Many machine learning algorithms and almost all deep learning architectures are incapable of processing plain texts in their raw form. This means that their input to the algorithms must be numerical in order to solve classification or regression problems. Hence, it is necessary to encode these categorical variables into numerical values using encoding techniques. Categorical features are common and often of high cardinality. One-hot encoding in such circumstances leads to very high dimensional vector representations, raising memory and computability concerns for machine learning models. This paper proposes a deep-learned embedding technique for categorical features encoding on categorical datasets. Our technique is a distributed representation for categorical features where each category is mapped to a distinct vector, and the properties of the vector are learned while training a neural network. First, we create a data vocabulary that includes only categorical data, and then we use word tokenization to make each categorical data a single word. After that, feature learning is introduced to map all of the categorical data from the vocabulary to word vectors. Three different datasets provided by the University of California Irvine (UCI) are used for training. The experimental results show that the proposed deeplearned embedding technique for categorical data provides a higher F1 score of 89% than 71% of onehot encoding, in the case of the Long short-term memory (LSTM) model. Moreover, the deep-learned embedding technique uses less memory and generates fewer features than one-hot encoding.
Wireless-powered communication networks (WPCNs) consist of wireless devices (WDs) that transmit information to the hybrid access point (HAP). In this situation, there is interference among WDs that is considered to be noise and causes information loss because of adjacent signals. Moreover, power is limited and can be lost if transmission distance is long. This paper studies sum-throughput maximization with sectored cells for WPCN. We designed a downlink (DL) energy beamforming by sector based on the hybrid space division multiple access (SDMA) and nonorthogonal multiple access (NOMA) approach to maximize the sum throughput. First, a cell is divided into several sectors, and signals from each sector are transmitted to each antenna of the HAP, so that the signals are not adjacent. Further, the HAP decodes the overlapping information of each sector. Next, power allocation is optimized by sector. To optimize power allocation, a constrained optimization problem is formulated and then converted into a nonconstraint optimization problem using the interior penalty method. The optimal solution derives the maximal value to the problem. Power for each sector is optimally allocated according to this optimal solution. Under this consideration, sum-throughput maximization is performed by optimally allocating DL energy beamforming by sector. We analyzed sum throughput and fairness, and then compared them according to the number of sectors. Performance results show that the proposed optimal power allocation by sector using hybrid SDMA/NOMA outperforms the existing equal power allocation by sector in terms of the sum throughput while fairness is also maintained. Moreover, the performance difference between the hybrid approach and SDMA, which optimally allocates power by sector, was about 1.4 times that of sum throughput on average, and the hybrid approach was dominant. There was also no difference in fairness performance.
The communication paradigms for Delay/Disruption Tolerant Networks (DTN) have been modeled after email. Supporting email over DTN in a backwards compatible manner in a heterogeneous environment has yet to be fully defined. In the Simple Mail Transfer Protocol (SMTP) based on TCP/IP used in the existing terrestrial Internet, the protocol works through multiple interactions between the sender’s mail server and the receiver’s mail server. However, in the space Internet environment, since the contact times are limited, reliability cannot be guaranteed for the interaction between the server and the client used in the existing SMTP. Therefore, this paper proposes a novel mail transfer protocol, DTN-SMTP for space Internet over DTN. To minimize the interaction of the existing SMTP, it relies on one-way transmission and optionally performs retransmission mechanisms. Finally, we have built and configured two DTN nodes to implement DTN-SMTP. Also, we have confirmed the mail’s reception and the file attachment from the external mail client with minimized interactions between the SMTP messages.
Wireless Powered Communication Network (WPCN) consists of Hybrid Access Point (HAP) that performs power transmission and data collection at the same time, and multiple nodes that can transmit data. In WPCN, depending on the wireless communication environment, the nodes cannot be able to transmit data because they can fail to receive power. Hence, increasing the transmission rate under a given resource is one of the very important issues. In ordinary mobile communications, a cell is divided into several sectors and the data is collected through multiple antennas to increase the transmission rate using SDMA. As a result, if the number of nodes in the one sector increases, the interference between nodes increases, and the transmission rate may decrease. Accordingly, in order to maximize performance, the number of nodes that can exist in a sector must be limited. The transmission rate between nodes according to the distance difference may not be fair because the nodes far from the HAP charge a small amount of power by attenuation of the signal, and the nodes close to the HAP charge a relatively large amount of power. Therefore, we propose Hybrid SDMA and Non-Orthogonal Multiple Access (NOMA) as a way to maximize the performance in term of both Sum-Throughput and Fairness. Also, we prove that there is a tradeoff between Sum-Throughput and Fairness according to the number of sectors. The simulation results show that the Hybrid SDMA and NOMA improves the performance substantially compared to the conventional SDMA.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.