It is expected to provide higher accuracy than existing methods and improve significantly the efficiency of detecting malicious comments. The proposed system can be applied to social media platforms and online communities.

For many sensor network applications, minimizing the energy consumed as well as extending the network lifetime are the most important objectives to be achieved, these objectives have pushed the scientific community to propose new solutions to minimize the total energy consumed by the sensors without degrading the network performances, amongst the proposed solutions, the clustering techniques. In this work we focus on hierarchical routing protocols, more precisely clustering in wireless sensor networks. We propose an energy-efficient hierarchical routing protocol for WSNs called EEV-LEACH (Energy Efficient Vice Low Adaptive Clustering Hierarchy), which represents a new variant of the LEACH protocol. Our energy-efficient protocol aims to maximize the lifetime of the network, by minimizing the energy consumption of each sensors nodes and cluster-heads. Minimizing the wasted energy by each sensor node is achieved by minimizing the periodic selection of CHs in each round. Minimizing the periodic selection of CHs allows decreasing the association messages exchanged between the CH and the nodes, so the consumed energy and overhead are minimized. EEV-LEACH aims also to minimize the energy consumed by the cluster-heads (CHs) by using vice CHs , which will share the workload with the CHs in an alternative way. The performances of our protocol EEV-LEACH is compared to, LEACH, LEACH-S and TL-LEACH by using MATLAB simulator, the results show that EEV-LEACH protocol extend the network lifetime and it minimizes the overall overhead versus LEACH, LEACH-S and TL-LEACH protocols.

A medium scale Urdu speakers' and English speakers' database with multiple accents and dialects has been developed to use in Urdu Speaker Verification Systems, English Speaker Verification Systems, accents and dialect verification systems. Urdu is the national language of Pakistan and English is the official language. Majority of the people are non-native Urdu speakers and non-native English in all regions of Pakistan in general and Gilgit-Baltistan region in particular. In order to design Urdu and English speaker verification systems for security applications in general and telephone banking in particular, two databases has been designed one for foreign accent of Urdu and another for foreign accent of English language. For the design of databases, voice data is collected from 180 speakers from GB region of Pakistan who could speak Urdu as well as English. The speakers include both genders (males and females) with different age groups ranging from 18 to 69 years. Finally, using a subset of the data, Multilayer Perceptron based speaker verification system has been designed. The designed system achieved overall accuracy rate of 83.4091% for English dataset and 80.0454% for Urdu dataset. It shows slight differences (4.0% with English and 7.4% with Urdu) in recognition accuracy if compared with the recently proposed multilayer perceptron (MLP) based SIS achieved 87.5% recognition accuracy

Communication systems where chaotic signals are used as carrier signals are called Direct Chaotic Communication (DCC). DCC systems have the disadvantage of low bit-error rate (BER) and signal to noise ratio (SNR) performance. The main reason for this disadvantage is that the DCC receiver circuits are constant in the decision block with the threshold voltage values. In this study, a new receiver circuit has been designed to increase BER / SNR performance in digital based DCC systems. According to this, the noise obtained in the receiver circuits of the communication systems is accepted as the dirac delta function. Then a decision block with two inputs is performed using the dirac delta function and the ramp function is obtained. The numerical and the experimental results of the study reveal that proposed model shows much better performance between %70 and %96.

This paper is about information technology of creation of mobile (of rapid deployment) security systems of the area perimeter. This system appears to be a complex of models and methods, information, software and hardware means that are interacted with users during decision-making and control of implementation for management solutions. The proposed information technology aimed at improving the protection level for security departments by automating the process of dangers detection for perimeters and decision-making for alarm. The structural model of the system, the model of system's components interaction and the model of identifying the subjects of emergencies threats have been proposed. A method for identifying unauthorized access to the perimeter of the protected object, using the production model of knowledge representation, was created. It is a set of linguistic expressions (such as "IF-THEN") and knowledge matrix. The method of ranking for objects, which are threats of unauthorized access to the perimeter for protected area, has been proposed. Practical value of work consists in the possibility of the use this information technology by perimeter's security systems of various objects. Proposed models are complete and suitable for the hardware and software implementation.

The Internet of Things (IoT) is an emerging element that is becoming increasingly indispensable to the Internet and shaping our current understanding of the future of the Internet. IoT continues to extend deeper into the daily lives of people, offering distributed and critical services. In contrast with current Internet, IoT depends on a dynamic architecture where physical objects with embedded sensors will communicate via cloud to send and analyze data [1-3]. Its security troubles will surely impinge all aspects of civilization. Mobile agents are widely used in the context of the IoT and due to the possibility of transmitting their execution status from one device to another in an IoT network, they offer many advantages such as reducing network load, encapsulating protocols, exceeding network latency, etc. Also, cryptographic technologies, like PKI and Blockchain technology, and Artificial Intelligence are growing rapidly allowing the addition of an approved security layer in many areas. Security issues related to mobile agent migration can be resolved with the use of these technologies, thus allowing increased reliability and credibility and ensure information collecting, sharing, and processing in IoT environments, while ensuring maximum autonomy by relying on the AI to allow the agent to choose the most secure and optimal path between the nodes of an IoT environment. This paper aims to present a new model to secure mobile agents in the context of the Internet of Things based on Public Key Infrastructure (PKI), Ethereum Blockchain Technology and Q-learning. The proposed model provides a secure migration of mobile agents to ensure security and protect the IoT application against malevolent nodes that could infiltrate these IoT systems.

Lung cancer is a complex and frightening disease that typically results in death in both men and women. Therefore, it is more crucial to thoroughly and swiftly evaluate the malignant nodules. Recent years have seen the development of numerous strategies for diagnosing lung cancer, most of which use CT imaging. These techniques include supervisory and non-supervisory procedures. This study revealed that computed tomography scans are more suitable for obtaining reliable results. Lung cancer cannot be accurately predicted using unsupervised approaches. As a result, supervisory techniques are crucial in lung cancer prediction. Convolutional neural networks (CNNs) based on deep learning techniques has been used in this paper. Convolutional neural networks (CNN)-based deep learning procedures have produced results that are more precise than those produced by traditional machine learning procedures. A number of statistical measures, including accuracy, precision, and f1, have been computed.

Corona Virus is a big threat to humanity. Now, the whole world is struggling to reduce the spread of Corona virus. Wearing masks is one of the practices that help to control the spread of the virus according to the world health organization. However, ensuring all people wear facemask is not an easy task. In this paper, we propose a simple and effective model for real-time monitoring using the convolution neural network to detect whether an individual wears a face mask or not. The model is trained, validated, tested upon two datasets. Corresponding to dataset 1, the accuracy of the model was 95.77% and, it was 94.58% for dataset 2.

This paper proposed n approaches to designing local area networks using Prim's MST Algorithm of an organization. Designing the local area network of an organization is a typical problem faced with how we optimally arrange the networks between computers nodes while faced the imperative of area and installment cost. One of the cost parts that value to be considered is the local network cable price. The shorter the aggregate link length of the network, obviously the installation cost will be less. The MST problem has essential applications in network design which is broadly concentrated in the study of literature. The MST problem shows up in the local area network design where computers and other nodes connect them and must be picked most gainfully. The application of Prim's algorithms is shown to the outline design of local area networks in an organization. This Prim's algorithm works by picking the shortest path beginning from the first node until all nodes in the graph are linked. The following research is planned to design a prims algorithm to solve local area network design problems. Our research is analyzed, and intriguing results are gotten. The outcomes got to justify the need to apply this sort of algorithm for benefit and efficiency.

The next generation 5g communications are used with baseband precoders and beam forming. The technology is needed to update the all the available characteristics in the present wireless communication system. In the mmWave MIMO system the number of antenna are increased to improve the spectral efficiency of the system.

Wireless Sensor Networks (WSN) includes a large number of small sensor nodes and low cost, which are randomly located in a region. The wireless sensor network has attracted much attention from universities and industry around the world over the past decades, with features denser levels of node deployment, self-configuration, uncertainty of sensor nodes, computing, and memory constraints. Black-hole attack is one of the most known attacks on this network. In this study, the combination of fuzzy logic and particle swarm optimization (PSO) algorithms is proposed as an effective method for detecting black-hole attack in the AODV protocol. In the current study, a new function has been proposed in order to determine the membership of fuzzy parameters based on the particle swarm optimization algorithm. The proposed method was evaluated in different scenarios and was compared with other state of arts. The simulation result of this method proved the better performance in both detection rate and delivered packet rate.

In current day information transmitted from one place to another by using network communication technology. Due to such transmission of information, networking system required a high security environment. The main strategy to secure this environment is to correctly identify the packet and detect if the packet contain a malicious and any illegal activity happened in network environments. To accomplish this we use intrusion detection system (IDS). Intrusion detection is a security technology that design detects and automatically alert or notify to a responsible person. However, creating an efficient Intrusion Detection System face a number of challenges. These challenges are false detection and the data contain high number of features. Currently many researchers use machine learning techniques to overcome the limitation of intrusion detection and increase the efficiency of intrusion detection for correctly identify the packet either the packet is normal or malicious. Many machine-learning techniques use in intrusion detection. However, the question is which machine learning classifiers has been potentially to address intrusion detection issue in network security environment. Choosing the appropriate machine learning techniques required to improve the accuracy of intrusion detection system. In this work, three machine learning classifier are analyzed. Support vector Machine, Naïve Bayes Classifier and K-Nearest Neighbor classifiers. These algorithms tested using NSL KDD dataset by using the combination of Chi square and Extra Tree feature selection method and Python used to implement, analyze and evaluate the classifiers. Experimental result show that K-Nearest Neighbor classifiers outperform the method in categorizing the packet either is normal or malicious.

Mobile Ad hoc Network (MANET) is a self organizing network in which a group of wireless nodes communicate among themselves without requiring any centralized infrastructure. This important characteristic of mobile ad hoc networks allows the hassle free set up of the network for communications in different emergency situations such as battlefield and natural disaster zones. Multi hop communication in MANET is achieved only by the cooperation of nodes in forwarding data packets. This feature of MANET is largely exploited to launch a security attack called black hole attack. In this paper we propose a light weight non cryptographic solution to defend the network from black hole attack and enables communication even in the presence of the attack. In this scheme, by analyzing only the control packets used for routing in the network, the nodes identify the presence of black hole attack. Based on the collective judgment by the participating nodes in the routing path, a secure route free of black hole nodes is selected for communication by the host. Simulation results validate and ensure the effectiveness of the proposed solution in the presence of attack.

The success of cognitive radio network (CRN) depends upon the accurate spectrum sensing. The hidden and open terminal problems are serious threats in the way of reliable communication. Cluster based architecture with cooperative spectrum sensing is widely adapted to overcome these challenges. In this paper, we propose a cluster based architecture with overlapping antennas. The number of overlapping antennas increases the overall performance of the system by improving the accuracy of detection. But on the other hand the overlapping antennas, increases the over heads of the system as well. So in order to achieve a balance between efficiency and system overhead, optimal numbers of overlapping antennas are suggested in this paper. Mathematical model along with simulations are presented in this paper which guarantees the sufficient number of overlapping antennas in the cluster.

The problem of handling uncertain data has been attracting the attention of researchers. This paper mainly focuses on uncertain data clustering and noise data streams. Therefore, we will provide a framework to realize the effect of uncertainty. Nowadays, a large number of tenders are present which measure the data roughly. As, sensors normally have distortion in their results cause of the imprecisions transmission in data and retrieval. Mostly these errors are identified. This information is used for minimizing process to advance results according to quality. In this paper, we compare general methods of monitor uncertainty, which have described in the different research papers.

Billions of the objects around us are transformed to the IoT device by connecting them with the internet and control in that way of collecting and sharing data. Privacy is required to keep the data save from the security attacks in internet of things. Computer vision is used for monitoring the people. Computer vision algorithms, application and tools are primarily used in IOT for human movement's analysis. Traditional system and algorithms are unable to detect the human in a perfect manner. Use of the thermal camera is degraded the movements of human detection. In this paper we propose a new IoT system that is combined with the latest feature of computer vision to detect the position using computer vision. It is a useful technology that helps to keep an eye on your house and office. It will alert you if anybody enters your home or office and do any harm at your place. For that purpose, the credit card size Raspberry PI card will be used. Histogram of oriented gradient (HOG) algorithm is used to detect the person in the image.

In a system we use to share the data over the around the world. While sharing the data is to keep up the information confidentially. Attacker in the system may capture this privately data or distorted. So security is the principle piece of concern. There are a few security attacks in system. A standout among the most critical and modern day dangers is DDoS (Distributed disavowal of administrations) attacks. It gives an opportunity to an attacker to expand access to a huge number of computers by use their vulnerabilities to set up attacks systems or Botnets. The fundamental thought of this paper is to concentrate on modern day approaches managing and Detection of DDoS attacks

A dye-sensitized solar cell (DSSC) with a nanocrystalline TiO₂ film electrode on ITO glass, N719 dye, CsSnI₃ as solid state electrolyte to solve constancy problems such as electrode corrosion and electrolyte permeation, and counter WO₃ electrode, designed and simulated by wxAmps software. As research results has proved, that select graphene as 2D bridges into the nanocrystalline electrodes of dye-sensitized solar cells, which brought a faster electron transport and a lower recombination, together with a higher light scattering³. Compared to 1D nanomaterials and liquid electrolytes using in typical DSSCs, this simulation's results show more excellent properties and energy conversion efficiency (20.7102%).

In cipher algorithms, encryption and decryption is based on the same key. There are some limitations in cipher algorithms, for example in polyalphabetic substitution cipher the key size must be equal to plaintext otherwise it will be repeated and if the key is known then encryption become useless. This paper aims to improve the said limitations by a proposed algorithm TKSA in which the key is modified on polyalphabetic substitution cipher to maintain the size of key and plaintext. Each plaintext character is substituted by alternative message. The mode of substitution is transformed cyclically which depends on a current position of the modified communication. Three keys are used in encryption and decryption process on 8 or 16 rounds with the XOR of 1st key. This study also identifies a single-key attack on multiple rounds block cipher in mobile communications and applied the proposed technique to prevent the attack. By utilization of the TKSA algorithm, the decryption is illustrated, and security is analyzed in detail with mathematical examples.

The use of Short Message Services (SMS) as a mechanism of communication has resulted to loss of sensitive information such as credit card details, medical information and bank account details (user name and password). Several Machine learning-based approaches have been proposed to address this problem, but they are still unable to detect modified SMS spam messages more accurately. Thus, in this research, a stack- ensemble of four machine learning algorithms consisting of Random Forest (RF), Logistic Regression (LR), Multilayer Perceptron (MLP), and Support Vector Machine (SVM), were employed to detect more accurately SMS spams. The simulation was carried out using Python Scikit- learn tools. The performance evaluation of the proposed model was carried out by benchmarking it with an existing model. The evaluation results showed that the proposed model has an increase of 3.03% of accuracy, 8.94% of Recall, 2.17% of F-measure; and a decrease of 4.55% of Precision over the existing model. In conclusion, the ensemble method performed better than any individual algorithms and can be adopted by the Network service providers for better Quality of Service.

This paper presents a subfamily of quasi-orthogonal space time block codes (QOSTBC), named Exclusive Conjugate (ECQOSTBC), with full rate, full diversity and simple decoding at the receiver. Our approach estimates feedback constants at the receiver and the transmitter in turn modifies the transmitted symbols based on the estimated constants. This approach is an alternative method to those used in the literature to overcome the challenge of no existing STBC with full diversity and full rate with simple decoding for more than two transmitted antennas. Our simulation results show that the proposed family has better performance in terms of BER-SNR when compared to other codes presented in the literature. Finally, the estimated feedback constants in this work consists of only two real constants.

This paper introduces a new approach to semantic image retrieval using shape descriptors as dispersion and moment in conjunction with discriminative model of Latent-dynamic Conditional Random Fields (LDCRFs). The target region is firstly localized via the background subtraction model. Then the features of dispersion and moments are employed to k-mean procedure to extract object's feature as second stage. After that, the learning process is carried out by LDCRFs. Finally, SPARQL language on input text or image query is to retrieve semantic image based on sequential processes of Query Engine, Matching Module and Ontology Manger. Experimental findings show that our approach can be successful retrieve images against the mammals Benchmark with rate 98.11. Such outcomes are likely to compare very positively with those accessible in the literature from other researchers.

In the last 10 years, artificial intelligence (AI) has shown more predictive accuracy than humans in many fields. Its promising future founded on its great performance increases people's concern about its black-box mechanism. In many fields, such as medicine, mistakes lacking explanations are hardly accepted. As a result, research on interpretable AI is of great significance. Although much work about interpretable AI methods are common in classification tasks, little has focused on segmentation tasks. In this paper, we explored the interpretability on a Deep Retinal Image Understanding (DRIU) network, which is used to segment the vessels from retinal images. We combine the Grad Class Activation Mapping (Grad-CAM), commonly used in image classification, to generate saliency map, with the segmentation task network. Through the saliency map, we got information about the contribution of each layer in the network during predicting the vessels. Therefore, we adjusted the weights of last convolutional layer manually to prove the accuracy of the saliency map generated by Grad-CAM. According to the result, we found the layer 'upsample2' to be the most important during segmentation, and we improved the mIoU score (an evaluation method) to some extent.

Retinal vessel analysis plays a vital role in the detection of some diseases. For example, diabetic retinopathy which may lead to blindness is one of the most common diseases that cause retinal blood vessel structure to change. However, doctors usually take a lot of time and money to collect and label training sets. Thus, automated vessel segmentation as the first step toward computer-aided analysis of fundus remains an active research avenue. We propose an automated Retinal vessel segmentation method based on the GAN network. Traditional image segmentation networks are unsupervised, and GAN is a new semi-supervised network due to adding a Discriminator. By training the discriminator network, we can capture the quality of the generator's output and drive it closer to the true image features. In our experiment, we use DRIVE dataset for training and testing. The final segmentation effect is represented by the Dice coefficient. Experimental results show that the GAN network can effectively improve the edge effect of image segmentation. Compared with the traditional U-net network, GAN shows about 1.55% higher segmentation accuracy.