IAES International Journal of Artificial Intelligence (IJ-AI)
Not a member yet
1769 research outputs found
Sort by
Reinforcement of low-resource language translation with neural machine translation and backtranslation synergies
Get PDFThis research investigates challenges and advancements in neural machine translation (NMT), specifically targeting English-to-Kannada translation. Emphasizing the scarcity of data and linguistic complexity in low-resource languages (LRL), particularly Kannada, the study underscores the need for specialized techniques. Starting with exploration of Kannada's historical and cultural significance, the paper highlights critical importance of linguistic comprehension. The primary objective is to develop robust NMT models for precise and contextually relevant translations in low-resource scenarios. The novelty of this research lies in its innovative approach to Kannada NMT challenges, incorporating comprehensive examination of historical and cultural context to establish strong linguistic foundation. Motivated by the urgency to address translation needs in LRL, the paper proposes novel strategies, advocating notably for backtranslation to generate synthetic parallel corpora. Rigorous testing, including bilingual evaluation understudy (BLEU) score assessments, evaluates effectiveness of these proposed approaches. Beyond assessing backtranslation, the study explores challenges faced by Kannada NMT in handling dialectical and spelling variations. The research reports substantial 83-percentage-point average increase in BLEU scores, contingent on aligning unique Kannada terms with the same domain as existing occurrences. This study contributes significantly to Kannada natural language processing by offering novel insights into NMT intricacies and providing practical solutions for enhancing translation accuracy in low-resource settings
Optimized multi-layer self-attention network for feature-level data fusion in emotion recognition
Get PDFUnderstanding human emotions across diverse data sources presents challenges in various applications including healthcare, human-machine interaction, security, marketing, and gaming. Prior research has explored fusion techniques to address multimodal data heterogeneity, yet often overlooks the importance of discriminative unimodal information and potential complementarity among fusion strategies. Recognizing emotions from video and audio data poses challenges such as non-verbal cues interpretation, varying expression, ambiguity in context, and the need for nuanced feature extraction to capture subtle emotional nuances accurately. To tackle these issues, it is imperative to employ efficient emotion representation and multimodal fusion techniques, as these tasks have significant importance within the realm of multifaceted recognizing study. This study introduced a novel approach, optimized multi-layer self-attention network for emotion recognition (OMSN-ER), focusing on feature-level data fusion. OMSN-ER precisely assesses emotional states by merging facial and voice data, utilizing a multi-layer progressive dense residual fusion network and a self-attention mountain gazelle convolution neural network. Implemented in Python with the RAVDESS dataset, the methodology achieves exceptional accuracy (0.9908), surpassing benchmarks and demonstrating efficacy in multimodal emotion recognition. This research represents promising advancements in the intricate field of emotion recognition
Automatic speech recognition for Indonesian medical dictation in cloud environment
Get PDFThis paper introduces SPWPM, an automatic speech recognition (ASR) system designed specifically for Indonesian medical dictation. The main objective of SPWPM is to assist medical professionals in producing medical reports and diagnosing patients. Deployed within a cloud computing service architecture, SPWPM strives to achieve a minimum speech recognition accuracy of 95%. The ASR model of SPWPM is developed using Kaldi and PyChain technologiesβcreating a comprehensive training dataset involving collaboration with PT Dua-Empat-Tujuh and Harapan Kita Hospital. Several optimization techniques were applied, including language modeling with smoothing, lexicon generation using the Grapheme-to-Phoneme Converter, and data augmentation. The readiness of this technology to assist hospital users was assessed through two evaluations: the SPWPM architecture test and the SPWPM speech recognition test. The results demonstrate the system's preparedness in accurately transcribing medical dictation, showcasing its potential to enhance medical reporting for healthcare professionals in hospital environments
Enhancing road image clarity with residual neural network dehazing model
Get PDFLane markers, or road markers, are the painted lines on a roadway that separate different lanes of traffic. Lane markers guide drivers and ensure orderly vehicle flow. They are essential for advanced driver assistance systems (ADAS), providing reference points for vehicle positioning on the road. These markers enable ADAS to give warnings, assistance, and automation features that enhance driver safety and convenience. However, unpredictable illumination, such as a foggy environment, can suppress marker visibility, impacting ADAS's performance. Deep learning-based methods are well-known for their superiority in handling various haze patterns. This paper presents a residual network (ResNet)-based deep learning model to improve road image clarity impacted by fog. The residual neural network dehaze model (RNN-D) utilises a joint loss function to produce haze-free images with improved lighting conditions and enhanced details. The model was trained, validated, and fine-tuned using hazy and corresponding non-hazy datasets to ensure that the model is quantitatively superior in the peak signal-to-noise ratio (PSNR) and the structural similarity index measure (SSIM). RNN-D achieved an average PSNR of 27.98 and SSIM of 0.8 on multiple open sourced datasets. The proposed algorithm's superior performance and visually appealing results make it a powerful tool for real-world image dehazing applications
The performance analysis of hyper-heuristics algorithms over examination timetabling problems
Get PDFIn general, uncapacitated exam timetabling is conducted manually, which can be time-consuming. Many studies aim to automate and optimize uncapacitated exam timetabling. However, pinpointing the most efficient algorithm is challenging since most studies assert that their algorithms surpass previous ones. To identify the optimal algorithm, this research evaluates the performance of four algorithms: Hill climbing (HC), simulated annealing (SA), great deluge (GD), and tabu search (TS) in addressing the exam timetabling problem. The Kempe chain operatorβs influence on optimization solutions is also examined. A simple random method is employed to select the low-level heuristic (LLH). The Carter (Toronto) dataset served as the test material, with each algorithm undergoing 200,000 iterations for comparison. The results indicate that the TS algorithm is superior, providing the best solution in 13 instances. The use of a tabu list enhanced the search processβs efficiency by preventing redundant modifications. The Kempe chain LLH exhibited a tendency towards achieving better solutions
A survey on plant leaf disease identification and classification by various machine-learning technique
Get PDFAn overview of methods for identifying plants diseases is given in this article. Each sample is categorized by being divided into various groups. The approach of classification involves identifying healthy and diseased leaves based on morphological traits including texture, color, shape, and pattern, among others. Sorting and categorizing plants can be challenging, especially when doing so across a large area, due to the closeness of their visual qualities. There are several methods based on computer vision and image processing. Selecting the right categorization method can be difficult because the outcomes rely on the data you supply. There are several applications for the categorization of plant leaf diseases in fields like agriculture and biological research. This article gives a summary of several approaches currently in use for identifying and categorizing leaf diseases, as well as their benefits and drawbacks. These approaches include preprocessing methods, feature extraction and selection methods, datasets employed, classifiers, and performance metric
A hybrid deep learning optimization for predicting the spread of a new emerging infectious disease
Get PDFIn this study, a novel approach geared toward predicting the estimated number of coronavirus disease (COVID-19) cases was developed. Combining long short-term memory (LSTM) neural networks with particle swarm optimization (PSO) along with grey wolf optimization (GWO) employ hybrid optimization algorithm techniques. This investigation utilizes COVID-19 original data from the Ministry of Health of Indonesia, period 2020-2021. The developed LSTM-PSO-GWO hybrid optimization algorithm can improve the performance and accuracy of predicting the spread of the COVID-19 virus in Indonesia. In initiating LSTM initial weights with weaknesses, using the hybrid optimization algorithm helps overcome these problems and improve model performance. The results of this study suggest that the LSTM-PSO-GWO model can be utilized as an effective and reliable predictive tool to gauge the COVID-19 virusβs spread in Indonesia.
DepXGBoot: Depression detection using a robust tuned extreme gradient boosting model generator
Get PDFIn terms of severity and prevalence, depression is the worst. Suicide rates have risen because of this and are on the rise universally. Consequently, effective diagnosis and therapy must reduce the impact of depression. There is often more than one factor at play when determining why someone has been diagnosed with depression. In addition to alcohol and substance abuse, other possible causes include problems with physical health, adverse reactions to medications, life-changing events, and social circumstances. In this paper, exploratory data analysis is conducted to understand the insights of the sensorimotor database depression comprising depressive experiences in individuals who are either unipolar or bipolar. This study proposes a robust tuned extreme gradient boosting model generator to automatically predict the state of depression. The performance is optimized by determining the best combination of hyperparameters for the extreme gradient boosting model. By harnessing the power of advanced machine learning methodologies, this study underscores comparative analysis and the importance of data-driven innovation in mental health and clinical practice. Future developments for the robust tuned extreme gradient boosting modelβs application and study to forecast depression in the sensorimotor database depression can be used to track changes in depressed states over time by integrating it with longitudinal and multimodal data
Signalling overhead minimization aware handover execution using ensemble learning in next generation wireless networks
Get PDFUpcoming smart intelligent heterogeneous wireless networks (HWNs) and their uses can greatly benefit from the merging of long-term evolution (LTE) sub-6 GHz along with millimeter wave (mmWave) frequencies by boosting the coverage, bandwidth, reliability, seamless connectivity, and high quality of service (QoS). Nevertheless, because of the inability of directed waves in terms of coverage, it is difficult to locate the appropriate mmWave remote radio units (RRUs). Therefore, it is crucial to lessen the burden of the handover signaling processes. In meeting research requirements this paper presents signaling overhead minimization aware handover execution (SOMAHE) model. The SOMAHE model first introduces a novel handover mechanism between LTE and mmWave is presented in this research, followed by a machine learning (ML)-based autonomous handover execution technique. To estimate the handover success rate, the model introduces a feature ensemble learning (FEL) model built using XGBoost (XGB) model that makes use of sampling windows channel data. To conclude, combining FEL into the SOMAHE model reduces signaling overhead while simultaneously increasing the handover success-rate. Experiment results with varying mobile terminals, demonstrate that the SOMAHE model significantly outperforms the existing standard deep q-networks (DQN)-based handover-execution method
Word embedding for detecting cyberbullying based on recurrent neural networks
Get PDFThe phenomenon of cyberbullying has spread and has become one of the biggest problems facing users of social media sites and generated significant adverse effects on society and the victim in particular. Finding appropriate solutions to detect and reduce cyberbullying has become necessary to mitigate its negative impacts on society and the victim. Twitter comments on two datasets are used to detect cyberbullying, the first dataset was the Arabic cyberbullying dataset, and the second was the English cyberbullying dataset. Three different pre-trained global vectors (GloVe) corpora with different dimensions were used on the original and preprocessed datasets to represent the words. Recurrent neural networks (RNN), long short-term memory (LSTM), Bidirectional LSTM (BiLSTM), gated recurrent unit (GRU), and Bidirectional GRU (BiGRU) classifiers utilized, evaluated and compared. The GRU outperform other classifiers on both datasets; its accuracy on the Arabic cyberbullying dataset using the Arabic GloVe corpus of dimension equal to 256D is 87.83%, while the accuracy on the English datasets using 100 D pre-trained GloVe corpus is 93.38%