This work presents a novel semi-supervised dictionary learning framework that updates the dictionary by online learning and is efficient in utilizing the training data. The method employs a two-stage process to train ...
详细信息
ISBN:
(数字)9798331506520
ISBN:
(纸本)9798331506537
This work presents a novel semi-supervised dictionary learning framework that updates the dictionary by online learning and is efficient in utilizing the training data. The method employs a two-stage process to train the dictionary: initial training with limited labeled data, followed by online refinement using abundant unlabeled data. We introduce an adaptive correction weight to control the influence of new unlabeled data on the dictionary update based on its consistency with the current model estimate. This approach enables efficient use of the training data set. Moreover, results in faster dictionary convergence and improves data representation accuracy, especially in scenarios with limited training data. Experimental results demonstrate significant enhancement in the classification accuracy of the proposed method compared to the state-of-the-art semi-supervised dictionary learning methods, particularly when dealing with a limited number of training samples.
In the current era, the deployment of video surveillance systems (VSSs) is becoming a common practice in society for properly maintaining laws and order in public and private places. The surveillance video data (SD) g...
详细信息
This paper presents Super-LoRa, a novel approach to enhancing the throughput of LoRa networks by leveraging the inherent robustness of LoRa modulation against interference. By superimposing multiple payload symbols, S...
详细信息
Wireless sensor networks (WSNs) have so many uses, both in the military and in the civilian world, they are becoming one of the most popular research topics in computerscience. Many sensor nodes make up a WSN, and th...
详细信息
Wireless sensor networks (WSNs) have so many uses, both in the military and in the civilian world, they are becoming one of the most popular research topics in computerscience. Many sensor nodes make up a WSN, and they all gather and forward data to the central point. However, there are a number of security concerns with WSN due to deployment strategies, communication routes, and resource-constrained nodes. Determining unauthorized access is therefore crucial to enhancing security. The Intrusion Detection System (IDS) is necessary to guarantee the dependability and security of WSN services. This IDS must be able to identify the greatest number of security threats and be in harmony with the features of WSNs. All communication networks require the services provided by the network intrusion detection system (NIDS). IDS frequently include machine learning (ML) approaches; yet, ML techniques’ effectiveness is subpar when dealing with imbalanced attacks. This research proposed an IDS implied on deep neural networks (DNN) to enhance performance. The most effective features from the dataset are chosen through the cross-correlation method. Next, a DNN structure that is intended to detect intrusions is developed using the parameters that have been chosen. The NSL-KDD intrusion dataset is used for testing-training for the proposed model. According to the experiment’s outcomes such as Accuracy 96.23%, Precision 95.75%, and Recall 92.82% the proposed DNN performs more efficiently in detecting attacks over traditional ML models like RF(random forests), DT(Decision trees), and SVM(Support vector machine) and DL model like Autoencoder.
Cryptocurrency mining data centers consume 100-200 times more energy than conventional office areas annually. Regulating power consumption, cooling mechanisms, and thermal control performance is crucial to creating a ...
详细信息
Cryptocurrency mining data centers consume 100-200 times more energy than conventional office areas annually. Regulating power consumption, cooling mechanisms, and thermal control performance is crucial to creating a greener and more energy-efficient crypto-mining data center. This paper presents a new cryptocurrency mining data center design that is both environmentally friendly and energy-efficient. The design considers popular green and energy-saving data center cooling and temperature management approaches, as well as cost-effective operations. The total monthly cost of the proposed data center is 358025 USD, with renewable energy generating 68520 kW of electricity. The monthly profit from Bitcoin mining is 3200806.969 USD, while Ethereum mining is 2317353.503 USD. The PUE number is 1.04, and the DCiE is 96.15 percent. These statistics help determine the model’s conclusion.
This paper introduces a prototype for a new approach to assistive robotics, integrating edge computing with Natural Language Processing (NLP) and computer vision to enhance the interaction between humans and robotic s...
详细信息
The increasing spread of diseases transmitted by mosquitoes, including malaria and dengue, poses a major global health challenge. Traditional mosquito detection methods, which are based on manual trapping and counting...
The increasing spread of diseases transmitted by mosquitoes, including malaria and dengue, poses a major global health challenge. Traditional mosquito detection methods, which are based on manual trapping and counting, are time-consuming and inefficient for continuous monitoring. Recently, sensor-based systems have been developed that utilize acoustic signatures. Still, their effectiveness is limited by deep learning models that struggle with noisy environments and fail to adapt to new conditions. Additionally, the scarcity of labeled data for training these models remains a significant obstacle, further reducing their accuracy and generalizability. This paper proposes a novel approach to overcome these limitations by developing an adaptable pipeline to create environment-specific deep-learning models for mosquito detection at diverse locations. This study addresses the challenge of data scarcity and evaluates various feature extraction strategies, such as log-mel and per-channel energy normalization (PCEN), can enhance model robustness in different environmental settings. Our proposed solution successfully creates models that achieve accuracy greater than 90% for any given environment, improving adaptability and supporting public health efforts to control vector-borne diseases. Experimental results confirm this by testing CNN and TCN models in different environments. PCEN preprocessing outperformed log Mel, with the CNN model achieving the highest accuracy of 93.25% in the open environment. Cross-testing results further justify the approach of using environment-specific models.
The transition from traditional energy or electrical grids to smart energy or electrical grids has significantly transformed energy management. This evolution emphasizes decentralization, efficiency, and sustainabilit...
详细信息
The transition from traditional energy or electrical grids to smart energy or electrical grids has significantly transformed energy management. This evolution emphasizes decentralization, efficiency, and sustainability in energy systems. However, it also introduces numerous risks, including cyber-physical system vulnerabilities and challenges in energy trading. The application of blockchain and Machine Learning (ML) offers potential solutions to these issues. Blockchain enhances energy transactions by making them safer, more transparent, and tamper-proof, while ML optimizes grid performance by improving predictions, fault detection, and anomaly identification. This systematic review examines the application of blockchain and ML in peer-to-peer (P2P) energy trading within smart grids and analyzes how these technologies complement each other in mitigating risks and enhancing the efficiency of smart grids. Blockchain enhances security by providing privacy for transactions and maintaining immutable records, while ML predicts market trends, identifies fraudulent activities, and ensures efficient energy use. The paper identifies critical challenges in smart grids, such as unsecured communication channels and vulnerabilities to cyber threats, and discusses how blockchain and ML address these issues. Furthermore, the study explores emerging trends, such as lightweight blockchain systems and edge computing, to overcome implementation challenges. A new architecture is proposed, integrating blockchain with ML algorithms to create resilient, secure, and efficient energy trading markets. The paper underscores the need for global standardization, improved cybersecurity measures, and further research into how blockchain and ML can revolutionize smart grids. This study integrates current knowledge with a forward-looking perspective, providing valuable insights for researchers, policymakers, and stakeholders in the energy sector to collaboratively build a future of efficient and int
Cloud security is an important aspect in centralized data management in public resources. By increasing data processing and service access level, the integrity level be deformed due to data leakage, spoofing, and key ...
详细信息
The increasing deployment of data-intensive applications on mobile devices poses a formidable challenge in designing flash-based file systems tailored to these needs. Studies have shown that adopting delta compression...
详细信息
暂无评论