Displaying publications 1 - 20 of 218 in total

Abstract:
Sort:
  1. Abdulhussain SH, Mahmmod BM, Naser MA, Alsabah MQ, Ali R, Al-Haddad SAR
    Sensors (Basel), 2021 Mar 12;21(6).
    PMID: 33808986 DOI: 10.3390/s21061999
    Numeral recognition is considered an essential preliminary step for optical character recognition, document understanding, and others. Although several handwritten numeral recognition algorithms have been proposed so far, achieving adequate recognition accuracy and execution time remain challenging to date. In particular, recognition accuracy depends on the features extraction mechanism. As such, a fast and robust numeral recognition method is essential, which meets the desired accuracy by extracting the features efficiently while maintaining fast implementation time. Furthermore, to date most of the existing studies are focused on evaluating their methods based on clean environments, thus limiting understanding of their potential application in more realistic noise environments. Therefore, finding a feasible and accurate handwritten numeral recognition method that is accurate in the more practical noisy environment is crucial. To this end, this paper proposes a new scheme for handwritten numeral recognition using Hybrid orthogonal polynomials. Gradient and smoothed features are extracted using the hybrid orthogonal polynomial. To reduce the complexity of feature extraction, the embedded image kernel technique has been adopted. In addition, support vector machine is used to classify the extracted features for the different numerals. The proposed scheme is evaluated under three different numeral recognition datasets: Roman, Arabic, and Devanagari. We compare the accuracy of the proposed numeral recognition method with the accuracy achieved by the state-of-the-art recognition methods. In addition, we compare the proposed method with the most updated method of a convolutional neural network. The results show that the proposed method achieves almost the highest recognition accuracy in comparison with the existing recognition methods in all the scenarios considered. Importantly, the results demonstrate that the proposed method is robust against the noise distortion and outperforms the convolutional neural network considerably, which signifies the feasibility and the effectiveness of the proposed approach in comparison to the state-of-the-art recognition methods under both clean noise and more realistic noise environments.
    Matched MeSH terms: Feasibility Studies
  2. Ng KM, Reaz MB
    PLoS One, 2016;11(1):e0144798.
    PMID: 26731745 DOI: 10.1371/journal.pone.0144798
    Platoon based traffic flow models form the underlying theoretical framework in traffic simulation tools. They are essentially important in facilitating efficient performance calculation and evaluation in urban traffic networks. For this purpose, a new platoon-based macroscopic model called the LWR-IM has been developed in [1]. Preliminary analytical validation conducted previously has proven the feasibility of the model. In this paper, the LWR-IM is further enhanced with algorithms that describe platoon interactions in urban arterials. The LWR-IM and the proposed platoon interaction algorithms are implemented in the real-world class I and class II urban arterials. Another purpose of the work is to perform quantitative validation to investigate the validity and ability of the LWR-IM and its underlying algorithms to describe platoon interactions and simulate performance indices that closely resemble the real traffic situations. The quantitative validation of the LWR-IM is achieved by performing a two-sampled t-test on queues simulated by the LWR-IM and real queues observed at these real-world locations. The results reveal insignificant differences of simulated queues with real queues where the p-values produced concluded that the null hypothesis cannot be rejected. Thus, the quantitative validation further proved the validity of the LWR-IM and the embedded platoon interactions algorithm for the intended purpose.
    Matched MeSH terms: Feasibility Studies
  3. Low WZ, Khoo BE, Abdullah AF
    J Forensic Sci, 2016 07;61(4):1093-9.
    PMID: 27364293 DOI: 10.1111/1556-4029.13063
    Nondestructive techniques for gathering evidence are important in the field of forensics. Due to the geometry of the substrates, nondestructive visualization of fingermarks on curved surfaces remains challenging. A novel contactless technique was developed for visualizing and recording fingermark patterns on nonporous curved surfaces of circular cross section. The technique utilizes a plane mirror to transmit rays from a light source to illuminate the area of interest for fingermark visualization. The fingermark acquisition system consists of a digital single-lens reflex (SLR) camera, a plane mirror, and a white light source. Mathematical equations are used to calculate the mirror size. Experiments were performed on various curved surfaces to determine the feasibility and effectiveness of the technique. Spectral Image Validation and Verification (SIVV) was used to analyze the captured images. The results of this study indicate that the technique described here is able to reveal fingermark patterns on curved surfaces of circular cross section.
    Matched MeSH terms: Feasibility Studies
  4. Bi Y, Xu X, Chua SY, Chow EMT, Wang X
    Sensors (Basel), 2018 Mar 07;18(3).
    PMID: 29518889 DOI: 10.3390/s18030798
    Laser sensing has been applied in various underwater applications, ranging from underwater detection to laser underwater communications. However, there are several great challenges when profiling underwater turbulence effects. Underwater detection is greatly affected by the turbulence effect, where the acquired image suffers excessive noise, blurring, and deformation. In this paper, we propose a novel underwater turbulence detection method based on a gated wavefront sensing technique. First, we elaborate on the operating principle of gated wavefront sensing and wavefront reconstruction. We then setup an experimental system in order to validate the feasibility of our proposed method. The effect of underwater turbulence on detection is examined at different distances, and under different turbulence levels. The experimental results obtained from our gated wavefront sensing system indicate that underwater turbulence can be detected and analyzed. The proposed gated wavefront sensing system has the advantage of a simple structure and high detection efficiency for underwater environments.
    Matched MeSH terms: Feasibility Studies
  5. Muda AS, Ralib AR, Yaacob Y, Zakaria R, Bakar AA
    Malays J Med Sci, 2011 Oct;18(4):91-7.
    PMID: 22589679
    Endovascular treatment of wide-necked aneurysms poses a challenge for the endovascular therapist. The Y-stent-assisted technique has been used for stent-assisted coil embolisation for wide-necked bifurcation aneurysms. This technique has been described for basilar tip aneurysms and middle cerebral artery bifurcation aneurysms using Neuroform and Enterprise stents. We report 2 cases of wide-necked bifurcation aneurysms that were treated with Y-stent-assisted coil embolisation using a new, fully retrievable and detachable intracranial stent (Solitaire AB™). We describe the advantages of a fully retrievable and detachable stent and its feasibility of forming a Y configuration.
    Matched MeSH terms: Feasibility Studies
  6. Kapitaniak T, Mohammadi SA, Mekhilef S, Alsaadi FE, Hayat T, Pham VT
    Entropy (Basel), 2018 Sep 05;20(9).
    PMID: 33265759 DOI: 10.3390/e20090670
    In this paper, we introduce a new, three-dimensional chaotic system with one stable equilibrium. This system is a multistable dynamic system in which the strange attractor is hidden. We investigate its dynamic properties through equilibrium analysis, a bifurcation diagram and Lyapunov exponents. Such multistable systems are important in engineering. We perform an entropy analysis, parameter estimation and circuit design using this new system to show its feasibility and ability to be used in engineering applications.
    Matched MeSH terms: Feasibility Studies
  7. Khan R, Go Y
    Glob Chall, 2020 Feb;4(2):1900060.
    PMID: 32042443 DOI: 10.1002/gch2.201900060
    Malaysia targets to become the second-largest producer of solar photovoltaic (PV) in the world by increasing the current output from 12% to 20% in 2020. The government also expects to achieve 45% reduction of greenhouse gas emission by 2030 through renewable energy mainly by solar PV. Large-scale solar (LSS) aims to produce 2.5 GW, which contributes to 10% of the nation's electricity demands. The LSS system is held back by the grid-scale integration, transmission, and distribution infrastructure. Thus, power system analysis is crucial to achieve optimization in LSS to power grid integration. This paper investigates various power system analysis models and recommends an optimized configuration based on Malaysia's LSS scenario. In stage 1, an optimal PV sizing is carried out based on real data of LSS installation in different locations. In stage 2, power analysis is carried out using to analyze the potential difference variation when connected to a nine-bus power system. The potential variation at each bus of the system is assessed and hence provides a feasibility statement on the most effective configurations for LSS-grid integration. This paper serves as the reference model for LSS-grid integration in Malaysia and is expected to be replicated in the other countries with similar conditions.
    Matched MeSH terms: Feasibility Studies
  8. Zulkifley MA, Behjati M, Nordin R, Zakaria MS
    Sensors (Basel), 2021 Apr 18;21(8).
    PMID: 33919486 DOI: 10.3390/s21082848
    Conventional and license-free radio-controlled drone activities are limited to a line-of-sight (LoS) operational range. One of the alternatives to operate the drones beyond the visual line-of-sight (BVLoS) range is replacing the drone wireless communications system from the conventional industrial, scientific, and medical (ISM) radio band to a licensed cellular-connected system. The Long Term Evolution (LTE) technology that has been established for the terrestrial area allows command-and-control and payload communications between drone and ground station in real-time. However, with increasing height above the ground, the radio environment changes, and utilizing terrestrial cellular networks for drone communications may face new challenges. In this regard, this paper aims to develop an LTE-based control system prototype for low altitude small drones and investigate the feasibility and performance of drone cellular connectivity at different altitudes with measuring parameters such as latency, handover, and signal strength. The measurement results have shown that by increasing flight height from ground to 170 m the received signal power and the signal quality levels were reduced by 20 dBm and 10 dB respectively, the downlink data rate decreased to 70%, and latency increased up to 94 ms. It is concluded that although the existing LTE network can provide a minimum requirement for drone cellular connectivity, further improvements are still needed to enhance aerial coverage, eliminate interference, and reduce network latency.
    Matched MeSH terms: Feasibility Studies
  9. Setiyo M, Widodo EM, Rosyidi MI, Waluyo B, Pambuko ZB, Tamaldin N
    Heliyon, 2020 Jan;6(1):e03318.
    PMID: 32051877 DOI: 10.1016/j.heliyon.2020.e03318
    Consumer interest in privately managed urban transport services in Indonesia are showing a declining trend. On the other hand, the presence of Transportation on Demand (ToD) based on Internet of Things (IoT) has attracted the majority of conventional fleet customers which contribute to the declining trend of occupancy. Therefore, this study aims to present a feasibility study of a small car RE60 Three Passenger and One Driver (3P+1D) four-wheeler as an alternative to replace conventional fleets. The Break-Even Point (BEP), Net Present Value (NPV), Internal Rate of Return (IRR), and Payback Period (PP) are analyzed based on vehicle operating data. The analysis shows that there is an additional monthly income flow of IDR 1,533,122 and IDR 2,536,946 from RE60 operations compared to the high and low consumption of fuel from existing fleets, respectively. In conclusion, it is feasible to invest in small car RE60 as a replacement for the existing fleets since the fundamental indicators (BEP, NPV, IRR, and PP) showed positive results before the specified instalment period. Sensitivity analysis also shows good results, NPV shows positive results (>0) although the input conditions are made pessimistic to -30% from NPV base case. The BEP of RE60 will cut distance travelled at 190,670 km and 115,225 km, respectively. NPV of IDR 33,088,000 and IDR 80,841,000 will be obtained at the 60th month after the operation and IRR also enabled good scores, at 2.24% and 4.17%.
    Matched MeSH terms: Feasibility Studies
  10. Khan A, Zarin R, Hussain G, Ahmad NA, Mohd MH, Yusuf A
    Results Phys, 2021 Jan;20:103703.
    PMID: 33520623 DOI: 10.1016/j.rinp.2020.103703
    The dynamic of covid-19 epidemic model with a convex incidence rate is studied in this article. First, we formulate the model without control and study all the basic properties and results including local and global stability. We show the global stability of disease free equilibrium using the method of Lyapunov function theory while for disease endemic, we use the method of geometrical approach. Furthermore, we develop a model with suitable optimal control strategies. Our aim is to minimize the infection in the host population. In order to do this, we use two control variables. Moreover, sensitivity analysis complemented by simulations are performed to determine how changes in parameters affect the dynamical behavior of the system. Taking into account the central manifold theory the bifurcation analysis is also incorporated. The numerical simulations are performed in order to show the feasibility of the control strategy and effectiveness of the theoretical results.
    Matched MeSH terms: Feasibility Studies
  11. Keng SL, Mohd Salleh Sahimi HB, Chan LF, Woon L, Eu CL, Sim SH, et al.
    BMC Psychiatry, 2021 10 04;21(1):486.
    PMID: 34607589 DOI: 10.1186/s12888-021-03500-y
    AIM/BACKGROUND: Even though dialectical behavior therapy (DBT) has received substantial empirical support in treating patients with borderline personality disorder (BPD), fewer studies have evaluated whether a brief DBT skills group may be effective in improving clinical outcomes in this population. Further, less is known regarding the feasibility and outcomes of DBT beyond Euro-American contexts. This paper describes outcomes from a pilot study examining the feasibility, acceptability, and clinical outcomes following completion of a shortened, 14-week DBT skills group in a sample of Muslim-majority BPD patients in Malaysia.

    METHODS: Twenty patients were recruited from a public hospital and attended DBT skills groups in an outpatient clinic. Participants completed measures assessing psychological symptoms, self-harm behaviors, suicidal ideation, emotion regulation difficulties, self-compassion, and well-being pre- and post-intervention.

    RESULTS: There were significant reductions in depressive symptoms, stress, and emotion regulation difficulties, as well as increases in self-compassion and well-being from pre- to post-intervention. A trend was found for decreases in frequency and types of non-suicidal self-harm behaviors, suicidal ideation, and anxiety symptoms. Qualitative content analyses of participants' feedback indicated that the vast majority of participants perceived a positive impact from the skills group, with mindfulness and distress tolerance being rated frequently as skills that were beneficial.

    CONCLUSION: These preliminary findings suggest that DBT skills training is feasible and acceptable in a Muslim-majority, low resource clinical setting, and holds promise in improving clinical outcomes among BPD patients in Malaysia.

    Matched MeSH terms: Feasibility Studies
  12. Lim HM, Abdullah A, Ng CJ, Teo CH, Valliyappan IG, Abdul Hadi H, et al.
    Int J Med Inform, 2021 11;155:104567.
    PMID: 34536808 DOI: 10.1016/j.ijmedinf.2021.104567
    BACKGROUND: COVID-19 telemonitoring applications have been developed and used in primary care to monitor patients quarantined at home. There is a lack of evidence on the utility and usability of telemonitoring applications from end-users' perspective.

    OBJECTIVES: This study aimed to evaluate the feasibility of a COVID-19 symptom monitoring system (CoSMoS) by exploring its utility and usability with end-users.

    METHODS: This was a qualitative study using in-depth interviews. Patients with suspected COVID-19 infection who used CoSMoS Telegram bot to monitor their COVID-19 symptoms and doctors who conducted the telemonitoring via CoSMoS dashboard were recruited. Universal sampling was used in this study. We stopped the recruitment when data saturation was reached. Patients and doctors shared their experiences using CoSMoS, its utility and usability for COVID-19 symptoms monitoring. Data were coded and analysed using thematic analysis.

    RESULTS: A total of 11 patients and 4 doctors were recruited into this study. For utility, CoSMoS was useful in providing close monitoring and continuity of care, supporting patients' decision making, ensuring adherence to reporting, and reducing healthcare workers' burden during the pandemic. In terms of usability, patients expressed that CoSMoS was convenient and easy to use. The use of the existing social media application for symptom monitoring was acceptable for the patients. The content in the Telegram bot was easy to understand, although revision was needed to keep the content updated. Doctors preferred to integrate CoSMoS into the electronic medical record.

    CONCLUSION: CoSMoS is feasible and useful to patients and doctors in providing remote monitoring and teleconsultation during the COVID-19 pandemic. The utility and usability evaluation enables the refinement of CoSMoS to be a patient-centred monitoring system.

    Matched MeSH terms: Feasibility Studies
  13. Rahim F, Abdullah SRS, Hasan HA, Kurniawan SB, Mamat A, Yusof KA, et al.
    Sci Total Environ, 2022 Mar 25;814:152799.
    PMID: 34982990 DOI: 10.1016/j.scitotenv.2021.152799
    A reedbed system planted with Phragmites australis was implemented to treat chlorinated hydrocarbon-contaminated groundwater in an industrial plant area. Reedbed commissioning was conducted from July 2016 to November 2016 to treat contaminated groundwater via a pump-and-treat mechanism. Combination of horizontal and vertical reedbed systems was applied to treat 1,2-dichloroethane (1,2 DCA) under four parallel installations. The 2-acre horizontal and vertical reedbed systems were designed to treat approximately 305 m3/day of pumped groundwater. Initial concentration of 1,2 DCA was observed at 0.362 mg/L to 4320 mg/L, and the reedbed system successfully reduced the concentration up to 67.9%. The average outlet concentration was measured to be 2.08 mg/L, which was lower than the site-specific target level of 156 mg/L. Natural attenuation analysis was conducted using first-order decay kinetics, showing an average natural attenuation rate of 0.00372/year. Natural attenuation of 1,2 DCA was observed in shallow monitoring wells, which was indicated by the reduction trend of 1,2 DCA concentration, thereby confirming that the reedbed system worked well to remove 1.2 DCA from contaminated groundwater at the shallow profile.
    Matched MeSH terms: Feasibility Studies
  14. Siti A'iasah Hashim, Khairul Zaman Mohd Dahlan, Khomsaton Abu Bakar, Ayub Muhamad
    MyJurnal
    A laboratory scale test rig to treat simulated flue gas using electron beam technology was installed at the Alurtron EB-Irradiation Center, MINT. The experiment test rig was proposed as a result of feasibility studies conducted jointly by IAEA, MINT and TNB Research in 1997. The test rig system consists of several components, among others, diesel generator sets, pipe ducts, spray cooler, ammonia dosage system, irradiation vessel, bag filter and gas analyzers. The installation was completed and commissioned in October 2001. Results from the commissioning test runs and subsequent experimental work showed that the efficiency of flue gas treatment is high. It was proven that electron beam technology might be applied in the treatment of air pollutants. This paper describes the design and work function of the individual major components as well as the full system function. Results from the initial experimental works are also presented.
    Matched MeSH terms: Feasibility Studies
  15. Karniza Khalid, Thyagarajan, Dandaithapani, Muhammad Zul Azri Mohammad Yusof, Ruzita Jamaluddin
    MyJurnal
    Medical professionals work in a constantly stressful environment. The nature of the profession requires routine extended working hours, but little is known about the effect of long working hours on selective physiological measures. A cross-sectional feasibility study was conducted from 1 October 2017 until 30 April 2018 on medical doctors in a tertiary health centre in northwest Malaysia. There was a total of 55 study participants recruited. The overall systolic blood pressure (SBP) was highest after working 24-hour stretch (p=0.006) and the overall diastolic blood pressure (DBP) were highest after working for 33 hours in a single stretch, at the end of on call rotation (p
    Matched MeSH terms: Feasibility Studies
  16. Ramli NM, Verreth JAJ, Yusoff FM, Nurulhuda K, Nagao N, Verdegem MCJ
    PMID: 33015002 DOI: 10.3389/fbioe.2020.01004
    This review investigates the performance and the feasibility of the integration of an algal reactor in recirculating aquaculture systems (RAS). The number of studies related to this topic is limited, despite the apparent benefit of algae that can assimilate part of the inorganic waste in RAS. We identified two major challenges related to algal integration in RAS: first, the practical feasibility for improving nitrogen removal performance by algae in RAS; second, the economic feasibility of integrating an algal reactor in RAS. The main factors that determine high algal nitrogen removal rates are light and hydraulic retention time (HRT). Besides these factors, nitrogen-loading rates and RAS configuration could be important to ensure algal performance in nitrogen removal. Since nitrogen removal rate by algae is determined by HRT, this will affect the size (area or volume) of the algal reactor due to the time required for nutrient uptake by algae and large surface area needed to capture enough light. Constraints related to design, space, light capture, and reactor management could incur additional cost for aquaculture production. However, the increased purification of RAS wastewater could reduce the cost of water discharge in places where this is subject to levees. We believe that an improved understanding of how to manage the algal reactor and technological advancement of culturing algae, such as improved algal reactor design and low-cost artificial light, will increase the practical and economic feasibility of algal integration in RAS, thus improving the potential of mass cultivation of algae in RAS.
    Matched MeSH terms: Feasibility Studies
  17. Khoo KS, Chew KW, Ooi CW, Ong HC, Ling TC, Show PL
    Bioresour Technol, 2019 Oct;290:121794.
    PMID: 31319214 DOI: 10.1016/j.biortech.2019.121794
    This work aimed to study the application of liquid biphasic flotation (LBF) for the efficient and rapid recovery of astaxanthin from H. pluvialis microalgae. The performance of LBF for the extraction of astaxanthin was studied comprehensively under different operating conditions, including types and concentrations of food-grade alcohol and salt, volume ratio, addition of neutral salt, flotation period, and mass of dried H. pluvialis biomass powder. The maximum recovery, extraction efficiency and partition coefficient of astaxanthin obtained from the optimum LBF system were 95.11 ± 1.35%, 99.84 ± 0.05% and 385.16 ± 3.87, respectively. A scaled-up LBF system was also performed, demonstrating the feasibility of extracting natural astaxanthin from microalgae at a larger scale. This exploration of LBF system opens a promising avenue to the extraction of astaxanthin at lower cost and shorter processing time.
    Matched MeSH terms: Feasibility Studies
  18. Leong WH, Azella Zaine SN, Ho YC, Uemura Y, Lam MK, Khoo KS, et al.
    J Environ Manage, 2019 Nov 01;249:109384.
    PMID: 31419674 DOI: 10.1016/j.jenvman.2019.109384
    The microalgal-bacterial co-cultivation was adopted as an alternative in making microbial-based biofuel production to be more feasible in considering the economic and environmental prospects. Accordingly, the microalgal-bacterial symbiotic relationship was exploited to enhance the microbial biomass yield, while bioremediating the nitrogen-rich municipal wastewater. An optimized inoculation ratio of microalgae and activated sludge (AS:MA) was predetermined and further optimization was performed in terms of different increment ratios to enhance the bioremediation process. The nitrogen removal was found accelerating with the increase of the increment ratios of inoculated AS:MA, though all the increment ratios had recorded a near complete total nitrogen removal (94-95%). In light of treatment efficiency and lipid production, the increment ratio of 0.5 was hailed as the best microbial population size in accounting the total nitrogen removal efficiency of 94.45%, while not compromising the lipid production of 0.241 g/L. Moreover, the cultures in municipal wastewater had attained higher biomass and lipid productions of 1.42 g/L and 0.242 g/L, respectively, as compared with the synthetic wastewater which were only 1.12 g/L (biomass yield) and 0.175 g/L (lipid yield). This was possibly due to the presence of trace elements which had contributed to the increase of biomass yield; thus, higher lipid attainability from the microalgal-bacterial culture. This synergistic microalgal-bacterial approach had been proven to be effective in treating wastewater, while also producing useful biomass for eventual lipid production with comparable net energy ratio (NER) value of 0.27, obtained from the life-cycle analysis (LCA) studies. Thereby, contributing towards long-term sustainability and possible commercialization of microbial-based biofuel production.
    Matched MeSH terms: Feasibility Studies
  19. Ooi, Ching Sheng, Lim, Meng Hee, Lee, Kee Quen, Kang, Hooi Siang, Mohd Salman Leong
    MyJurnal
    Previous studies have indicated that the pipe-surface-mounted helical strakes effectively reduce vortex-induced vibration (VIV) under a uniform flow application, particularly during the lock-in region. Since VIV experiments are time-consuming, observation is generated with an interval helical strakes parameter in pitch and height to lessen tedious procedures and repetitive post-processing analyses. The aforementioned result subset is insufficient for helical strakes design optimisation because the trade-off between the helical strakes dimension, lock-in region and flow velocity are non-trivial. Thus, a parametric model based on an improved recursive least squares (RLS) parameter estimation technique is proposed to define the statistical relationship between input, or strakes and pipe dimension, and output, or VIV amplitude ratio. As results suggested, revised RLS estimated VIV model demonstrated an optimal prediction with the highest coefficient of determination and lowest Integral Absolute Error. The feasibility of VIV parametric model was validated by embed into Genetic Algorithm (GA) as the fitness function to acquire a desirable helical strakes dimension with minimum VIV amplitude. The rapid generation of optimal helical strakes dimension which returned the highest VIV suppression implied a superior simulation method compared to the experimental outcome.
    Matched MeSH terms: Feasibility Studies
  20. Ba Wazir AS, Karim HA, Abdullah MHL, AlDahoul N, Mansor S, Fauzi MFA, et al.
    Sensors (Basel), 2021 Jan 21;21(3).
    PMID: 33494254 DOI: 10.3390/s21030710
    Given the excessive foul language identified in audio and video files and the detrimental consequences to an individual's character and behaviour, content censorship is crucial to filter profanities from young viewers with higher exposure to uncensored content. Although manual detection and censorship were implemented, the methods proved tedious. Inevitably, misidentifications involving foul language owing to human weariness and the low performance in human visual systems concerning long screening time occurred. As such, this paper proposed an intelligent system for foul language censorship through a mechanized and strong detection method using advanced deep Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) through Long Short-Term Memory (LSTM) cells. Data on foul language were collected, annotated, augmented, and analysed for the development and evaluation of both CNN and RNN configurations. Hence, the results indicated the feasibility of the suggested systems by reporting a high volume of curse word identifications with only 2.53% to 5.92% of False Negative Rate (FNR). The proposed system outperformed state-of-the-art pre-trained neural networks on the novel foul language dataset and proved to reduce the computational cost with minimal trainable parameters.
    Matched MeSH terms: Feasibility Studies
Related Terms
Filters
Contact Us

Please provide feedback to Administrator (tengcl@gmail.com)

External Links