arXiv subjects

Mohammad Ebrahimi

Publications and source records attributed to Mohammad Ebrahimi.

5 recordsLinked to original sources

arXiv2024

Energy Efficient Computation Offloading and Virtual Connection Control in Uplink Small Cell Networks

Nowadays, the use of soft computational techniques in power systems under the umbrella of machine learning is increasing with good reception. In this paper, we first present a deep learning approach to find the optimal configuration for HetNet systems. We used a very large number of radial configurations of a test system for training purposes. We also studied the issue of joint carrier/power allocation in multilayer hierarchical networks, in addition to ensuring the quality of experience for all subscribers, to achieve optimal power efficiency. The proposed method uses an adaptive load equilibrium model that aims to achieve "almost optimal" equity among all servers from the standpoint of the key performance indicator. Unlike current model-based energy efficiency methods, we propose a joint resource allocation, energy efficiency, and flow control algorithm to solve common nonconvex and hierarchical optimization problems. Also, by referring to the allocation of continuous resources based on SLA, we extended the proposed algorithm to common flow/power control and operational power optimization algorithm to achieve optimal energy efficiency along with ensuring user's throughput limitations. Also, simulation results show that the proposed controlled power/flow optimization approach can significantly increase energy efficiency compared to conventional designs using network topology adjustment capability.

cs.NI↗

arXiv2024

A New Method for Cross-Lingual-based Semantic Role Labeling

Semantic role labeling is a crucial task in natural language processing, enabling better comprehension of natural language. However, the lack of annotated data in multiple languages has posed a challenge for researchers. To address this, a deep learning algorithm based on model transfer has been proposed. The algorithm utilizes a dataset consisting of the English portion of CoNLL2009 and a corpus of semantic roles in Persian. To optimize the efficiency of training, only ten percent of the educational data from each language is used. The results of the proposed model demonstrate significant improvements compared to Niksirt et al.'s model. In monolingual mode, the proposed model achieved a 2.05 percent improvement on F1-score, while in cross-lingual mode, the improvement was even more substantial, reaching 6.23 percent. Worth noting is that the compared model only trained two of the four stages of semantic role labeling and employed golden data for the remaining two stages. This suggests that the actual superiority of the proposed model surpasses the reported numbers by a significant margin. The development of cross-lingual methods for semantic role labeling holds promise, particularly in addressing the scarcity of annotated data for various languages. These advancements pave the way for further research in understanding and processing natural language across different linguistic contexts.

cs.CL↗

arXiv2023

Fast and Scalable Beamforming for RIS-Assisted Downlink Multi-group Multicasting

This paper considers downlink multi-group multicasting via beamforming facilitated by a reconfigurable intelligent surface (RIS). We develop a fast and scalable algorithm for the joint base station (BS) and RIS beamforming optimization to minimize the transmit power while meeting user quality-of-service (QoS) targets. By analyzing the structure of the QoS constraints, we reformulate the problem and show that the joint beamforming optimization inherently consists of a multicast beamforming QoS problem for the BS and a passive multicast beamforming max-min-fair (MMF) problem for the RIS. We propose a fast alternating multicast beamforming (AMBF) algorithm to effectively solve the two subproblems alternatingly. For the BS multicast subproblem, we utilize the optimal multicast beamforming structure to efficiently determine the BS beamformers. For the RIS multicast subproblem, we reformulate the MMF problem and apply a first-order projected subgradient algorithm (PSA), which yields simple closed-form updates. The computational complexity of the AMBF algorithm grows linearly with the number of RIS elements and BS antennas. We further consider joint BS and RIS beamforming for the weighted MMF design objective, subject to the BS transmit power budget. We propose an alternating PSA (APSA) fast algorithm to compute the beamforming solutions for the BS and RIS. APSA consists of only closed-form updates per iteration, yielding linear computational complexity in the number of RIS elements and BS antennas. Simulation results show the efficacy of our proposed algorithms in terms of performance and computational cost compared to alternative methods.

eess.SP↗

arXiv2017

A Semantically Motivated Approach to Compute ROUGE Scores

ROUGE is one of the first and most widely used evaluation metrics for text summarization. However, its assessment merely relies on surface similarities between peer and model summaries. Consequently, ROUGE is unable to fairly evaluate abstractive summaries including lexical variations and paraphrasing. Exploring the effectiveness of lexical resource-based models to address this issue, we adopt a graph-based algorithm into ROUGE to capture the semantic similarities between peer and model summaries. Our semantically motivated approach computes ROUGE scores based on both lexical and semantic similarities. Experiment results over TAC AESOP datasets indicate that exploiting the lexico-semantic similarity of the words used in summaries would significantly help ROUGE correlate better with human judgments.

cs.CL↗

arXiv2016

On Improving Informativity and Grammaticality for Multi-Sentence Compression

Multi Sentence Compression (MSC) is of great value to many real world applications, such as guided microblog summarization, opinion summarization and newswire summarization. Recently, word graph-based approaches have been proposed and become popular in MSC. Their key assumption is that redundancy among a set of related sentences provides a reliable way to generate informative and grammatical sentences. In this paper, we propose an effective approach to enhance the word graph-based MSC and tackle the issue that most of the state-of-the-art MSC approaches are confronted with: i.e., improving both informativity and grammaticality at the same time. Our approach consists of three main components: (1) a merging method based on Multiword Expressions (MWE); (2) a mapping strategy based on synonymy between words; (3) a re-ranking step to identify the best compression candidates generated using a POS-based language model (POS-LM). We demonstrate the effectiveness of this novel approach using a dataset made of clusters of English newswire sentences. The observed improvements on informativity and grammaticality of the generated compressions show that our approach is superior to state-of-the-art MSC methods.

cs.CL↗