{"title":"Editors and Reviewers","authors":"","doi":"10.23919/SAIEE.2021.9432890","DOIUrl":"10.23919/SAIEE.2021.9432890","url":null,"abstract":"","PeriodicalId":42493,"journal":{"name":"SAIEE Africa Research Journal","volume":"112 2","pages":"c2-c2"},"PeriodicalIF":1.4,"publicationDate":"2021-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.23919/SAIEE.2021.9432890","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44265159","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Guest Editorial: SAUPEC/RobMech/PRASA 2020","authors":"","doi":"10.23919/SAIEE.2021.9432894","DOIUrl":"10.23919/SAIEE.2021.9432894","url":null,"abstract":"","PeriodicalId":42493,"journal":{"name":"SAIEE Africa Research Journal","volume":"112 2","pages":"66-66"},"PeriodicalIF":1.4,"publicationDate":"2021-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.23919/SAIEE.2021.9432894","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44865030","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Class-Selective Mini-Batching and Multitask Learning for Visual Relationship Recognition","authors":"S. Josias;W. Brink","doi":"10.23919/SAIEE.2021.9432898","DOIUrl":"10.23919/SAIEE.2021.9432898","url":null,"abstract":"An image can be described by the objects within it, and interactions between those objects. A pair of object labels together with an interaction label is known as a visual relationship, and is represented as a triplet of the form (subject, predicate, object). Recognising visual relationships in images is a challenging task, owing to the combinatorially large number of possible relationship triplets, which leads to an extreme multiclass classification problem. In addition, the distribution of visual relationships in a dataset tends to be long-tailed, i.e. most triplets occur rarely compared to a small number of dominating triplets. Three strategies to address these issues are investigated. Firstly, instead of predicting the full triplet, models can be trained to predict each of the three elements separately. Secondly a multitask learning strategy is investigated, where shared network parameters are used to perform the three separate predictions. Thirdly, a class-selective mini-batch construction strategy is used to expose the network to more of the rare classes during training. Experiments demonstrate that class-selective mini-batch construction can improve performance on classes in the long tail of the data distribution, possibly at the expense of accuracy on the small number of dominating classes. It is also found that a multitask model neither improves nor impedes performance in any significant way, but that its smaller size may be beneficial. In an effort to better understand the behaviour of the various models, a novel evaluation approach for visual relationship recognition is introduced. We conclude that the use of semantics can be helpful in the modelling and evaluation process.","PeriodicalId":42493,"journal":{"name":"SAIEE Africa Research Journal","volume":"112 2","pages":"99-109"},"PeriodicalIF":1.4,"publicationDate":"2021-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.23919/SAIEE.2021.9432898","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47908457","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Investigative analysis of channel selection algorithms in cooperative spectrum sensing in cognitive radio networks","authors":"J. Tlouyamma;M. Velempini","doi":"10.23919/SAIEE.2021.9340532","DOIUrl":"https://doi.org/10.23919/SAIEE.2021.9340532","url":null,"abstract":"The proliferation of wireless mobile devices has led to a number of challenges in mobile data communication. The world is experiencinganincreasingusage of finite spectrum bands for social media and other data communication services. It is due to this high usage that the Federal Communications Commission(FCC) sought to open up some spectrum bands to be used opportunistically by secondary users (SUs). However, the coexistence of Primary Users (PUs) and SUs may cause interference which leads to wastage of spectrum resources. This study investigates the impact of interferences between PUs and SUs. To ensure higher detection of PU signal, a cooperative rule was used to decide which SU to share and makea final decision about the availability of the spectrum band. To maximize the throughput of SU, a maximum likelihood function was designed to reduce delays in searching for the next available channel for data transmission. To discover more transmission opportunities and ensuring that a good number of free channels are detected, a parallel sensing technique was employed. Matlabwas used to simulate and generate the results in a distributed cognitive radio environment. The proposed extended generalizedpredictive channel selection algorithm (EXGPCSA) outperformed otherschemes in literature in terms of throughput, service timeandprobability of detection.","PeriodicalId":42493,"journal":{"name":"SAIEE Africa Research Journal","volume":"112 1","pages":"4-14"},"PeriodicalIF":1.4,"publicationDate":"2021-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.23919/SAIEE.2021.9340532","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67992283","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Oluwaseyi P. Babalola;Ayinde M. Usman;Olayinka O. Ogundile;Daniel J. J. Versfeld
{"title":"Detection of Bryde's whale short pulse calls using time domain features with hidden Markov models","authors":"Oluwaseyi P. Babalola;Ayinde M. Usman;Olayinka O. Ogundile;Daniel J. J. Versfeld","doi":"10.23919/SAIEE.2021.9340533","DOIUrl":"https://doi.org/10.23919/SAIEE.2021.9340533","url":null,"abstract":"Passive acoustic monitoring (PAM) is generally usedto extract acoustic signals produced by cetaceans. However, the large data volume from the PAM process is better analyzed using an automated technique such as the hidden Markovmodels (HMM). In this paper, the HMM is used as a detection and classification technique due to its robustness and low time complexity. Nonetheless, certain parameters, such as the choice of features to be extracted from the signal, the frame duration, and the number of states affect the performance of the model. Theresults show that HMM exhibits best performances as the number of states increases with short frame duration. However, increasing the number of states creates more computational complexity in the model. The inshore Bryde's whales produce short pulse calls with distinct signal features, which are observable in the time-domain. Hence, a time-domain feature vector is utilized to reduce the complexity of the HMM. Simulation results also show that average power as a time-domain feature vector provides the best performance compared to other feature vectors for detecting the short pulse call of inshore Bryde's whales based on the HMM technique. More so, the extracted features such as the average power, mean, and zero-crossing rate, are combined to form a single 3-dimensional vector (PaMZ). The PaMZ-HMM shows improved performance and reduced complexity over existing feature extraction techniques such as Mel-scale frequency cepstral coefficients (MFCC) and linear predictive coding (LPC). Thus, making the PaMZ-HMM suitable for real-time detection.","PeriodicalId":42493,"journal":{"name":"SAIEE Africa Research Journal","volume":"112 1","pages":"15-23"},"PeriodicalIF":1.4,"publicationDate":"2021-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.23919/SAIEE.2021.9340533","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67992473","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Craig S. Carlson;Aurélie Deroubaix;Clement Penny;Michiel Postema
{"title":"On the attenuation of ultrasound by pure black tattoo ink","authors":"Craig S. Carlson;Aurélie Deroubaix;Clement Penny;Michiel Postema","doi":"10.23919/SAIEE.2021.9340534","DOIUrl":"https://doi.org/10.23919/SAIEE.2021.9340534","url":null,"abstract":"Black tattoo ink comprises hydrophobic carbonblack nanoparticles. We hypothesized that black tattoo inkdemonstrates transient dynamic activity in an ultrasound field. Brightness-mode sonography was performed on cylindrical receptacles of different bore diameters, filled with black tattooink, water, saline, or air, using pulsed ultrasound with center frequencies of 13 MHz and 5 MHz. The scattering from black ink itself lasted less than tenminutes. At 13-MHz sonication, a transient drop in sound speed was observed, as well as a transient lessening of scattering from distal phantom tissue. The linear acoustic attenuation coefficient of pure black ink was measured to be 0.15±0.01 dB cm\u0000<sup>−1</sup>\u0000 MHz\u0000<sup>−1</sup>\u0000, equal to whole blood. Low-intensity ultrasonic tattoo removal would be of interestas an alternative to techniques that damage surrounding tissue.","PeriodicalId":42493,"journal":{"name":"SAIEE Africa Research Journal","volume":"112 1","pages":"24-31"},"PeriodicalIF":1.4,"publicationDate":"2021-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.23919/SAIEE.2021.9340534","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67992286","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mohamed K. Elmezughi;Thomas J. Afullo;Nicholas O. Oyie
{"title":"Performance study of path loss models at 14, 18, and 22 GHz in an indoor corridor environment for wireless communications","authors":"Mohamed K. Elmezughi;Thomas J. Afullo;Nicholas O. Oyie","doi":"10.23919/SAIEE.2021.9340535","DOIUrl":"https://doi.org/10.23919/SAIEE.2021.9340535","url":null,"abstract":"The critical rule to achieve extremely high peaks of data transmission is the availability of a tremendous amount of bandwidth. The super high frequency (SHF) and the millimeter-wave (mmWave) frequency bands are the candidates for the deployment of the 5G cellular system and for satisfying future needs due to their massively available blocks of contiguous raw bandwidth that is capable of supporting additional data traffic for multimedia services. This research paper presents propagation measurements at three frequencies above 6 GHz, which are 14, 18, and 22 GHz frequency bands. The measurements were carried out or both line-of-sight (LOS) and non-line-of-sight (NLOS) communication scenarios in an indoor corridor environment to present frequency- and distance-dependent wireless channel models. Moreover, this study presents, investigates, and compares the performance of two well-known path loss prediction models; the single frequency close-in (CI) free space reference distance model and the single frequency floating intercept (FI) model. The LOS comparison study shows that the CI and FI models provide comparable and accurate estimates that fit the real measured data for the frequency bands selected. Furthermore, the study investigates the behavior of the path loss exponent (PLE) and the FI model parameters as a function of the reception angle of arrival (AoA) in the NLOS scenario. It is observed from this work that the path loss models' parameters exhibit symmetrical behavior around 180° AoA. The FI model provides the same standard deviation values as the CI model in the LOS scenario. In contrast, the FI model offers a notable reduction(up to 2.84 dB) compared to the CI model in the NLOS scenario. Finally, the LOS and NLOS results reveal that the CI and FI models can be trusted as good path loss models for corridor environments and exhibit stable behavior over measured distances and frequencies.","PeriodicalId":42493,"journal":{"name":"SAIEE Africa Research Journal","volume":"112 1","pages":"32-45"},"PeriodicalIF":1.4,"publicationDate":"2021-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.23919/SAIEE.2021.9340535","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67992285","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Design and implementation of a Luganda text normalization module for a speech synthesis software program","authors":"Ronald Kizito;Wayne S. Okello;Sulaiman Kagumire","doi":"10.23919/SAIEE.2020.9194384","DOIUrl":"https://doi.org/10.23919/SAIEE.2020.9194384","url":null,"abstract":"This paper describes a Luganda text normalization module, a crucial component needed for a Luganda Text to Speech system. We describe the use of a rule-based approach for detection, classification and verbalization of Luganda text. At the core of this module are the Luganda grammar rules that were hand-built to normalize Non-Standard Words (NSWs) from different semiotic and noun classes. Input text is first analyzed, matched against handcrafted patterns developed using regular expressions to detect any NSWs. Upon detection, NSWs are tokenized and classified into one of the semiotic classes and then if necessary, into one of the Luganda noun classes. These are subsequently verbalized, each according to its semiotic as well as noun class, and a new text file is produced. We tested the module with 7 datasets and achieved average detection and normalization rates of 82% and 77.7% respectively.","PeriodicalId":42493,"journal":{"name":"SAIEE Africa Research Journal","volume":"111 4","pages":"149-154"},"PeriodicalIF":1.4,"publicationDate":"2020-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.23919/SAIEE.2020.9194384","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"68066486","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A novel low line regulation CMOS voltage reference without BJTs and resistors","authors":"Changqing Zhang;Xia Wu;Wanling Deng;Junkai Huang","doi":"10.23919/SAIEE.2020.9194381","DOIUrl":"10.23919/SAIEE.2020.9194381","url":null,"abstract":"A novel CMOS-only low line regulation voltage reference is presented in this paper. An output subcircuit composed of MOSFETs operating in the subthreshold region and saturation region is utilized to eliminate the temperature dependence of mobility and oxide capacitance, and produces a temperature-insensitive voltage reference. No bipolar junction transistors (BJTs) or resistors are used which can decrease the area greatly. By using most of the transistors operating in the subthreshold region, the power dissipation and the supply voltage are reduced. The proposed voltage reference is designed in the standard 0.18 μm CMOS process. The simulation results show that the output voltage is 958.971 mV at TT process corners, a temperature coefficient of 18.6096 ppm/°C range from20 °C to 110 °C is achieved, the line regulator (LR) of the proposed circuit is 0.037 mV/V from 1.5 V to 2.5 V supply voltage, and the power supply rejection ratio (PSRR) is75.77 dB at 100 Hz. The active area of the presented voltage reference is 0.0038 mm\u0000<sup>2</sup>\u0000.","PeriodicalId":42493,"journal":{"name":"SAIEE Africa Research Journal","volume":"111 4","pages":"130-137"},"PeriodicalIF":1.4,"publicationDate":"2020-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.23919/SAIEE.2020.9194381","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48166586","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Editors and reviewers","authors":"","doi":"10.23919/SAIEE.2020.9194379","DOIUrl":"https://doi.org/10.23919/SAIEE.2020.9194379","url":null,"abstract":"","PeriodicalId":42493,"journal":{"name":"SAIEE Africa Research Journal","volume":"111 4","pages":"128-128"},"PeriodicalIF":1.4,"publicationDate":"2020-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.23919/SAIEE.2020.9194379","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"68066487","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}