Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Eiad Almekhlafi has a total of 34 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    YMGD: A yemeni music genres database with audio recordings, mel-spectrograms, and metadata

    by Eiad Al-Mekhlafi, Moeen Al-Makhlafi, Saher Qaida, Ahmed Asqeina, Ahmed Alawadhia, Nawaf Q. Othman

  • Open Access

    YSED: Yemeni speech emotion dataset

    by Somia Derhem, Eiad Al-Mekhlafi, Nashwan Ahmed Al-Majmar, Moeen Al-Makhlafi


  • AlveoliNet: An Incrementally Scalable, Cost-Effective, and High-Performance Two-Layer Based Architecture for Data Centers

    by Moeen Al-Makhlafi, Huaxi Gu, Ahlam Almuaalemi, Eiad Almekhlafi

    The escalating count of online services and substantial influx of data triggers the rapid expansion of data center networks (DCNs). DCN should ensure high scalability, low latency, and cost-efficiency, allowing it to adapt swiftly to the dynamic demands of evolving services. The task of constructing a DCN that marries flexibility, cost-effectiveness, low latency, and robust scalability has emerged as a formidable challenge. Driven by this prevailing tendency, this paper proposes a novel server-centric network termed $AlveoliNet$ . $AlveoliNet$ is a symmetric network encompassing several clusters formed of two switch layers and two server types: Symmetric and Binary servers. The Symmetric servers have two ports, implying lower cable complexity and construction cost. To perform remarkably with respect to fault tolerance, incremental scalability, and wide bisection width, the Binary servers are endowed with multi-port in accordance with the network level. $AlveoliNet$ supports incremental incorporation of servers while maintaining its fundamental topological characteristics; its diameter cannot be beyond five hops, irrespective of the DCN size. Additionally, two routing algorithms are designed exclusively for this architecture. The performance evaluations and empirical findings illustrate that $AlveoliNet$ achieves a harmonious equilibrium between flexibility, remarkable fault-tolerance, incremental scalability, cost-efficiency, and power savings compared to cutting-edge DCN structures. Specifically, the evaluation results demonstrate that for 103,680 nodes operating at 10 GB/s, the construction cost of $AlveoliNet$ is approximately 28.8%, 75.7%, 74.6%, 43.2%, and 60.5% of the cost of $Fat$ - $Tree$ , $Totoro$ , $DCell$ , $BCube$ , and $LaScaDa$ , respectively. Furthermore, the simulation outcomes reveal $AlveoliNet$ as a highly promising architecture, surpassing $Totoro$ , $DCell$ , $BCube$ , $LaScaDa$ , and $FiConn$ regarding latency by approximately 12%, 14%, 18%, 4%, and 31%, respectively.


  • Open Access

    Cross-Corpus Multilingual Speech Emotion Recognition: Amharic vs. Other Languages

    by Ephrem Afele Retta, Richard Sutcliffe, Jabar Mahmood, Michael Abebe Berwo, Eiad Almekhlafi, Sajjad Ahmad Khan, Shehzad Ashraf Chaudhry, Mustafa Mhamed, Jun Feng

    In a conventional speech emotion recognition (SER) task, a classifier for a given language is trained on a pre-existing dataset for that same language. However, where training data for a language do not exist, data from other languages can be used instead. We experiment with cross-lingual and multilingual SER, working with Amharic, English, German, and Urdu. For Amharic, we use our own publicly available Amharic Speech Emotion Dataset (ASED). For English, German and Urdu, we use the existing RAVDESS, EMO-DB, and URDU datasets. We followed previous research in mapping labels for all of the datasets to just two classes: positive and negative. Thus, we can compare performance on different languages directly and combine languages for training and testing. In Experiment 1, monolingual SER trials were carried out using three classifiers, AlexNet, VGGE (a proposed variant of VGG), and ResNet50. The results, averaged for the three models, were very similar for ASED and RAVDESS, suggesting that Amharic and English SER are equally difficult. Similarly, German SER is more difficult, and Urdu SER is easier. In Experiment 2, we trained on one language and tested on another, in both directions for each of the following pairs: Amharic↔German, Amharic↔English, and Amharic↔Urdu. The results with Amharic as the target suggested that using English or German as the source gives the best result. In Experiment 3, we trained on several non-Amharic languages and then tested on Amharic. The best accuracy obtained was several percentage points greater than the best accuracy in Experiment 2, suggesting that a better result can be obtained when using two or three non-Amharic languages for training than when using just one non-Amharic language. Overall, the results suggest that cross-lingual and multilingual training can be an effective strategy for training an SER classifier when resources for a language are scarce.


  • Open Access

    A deep CNN architecture with novel pooling layer applied to two Sudanese Arabic sentiment data sets

    by Mustafa Mhamed, Richard Sutcliffe, Husam Quteineh, Xia Sun, Eiad Almekhlafi, Ephrem Afele Retta, Jun Feng

    Arabic sentiment analysis has become an important research field in recent years. Initially, work focused on Modern Standard Arabic (MSA), which is the most widely used form. Since then, work has been carried out on several different dialects, including Egyptian, Levantine and Moroccan. Moreover, a number of data sets have been created to support such work. However, up until now, no work has been carried out on Sudanese Arabic, a dialect which has 32 million speakers. In this article, two new public data sets are introduced, the two-class Sudanese Sentiment Data set (SudSenti2) and the three-class Sudanese Sentiment Data set (SudSenti3). In the preparation phase, we establish a Sudanese stopword list. Furthermore, a convolutional neural network (CNN) architecture, Sentiment Convolutional MMA (SCM), is proposed, comprising five CNN layers together with a novel Mean Max Average (MMA) pooling layer, to extract the best features. This SCM model is applied to SudSenti2 and SudSenti3 and shown to be superior to the baseline models, with accuracies of 92.25% and 85.23% (Experiments 1 and 2). The performance of MMA is compared with Max, Avg and Min and shown to be better on SudSenti2, the Saudi Sentiment Data set and the MSA Hotel Arabic Review Data set by 1.00%, 0.83% and 0.74%, respectively (Experiment 3). Next, we conduct an ablation study to determine the contribution to performance of text normalisation and the Sudanese stopword list (Experiment 4). For normalisation, this makes a difference of 0.43% on two-class and 0.45% on three-class. For the custom stoplist, the differences are 0.82% and 0.72%, respectively. Finally, the model is compared with other deep learning classifiers, including transformer-based language models for Arabic, and shown to be comparable for SudSenti2 (Experiment 5).


  • Open Access

    A New Amharic Speech Emotion Dataset and Classification Benchmark

    by Ephrem Afele Retta, Eiad Almekhlafi, Richard Sutcliffe, Mustafa Mhamed, Haider Ali, Jun Feng

    In this article we present the Amharic Speech Emotion Dataset (ASED), which covers four dialects (Gojjam, Wollo, Shewa, and Gonder) and five different emotions (neutral, fearful, happy, sad, and angry). We believe it is the first Speech Emotion Recognition (SER) dataset for the Amharic language. Sixty-five volunteer participants, all native speakers of Amharic, recorded 2,474 sound samples, 2 to 4 seconds in length. Eight judges (two for each dialect) assigned emotions to the samples with high agreement level (Fleiss kappa = 0.8). The resulting dataset is freely available for download. Next, we developed a four-layer variant of the well-known VGG model, which we call VGGb. Three experiments were then carried out using VGGb for SER, using ASED. First, we investigated which features work best for Amharic, FilterBank, Mel Spectrogram, or Mel-frequency Cepstral Coefficient (MFCC). This was done by training three VGGb SER models on ASED, using FilterBank, Mel Spectrogram, and MFCC features, respectively. Four forms of training were tried, standard cross-validation and three variants based on sentences, dialects, and speaker groups. Thus, a sentence used for training would not be used for testing, and the same for a dialect and speaker group. MFCC features were superior under all four training schemes. MFCC was therefore adopted for Experiment 2, where VGGb and three well-known existing models were compared on ASED: RESNet50, AlexNet, and LSTM. VGGb was found to have very good accuracy (90.73%) as well as the fastest training time. In Experiment 3, the performance of VGGb was compared when trained on two existing SER datasets—RAVDESS (English) and EMO-DB (German)—as well as on ASED (Amharic). Results are comparable across these languages, with ASED being the highest. This suggests that VGGb can be successfully applied to other languages. We hope that ASED will encourage researchers to explore the Amharic language and to experiment with other models for Amharic SER.


  • RibsNet: A Scalable, High-Performance, and Cost-Effective Two-Layer-Based Cloud Data Center Network Architecture

    by Moeen Al-Makhlafi, Huaxi Gu, Ahlam Almuaalemi, Eiad Almekhlafi, Musbahu M. Adam

    Today, we witness an unprecedented surge of data traffic due to the explosive growth of smart devices and intelligent applications. Hence, supporting the Data Center Networks (DCNs) infrastructure by accommodating myriads of servers becomes natural and inevitable. This vision can be realized by providing an interconnecting architecture with higher scalability and remarkable capacity while maintaining fault tolerance, minimum latency, and cost and power efficiency. Motivated by this trend, this paper proposes a new network based on dual-centric dubbed RibsNet, which is a symmetric network composed of two layers of switches and dual-port servers. The proposed network enables the servers to establish all kinds of connections (server-switch and server-server), thus enhancing network fault tolerance with high bisection width and maximizing its performance and reliability. RibsNet allows the gradual addition of servers while preserving all its topological properties; it has a stable and low diameter, which does not exceed six regardless of the DCN’s size. Furthermore, an efficient and fault tolerant routing scheme, exclusively designed for this network, is proposed to enhance the routing efficiency and address different types of failures. Theoretical analysis proves that RibsNet strikes a good balance among several connections within the network and brings outstanding gains in terms of incremental scalability, bisection width, and cost and power savings against various cutting-edge DCNs architectures. Simulation results demonstrate RibsNet as a promising structure that outperforms BCube, DCell, HSDC, and FiConn in terms of latency and throughput by approximately 8%, 6%, 7%, and 26%, respectively.


  • Open Access

    A Deep CNN Architecture with Novel Pooling Layer Applied to Two Sudanese Arabic Sentiment Datasets

    by Mustafa Mhamed, Richard Sutcliffe, Xia Sun, Jun Feng, Eiad Almekhlafi, Ephrem A. Retta

    Arabic sentiment analysis has become an important research field in recent years. Initially, work focused on Modern Standard Arabic (MSA), which is the most widely-used form. Since then, work has been carried out on several different dialects, including Egyptian, Levantine and Moroccan. Moreover, a number of datasets have been created to support such work. However, up until now, less work has been carried out on Sudanese Arabic, a dialect which has 32 million speakers. In this paper, two new publicly available datasets are introduced, the 2-Class Sudanese Sentiment Dataset (SudSenti2) and the 3-Class Sudanese Sentiment Dataset (SudSenti3). Furthermore, a CNN architecture, SCM, is proposed, comprising five CNN layers together with a novel pooling layer, MMA, to extract the best features. This SCM+MMA model is applied to SudSenti2 and SudSenti3 with accuracies of 92.75% and 84.39%. Next, the model is compared to other deep learning classifiers and shown to be superior on these new datasets. Finally, the proposed model is applied to the existing Saudi Sentiment Dataset and to the MSA Hotel Arabic Review Dataset with accuracies 85.55% and 90.01%.

  • Open Access

    Kinit Classification in Ethiopian Chants, Azmaris and Modern Music: A New Dataset and CNN Benchmark

    by Ephrem A. Retta, Richard Sutcliffe, Eiad Almekhlafi, Yosef K. Enku, Eyob Alemu, Tigist D. Gemechu, Michael A. Berwo, Mustafa Mhamed, Jun Feng

    In this paper, we create EMIR, the first-ever Music Information Retrieval dataset for Ethiopian music. EMIR is freely available for research purposes and contains 600 sample recordings of Orthodox Tewahedo chants, traditional Azmari songs and contemporary Ethiopian secular music. Each sample is classified by five expert judges into one of four well-known Ethiopian Kinits, Tizita, Bati, Ambassel and Anchihoye. Each Kinit uses its own pentatonic scale and also has its own stylistic characteristics. Thus, Kinit classification needs to combine scale identification with genre recognition. After describing the dataset, we present the Ethio Kinits Model (EKM), based on VGG, for classifying the EMIR clips. In Experiment 1, we investigated whether Filterbank, Mel-spectrogram, Chroma, or Mel-frequency Cepstral coefficient (MFCC) features work best for Kinit classification using EKM. MFCC was found to be superior and was therefore adopted for Experiment 2, where the performance of EKM models using MFCC was compared using three different audio sample lengths. 3s length gave the best results. In Experiment 3, EKM and four existing models were compared on the EMIR dataset: AlexNet, ResNet50, VGG16 and LSTM. EKM was found to have the best accuracy (95.00%) as well as the fastest training time. We hope this work will encourage others to explore Ethiopian music and to experiment with other models for Kinit classification.