Journal articles on the topic 'Ieee 802. 11, wlan'

Reconfiguration Communication System (RCS) intelligently provides interoperating platforms that enable communication with lower standards. Incremental demand for wireless services required justifiable capacity improvement of communication protocols. To ugrade existing wireless systems using APs computational techniques, the operational capability is facilitated flexible scaling and transmission reliability. This paper examines the communication requirements of relevant IEEE standardizations in cognition and interoperations. The impact of larger frame sizes and high delivery rates were examined in Ad-hoc wlan configuration. Using multi-user multiple inputs multiple outputs (MIMO) technology as communication elements in bands below 6GHz, Throughput performance was investigated using enterprise Network Simulator Package (eNSP). A significant reduction in packet errors was recorded in the simulations. This suggests an improved throughput, provided by flexible switching over long-distances. IEEE802.11ac standard implementation confirmed efficient cognition while IEEE 802.22 technology established interoperability techniques during reconfigurations. Protocol amendment to IEEE 802.11a standardization provided higher throughput measure characterized for transmissions below 6GHz traffics. IEEE 802.11af enables multiple multimedia data streaming while co-existence of multiple users on the network guaranteed system scaling. The co-existence of increasingly served users were provisioned by IEEE 8802.16h, while interoperation was facilitated by 802.22 to encourage dynamic resource utilization. Also, dual-stack AP peers in P2P modes provided much flexibility in parameter switching to enable fast handoffs. Support to local network management systems by reconfiguration made entire network scale with reduced latency and resultantly improved throughput performance was attributed to IEEE 802.11ac, 802.11af, 802.16h and IEEE 802.22 standardization implementations.

Abstract : Wi-Fi technologies are widely used generally using IEEE 802 wireless standardization. 11a/b/g which works at a frequency of 2.4 GHz. These devices are found in almost all places, such as in offices – Government offices, private companies, entertainment venues, and educational venues. Currently the need for Wi-Fi (wireless fidelity) is very much needed, because nowadays many gadget devices that have been equipped with Wi-Fi so that with Wi-Fi Everyone can access the Internet everywhere. Based on the results of a field survey conducted on the WLAN network in the office of the Dinas Pendidikan Kayuagung in South Sumatera, from all computer units in the office is connected to the Internet through a network cable or wireless network, that the wireless network felt is still less optimal because there are some areas that are not covered or affordable by the Wi-Fi network. The researcher aims to redesign and rebrand Wi-Fi networks based on the scope of the area to be more optimal. While the research method to be used is the method PPDIOO (Prepare Plan Design Implement Operate and Optimize).

Purpose. One of the new additions in the IEEE 802.11n standard amendment was the introduction of the short inter-symbol guard interval, which makes it possible to operate at slightly higher data rates. However, using a short guard interval is not always recommended. The fact is that on some types of sites where radio coverage is provided, the peculiarities of signal propagation with a short guard interval may give worse frame retry rate. In modern networks, this aspect remains more relevant than ever, and the task of correct guard interval configuration remains relevant for both the designer and the administrator of a wireless network. In order to conduct a comparative analysis of the measurement results with a short and long guard inter-symbol interval, it is necessary to conduct a full-scale radio site-survey of industrial WLAN site. As part of the present experiment, a WLAN was investigated at a site in one of the industrial zones of St. Petersburg. The main goal of the work is to experimentally determine the benefits that can be obtained from choosing a modulation and coding scheme with a long inter-symbol guard interval using the example of a distributed wireless network of the IEEE 802.11n/ac/ax standard. A related goal is to experimentally test the potential for reducing the radiation power of access points radios in order to improve network performance. Methods. Conducting a radio survey of a wireless network at a typical industrial site with subsequent analysis of its results. Novelty. The novelty of the presented solution includes a full-scale examination of an actually operated industrial network with simultaneous monitoring of characteristics at various levels of the OSI model: physical (spectrum analysis), channel (protocol analysis), application (control of application operation). Results. Analysis of the collected data shows a practically significant difference between the values of the frame retry rate for different values of the duration of the inter-symbol guard interval and the radiation power of the radio modules of the access points. Practical relevance. In is quantitatively shown that there is a reduction in frame retry rate by 8-10% in an production wireless network, achievable through correct control of the inter-symbol interval length for an industrial site.

A compact circular structured monopole antenna for ultrawideband (UWB) and UWB dual-band notch applications is designed and fabricated on an FR4 substrate. The UWB antenna has a hybrid configuration of the circle and three ellipses as the radiating plane and less than a quarter-lowered ground plane. The overall dimensions of the projected antennas are 16 × 11 × 1.6 mm3, having a −10 dB impedance bandwidth of 113% (3.7–13.3 GHz). Further, two frequency band notches were created using two inverted U-shaped slots on the radiator. These slots notch the frequency band from 5–5.6 GHz and 7.3–8.3 GHz, covering IEEE 802.11, Wi-Fi, WLAN, and the entire X-band satellite communication. A comprehensive frequency and time domain analysis is performed to validate the projected antenna design’s effectiveness. In addition, a circuit model of the projected antenna design is built, and its performance is evaluated. Furthermore, unlike the traditional technique, which uses the simulated surface current distribution to verify functioning, characteristic mode analysis (CMA) is used to provide deeper insight into distinct modes on the antenna.

Cognitive radio (CR) is one of the compelling ideas to solve the spectrum scarcity problem for rapid developments in wireless communication systems. In CR systems, signal detection for orthogonal frequency division multiplexing (OFDM) systems in severe noise environments is a key challenge. The area of practical primary user detection has not been explored in depth. The proposed method is an effective method for sensing OFDM applications, which are the practical primary users, for low signal-to-noise (SNR) cases. In the proposed method, the parallel combination of the comb filter and the time-domain autocorrelation function is exploited. The detection performance is measured for various OFDM system applications, including the IEEE 802.11a wireless LAN (WLAN) radio interface, long-term evaluation (LTE), and digital audio broadcasting (DAB) for various CP ratios under 16-quadrature amplitude modulation (16-QAM) and 64-quadrature amplitude modulation (64-QAM) over multipath Rayleigh fading channels with additive white Gaussian noise (AWGN). Furthermore, the OFDM sensing is possible in the presence of noise uncertainty and the sensing performance is compared under consideration with and without noise uncertainty cases. The simulation results demonstrated that our proposed method undoubtedly improves the sensing performances (up to 11 dB SNR gain) of practical primary users more than the conventional spectrum detection methods for low SNR cases.

Introduction & Purpose Change of direction (COD) movements are a common cause of injuries to the anterior cruciate ligament (ACL), especially in sports such as soccer, basketball, handball (Agel et al., 2016). In Mohr et al., (2024) an 8-week injury prevention training program including COD technique training was investigated. The movements during COD were recorded in an experimental setup with a marker-based system before and after the training program. While Mohr and colleagues observed training effects on the COD movement strategy, it remains unknown whether the ACL forces are actually reduced by the training program. The purpose of this project was to 1) develop a simulation-based approach to estimate ACL forces during COD movements using musculoskeletal simulations (OpenSim) and finite element (FE) knee simulations, and 2) use existing kinematics from a COD movement of one athlete before and after the 8-week injury prevention training program to investigate training effects on ACL force (Mohr et al., 2024). Methods The model OKS008 from the publicly-available collection of Open Knee(s) (OKS) FE models (2nd generation) of the Cleveland Clinic (Chokhandre et al., 2023) was implemented in the FE software Abaqus CAE. In the original OKS008 model (Chokhandre et al., 2023) material parameters and pre-strains were taken from literature. However, the pre-strain of the ligaments is very individual (Lahkar et al., 2021). Therefore, in this study, the pre-strain of the ligaments and four material parameters of the OKS008 model were fit to in vitro kinetic testing data, using an optimization algorithm (interior-point algorithm). The kinetic data from in-vitro tests is available alongside with the OKS knee models, for which all donor knees were mechanically tested during passive flexion experiments (Chokhandre et al., 2023). The optimization was solved based on about 550 FE simulations over the course of one month (AMD Ryzen threadripper 3960 x 24-core processor x 48, 35 cores were used). The effect of the knee kinematics from Mohr and colleagues (2024) on the loading of the anterior cruciate ligament (ACL) was then investigated with the optimized FE knee model in a post-processing step. Inverse kinematics in OpenSim was used to determine the 3D knee joint kinematics of one athlete during a maximum-speed 135° COD movement before and after the injury prevention training program. This athlete was selected because after the 8-week injury prevention training program, he showed a significant reduction in maximum knee adduction moment. The run-up velocity of the athlete on the COD was 3.97 m/s before the training program (baseline) and 4.09 m/s after the training program (follow-up). To simulate the COD movements in Abaqus, the FE knee model was driven by the measured knee kinematics of the COD, where the secondary kinematics (knee adduction and internal rotation) of the OpenSim model were added to the FE model’s secondary kinematics during passive flexion. The resulting force on the ACL was calculated by a free body cut in Abaqus CAE. Results The pre-strain optimized FE knee model closely reproduced the secondary kinematics (abduction, internal rotation) of the donor knee during passive flexion (mean error of 2.1687° before vs. 0.5799° after optimization). The athlete’s maximum ACL force during the COD before the training program was 457 N, while after the training program a reduction in ACL force during the COD to 246 N was observed (46% reduction). The ACL force during the COD before and after the injury prevention training program is shown in Figure 1. Discussion A publicly available FE knee model was successfully optimized based on cadaveric mechanical testing data and implemented into a simulation-based approach to estimate ACL force. The plausibility of the model was checked by a mesh study and comparison with cadaver studies done in Wascher et al. (1993) and Hosseini Nasab et al. (2016). The timing of peak ACL force during a simulated COD movement, between 50 ms and 100 ms after initial contact, is physiologically plausible given that ACL injuries during CODs typically occur around 50 ms after initial contact (Krosshaug et al., 2007). The pre-strain optimization showed that it is necessary to estimate material parameters, e.g. ligament pre-strain, individually for each model to obtain realistic mechanical behaviour. The case study demonstrated a reduction in ACL force during a COD by 46% following an injury prevention training program. The existing kinematic data from Mohr and colleagues (2024) show that the analyzed athlete performed the COD with decreased knee internal rotation and abduction after the 8-week injury prevention training. It is assumed that the ACL force was reduced due to the lower internal rotation and abduction. Figure 1 show further interesting observations that warrant investigation, e.g. the time-shifted peak ACL force following training. This will be done in future studies including more athletes. Importantly, ACL forces during change of direction (COD) were calculated by applying only rotational kinematics to the FE model. The next step will be to implement joint reaction forces (JRF) into the FE simulations because they would have an effect on the ACL force (Esrafilian et al., 2022). It is therefore advisable to include the JRF in the subsequent simulations in order to obtain more physiologically relevant results. Conclusion We developed a FE simulation model in Abaqus CAE of the OKS008 knee to estimate and compare ACL forces based on the existing kinematics of a COD movement. However, individual material parameter estimation is required for each model. The material parameter estimation increases the replicability of the specimen specific mechanical cadaver testing. This is an improvement to the original OKS008 model. For the one analyzed athlete, after the 8-week injury prevention exercise program (Mohr et al., 2024) the ACL force caused by rotational kinematics of a COD is less than before the exercise program. The maximum ACL force during COD is reduced by 46% after the exercise program. References Agel, J., Rockwood, T., & Klossner, D. (2016). Collegiate ACL injury rates across 15 sports: National collegiate athletic association injury surveillance system data update (2004-2005 through 2012-2013). Clinical Journal of Sport Medicine, 26(6), 518-523. https://doi.org/10.1097/JSM.0000000000000290 Chokhandre, S., Schwartz, A., Klonowski, E., Landis, B., & Erdemir, A. (2023). Open knee(s): A free and open source library of specimen-specific models and related digital assets for finite element analysis of the knee joint. Annals of Biomedical Engineering, 51, 10-23. https://doi.org/10.1007/s10439-022-03074-0 Esrafilian, A., Stenroth, L., Mononen, M. E., Vartiainen, P., Tanska, P., Karjalainen, P. A., Suomalainen, J.-S., Arokoski, J. P. A., Saxby, D. J., Lloyd, D. G., & Korhonen, R. K. (2022). Toward tailored rehabilitation by implementation of a novel musculoskeletal finite element analysis pipeline. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 30, 789-802. https://doi.org/10.1109/TNSRE.2022.3159685 Hosseini Nasab, S. H., List, R., Oberhofer, K., Fucentese, S. F., Snedeker, J. G., & Taylor, W. R. (2016). Loading patterns of the posterior cruciate ligament in the healthy knee: A systematic review. PLoS One, 11(11), Article e0167106. https://doi.org/10.1371/journal.pone.0167106 Krosshaug, T., Nakamae, A., Boden, B. P., Engebretsen, L., Smith, G., Slauterbeck, J. R., Hewett, T. E., & Bahr, R. (2007). Mechanisms of anterior cruciate ligament injury in basketball: Video analysis of 39 cases. The American Journal of Sports Medicine, 35(3), 359-67. https://doi.org/10.1177/0363546506293899 Lahkar, B. K., Rohan, P.-Y., Pillet, H., Thoreux, P., & Skalli, W. (2021). Development and evaluation of a new procedure for subject-specific tensioning of finite element knee ligaments. Computer Methods in Biomechanics and Biomedical Engineering, 24(11), 1195-1205. https://doi.org/10.1080/10255842.2020.1870220 Mohr, M., Federolf, P., Heinrich, D., Nitschke, M., Raschner, C., Scharbert, J., & Koelewijn, A. D. (2024). An 8-week injury prevention exercise program combined with change-of-direction technique training limits movement patterns associated with anterior cruciate ligament injury risk. Scientific Reports, 14, Article 3115. https://doi.org/10.1038/s41598-024-53640-w Wascher, D. C., Markolf, K. L., Shapiro, M. S., & Finerman, G. A. (1993). Direct in vitro measurement of forces in the cruciate ligaments. Part I: The effect of multiplane loading in the intact knee. The Journal of Bone and Joint Surgery, 75(3), 377-386. https://doi.org/10.2106/00004623-199303000-00009

The widespread adoption of IEEE 802.11 WLANs is attributed to their inherent mobility, flexibility, and cost-effectiveness. Within the IEEE 802 working group, a dedicated task group is diligently advancing WLAN technologies, particularly tailored for dense network scenarios. Amidst these advancements, the 802.11ac protocols have emerged as a preferred choice, delivering superior data transfer rates compared to the preceding 802.11n standard. Significantly, the sixth-generation wireless protocol, IEEE 802.11ax, has been introduced, showcasing enhanced performance capabilities that outpace its fifth-generation predecessor, 802.11ac.In this pioneering investigation, we engage in an in-depth simulation-based scrutiny of prominentWLAN protocols—namely, IEEE 802.11n, IEEE 802.11ac, and the cutting-edge IEEE 802.11ax. Our exhaustive analyses traverse a spectrum of critical metrics, encompassing throughput, coverage, spectral efficiency, Tx/Rx gain, and Tx/Rx power.In a single-user and SISO scenario, both 802.11ac and 802.11ax outperform 802.11n. Significantly, 802.11ax surpasses the previous 802.11n/ac standards, highlighting substantial advancements in wireless performance.

Antena merupakan satu komponen penting dalam sistem komukasi wayarles. Antena mikrojalur boleh digunakan untuk aplikasi wayarles kerana ia mempunyai ciri–ciri seperti ringan, mudah dipasang dan dihasilkan dalam kuantiti yang banyak. Walaupun antenna mikrojalur mempunyai ciri–ciri tersebut yang menjadikannya sesuai untuk digunakan dalam aplikasi wayarles, namun ia mempunyai satu kekurangan yang agak serius, iaitu ciri lebar jalur yang sempit. Selalunya, antena mikrojalur mempunyai jalur di antara 1 – 3%. Tetapi, sekiranya kekurangan ini dapat diatasi, potensi antena mikrojalur boleh dimaksimumkan. Satu teknik alternatif untuk memperluaskan lebar jalur antena mikrojalur telah dikaji dan dicadangkan di sini. Aplikasi wayarles yang telah dipilih untuk dikaji ialah rangkaian kawasan tempatan tanpa wayar (WLAN) berasaskan kepada piawaian IEEE 802.11b. Di Malaysia, jalur WLAN adalah di antara 2.4 GHz hingga 2.48 GHz. Teknik yang dipilih untuk meluaskan lebar jalur ini ialah Antena Mikrojalur Dua Tampal Serupa Dengan Ruangan Udara (IDMA). Dengan menggunakan teknik ini, perluasan lebar jalur hingga lebih kurang 11% dapat dicapai. Jalur ini sememangnya dapat merangkumi jalur WLAN dengan frekuensi operasinya pada 2.45 GHz. Kata kunci: Rangkaian kawasan tempatan wayarles (WLAN); antena mikrojalur dua tampal serupa dengan ruangan udara (IDMA) Antenna is a vital component in wireless application systems. The microstrip antenna can be used for wireless applications as it has features such as light weight, easily mounted and it is easy to mass produce. Although there are many features that suits well for microstrip antenna to be deployed for wireless applications, there is a very serious limitation where it has a very narrow bandwidth. The typical bandwidth of the microstrip antennas is between 1 – 3%. If this limitation is eliminated, the microstrip antenna can be used to its full potential. An alternative bandwidth enhancement technique is studied and then proposed in order to broaden the bandwidth of the microstrip antenna. The wireless application that is selected to be studied is the Wireless Local Area Network (WLAN) based on the IEEE 802.11b standard. In Malaysia, this WLAN band spans from 2.4 GHz to 2.48 GHz. The bandwidth enhancement technique which is selected is the Identical Dual–Patch Microstrip Antenna with Air–Gap (IDMA). By using this technique, a bandwidth enhancement of about 11% has been achieved. This bandwidth very well covers the required WLAN band with an operating frequency of 2.45 GHz. Key words: Wireless local area network (WLAN); identical dual patch microstrip antenna with air–gap (IDMA)

The design and simulation of defected ground structure microstrip patch antenna for Worldwide Interoperability for Microwave Access (WiMAX) and Wireless Local Area Network (WLAN) applications are additionally testing as the antenna ought to be little in size, light in weight, easy to manufacture, minimal effort, and simplicity of joining in such gadgets. The target of this work is to plan and creation of an antenna which will be appropriate for WiMAX and WLAN applications with improved gain and optimized bandwidth. WiMAX depend on gauges, for example, IEEE 802.16, intended to work between 2-11 GHz and spreads S, C and X microwave recurrence groups. Metropolitan Area Network (MAN) conventions are in the 2.3 GHz, 2.5 GHz, 3.5 GHz and 5.8 GHz ranges. A planar antenna with imperfect ground plane is proposed and manufactured, 3.5/5.5 GHz WiMAX band, 5.2/5.8 GHz WLAN band, 4/6 GHz satellite correspondence, and different remote correspondence applications. This structure canvassed two groups in which it is extending from 3.34-8.72 GHz implies a band of 5.38 GHz with impedance BW 89.22%. The resonating frequencies are 3.92 GHz and 7.88 GHz with return loss - 35.59 dB and - 31.99 dB, VSWR 1.03 and 1.05 and gain 9.46 dB and 0.14 dB respectively. The second band covers 9.22-13.06 GHz implies a band of 3.84 GHz with impedance BW 34.47%. This resounds at 10.58 GHz with return loss - 55.52 dB, VSWR 1.00 and gain is 7.09 dB. The deliberate outcomes are in great concurrence with reproduced consequences of the proposed antenna.

Abstract A compact, multiband flexible antenna for off Body Communication (OBC) at 2.45 GHz and UWB low and high bands are presented as required by the IEEE 802.15.6TM standard, 2012. The antenna exhibits a directional radiation pattern and provides good gain and a low specific absorption rate (SAR). The proposed antenna has a compact footprint of 44 × 32 ×1.5 mm3. The proposed antenna is fabricated by placing a conductive fabric on a 1.5 mm thick polydimethylsiloxane (PDMS) polymer to enhance high flexibility and durability. A full ground made of conductive textile is used on the underside of the dielectric to reduce the load directed towards the antenna caused by the layers of human tissue underneath and to minimize back radiation from the human body. The proposed antenna design combines square and circular rings to achieve multi-band characteristics. Edge chamfering, slotting, and stub addition bandwidth expansion techniques are used to achieve wide bandwidth. The proposed antenna demonstrates exceptional resistance to the human body's load and physical deformation. The proposed antenna is a compact single-layer substrate flexible FGP (FGP) antenna operable in the WLAN (2.45 GHz), lower (3.2-4.6 GHz), and higher UWB (6.2-11 GHz) bands specified by IEEE. 802.15.6.

This paper presents a novel CPW fed patch antenna supporting a wide band from 2.7 GHz – 6.5 GHz. The antenna is compact with size 32 x 30 x 1.6mm³, built over FR4-epoxy substrate (ε_r=4.4). Bandwidth enhancement has been achieved by using the concept of modified ground structure (MGS). For this purpose structural design has been optimized by parametric simulations in CST MWS. The proposed antenna can perform well in variety of wireless communication services including 5.15 GHz- 5.35 GHz and 5.725 GHz- 5.825 GHz WLAN IEEE 802.11 g/a, 5.2/ 5.5/ 5.8 GHz Wi-Fi, 3.5/5.5 GHz WiMax applications  and 3.7 - 4.2 GHz C band satellite communications bands. The measured experimental results show that bandwidth (S₁₁ < -10 dB) of antenna is 3.8 GHz. The performance of antenna is studied in terms of reflection coefficient, radiation characteristics, current distribution and gain.

Chemical compounds (drugs) and diseases are among top searched keywords on the PubMed database of biomedical literature by biomedical researchers all over the world (according to a study in 2009). Working with PubMed is essential for researchers to get insights into drugs’ side effects (chemical-induced disease relations (CDR), which is essential for drug safety and toxicity. It is, however, a catastrophic burden for them as PubMed is a huge database of unstructured texts, growing steadily very fast (~28 millions scientific articles currently, approximately two deposited per minute). As a result, biomedical text mining has been empirically demonstrated its great implications in biomedical research communities. Biomedical text has its own distinct challenging properties, attracting much attetion from natural language processing communities. A large-scale study recently in 2018 showed that incorporating information into indenpendent multiple-input layers outperforms concatenating them into a single input layer (for biLSTM), producing better performance when compared to state-of-the-art CDR classifying models. This paper demonstrates that for a CNN it is vice-versa, in which concatenation is better for CDR classification. To this end, we develop a CNN based model with multiple input concatenated for CDR classification. Experimental results on the benchmark dataset demonstrate its outperformance over other recent state-of-the-art CDR classification models.
 Keywords: 
 Chemical disease relation prediction, Convolutional neural network, Biomedical text mining
 References
 [1] Paul SM, S. Mytelka, C.T. Dunwiddie, C.C. Persinger, B.H. Munos, S.R. Lindborg, A.L. Schacht, How to improve R&D productivity: The pharmaceutical industry's grand challenge, Nat Rev Drug Discov. 9(3) (2010) 203-14. https://doi.org/10.1038/nrd3078.
 [2] J.A. DiMasi, New drug development in the United States from 1963 to 1999, Clinical pharmacology and therapeutics 69 (2001) 286-296. https://doi.org/10.1067/mcp.2001.115132.
 [3] C.P. Adams, V. Van Brantner, Estimating the cost of new drug development: Is it really $802 million? Health Affairs 25 (2006) 420-428. https://doi.org/10.1377/hlthaff.25.2.420.
 [4] R.I. Doğan, G.C. Murray, A. Névéol et al., "Understanding PubMed user search behavior through log analysis", Oxford Database, 2009.
 [5] G.K. Savova, J.J. Masanz, P.V. Ogren et al., "Mayo clinical text analysis and knowledge extraction system (cTAKES): Architecture, component evaluation and applications", Journal of the American Medical Informatics Association, 2010.
 [6] T.C. Wiegers, A.P. Davis, C.J. Mattingly, Collaborative biocuration-text mining development task for document prioritization for curation, Database 22 (2012) pp. bas037.
 [7] N. Kang, B. Singh, C. Bui et al., "Knowledge-based extraction of adverse drug events from biomedical text", BMC Bioinformatics 15, 2014.
 [8] A. Névéol, R.L. Doğan, Z. Lu, "Semi-automatic semantic annotation of PubMed queries: A study on quality, Efficiency, Satisfaction", Journal of Biomedical Informatics 44, 2011.
 [9] L. Hirschman, G.A. Burns, M. Krallinger, C. Arighi, K.B. Cohen et al., Text mining for the biocuration workflow, Database Apr 18, 2012, pp. bas020.
 [10] Wei et al., "Overview of the BioCreative V Chemical Disease Relation (CDR) Task", Proceedings of the Fifth BioCreative Challenge Evaluation Workshop, 2015.
 [11] P. Verga, E. Strubell, A. McCallum, Simultaneously Self-Attending to All Mentions for Full-Abstract Biological Relation Extraction, In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies 1 (2018) 872-884.
 [12] Y. Shen, X. Huang, Attention-based convolutional neural network for semantic relation extraction, In: Proceedings of COLING 2016, the Twenty-sixth International Conference on Computational Linguistics: Technical Papers, The COLING 2016 Organizing Committee, Osaka, Japan, 2016, pp. 2526-2536.
 [13] Y. Peng, Z. Lu, Deep learning for extracting protein-protein interactions from biomedical literature, In: Proceedings of the BioNLP 2017 Workshop, Association for Computational Linguistics, Vancouver, Canada, 2016, pp. 29-38.
 [14] S. Liu, F. Shen, R. Komandur Elayavilli, Y. Wang, M. Rastegar-Mojarad, V. Chaudhary, H. Liu, Extracting chemical-protein relations using attention-based neural networks, Database, 2018.
 [15] H. Zhou, H. Deng, L. Chen, Y. Yang, C. Jia, D. Huang, Exploiting syntactic and semantics information for chemical-disease relation extraction, Database, 2016, pp. baw048.
 [16] S. Liu, B. Tang, Q. Chen et al., Drug–drug interaction extraction via convolutional neural networks, Comput, Math, Methods Med, Vol (2016) 1-8. https://doi.org/10.1155/2016/6918381.
 [17] L. Wang, Z. Cao, G. De Meloet al., Relation classification via multi-level attention CNNs, In: Proceedings of the Fifty-fourth Annual Meeting of the Association for Computational Linguistics 1 (2016) 1298-1307. 
 https://doi.org/10.18653/v1/P16-1123.
 [18] J. Gu, F. Sun, L. Qian et al., Chemical-induced disease relation extraction via convolutional neural network, Database (2017) 1-12. https://doi.org/10.1093/database/bax024.
 [19] H.Q. Le, D.C. Can, S.T. Vu, T.H. Dang, M.T. Pilehvar, N. Collier, Large-scale Exploration of Neural Relation Classification Architectures, In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, 2018, pp. 2266-2277.
 [20] Y. LeCun, L. Bottou, Y. Bengio, P. Haffner, Gradient-based learning applied to document recognition, In Proceedings of the IEEE. 86(11) (1998) 2278-2324.
 [21] Y. Kim, Convolutional neural networks for sentence classification, ArXiv preprint arXiv:1408.5882.
 [22] C. Nagesh, Panyam, Karin Verspoor, Trevor Cohn and Kotagiri Ramamohanarao, Exploiting graph kernels for high performance biomedical relation extraction, Journal of biomedical semantics 9(1) (2018) 7.
 [23] H. Zhou, H. Deng, L. Chen, Y. Yang, C. Jia, D. Huang, Exploiting syntactic and semantics information for chemical-disease relation extraction, Database, 2016.