International Journal of Communication Networks and Information Security (IJCNIS)
Not a member yet
1021 research outputs found
Sort by
Detection and Analysis of Disease from Brain MRI Image Using Machine Learning
No full textNow a day’s tumor is second leading cause of cancer. Due to cancer large no of patients are in danger. The medical field needs fast, automated, efficient and reliable technique to detect tumor like brain tumor. Detection plays very important role in treatment. If proper detection of tumor is possible then doctors keep a patient out of danger. Various image processing techniques are used in this application. Using this application doctors provide proper treatment and save a number of tumor patients. A tumor is nothing but excess cells growing in an uncontrolled manner. Brain tumor cells grow in a way that they eventually take up all the nutrients meant for the healthy cells and tissues, which results in brain failure. Currently, doctors locate the position and the area of brain tumor by looking at the MR Images of the brain of the patient manually. This results in inaccurate detection of the tumor and is considered very time consuming. A tumor is a mass of tissue it grows out of control. We can use a Deep Learning architectures CNN (Convolution Neural Network) generally known as NN (Neural Network) and VGG 16(visual geometry group) Transfer learning for detect the brain tumor. In this paper, the design and implementation of a tumor detection system using two CNN models is considered. Digital image processing and Deep Learning technologies enable us to develop an automatic system for the diagnosis/detection of various kind of diseases and abnormalities. The tumor detection system may include image enhancement, segmentation, data augmentation, features extraction and classification; all these steps are discussed in details in the above sections. To work on CNNs, powerful GPU based system are required to speed up the process, lot of processing is carried out and also lot of RAM is required to process the images for testing. CNNs have also some options such as optimization technique selection, Number of Epoch, Batch size, iteration and learning rate. These options are tuned to get the optimal results from the CNN model. Learning rate is used to update the weights and bias in training phase, learning rate changes the weights. One Epoch is when the model see all images in training, as the training data maybe of very big sizes, the data in each Epoch is divided into batch sizes. Every epoch has a training and test session, after each Epoch the weights are updated according to the learning rate, optimization algorithms are used to update the learning of a CNN adaptively. When the best weights for training are computed, the model is said to be trained. All the experimental work is carried out in MATLAB simulation tool
Enhancing Student Comprehension of Audio Mixing and Mastering Through Jigsaw Activity: A Study of Pedagogical Impact
No full textAudio mixing and mastering are always being teach as a practice-based learning. The student-centered learning for this topic is related when student use their understanding and develop their skills in listening while adjusting knobs or audios technical which contributed to their final project. Jigsaw activity approaches is being selected to determine the student’s understanding towards audio mixing and mastering in practice-based learning. A quantitative and content analysis method is being conducted for this study. The method of jigsaw activity had been practiced in the class session which the result varied in four activities that being prepared to analyze the student’s understanding. The four activities are preparing slides, quiz, practical hands on, and questionnaire. The results shown the jigsaw contributed on enhancing student’s understanding towards mixing and mastering activities. Although the students applied their understanding more on the practical activities, the jigsaw activity still influence towards the student’s understanding in practice-based learning subject
Navigating Security Threats and Solutions using AI in Wireless Sensor Networks
No full textWireless Sensor Networks (WSNs) are increasingly pivotal in applications such as environmental monitoring, smart cities, and healthcare, yet their widespread use introduces significant security challenges. These challenges arise due to the inherent vulnerabilities of WSNs, including their wireless communication medium and limited resources. Key security threats facing WSNs include eavesdropping, where unauthorized entities intercept sensitive data; node compromise, where malicious actors take control of sensor nodes to disrupt network operations; and denial of service (DoS) attacks, which overwhelm the network with excessive traffic or tasks. Additionally, Sybil attacks, wormhole attacks, and sinkhole attacks further compromise network integrity and data accuracy. Artificial Intelligence (AI) offers transformative solutions to these security threats by enhancing threat detection, response, and overall network resilience. AI-driven anomaly detection leverages machine learning to identify deviations from normal network behavior, thus recognizing potential threats. Intrusion Detection Systems (IDSs) powered by AI analyze network traffic and node activities to detect and respond to unauthorized access or malicious behavior in real-time. AI also optimizes secure routing protocols through reinforcement learning and dynamic adjustments, ensuring that data paths avoid compromised nodes. AI contributes to data encryption and authentication by selecting efficient cryptographic algorithms and improving authentication mechanisms. The integration of AI into WSN security also addresses energy constraints by designing energy-efficient solutions for encryption, monitoring, and response. AI techniques enable self-healing capabilities, allowing WSNs to predict and address potential failures autonomously. Despite these advancements, challenges such as scalability, adaptability, resource constraints, and privacy concerns must be addressed. This paper explores these AI-driven solutions and identifies future research directions to enhance the security and resilience of Wireless Sensor Networks
XAI - Credit Risk Analysis
No full textThis paper delves into the integration of Explainable AI (XAI) techniques with machine learningmodels for credit risk classification, addressing the critical issue of model transparency in financialservices. We experimented with various models, including Logistic Regression, Random Forest,XGBoost, LightGBM, and Artificial Neural Networks (ANN), on real-world credit datasets to predictborrower risk levels. Our results show that while ANN achieved the highest accuracy at 95.3%,Random Forest followed closely with 95.23%. Logistic Regression also performed strongly with anaccuracy of 94.68%, while XGBoost and LightGBM delivered slightly lower accuracies of 94.4% and94.37%, respectively. However, the superior accuracy of these complex models, particularly ANN,comes with a trade-off: reduced transparency, making it difficult for stakeholders to understand thedecision-making process. To address this, we applied XAI techniques such as SHAP (SHapleyAdditive exPlanations) and LIME (Local Interpretable Model-agnostic Explanations) to provideclear and understandable explanations for the predictions made by these models. This integrationnot only enhanced model interpretability but also built trust among stakeholders and ensuredcompliance with regulatory standards. This study illustrates how XAI serves as an effective mediatorbetween the precision of sophisticated machine learning algorithms and the demand for clarity inevaluating credit risk. XAI offers a well-balanced method for managing risk in finance, harmonizingthe need for both accuracy and interpretability
Optimized Feature Selection and classification for Non-Portable Executable Malware
No full textMalware is a program that executes harmful acts and steals information. nowadays it is widely recognized as oneof the largest hazards. In this research work machine learning is used to identify and detect Non-PE file features. The variousdistinct aspects of the Non-PE files features can correlate with one another, being clean or affected, led to the identification ofsuch features. by using machine learning algorithms such as Ada Boost Classifier,Gaussian NB, KNClassifier,RF Classifier, SGD classifier, and feature selection produced the best detection rate also Prediction accuracy of thealgorithms is used to compare the efficacy and efficiency
The Influence of Organizational Culture on Performance, with Innovative Behavior, Job Satisfaction, and Work Motivation as Intervening Variables in Bireuen District Government
No full textVarious factors cause an institution to have decreased performance. This research examines organizational culture's influence on performance, with innovative behavior, job satisfaction, and work motivation as intervening variables. The Regency government conducted this research with echelon II, III, and IV officials. The sampling method used a saturated sample, so 238 respondents were obtained. Two hundred two respondents returned the questionnaire. The data analysis technique uses SmartPLS software, structural equation modeling, or SEM. The study's findings clarify that organizational culture positively influences innovative behavior, job satisfaction, work motivation, and performance. It also positively affects innovative behavior's impact on performance, job satisfaction's impact on performance, and motivation work's impact on performance. In addition, organizational culture positively influences performance through innovative behavior, job satisfaction positively influences performance, and organizational culture positively impacts performance through work motivation
Machine Inspired IOT based Framework for Real-Time Heart Disease Prediction
No full textThe rapid advancements in Internet of Things (IoT) technologies have enabled the development of innovative healthcare solutions, particularly in the field of real-time disease prediction and management. This paper presents a machine-inspired IoT-based framework designed for the real-time prediction of heart disease. The proposed framework integrates IoT-enabled wearable devices that continuously monitor vital signs such as heart rate, blood pressure, and oxygen saturation. These devices transmit data to a central processing unit where machine learning algorithms analyze the information to detect early signs of heart disease. By leveraging real-time data and advanced predictive models, the framework aims to provide timely alerts to healthcare providers and patients, thereby facilitating early intervention and reducing the risk of severe cardiac events. The framework's architecture is built on a robust and scalable IoT infrastructure that ensures seamless data collection, transmission, and analysis. Machine learning techniques, including supervised learning models and ensemble methods, are employed to enhance the accuracy of heart disease predictions. The system also incorporates edge computing to reduce latency and improve processing efficiency, enabling real-time analysis even in resource-constrained environments. Experimental results demonstrate the framework's potential in achieving high predictive accuracy while maintaining low power consumption, making it a viable solution for continuous heart health monitoring. This work contributes to the growing field of smart healthcare by offering a practical and efficient approach to real-time heart disease prediction, ultimately aiming to improve patient outcomes through proactive healthcare management
“Enhancing Mental Health Assessments: The Role of Voting Classifiers in Evaluating Depression's Impact on Quality of Life”
No full textDepression continues to pose a significant global challenge,ranking as one of the most prevalent and costly mental disordersthat substantially impairs quality of life, supported by asubstantial body of research. Enhancing our comprehension ofthe factors influencing quality of life is paramount for optimizinglong-term outcomes and reducing disability in individualsgrappling with depression. This study primarily focuses on theidentification of depression based on lifestyle and livelihoodfactors. It's noteworthy that depression can afflict individualsacross all age groups, genders, and backgrounds, often arisingfrom a complex interplay of genetic, biological, environmental,and psychological elements. Furthermore, major life events,chronic stress, trauma, or a family history of depression cancontribute to its emergence.In the realm of healthcare, machine learning techniques areincreasingly employed to process and analyze diverse data types,with the aim of better understanding the relationship betweenquality of life factors and depression. Various classificationalgorithms, such as Random Forest, Decision Tree, Naive Bayes,Support Vector Machine, and PPMCSVM, have been utilized forthis analysis. However, existing approaches have encounteredchallenges related to their accuracy in predicting depression.Consequently, the primary objective of this proposed research isto enhance depression prediction by leveraging an ensembletechnique that identifies the determinants of quality of lifeamong individuals affected by depression. To attain this goal, thestudy employs KNN (K-Nearest Neighbour) and Voting Classifieralgorithms. The Voting Classifier aids in uncovering the rootcauses of depression in each individual. The results of thisinvestigation reveal that the proposed model can effectivelypredict the causes of depression, thus opening avenues for moretargeted intervention and treatment strategies
Caries Dental Detection Using UNet Deep Learning Methods
No full textDental caries, a prevalent oral health issue, can lead to severeconsequences if not detected early. This study explores theapplication of U-Net, a deep learning architecture, for theautomatic detection of dental caries from radiographic images.U-Net's architecture, characterized by its encoder-decoderstructure with skip connections, allows for precise segmentationand localization of carious lesions. We employed a dataset ofannotated dental X-ray images to train and validate our model.The results demonstrate that the U-Net-based approach achieveshigh accuracy in identifying carious regions, outperformingtraditional methods in both sensitivity and specificity. Thismethod holds significant promise for enhancing diagnosticworkflows and improving early intervention strategies in dentalcare
AGE FEATURES OF CHANGES IN THE ANGLE OF THE SPINE AND AGE FEATURES OF ANTHROPOMETRIC INDICATORS OF VARIOUS SECTIONS OF THE SPINE IN BOYS AND GIRLS AGED FROM 11 TO 16 YEARS
No full textThe article examines age-related changes in the angle of inclination of various sections of the spinal column, as well as age-related features of anthropometric characteristics of the spinal column in boys and girls aged from 11 to 16 years old, who do not have pathological changes in the spinal column. [12].
The purpose of the study: to study the change in the angle of inclination in various parts of the spinal column, as well as age-related features of anthropometric indicators of various parts of the spinal column in adolescents