The advent of new technologies like artificial intelligence, and big data has influenced many cyber attackers to launch their attacks on the network. Hence researchers have already proposed Intrusion Detection Systems...
详细信息
The advent of new technologies like artificial intelligence, and big data has influenced many cyber attackers to launch their attacks on the network. Hence researchers have already proposed Intrusion Detection Systems by incorporating machine learning as well. Building an effective IDS is still a challenging task because of low accuracy. Managing high dimensional data is another major problem that occurs in IDS. Hence in this paper, an efficient Machine Learning based Intrusion Detection System is developed by means of a novel stable feature selection strategy called IV-RFE. The proposed methodology aims to select only the relevant features that contribute to the attack, which is purely based on relative variance, and weight factor in combination with RFE. This methodology increases the performance in terms of accuracy and maintains a stable set of features. Previous studies only focussed on the feature selection strategy and their performance. The feature stability also has to be considered which is an equally important metric, especially in the field of Intrusion Detection Systems. Hence in the current study, an efficient ML based IDS is proposed which selects only the relevant and stable features. Experimental results also revealed that the proposed IV-RFE outperformed well for three attacks with respect to accuracy and stability metrics also. The results show that stability is also an important indicator in selecting the features in the field of Intrusion Detection Systems.
*** contamination in surface waters has proven to be a significant public health concern, requiring innovative monitoring solutions. This paper presents the design of an AI-driven mobile application to predict whether...
详细信息
ISBN:
(数字)9798331507817
ISBN:
(纸本)9798331507824
*** contamination in surface waters has proven to be a significant public health concern, requiring innovative monitoring solutions. This paper presents the design of an AI-driven mobile application to predict whether *** bacteria are present at levels exceeding acceptable thresholds in surface waters. The methodology employs sensor devices to collect water quality data parameters, such as water temperature, pH, dissolved oxygen, and turbidity. A dataset is generated based on these parameters, and machine learning (ML) algorithms are applied to evaluate accuracy, precision, recall, and processing time. Additionally, our ML algorithms establish a correlation matrix among water quality parameters to identify the key factors influencing *** levels. We applied various machine learning techniques to the dataset, including Support Vector Regression (SVR), Random Forest Classification (RFC), XGBoost, and ensemble methods that combine these algorithms. Our findings indicate that the ensemble of Random Forest Classification and XGBoost achieved the highest accuracy at 99.9%. Our Mobile App lets Users view E. coli predictions based on current sensor values.
One common mental health condition that can seriously impair daily functioning is panic disorder. It is a type of anxiety disorder characterized by frequent, unplanned panic attacks. Effective treatment requires early...
详细信息
ISBN:
(数字)9798350357509
ISBN:
(纸本)9798350357516
One common mental health condition that can seriously impair daily functioning is panic disorder. It is a type of anxiety disorder characterized by frequent, unplanned panic attacks. Effective treatment requires early and precise detection. With objective, data-driven methods, machine learning (ML) presents a promising way to improve panic disorder detection in early stages and supports broader public health initiatives aimed at mental health awareness and treatment accessibility. This study presents an efficient machine learning framework designed to enhance panic disorder detection by reducing the false negative rate (FNR) through the integration of Synthetic Minority Over-sampling Technique (SMOTE). The proposal employs four ML algoithms including Logistic Regression, Random Forest, K-nearest Neighbor and Decision Tree ensuring that the model is trained effectively on minority class instances using SMOTE. Our results demonstrate a significant reduction in FNR, facilitating earlier detection and timely intervention for patients. We achieved around 71%-92% reduction in the false negative rate, leading to a substantial enhancement in the overall diagnostic performance of the model including precision upto 34%, recall upto 91%, f1-score upto 81% for different ML algorithms. Thus, the importance of this research lies in enhancing diagnostic performance and improving patient outcomes, facilitating a more effective and empathetic approach to mental health diagnosis.
In this paper, we propose BR-MTRL, a Byzantine-resilient multi-task representation learning framework that handles faulty or malicious agents. Our approach leverages representation learning through a shared neural net...
详细信息
Due to speedy development in internet technology, peoples have usually dependent upon internet enabled digital equipment’s in a wide range of application. As a result, different challenges relating to information sec...
详细信息
Campus violence is a critical social issue affecting educational institutions around the world. The extremely high frequency not only affects the actual learning process but leads to anxiety and adversely affects both...
详细信息
This research studies new methods used to detect SAD problems based on both mental and physical signals. Because mental health problems affect people worldwide traditional ways to identify these issues and diagnose th...
详细信息
ISBN:
(数字)9798331519582
ISBN:
(纸本)9798331519599
This research studies new methods used to detect SAD problems based on both mental and physical signals. Because mental health problems affect people worldwide traditional ways to identify these issues and diagnose them do not work for today's demands. This research evaluates AI-powered methods using several input sources including speech, facial expressions and biometric information to better screen patients and expand testing capacity. This discussion covers issues with patient data changes and ethical questions while exploring new methods including transformer processing and shared learning. These results show that AI can change how mental health is diagnosed by helping doctors catch problems sooner and deliver better results to patients.
A need for a strategic framework for tweet classification and recommendation has emerged, specifically for geographical catastrophes and events. This paper proposes a semantics-oriented model for disaster tweet classi...
详细信息
Millimeter-wave network deployment is an essential and ongoing problem due to the limited coverage and expensive network infrastructure. In this work, we solve a joint network deployment and resource allocation optimi...
详细信息
Millimeter-wave network deployment is an essential and ongoing problem due to the limited coverage and expensive network infrastructure. In this work, we solve a joint network deployment and resource allocation optimization problem for a mmWave cell-free massive MIMO network considering indoor environments. The objective is to minimize the number of deployed access points (APs) for a given environment, bandwidth, AP cooperation, and precoding scheme while guaranteeing the rate requirements of the user equipments (UEs). Considering coherent joint transmission (C-JT) and non-coherent joint transmission (NC-JT), we solve the problem of AP placement, UE-AP association, and power allocation among the UEs and resource blocks jointly. For numerical analysis, we model a mid-sized airplane cabin in ray-tracing as an exemplary case for IDS. Results demonstrate that a minimum data rate of 1 Gbps can be guaranteed with less than 10 APs with C-JT. From a holistic network design perspective, we analyze the trade-off between the required fronthaul capacity and the processing capacity per AP, under different network functional split options. We observe an above 600 Gbps fronthaul rate requirement, once all network operations are centralized, which can be reduced to 200 Gbps under physical layer functional splits. 2002-2012 IEEE.
Software quality enhancement can be done by identifying the refactoring scope of the existing open-source projects in real time. The refactoring mechanism alters the internal structure of the code base without changin...
详细信息
ISBN:
(数字)9798331522100
ISBN:
(纸本)9798331522117
Software quality enhancement can be done by identifying the refactoring scope of the existing open-source projects in real time. The refactoring mechanism alters the internal structure of the code base without changing the external result. Objectives: In this work, we have assured the project quality by considering different source code metrics as input that helps to evaluate the refactoring score. Methodology: Software metrics used are NOI, SLOC, LOC, WMC, and CCL are considered as input parameters and implemented five different types of boosting algorithms. Result Analysis: As there are many extra features, we have selected 20 relevant features out of 115 using Recursive Feature Elimination (RFE). It is observed that Extreme Gradient Boosting (XGB) is best suitable for identifying refactoring opportunities with an accuracy of 99%.Conclusion: A comparison of projects is performed and Titan projects highly required refactoring as it contains more dirty code.
暂无评论