The increasing dependence on smartphones with advanced sensors has highlighted the imperative of precise transportation mode classification, pivotal for domains like health monitoring and urban planning. This research...
详细信息
The increasing dependence on smartphones with advanced sensors has highlighted the imperative of precise transportation mode classification, pivotal for domains like health monitoring and urban planning. This research is motivated by the pressing demand to enhance transportation mode classification, leveraging the potential of smartphone sensors, notably the accelerometer, magnetometer, and gyroscope. In response to this challenge, we present a novel automated classification model rooted in deep reinforcement learning. Our model stands out for its innovative approach of harnessing enhanced features through artificial neural networks (ANNs) and visualizing the classification task as a structured series of decision-making events. Our model adopts an improved differential evolution (DE) algorithm for initializing weights, coupled with a specialized agent-environment relationship. Every correct classification earns the agent a reward, with additional emphasis on the accurate categorization of less frequent modes through a distinct reward strategy. The Upper Confidence Bound (UCB) technique is used for action selection, promoting deep-seated knowledge, and minimizing reliance on chance. A notable innovation in our work is the introduction of a cluster-centric mutation operation within the DE algorithm. This operation strategically identifies optimal clusters in the current DE population and forges potential solutions using a pioneering update mechanism. When assessed on the extensive HTC dataset, which includes 8311 hours of data gathered from 224 participants over two years. Noteworthy results spotlight an accuracy of 0.88±0.03 and an F-measure of 0.87±0.02, underscoring the efficacy of our approach for large-scale transportation mode classification tasks. This work introduces an innovative strategy in the realm of transportation mode classification, emphasizing both precision and reliability, addressing the pressing need for enhanced classification mechanisms in an eve
Channel prediction permits to acquire channel state information(CSI) without signaling overhead. However,almost all existing channel prediction methods necessitate the deployment of a dedicated model to accommodate a ...
详细信息
Channel prediction permits to acquire channel state information(CSI) without signaling overhead. However,almost all existing channel prediction methods necessitate the deployment of a dedicated model to accommodate a specific configuration. Leveraging the powerful modeling and multi-task learning capabilities of foundation models, we propose the first space-time-frequency(STF) wireless foundation model(WiFo) to address time-frequency channel prediction tasks in a unified manner. Specifically, WiFo is initially pre-trained over massive and extensive diverse CSI datasets. Then, the model will be instantly used for channel prediction under various CSI configurations without any fine-tuning. We propose a masked autoencoder(MAE)-based network structure for WiFo to handle heterogeneous STF CSI data, and design several mask reconstruction tasks for self-supervised pre-training to capture the inherent 3D variations of CSI. To fully unleash its predictive power, we build a large-scale heterogeneous simulated CSI dataset consisting of 160k CSI samples for *** validate its superior unified learning performance across multiple datasets and demonstrate its state-of-the-art(SOTA) zero-shot generalization performance via comparisons with other full-shot baselines.
The accurate and early detection of abnormalities in fundus images is crucial for the timely diagnosis and treatment of various eye diseases, such as glaucoma and diabetic retinopathy. The detection of abnormalities i...
详细信息
The accurate and early detection of abnormalities in fundus images is crucial for the timely diagnosis and treatment of various eye diseases, such as glaucoma and diabetic retinopathy. The detection of abnormalities in fundus images using traditional methods is often challenging due to high computational demands, scalability issues, and the requirement of large labeled datasets for effective training. To address these limitations, a new method called triplet-based orchard search (Triplet-OS) has been proposed in this paper. In this study, a GoogleNet (Inception) is utilized for feature extraction of fundus images. Also, the residual network is employed to detect abnormalities in fundus images. The Triplet-OS utilizes the medical imaging technique fundus photography dataset to capture detailed images of the interior surface of the eye, known as the fundus and the fundus includes the retina, optic disk, macula, and blood vessels. To enhance the performance of the Triplet-OS method, the orchard optimization algorithm has been implemented with an initial search strategy for hyperparameter optimization. The performance of the Triplet-OS method has been evaluated based on different metrics such as F1-score, specificity, AUC-ROC, recall, precision, and accuracy. Additionally, the performance of the proposed method has been compared with existing methods. Few-shot learning refers to a process where models can learn from just a small number of examples. This method has been applied to reduce the dependency on deep learning [1]. The goal is for machines to become as intelligent as humans. Today, numerous computing devices, extensive datasets, and advanced methods such as CNN and LSTM have been developed. AI has achieved human-like performance and, in many fields, surpasses human abilities. AI has become part of our daily lives, but it generally relies on large-scale data. In contrast, humans can often apply past knowledge to quickly learn new tasks [2]. For example, if given
In recent years,developed Intrusion Detection Systems(IDSs)perform a vital function in improving security and anomaly *** effectiveness of deep learning-based methods has been proven in extracting better features and ...
详细信息
In recent years,developed Intrusion Detection Systems(IDSs)perform a vital function in improving security and anomaly *** effectiveness of deep learning-based methods has been proven in extracting better features and more accurate classification than other *** this paper,a feature extraction with convolutional neural network on Internet of Things(IoT)called FECNNIoT is designed and implemented to better detect anomalies on the ***,a binary multi-objective enhance of the Gorilla troops optimizer called BMEGTO is developed for effective feature ***,the combination of FECNNIoT and BMEGTO and KNN algorithm-based classification technique has led to the presentation of a hybrid method called *** the next step,the proposed model is implemented on two benchmark data sets,NSL-KDD and TON-IoT and tested regarding the accuracy,precision,recall,and Fl-score *** proposed CNN-BMEGTO-KNN model has reached 99.99%and 99.86%accuracy on TON-IoT and NSL-KDD datasets,*** addition,the proposed BMEGTO method can identify about 27%and 25%of the effective features of the NSL-KDD and TON-IoT datasets,respectively.
作者:
Puri, ChetanReddy, K.T.V.
Department of Computer Science and Design Wardha India
Department of Artificial Intelligence and Data Science Wardha India
Fetal growth restriction and preterm delivery proceed to be major around the world wellbeing concerns, with serious consequences for the wellbeing of moms and babies. Provoke and exact estimating of these issues is ba...
详细信息
Cloud computing involves accessing and using computing resources, such as servers, storage, and software applications, over the Internet, enabling scalable access on demand. Cloud computing systems are becoming an ess...
详细信息
The rapid evolution of wireless technologies and the growing complexity of network infrastructures necessitate a paradigm shift in how communication networks are designed,configured,and managed. Recent advancements in...
详细信息
The rapid evolution of wireless technologies and the growing complexity of network infrastructures necessitate a paradigm shift in how communication networks are designed,configured,and managed. Recent advancements in large language models (LLMs) have sparked interest in their potential to revolutionize wireless communication systems. However, existing studies on LLMs for wireless systems are limited to a direct application for telecom language understanding. To empower LLMs with knowledge and expertise in the wireless domain, this paper proposes WirelessLLM, a comprehensive framework for adapting and enhancing LLMs to address the unique challenges and requirements of wireless communication networks. We first identify three foundational principles that underpin WirelessLLM:knowledge alignment, knowledge fusion, and knowledge evolution. Then,we investigate the enabling technologies to build WirelessLLM, including prompt engineering, retrieval augmented generation, tool usage, multi-modal pre-training, and domain-specific fine-tuning. Moreover, we present three case studies to demonstrate the practical applicability and benefits of WirelessLLM for solving typical problems in wireless networks. Finally, we conclude this paper by highlighting key challenges and outlining potential avenues for future research.
Windows malware is becoming an increasingly pressing problem as the amount of malware continues to grow and more sensitive information is stored on *** of the major challenges in tackling this problem is the complexit...
详细信息
Windows malware is becoming an increasingly pressing problem as the amount of malware continues to grow and more sensitive information is stored on *** of the major challenges in tackling this problem is the complexity of malware analysis,which requires expertise from human *** developments in machine learning have led to the creation of deep models for malware ***,these models often lack transparency,making it difficult to understand the reasoning behind the model’s decisions,otherwise known as the black-box *** address these limitations,this paper presents a novel model for malware detection,utilizing vision transformers to analyze the Operation Code(OpCode)sequences of more than 350000 Windows portable executable malware samples from real-world *** model achieves a high accuracy of 0.9864,not only surpassing the previous results but also providing valuable insights into the reasoning behind the *** model is able to pinpoint specific instructions that lead to malicious behavior in malware samples,aiding human experts in their analysis and driving further advancements in the *** report our findings and show how causality can be established between malicious code and actual classification by a deep learning model,thus opening up this black-box problem for deeper analysis.
Capturing the distributed platform with remotely controlled compromised machines using botnet is extensively analyzed by various ***,certain limitations need to be addressed *** provisioning of detection mechanism wit...
详细信息
Capturing the distributed platform with remotely controlled compromised machines using botnet is extensively analyzed by various ***,certain limitations need to be addressed *** provisioning of detection mechanism with learning approaches provides a better solution more broadly by saluting multi-objective *** bots’patterns or features over the network have to be analyzed in both linear and non-linear *** linear and non-linear features are composed of high-level and low-level *** collected features are maintained over the Bag of Features(BoF)where the most influencing features are collected and provided into the classifier ***,the linearity and non-linearity of the threat are evaluated with Support Vector Machine(SVM).Next,with the collected BoF,the redundant features are eliminated as it triggers overhead towards the predictor ***,a novel Incoming data Redundancy Elimination-based learning model(RedE-L)is built to classify the network features to provide robustness towards BotNets *** simulation is carried out in MATLAB environment,and the evaluation of proposed RedE-L model is performed with various online accessible network traffic dataset(benchmark dataset).The proposed model intends to show better tradeoff compared to the existing approaches like conventional SVM,C4.5,RepTree and so ***,various metrics like Accuracy,detection rate,Mathews Correlation Coefficient(MCC),and some other statistical analysis are performed to show the proposed RedE-L model's *** F1-measure is 99.98%,precision is 99.93%,Accuracy is 99.84%,TPR is 99.92%,TNR is 99.94%,FNR is 0.06 and FPR is 0.06 respectively.
Artificial intelligence together with its applications are advancing in all fields, particularly medical science. A considerable quantity of clinical data is available, yet the vast majority of it is wasted. It will b...
详细信息
暂无评论