A Sequential Handwriting Recognition Model Based on a Dynamically Configurable CRNN.

Handwriting recognition refers to recognizing a handwritten input that includes character(s) or digit(s) based on an image. Because most applications of handwriting recognition in real life contain sequential text in various languages, there is a need to develop a dynamic handwriting recognition system. Inspired by the neuroevolutionary technique, this paper proposes a Dynamically Configurable Convolutional Recurrent Neural Network (DC-CRNN) for the handwriting recognition sequence modeling task. The proposed DC-CRNN is based on the Salp Swarm Optimization Algorithm (SSA), which generates the optimal structure and hyperparameters for Convolutional Recurrent Neural Networks (CRNNs). In addition, we investigate two types of encoding techniques used to translate the output of optimization to a CRNN recognizer. Finally, we proposed a novel hybridized SSA with Late Acceptance Hill-Climbing (LAHC) to improve the exploitation process. We conducted our experiments on two well-known datasets, IAM and IFN/ENIT, which include both the Arabic and English languages. The experimental results have shown that LAHC significantly improves the SSA search process. Therefore, the proposed DC-CRNN outperforms the handcrafted CRNN methods.

A Patient-Specific Single Sensor IoT-Based Wearable Fall Prediction and Detection System.

Falls in older adults are a major cause of morbidity and mortality and are a key class of preventable injuries. This paper presents a patient-specific (PS) fall prediction and detection prototype system that utilizes a single tri-axial accelerometer attached to the patient's thigh to distinguish between activities of daily living (ADL) and fall events. The proposed system consists of two modes of operation: 1) fast mode for fall predication (FMFP) predicting a fall event (300-700 msec) before occurring and 2) slow mode for fall detection (SMFD) with a 1-sec latency for detecting a fall event. The nonlinear support vector machine classifier (NLSVM)-based FMFP algorithm extracts seven discriminating features for the pre-fall case to identify a fall risk event and alarm the patient. The proposed SMFD algorithm utilizes a Three-cascaded 1-sec sliding frames classification architecture with a linear regression-based offline training to identify a single and optimal threshold for each patient. Fall incidence will trigger an alarming notice to the concern healthcare providers via the Internet. Experiments are performed with 20 different subjects (age above 65 years) and a total number of 100 associated falls and ADL recordings indoors and outdoors. The accuracy of the proposed algorithms is furthermore validated via MobiFall Dataset. FMFP achieves sensitivity and specificity of 97.8% and 99.1%, respectively, while SMFD achieves sensitivity and specificity of 98.6% and 99.3%, respectively, for a total number of 600 measured falls and ADL cases from 77 subjects.

Harmony Search Algorithm for Word Sense Disambiguation.

Word Sense Disambiguation (WSD) is the task of determining which sense of an ambiguous word (word with multiple meanings) is chosen in a particular use of that word, by considering its context. A sentence is considered ambiguous if it contains ambiguous word(s). Practically, any sentence that has been classified as ambiguous usually has multiple interpretations, but just one of them presents the correct interpretation. We propose an unsupervised method that exploits knowledge based approaches for word sense disambiguation using Harmony Search Algorithm (HSA) based on a Stanford dependencies generator (HSDG). The role of the dependency generator is to parse sentences to obtain their dependency relations. Whereas, the goal of using the HSA is to maximize the overall semantic similarity of the set of parsed words. HSA invokes a combination of semantic similarity and relatedness measurements, i.e., Jiang and Conrath (jcn) and an adapted Lesk algorithm, to perform the HSA fitness function. Our proposed method was experimented on benchmark datasets, which yielded results comparable to the state-of-the-art WSD methods. In order to evaluate the effectiveness of the dependency generator, we perform the same methodology without the parser, but with a window of words. The empirical results demonstrate that the proposed method is able to produce effective solutions for most instances of the datasets used.

GCSF with or without chemotherapy compared to Plerixafor with GCSF as salvage mobilization regimen in patients with multiple myeloma and lymphoma: collection effectiveness and cost effectiveness analysis.

INTRODUCTION: Plerixafor is a novel mobilizing agent of peripheral blood stem cells (PBSCs) in lymphoma and multiple myeloma (MM) patients whose cells mobilize poorly. Due to the substantial cost associated with its use, we aimed to compare the effectiveness and cost effectiveness of Plerixafor + GCSF (PG) versus GCSF ± Chemotherapy (GC) as salvage mobilization regimens. METHODS: The charts of consecutive lymphoma and MM patients who had undergone at least one previous attempt of PBSCs mobilization that failed or resulted in an insufficient cell dose for transplant between 2007 and 2010 were retrospectively reviewed. Patients identified received salvage mobilization with GC (prior to 2009) or PG after Plerixafor's FDA approval. Data collected included demographics, medical histories, apheresis yields and transplant outcome. The cost effectiveness analysis was from the perspective of the Jordanian Ministry of Health. The incremental cost effectiveness ratio (ICER) was calculated by dividing the difference in cost by the difference in effectiveness for the two regimens. RESULTS: Five patients received GC and twelve received PG. A minimum CD34+ cell dose of 2 × 10(6) cells/kg was collected from 8 patients (67%) in the PG group compared to 3 (60%) in the GC group (p=0.79). The average costs were US$8570 and US$25,700 for the GC group and the PG group, respectively. The ICER was US$244,714 per successful stem cell collection. CONCLUSION: Salvage Plerixafor use showed a non-significant improvement in PBSCs collection with a significant increase in cost. Prospective comparative effectiveness studies are warranted to inform the optimal salvage mobilization regimen. To our knowledge, this is the first study from the Middle East to describe the effectiveness and cost effectiveness of Plerixafor.

Advanced gastric cancer in jordan from 2004 to 2008: a study of epidemiology and outcomes.

BACKGROUND: WE REPORT THE EPIDEMIOLOGIC FEATURES AND THE TREATMENT EXPERIENCE OF ADVANCED GASTRIC CANCER (GC) AT KING HUSSEIN CANCER CENTER (KHCC) IN JORDAN, AND WE RETROSPECTIVELY COMPARE OUTCOMES OF TWO DIFFERENT REGIMENS: DCF (docetaxel/cisplatin/5-fluorouracil) vs. ECF (epirubicin/cisplatin/5-fluorouracil). METHODS: Charts of 162 patients with inoperable GC treated between January 2004 and December 2008 were reviewed. A total 143 patients received chemotherapy (ECF = 113; DCF = 30). Choice of regimen was changed from ECF to DCF on January 2008 according to KHCC guidelines. RESULTS: The median patient age was 59 years, with a male:female ratio of 1.8:1. Lymph nodes (67.9%) and liver (49.4%) were the most common sites of metastasis. Primary disease site was stomach in 78.4%, gastroesophageal junction in 16.7%, lower esophagus in 4.9%. Poorly differentiated histology was predominant (46.9%). Anemia (53.7%), pain (48.1%), and reflux (44.4%) were the most common presenting symptoms. Helicobacter pylori infection was present in 79%. Average time between initial symptom and diagnosis was 6.0 months. The overall response rate (ORR) was 59.3% with DCF and 32.6% with ECF (P = .01). Time to tumor progression (TTP) was 6.9 months with DCF and 5.9 months with ECF (P = .005). Median survival was 11.0 months with DCF and 10.2 months with ECF (P = .17). CONCLUSION: Some epidemiologic features of GC in Jordan mimic those of high-risk areas. Our outcomes of chemotherapy are comparable to internationally reported data and suggest superiority of DCF over ECF in terms of ORR and TTP.