7 results for “Model Footprint”

Set a search alert

Research ArticleOpen accessIn the keywordsOptimized WFST-Based ASR for Arabic: Balancing Memory, Speed, and AccuracyWael A. Sultan, Mourad S. Semary, Sherif M. AbdouWeighted Finite-State Transducers (WFSTs) have revolutionized Automatic Speech Recognition (ASR) by enabling significantly faster decoding speeds compared to traditional systems that build the search space progressively. However, applying WFSTs to morphology-rich languages such as Arabic presents challenges due to the large vocabulary, resulting in extensive networks that exceed the memory capacity of standard CPUs. This study introduces various strategies to … …Journal of Computer Science, Vol. 22, Issue 2 · 23 Feb 2026 · 1,442 accessesView PDF Cite

Research ArticleOpen accessIn the keywordsLOW FOOTPRINT HIGH INTELLIGIBILITY MALAY SPEECH SYNTHESIZER BASED ON STATISTICAL DATALau Chee Yong, Tan Tian SweeSpeech synthesis plays a pivotal role nowadays. It can be found in various daily applications such as in mobile phones, navigation systems, languages learning software and so on. In this study, a Malay language speech synthesizer was designed using hidden Markov model to improve the performance of current Malay speech synthesizer and also extend Malay speech technology. Statistical parametric method … …Journal of Computer Science, Vol. 10, Issue 2 · 19 Nov 2013 · 6,722 accessesView PDF Cite

Review ArticleOpen accessIn the abstractHuman Activity Recognition at the Edge: A Systematic Review of Machine Learning Models, Deployment Constraints, and Latency Energy Accuracy Trade offsJose Antonio Rojas Guillén, Wini Ebelin Quispe Bautista, Arturo Gamarra MorenoHuman Activity Recognition (HAR) has become a key component of intelligent healthcare monitoring, assisted living, sports analytics, smart environments, and wearable computing. However, the migration of HAR models from cloud-centered architectures to edge, embedded, mobile, and wearable platforms introduces constraints related to computational capacity, memory footprint, battery consumption, inference time, and real-time responsiveness. This study presents a systematic literature review … …Journal of Computer Science, Vol. 22, Issue 8 · 7 Sep 2026 · 593 accessesView PDF Cite

Research ArticleOpen accessIn the abstractRelationship between Volumetric Water Footprint with Carcass and Meat Quality Characteristics Under Intensive Beef Cattle Production in South AfricaTinny Noluthando Macamba, Takalani Judas Mpofu, Khathutshelo Agree Nephawe et al.As water accessibility becomes more challenging due to the increasing human population and agricultural competition, it is crucial to select beef cattle with optimal water efficiency. The study aimed to investigate the relationship between volumetric water footprint with carcass and meat quality of beef cattle under an intensive production system. Thirty-three (33) beef cattle weaners of three different body frame … …American Journal of Animal and Veterinary Sciences, Vol. 19, Issue 3 · 12 Oct 2024 · 4,728 accessesView PDF Cite

Research ArticleOpen accessIn the abstractA Fuzzy Logic-Based Smart Traffic Management SystemsAdel Abdallah Abdou, Mohamed Hassan Farrag, A. S. TolbaTraffic congestion is a serious problem in many developing countrieslike Egypt. In the presence of thetraditional traffic light system, it creates health risks, wastes time andfuel, and pollutes the air. Therefore, there is a big need for a smart trafficmanagement system. This study contributes in solving this problem byintroducing an artificial intelligence-based smart traffic light system usingfuzzy logic to ensure … …Journal of Computer Science, Vol. 18, Issue 11 · 24 Nov 2022 · 7,180 accessesView PDF Cite

Research ArticleOpen accessIn the abstractEfficient Implementation of Stochastic Computing Based Deep Neural Network on Low Cost Hardware with Saturation ArithmeticSunny Bodiwala, Nirali NanavatiThis study presents an efficient and rapid implementation of Stochastic Computing (SC) based Deep Neural Network (DNN) on a low-cost hardware platform. The proposed technique uses bipolar signal encoding in stochastic computing which relatively gives low hardware footprint compared to binary computing. Thereinafter, stochastic max function is presented and subsequently used to approximate the hyperbolic tangent activation function in SC. … …Journal of Computer Science, Vol. 16, Issue 11 · 17 Nov 2020 · 6,875 accessesView PDF Cite

EditorialOpen accessIn the abstractProtecting crop species from biotic and abiotic constraints in the era of Global Change: are we ready for this challenge?Marco Landi, Giovanni BenelliReliable and affordable supply of food is of crucial importance to the progress and stability of human societies. During the last century, we have assisted to an extraordinary increase of crop yields, especially for the most widespread and consumed crop species, such as rice, wheat, corn and soybean. The Broadbalk experiment, one of the oldest continuous agronomic experiments in the … …American Journal of Agricultural and Biological Sciences, Vol. 11, Issue 2 · 4 Jun 2016 · 8,399 accessesView PDF Cite