Emotion identification from speech signals has been a research issue in human machine interaction applications for many years. Emotions incredibly play a vital role in our mental functioning. SER is the process of ide...
详细信息
ISBN:
(数字)9798350381887
ISBN:
(纸本)9798350381894
Emotion identification from speech signals has been a research issue in human machine interaction applications for many years. Emotions incredibly play a vital role in our mental functioning. SER is the process of identifying an individual speaker’s emotional state through the speech stream. The purpose of emotion recognition using speech processing is to develop a system that cans precisely asses a person’s emotional state based on their speech signals. They would use machine learning algorithms to analyze features such as pitch, tone, rhythm, and intensity of speech, and then classify the emotions expressed in the speech as happy, sad, angry, fearful, or neutral. The main applications of emotion recognition using speech processing include human-computer interaction, psychotherapy, and customer service. Inhuman-computer interaction, emotion recognition systems can provide more personalized and empathetic responses, enhancing the user experience. By analyzing their patients’ facial expressions and body language, therapists using emotion recognition systems in psychotherapy can better meet the needs of their patients. In customer service, emotion recognition systems can help companies to improve their customer satisfaction by detecting and responding to negative emotions expressed by customers. Neutral, Anger, Being happy, & Sadness are some of the few universal emotions that can be taught to any intelligent system with limited processing resources and ability to recognize and synthesize. as required. Mel-frequency cepstral coefficients (MFCC), a chromogram, a Mel scale spectrogram are extracted together with Tonal Centroid and Spectral Contrast characteristics. Deep Neural Network is used to understand human emotions, advancedsignalprocessing techniques, and sophisticated machine learning algorithms.
This study examines the challenges of detecting and classifying offensive language in Arabic, with a focus on natural language processing (NLP) methods. Arabic's distinctive linguistic characteristics, such as its...
详细信息
ISBN:
(数字)9798350327472
ISBN:
(纸本)9798350327489
This study examines the challenges of detecting and classifying offensive language in Arabic, with a focus on natural language processing (NLP) methods. Arabic's distinctive linguistic characteristics, such as its extensive morphology, present substantial obstacles to accurately classifying offensive content. This paper evaluates the approaches currently in use in this field and conducts a critical analysis of publicly accessible datasets frequently used to detect offensive language in Arabic. In addition to highlighting areas for further study and growth in the detection of Arabic offensive language, the aim is to offer insights into the state-of-the-art methodologies being used. In the analysis of public datasets, this paper evaluates their suitability for offensive language detection tasks in Arabic, considering factors such as dataset size, annotation quality, and representation of diverse offensive language categories. Furthermore, this paper investigates the existing methods utilized for detecting and classifying offensive language in Arabic, examining a range of NLP approaches used in the context of detecting Arabic offensive language. This includes machine learning algorithms, deep learning architectures, and linguistic aspects, all tailored to address the specific challenges associated with offensive language detection in the Arabic vernacular. Our investigation emphasizes the need for customized algorithms that take into account Arabic's unique linguistic characteristics. Future research should focus on developing advanced models that incorporate domain-specific knowledge, handle dialectal variations, and effectively capture the intricacies of Arabic morphology.
In this paper, a covert semantic communication framework is proposed for image transmission over wireless networks. In the proposed framework, devices extract and selectively transmit semantic information of image dat...
详细信息
In this paper, a covert semantic communication framework is proposed for image transmission over wireless networks. In the proposed framework, devices extract and selectively transmit semantic information of image data to a base station (BS). The semantic information consists of the objects in the image and a set of attributes of each object. A warden selects a device to detect and eavesdrops the semantic information. To ensure the security of semantic communications, a jammer, acts as the defender, requires to find a vulnerable device and transmits jamming signals to the vulnerable device. The metric to measure the performance of the covert semantic communications is defined as the difference in the average accuracy of the BS and the warden answering a set of questions for each image. To maximize the performance of covert semantic communications, each device and the jammer must jointly optimize their transmit power, determine the vulnerable device to be protected, and determine the partial semantic information that each device needs to transmit. To solve this problem, we propose a multi-agent policy gradient (MAPG) algorithm. The proposed algorithm enables each device and the jammer to cooperatively discover the vulnerable devices as well as find the semantic information transmission and power control policies that maximize the performance of the covert semantic communication system. Simulation results show that the proposed algorithm can improve the communication performance by up to 14.5% compared to the independent reinforcement learning.
In today’s digital era, ensuring the security of bank payments is imperative to maintain trust and integrity in financial transactions. With the proliferation of online banking and electronic payments, the risk of fr...
详细信息
ISBN:
(数字)9798350353068
ISBN:
(纸本)9798350353075
In today’s digital era, ensuring the security of bank payments is imperative to maintain trust and integrity in financial transactions. With the proliferation of online banking and electronic payments, the risk of fraudulent activities has escalated, posing a constant challenge to financial institutions and their clients. To counteract this threat, advanced techniques utilizing machine learning algorithms have emerged as indispensable tools for detecting and preventing fraudulent transactions effectively. This study proposes a novel strategy for enhancing bank payment security through the utilization of Gradient Boosting Machines (GBM) for fraud detection. GBM, a powerful ensemble learning technique, has demonstrated exceptional performance across various classification tasks, rendering it well-suited for identifying fraudulent activities within bank payments. By harnessing GBM, our objective is to elevate the accuracy and efficiency of fraud detection systems, consequently curtailing financial losses attributable to fraudulent transactions while minimizing false positives that could inconvenience legitimate clients. Emphasis is placed on feature selection and engineering to extract pertinent information from transactional data, enabling the model to effectively discern. To validate the efficacy of our approach, we conduct experiments utilizing authentic bank payment datasets, assessing the GBM-based fraud detection system’s accuracy, precision, recall, and F1-score. Our findings reveal significant enhancements in fraud detection performance compared to conventional methods, underscoring the effectiveness of GBM in mitigating the risks associated with fraudulent activities in banking transactions. In essence, this research contributes to the ongoing endeavours aimed at fortifying bank payment security by leveraging advanced machine learning techniques. By harnessing the prowess of GBM for fraud detection, financial institutions can bolster their defences against evo
Regular inspection of railway tracks is critical for providing safety and efficiency in railway transportation systems to minimize accidents, maintenance costs and improve reliability by early detection. In this paper...
详细信息
ISBN:
(数字)9798331505776
ISBN:
(纸本)9798331505783
Regular inspection of railway tracks is critical for providing safety and efficiency in railway transportation systems to minimize accidents, maintenance costs and improve reliability by early detection. In this paper, a systematic review for damage detection in railway tracks using Acoustic signals (sound generated at the wheel and track interaction point) during the movement of the train is presented. Distributed Acoustic Sensing (DAS) is a valuable method for quick, long-distance monitoring of railway maintenance and technological development and crucial for accident avoidance. In regions prone to frequent train accidents, free automation of inspection processes is essential to prevent disasters and to provide safe and reliable operation of train vehicles. A wide range of Structural Health Monitoring (SHM) systems sensor data is noisy, making Machine Learning (ML) algorithms paramount for detecting abnormal railroad conditions among many others and achieving higher accuracy in maintenance and inspection. Several advancedsignalprocessing techniques are used to recognize crack or misalignment patterns by employing Fourier transform and wavelet analysis. Further, the signals are classified through machine learning algorithms to classify between normal and damaged conditions, presenting a non-invasive, real-time and economic monitoring system that validates the system’s capability to detect several types of damage and could enhance rail infrastructure safety. Integration of these acoustic sensing with a set of trains in a predictive analytics framework makes the study of the field a scalable tool for efficient railway management.
The impact of aspect angle on Doppler effect hinders the capability of a monostatic radar to achieve human activity recognition (HAR) from all aspect angles, i.e., omnidirectional. To alleviate the “angle sensitivity...
详细信息
ISBN:
(数字)9798331539566
ISBN:
(纸本)9798331539573
The impact of aspect angle on Doppler effect hinders the capability of a monostatic radar to achieve human activity recognition (HAR) from all aspect angles, i.e., omnidirectional. To alleviate the “angle sensitivity”, sufficient and high-quality training data from multiple aspect angles is mandated. However, it would be time-consuming for the monostatic radar to collect the training data from all aspect angles. To address this issue, this paper proposes a high-quality synthetic data generation algorithm based on high-dimensional model representation (HDMR) for omnidirectional HAR. The aim is to augment a high-quality dataset with collected samples at the radar line-of-sight direction and few samples from other aspect angles. The quality of synthetic samples is evaluated by dynamic time wrapping distance (DTWD) between the synthetic and real samples. Subsequently, the synthetic samples are utilized to train a classifier based on ResNet50 to achieve omnidirectional HAR. Experimental results demonstrate that the averaged HAR accuracy of the proposed algorithm exceeds 91 % at different aspect angles. The quality of the synthetic samples generated by the proposed algorithm outperforms two commonly-used algorithms in the literature.
In the 6G mobile communication systems, the integration of sensing, communication, and array signalprocessing technologies heralds a new era of advanced situational awareness. However, this advancement raises critica...
详细信息
ISBN:
(数字)9798350363760
ISBN:
(纸本)9798350363777
In the 6G mobile communication systems, the integration of sensing, communication, and array signalprocessing technologies heralds a new era of advanced situational awareness. However, this advancement raises critical concerns about privacy and security, especially with the widespread deployment of devices equipped with radar-like sensing capability, including malicious ones. Moreover, suffering from rapidly changing spectrum environments and the restricted capability of spectrum prediction, jamming effectiveness evaluation values may not be fully obtained. Therefore, in order to effectively jam the malicious sensing device and improve the spectrum utilization, spectrum prediction is expected to be a key enabler, which features predicting the jamming effectiveness evaluation values and recommending frequency-domain subbands for utilization. In order to characterize the relation between jamming devices and malicious sensing devices when predicting spectrum, we construct a spectrum knowledge graph (SKG). In order to encode the KGE vectors from the triplets composed of entities and relations, we develop the CNN-based KGE model, where the CNN can be exploited to derive embedding encoded with knowledge of relations. In order to address the problem of predicting spectrum, we convert this issue into a node regression problem based graph model and graph convolution network (GCN). In order to address the problem of sparse feature vectors related to entities and relationships within the SKG, we exploit KGE vectors generated by a CNN-based KGE algorithm to replace the one-hot encoding method, which can be used to formulate the feature matrix in the graph model. Simulation results indicate that the spectrum prediction algorithm based on a knowledge-driven graph convolutional network (KGCN) can significantly improve the accuracy of spectrum prediction.
Gastrointestinal (GI) diseases are amongst the most painful and dangerous clinical cases, due to inefficient recognition of symptoms and thus, lack of early-diagnostic tools. The analysis of bowel sounds (BS) has been...
详细信息
ISBN:
(纸本)9781728111797
Gastrointestinal (GI) diseases are amongst the most painful and dangerous clinical cases, due to inefficient recognition of symptoms and thus, lack of early-diagnostic tools. The analysis of bowel sounds (BS) has been fundamental for GI diseases, however their long-term recordings require technical and clinical resources along with the patientt's motionless concurrence throughout the auscultation procedure. In this study, an end-to-end non-invasive solution is proposed to detect BS in real-life settings utilizing a smart-belt apparatus along with advancedsignalprocessing and deep neural network algorithms. Thus, high rate of BS identification and separation from other domestic and urban sounds have been achieved over the realization of an experiment where BS recordings were collected and analyzed out of 10 student volunteers.
A measurement method of radar cross-section (RCS) in reverberation chamber (RC) was recently introduced for a monostatic configuration. This communication extends this method to a quasi-monostatic configuration. Both ...
详细信息
A measurement method of radar cross-section (RCS) in reverberation chamber (RC) was recently introduced for a monostatic configuration. This communication extends this method to a quasi-monostatic configuration. Both configurations are compared, using the same signalprocessing. They provide similar results in comparison to anechoic chamber measurements. In addition, an advancedsignalprocessing allows for physical insight of backscattering properties of the target under test.
The cosmic microwave background (CMB) experiments have reached an era of unprecedented precision and complexity. Aiming to detect the primordial B-mode polarization signal, these experiments will soon be equipped with...
详细信息
ISBN:
(数字)9798331524937
ISBN:
(纸本)9798331524944
The cosmic microwave background (CMB) experiments have reached an era of unprecedented precision and complexity. Aiming to detect the primordial B-mode polarization signal, these experiments will soon be equipped with $10^{4}$ to $10^{5}$ detectors. Consequently, future CMB missions will face the substantial challenge of efficiently processing vast amounts of raw data to produce the initial scientific outputs - the sky maps - within a reasonable time frame and with available computational resources. To address this, we introduce BrahMap, a new map-making framework that will be scalable across both CPU and GPU platforms. Implemented in C++ with a user-friendly Python interface for handling sparse linear systems, BrahMap employs advanced numerical analysis and high-performance computing techniques to maximize the use of super-computing infrastructure. This work features an overview of the BrahMap’s capabilities and preliminary performance scaling results, with application to a generic CMB polarization experiment.
暂无评论